diff options
Diffstat (limited to 'tools/perf')
197 files changed, 14568 insertions, 8076 deletions
diff --git a/tools/perf/Documentation/Build.txt b/tools/perf/Documentation/Build.txt index f6fc6507ba55..3766886c4bca 100644 --- a/tools/perf/Documentation/Build.txt +++ b/tools/perf/Documentation/Build.txt @@ -47,3 +47,27 @@ Those objects are then used in final linking: NOTE this description is omitting other libraries involved, only focusing on build framework outcomes + +3) Build with ASan or UBSan +========================== + $ cd tools/perf + $ make DESTDIR=/usr + $ make DESTDIR=/usr install + +AddressSanitizer (or ASan) is a GCC feature that detects memory corruption bugs +such as buffer overflows and memory leaks. + + $ cd tools/perf + $ make DEBUG=1 EXTRA_CFLAGS='-fno-omit-frame-pointer -fsanitize=address' + $ ASAN_OPTIONS=log_path=asan.log ./perf record -a + +ASan outputs all detected issues into a log file named 'asan.log.<pid>'. + +UndefinedBehaviorSanitizer (or UBSan) is a fast undefined behavior detector +supported by GCC. UBSan detects undefined behaviors of programs at runtime. + + $ cd tools/perf + $ make DEBUG=1 EXTRA_CFLAGS='-fno-omit-frame-pointer -fsanitize=undefined' + $ UBSAN_OPTIONS=print_stacktrace=1 ./perf record -a + +If UBSan detects any problem at runtime, it outputs a “runtime error:” message. diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 86f3dcc15f83..462b3cde0675 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -114,7 +114,7 @@ Given a $HOME/.perfconfig like this: [report] # Defaults - sort-order = comm,dso,symbol + sort_order = comm,dso,symbol percent-limit = 0 queue-size = 0 children = true @@ -584,6 +584,20 @@ llvm.*:: llvm.opts:: Options passed to llc. +samples.*:: + + samples.context:: + Define how many ns worth of time to show + around samples in perf report sample context browser. + +scripts.*:: + + Any option defines a script that is added to the scripts menu + in the interactive perf browser and whose output is displayed. + The name of the option is the name, the value is a script command line. + The script gets the same options passed as a full perf script, + in particular -i perfdata file, --cpu, --tid + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 8f0c2be34848..58986f4cc190 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -459,6 +459,25 @@ Set affinity mask of trace reading thread according to the policy defined by 'mo node - thread affinity mask is set to NUMA node cpu mask of the processed mmap buffer cpu - thread affinity mask is set to cpu of the processed mmap buffer +--mmap-flush=number:: + +Specify minimal number of bytes that is extracted from mmap data pages and +processed for output. One can specify the number using B/K/M/G suffixes. + +The maximal allowed value is a quarter of the size of mmaped data pages. + +The default option value is 1 byte which means that every time that the output +writing thread finds some new data in the mmaped buffer the data is extracted, +possibly compressed (-z) and written to the output, perf.data or pipe. + +Larger data chunks are compressed more effectively in comparison to smaller +chunks so extraction of larger chunks from the mmap data pages is preferable +from the perspective of output size reduction. + +Also at some cases executing less output write syscalls with bigger data size +can take less time than executing more output write syscalls with smaller data +size thus lowering runtime profiling overhead. + --all-kernel:: Configure all used events to run in kernel space. @@ -495,6 +514,10 @@ overhead. You can still switch them on with: --switch-output --no-no-buildid --no-no-buildid-cache +--switch-max-files=N:: + +When rotating perf.data with --switch-output, only keep N files. + --dry-run:: Parse options then exit. --dry-run can be used to detect errors in cmdline options. diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 1a27bfe05039..f441baa794ce 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -105,6 +105,8 @@ OPTIONS guest machine - sample: Number of sample - period: Raw number of event count of sample + - time: Separate the samples by time stamp with the resolution specified by + --time-quantum (default 100ms). Specify with overhead and before it. By default, comm, dso and symbol keys are used. (i.e. --sort comm,dso,symbol) @@ -459,6 +461,10 @@ include::itrace.txt[] --socket-filter:: Only report the samples on the processor socket that match with this filter +--samples=N:: + Save N individual samples for each histogram entry to show context in perf + report tui browser. + --raw-trace:: When displaying traceevent output, do not use print fmt or plugins. @@ -477,6 +483,9 @@ include::itrace.txt[] Please note that not all mmaps are stored, options affecting which ones are include 'perf record --data', for instance. +--ns:: + Show time stamps in nanoseconds. + --stats:: Display overall events statistics without any further processing. (like the one at the end of the perf report -D command) @@ -494,6 +503,10 @@ include::itrace.txt[] The period/hits keywords set the base the percentage is computed on - the samples period or the number of samples (hits). +--time-quantum:: + Configure time quantum for time sort key. Default 100ms. + Accepts s, us, ms, ns units. + include::callchain-overhead-calculation.txt[] SEE ALSO diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 2e19fd7ffe35..9b0d04dd2a61 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -380,6 +380,9 @@ include::itrace.txt[] Set the maximum number of program blocks to print with brstackasm for each sample. +--reltime:: + Print time stamps relative to trace start. + --per-event-dump:: Create per event files with a "perf.data.EVENT.dump" name instead of printing to stdout, useful, for instance, for generating flamegraphs. diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 4bc2085e5197..39c05f89104e 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -72,9 +72,8 @@ report:: --all-cpus:: system-wide collection from all CPUs (default if no target is specified) --c:: ---scale:: - scale/normalize counter values +--no-scale:: + Don't scale/normalize counter values -d:: --detailed:: diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt index 849599f39c5e..869965d629ce 100644 --- a/tools/perf/Documentation/tips.txt +++ b/tools/perf/Documentation/tips.txt @@ -15,6 +15,7 @@ To see callchains in a more compact form: perf report -g folded Show individual samples with: perf script Limit to show entries above 5% only: perf report --percent-limit 5 Profiling branch (mis)predictions with: perf record -b / perf report +To show assembler sample contexts use perf record -b / perf script -F +brstackinsn --xed Treat branches as callchains: perf report --branch-history To count events in every 1000 msec: perf stat -I 1000 Print event counts in CSV format with: perf stat -x, @@ -34,3 +35,9 @@ Show current config key-value pairs: perf config --list Show user configuration overrides: perf config --user --list To add Node.js USDT(User-Level Statically Defined Tracing): perf buildid-cache --add `which node` To report cacheline events from previous recording: perf c2c report +To browse sample contexts use perf report --sample 10 and select in context menu +To separate samples by time use perf report --sort time,overhead,sym +To set sample time separation other than 100ms with --sort time use --time-quantum +Add -I to perf report to sample register values visible in perf report context. +To show IPC for sampling periods use perf record -e '{cycles,instructions}:S' and then browse context +To show context switches in perf report sample context add --switch-events to perf record. diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 0f11d5891301..0c52a01dc759 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -152,6 +152,13 @@ endif FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS) FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf +ifdef LIBZSTD_DIR + LIBZSTD_CFLAGS := -I$(LIBZSTD_DIR)/lib + LIBZSTD_LDFLAGS := -L$(LIBZSTD_DIR)/lib +endif +FEATURE_CHECK_CFLAGS-libzstd := $(LIBZSTD_CFLAGS) +FEATURE_CHECK_LDFLAGS-libzstd := $(LIBZSTD_LDFLAGS) + FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi # include ARCH specific config -include $(src-perf)/arch/$(SRCARCH)/Makefile @@ -227,6 +234,8 @@ FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS) FEATURE_CHECK_LDFLAGS-libaio = -lrt +FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl + CFLAGS += -fno-omit-frame-pointer CFLAGS += -ggdb3 CFLAGS += -funwind-tables @@ -713,7 +722,7 @@ else endif ifeq ($(feature-libbfd), 1) - EXTLIBS += -lbfd + EXTLIBS += -lbfd -lopcodes else # we are on a system that requires -liberty and (maybe) -lz # to link against -lbfd; test each case individually here @@ -724,12 +733,15 @@ else $(call feature_check,libbfd-liberty-z) ifeq ($(feature-libbfd-liberty), 1) - EXTLIBS += -lbfd -liberty + EXTLIBS += -lbfd -lopcodes -liberty + FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -ldl else ifeq ($(feature-libbfd-liberty-z), 1) - EXTLIBS += -lbfd -liberty -lz + EXTLIBS += -lbfd -lopcodes -liberty -lz + FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -lz -ldl endif endif + $(call feature_check,disassembler-four-args) endif ifdef NO_DEMANGLE @@ -782,6 +794,19 @@ ifndef NO_LZMA endif endif +ifndef NO_LIBZSTD + ifeq ($(feature-libzstd), 1) + CFLAGS += -DHAVE_ZSTD_SUPPORT + CFLAGS += $(LIBZSTD_CFLAGS) + LDFLAGS += $(LIBZSTD_LDFLAGS) + EXTLIBS += -lzstd + $(call detected,CONFIG_ZSTD) + else + msg := $(warning No libzstd found, disables trace compression, please install libzstd-dev[el] and/or set LIBZSTD_DIR); + NO_LIBZSTD := 1 + endif +endif + ifndef NO_BACKTRACE ifeq ($(feature-backtrace), 1) CFLAGS += -DHAVE_BACKTRACE_SUPPORT @@ -808,6 +833,10 @@ ifdef HAVE_KVM_STAT_SUPPORT CFLAGS += -DHAVE_KVM_STAT_SUPPORT endif +ifeq ($(feature-disassembler-four-args), 1) + CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE +endif + ifeq (${IS_64_BIT}, 1) ifndef NO_PERF_READ_VDSO32 $(call feature_check,compile-32) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 01f7555fd933..c706548d5b10 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -108,6 +108,9 @@ include ../scripts/utilities.mak # streaming for record mode. Currently Posix AIO trace streaming is # supported only when linking with glibc. # +# Define NO_LIBZSTD if you do not want support of Zstandard based runtime +# trace compression in record mode. +# # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALL @@ -481,8 +484,8 @@ $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_t mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh -$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl) - $(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@ +$(mmap_flags_array): $(linux_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl) + $(Q)$(SHELL) '$(mmap_flags_tbl)' $(linux_uapi_dir) $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@ mount_flags_array := $(beauty_outdir)/mount_flags_array.c mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index f0b1709a5ffb..92ee0b4378d4 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -343,6 +343,12 @@ 332 common statx __x64_sys_statx 333 common io_pgetevents __x64_sys_io_pgetevents 334 common rseq __x64_sys_rseq +# don't use numbers 387 through 423, add new calls after the last +# 'common' entry +424 common pidfd_send_signal __x64_sys_pidfd_send_signal +425 common io_uring_setup __x64_sys_io_uring_setup +426 common io_uring_enter __x64_sys_io_uring_enter +427 common io_uring_register __x64_sys_io_uring_register # # x32-specific system call numbers start at 512 to avoid cache impact @@ -361,7 +367,7 @@ 520 x32 execve __x32_compat_sys_execve/ptregs 521 x32 ptrace __x32_compat_sys_ptrace 522 x32 rt_sigpending __x32_compat_sys_rt_sigpending -523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait +523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait_time64 524 x32 rt_sigqueueinfo __x32_compat_sys_rt_sigqueueinfo 525 x32 sigaltstack __x32_compat_sys_sigaltstack 526 x32 timer_create __x32_compat_sys_timer_create @@ -375,7 +381,7 @@ 534 x32 preadv __x32_compat_sys_preadv64 535 x32 pwritev __x32_compat_sys_pwritev64 536 x32 rt_tgsigqueueinfo __x32_compat_sys_rt_tgsigqueueinfo -537 x32 recvmmsg __x32_compat_sys_recvmmsg +537 x32 recvmmsg __x32_compat_sys_recvmmsg_time64 538 x32 sendmmsg __x32_compat_sys_sendmmsg 539 x32 process_vm_readv __x32_compat_sys_process_vm_readv 540 x32 process_vm_writev __x32_compat_sys_process_vm_writev diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build index 7aab0be5fc5f..47f9c56e744f 100644 --- a/tools/perf/arch/x86/util/Build +++ b/tools/perf/arch/x86/util/Build @@ -14,5 +14,6 @@ perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o perf-$(CONFIG_AUXTRACE) += auxtrace.o +perf-$(CONFIG_AUXTRACE) += archinsn.o perf-$(CONFIG_AUXTRACE) += intel-pt.o perf-$(CONFIG_AUXTRACE) += intel-bts.o diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c new file mode 100644 index 000000000000..4237bb2e7fa2 --- /dev/null +++ b/tools/perf/arch/x86/util/archinsn.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "perf.h" +#include "archinsn.h" +#include "util/intel-pt-decoder/insn.h" +#include "machine.h" +#include "thread.h" +#include "symbol.h" + +void arch_fetch_insn(struct perf_sample *sample, + struct thread *thread, + struct machine *machine) +{ + struct insn insn; + int len; + bool is64bit = false; + + if (!sample->ip) + return; + len = thread__memcpy(thread, machine, sample->insn, sample->ip, sizeof(sample->insn), &is64bit); + if (len <= 0) + return; + insn_init(&insn, sample->insn, len, is64bit); + insn_get_length(&insn); + if (insn_complete(&insn) && insn.length <= len) + sample->insn_len = insn.length; +} diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 0c0a6e824934..2af067859966 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -224,7 +224,7 @@ static int do_threads(struct worker *worker, struct cpu_map *cpu) pthread_attr_t thread_attr, *attrp = NULL; cpu_set_t cpuset; unsigned int i, j; - int ret; + int ret = 0; if (!noaffinity) pthread_attr_init(&thread_attr); diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index 5a11534e96a0..fe85448abd45 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -293,7 +293,7 @@ static int do_threads(struct worker *worker, struct cpu_map *cpu) pthread_attr_t thread_attr, *attrp = NULL; cpu_set_t cpuset; unsigned int i, j; - int ret, events = EPOLLIN; + int ret = 0, events = EPOLLIN; if (oneshot) events |= EPOLLONESHOT; diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 98ad783efc69..a7784554a80d 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -39,6 +39,10 @@ #include <numa.h> #include <numaif.h> +#ifndef RUSAGE_THREAD +# define RUSAGE_THREAD 1 +#endif + /* * Regular printout to the terminal, supressed if -q is specified: */ diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index fa520f4b8095..b80eee455111 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -1975,7 +1975,7 @@ int cmd_kmem(int argc, const char **argv) goto out_delete; } - kmem_page_size = tep_get_page_size(evsel->tp_format->pevent); + kmem_page_size = tep_get_page_size(evsel->tp_format->tep); symbol_conf.use_callchain = true; } diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index c9f98d00c0e9..e0312a1c4792 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -70,10 +70,11 @@ int cmd_list(int argc, const char **argv) print_symbol_events(NULL, PERF_TYPE_HARDWARE, event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump); else if (strcmp(argv[i], "sw") == 0 || - strcmp(argv[i], "software") == 0) + strcmp(argv[i], "software") == 0) { print_symbol_events(NULL, PERF_TYPE_SOFTWARE, event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump); - else if (strcmp(argv[i], "cache") == 0 || + print_tool_events(NULL, raw_dump); + } else if (strcmp(argv[i], "cache") == 0 || strcmp(argv[i], "hwcache") == 0) print_hwcache_events(NULL, raw_dump); else if (strcmp(argv[i], "pmu") == 0) @@ -113,13 +114,14 @@ int cmd_list(int argc, const char **argv) event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump); print_symbol_events(s, PERF_TYPE_SOFTWARE, event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump); + print_tool_events(s, raw_dump); print_hwcache_events(s, raw_dump); print_pmu_events(s, raw_dump, !desc_flag, long_desc_flag, details_flag); print_tracepoint_events(NULL, s, raw_dump); print_sdt_events(NULL, s, raw_dump); - metricgroup__print(true, true, NULL, raw_dump, details_flag); + metricgroup__print(true, true, s, raw_dump, details_flag); free(s); } } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f3f7f3100336..c5e10552776a 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -62,6 +62,9 @@ struct switch_output { unsigned long time; const char *str; bool set; + char **filenames; + int num_files; + int cur_file; }; struct record { @@ -334,6 +337,41 @@ static int record__aio_enabled(struct record *rec) return rec->opts.nr_cblocks > 0; } +#define MMAP_FLUSH_DEFAULT 1 +static int record__mmap_flush_parse(const struct option *opt, + const char *str, + int unset) +{ + int flush_max; + struct record_opts *opts = (struct record_opts *)opt->value; + static struct parse_tag tags[] = { + { .tag = 'B', .mult = 1 }, + { .tag = 'K', .mult = 1 << 10 }, + { .tag = 'M', .mult = 1 << 20 }, + { .tag = 'G', .mult = 1 << 30 }, + { .tag = 0 }, + }; + + if (unset) + return 0; + + if (str) { + opts->mmap_flush = parse_tag_value(str, tags); + if (opts->mmap_flush == (int)-1) + opts->mmap_flush = strtol(str, NULL, 0); + } + + if (!opts->mmap_flush) + opts->mmap_flush = MMAP_FLUSH_DEFAULT; + + flush_max = perf_evlist__mmap_size(opts->mmap_pages); + flush_max /= 4; + if (opts->mmap_flush > flush_max) + opts->mmap_flush = flush_max; + + return 0; +} + static int process_synthesized_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample __maybe_unused, @@ -392,7 +430,7 @@ static int record__process_auxtrace(struct perf_tool *tool, size_t padding; u8 pad[8] = {0}; - if (!perf_data__is_pipe(data)) { + if (!perf_data__is_pipe(data) && !perf_data__is_dir(data)) { off_t file_offset; int fd = perf_data__fd(data); int err; @@ -543,7 +581,8 @@ static int record__mmap_evlist(struct record *rec, if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, opts->auxtrace_mmap_pages, opts->auxtrace_snapshot_mode, - opts->nr_cblocks, opts->affinity) < 0) { + opts->nr_cblocks, opts->affinity, + opts->mmap_flush) < 0) { if (errno == EPERM) { pr_err("Permission error mapping pages.\n" "Consider increasing " @@ -733,7 +772,7 @@ static void record__adjust_affinity(struct record *rec, struct perf_mmap *map) } static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist, - bool overwrite) + bool overwrite, bool synch) { u64 bytes_written = rec->bytes_written; int i; @@ -756,12 +795,19 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli off = record__aio_get_pos(trace_fd); for (i = 0; i < evlist->nr_mmaps; i++) { + u64 flush = 0; struct perf_mmap *map = &maps[i]; if (map->base) { record__adjust_affinity(rec, map); + if (synch) { + flush = map->flush; + map->flush = 1; + } if (!record__aio_enabled(rec)) { if (perf_mmap__push(map, rec, record__pushfn) != 0) { + if (synch) + map->flush = flush; rc = -1; goto out; } @@ -774,10 +820,14 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli idx = record__aio_sync(map, false); if (perf_mmap__aio_push(map, rec, idx, record__aio_pushfn, &off) != 0) { record__aio_set_pos(trace_fd, off); + if (synch) + map->flush = flush; rc = -1; goto out; } } + if (synch) + map->flush = flush; } if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode && @@ -803,15 +853,15 @@ out: return rc; } -static int record__mmap_read_all(struct record *rec) +static int record__mmap_read_all(struct record *rec, bool synch) { int err; - err = record__mmap_read_evlist(rec, rec->evlist, false); + err = record__mmap_read_evlist(rec, rec->evlist, false, synch); if (err) return err; - return record__mmap_read_evlist(rec, rec->evlist, true); + return record__mmap_read_evlist(rec, rec->evlist, true, synch); } static void record__init_features(struct record *rec) @@ -837,6 +887,8 @@ static void record__init_features(struct record *rec) if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns)) perf_header__clear_feat(&session->header, HEADER_CLOCKID); + perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT); + perf_header__clear_feat(&session->header, HEADER_STAT); } @@ -890,6 +942,7 @@ record__switch_output(struct record *rec, bool at_exit) { struct perf_data *data = &rec->data; int fd, err; + char *new_filename; /* Same Size: "2015122520103046"*/ char timestamp[] = "InvalidTimestamp"; @@ -910,7 +963,7 @@ record__switch_output(struct record *rec, bool at_exit) fd = perf_data__switch(data, timestamp, rec->session->header.data_offset, - at_exit); + at_exit, &new_filename); if (fd >= 0 && !at_exit) { rec->bytes_written = 0; rec->session->header.data_size = 0; @@ -920,6 +973,21 @@ record__switch_output(struct record *rec, bool at_exit) fprintf(stderr, "[ perf record: Dump %s.%s ]\n", data->path, timestamp); + if (rec->switch_output.num_files) { + int n = rec->switch_output.cur_file + 1; + + if (n >= rec->switch_output.num_files) + n = 0; + rec->switch_output.cur_file = n; + if (rec->switch_output.filenames[n]) { + remove(rec->switch_output.filenames[n]); + free(rec->switch_output.filenames[n]); + } + rec->switch_output.filenames[n] = new_filename; + } else { + free(new_filename); + } + /* Output tracking events */ if (!at_exit) { record__synthesize(rec, false); @@ -1093,7 +1161,7 @@ static int record__synthesize(struct record *rec, bool tail) return err; } - err = perf_event__synthesize_bpf_events(tool, process_synthesized_event, + err = perf_event__synthesize_bpf_events(session, process_synthesized_event, machine, opts); if (err < 0) pr_warning("Couldn't synthesize bpf events.\n"); @@ -1116,6 +1184,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) struct perf_data *data = &rec->data; struct perf_session *session; bool disabled = false, draining = false; + struct perf_evlist *sb_evlist = NULL; int fd; atexit(record__sig_exit); @@ -1216,6 +1285,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) goto out_child; } + if (!opts->no_bpf_event) + bpf_event__add_sb_event(&sb_evlist, &session->header.env); + + if (perf_evlist__start_sb_thread(sb_evlist, &rec->opts.target)) { + pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n"); + opts->no_bpf_event = true; + } + err = record__synthesize(rec, false); if (err < 0) goto out_child; @@ -1310,7 +1387,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (trigger_is_hit(&switch_output_trigger) || done || draining) perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING); - if (record__mmap_read_all(rec) < 0) { + if (record__mmap_read_all(rec, false) < 0) { trigger_error(&auxtrace_snapshot_trigger); trigger_error(&switch_output_trigger); err = -1; @@ -1411,6 +1488,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) record__synthesize_workload(rec, true); out_child: + record__mmap_read_all(rec, true); record__aio_mmap_read_sync(rec); if (forks) { @@ -1466,6 +1544,9 @@ out_child: out_delete_session: perf_session__delete(session); + + if (!opts->no_bpf_event) + perf_evlist__stop_sb_thread(sb_evlist); return status; } @@ -1813,6 +1894,7 @@ static struct record record = { .uses_mmap = true, .default_per_cpu = true, }, + .mmap_flush = MMAP_FLUSH_DEFAULT, }, .tool = { .sample = process_sample_event, @@ -1870,7 +1952,7 @@ static struct option __record_options[] = { OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize, "synthesize non-sample events at the end of output"), OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"), - OPT_BOOLEAN(0, "bpf-event", &record.opts.bpf_event, "record bpf events"), + OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "record bpf events"), OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq, "Fail if the specified frequency can't be used"), OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'", @@ -1879,6 +1961,9 @@ static struct option __record_options[] = { OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]", "number of mmap data pages and AUX area tracing mmap pages", record__parse_mmap_pages), + OPT_CALLBACK(0, "mmap-flush", &record.opts, "number", + "Minimal number of bytes that is extracted from mmap data pages (default: 1)", + record__mmap_flush_parse), OPT_BOOLEAN(0, "group", &record.opts.group, "put the counters into a counter group"), OPT_CALLBACK_NOOPT('g', NULL, &callchain_param, @@ -1968,9 +2053,11 @@ static struct option __record_options[] = { OPT_BOOLEAN(0, "timestamp-boundary", &record.timestamp_boundary, "Record timestamp boundary (time of first/last samples)"), OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str, - &record.switch_output.set, "signal,size,time", - "Switch output when receive SIGUSR2 or cross size,time threshold", + &record.switch_output.set, "signal or size[BKMG] or time[smhd]", + "Switch output when receiving SIGUSR2 (signal) or cross a size or time threshold", "signal"), + OPT_INTEGER(0, "switch-max-files", &record.switch_output.num_files, + "Limit number of switch output generated files"), OPT_BOOLEAN(0, "dry-run", &dry_run, "Parse options then exit"), #ifdef HAVE_AIO_SUPPORT @@ -2057,6 +2144,13 @@ int cmd_record(int argc, const char **argv) alarm(rec->switch_output.time); } + if (rec->switch_output.num_files) { + rec->switch_output.filenames = calloc(sizeof(char *), + rec->switch_output.num_files); + if (!rec->switch_output.filenames) + return -EINVAL; + } + /* * Allow aliases to facilitate the lookup of symbols for address * filters. Refer to auxtrace_parse_filters(). @@ -2182,6 +2276,7 @@ int cmd_record(int argc, const char **argv) pr_info("nr_cblocks: %d\n", rec->opts.nr_cblocks); pr_debug("affinity: %s\n", affinity_tags[rec->opts.affinity]); + pr_debug("mmap flush: %d\n", rec->opts.mmap_flush); err = __cmd_record(&record, argc, argv); out: diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index ee93c18a6685..4054eb1f98ac 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -47,9 +47,11 @@ #include <errno.h> #include <inttypes.h> #include <regex.h> +#include "sane_ctype.h" #include <signal.h> #include <linux/bitmap.h> #include <linux/stringify.h> +#include <linux/time64.h> #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> @@ -926,6 +928,43 @@ report_parse_callchain_opt(const struct option *opt, const char *arg, int unset) return parse_callchain_report_opt(arg); } +static int +parse_time_quantum(const struct option *opt, const char *arg, + int unset __maybe_unused) +{ + unsigned long *time_q = opt->value; + char *end; + + *time_q = strtoul(arg, &end, 0); + if (end == arg) + goto parse_err; + if (*time_q == 0) { + pr_err("time quantum cannot be 0"); + return -1; + } + while (isspace(*end)) + end++; + if (*end == 0) + return 0; + if (!strcmp(end, "s")) { + *time_q *= NSEC_PER_SEC; + return 0; + } + if (!strcmp(end, "ms")) { + *time_q *= NSEC_PER_MSEC; + return 0; + } + if (!strcmp(end, "us")) { + *time_q *= NSEC_PER_USEC; + return 0; + } + if (!strcmp(end, "ns")) + return 0; +parse_err: + pr_err("Cannot parse time quantum `%s'\n", arg); + return -1; +} + int report_parse_ignore_callees_opt(const struct option *opt __maybe_unused, const char *arg, int unset __maybe_unused) @@ -1044,10 +1083,9 @@ int cmd_report(int argc, const char **argv) OPT_BOOLEAN(0, "header-only", &report.header_only, "Show only data header."), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..." - " Please refer the man page for the complete list."), + sort_help("sort by key(s):")), OPT_STRING('F', "fields", &field_order, "key[,keys...]", - "output field(s): overhead, period, sample plus all of sort keys"), + sort_help("output field(s): overhead period sample ")), OPT_BOOLEAN(0, "show-cpu-utilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), OPT_BOOLEAN_FLAG(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, @@ -1120,6 +1158,8 @@ int cmd_report(int argc, const char **argv) OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"), + OPT_INTEGER(0, "samples", &symbol_conf.res_sample, + "Number of samples to save per histogram entry for individual browsing"), OPT_CALLBACK(0, "percent-limit", &report, "percent", "Don't show entries under that percent", parse_percent_limit), OPT_CALLBACK(0, "percentage", NULL, "relative|absolute", @@ -1147,6 +1187,10 @@ int cmd_report(int argc, const char **argv) OPT_CALLBACK(0, "percent-type", &report.annotation_opts, "local-period", "Set percent type local/global-period/hits", annotate_parse_percent_type), + OPT_BOOLEAN(0, "ns", &symbol_conf.nanosecs, "Show times in nanosecs"), + OPT_CALLBACK(0, "time-quantum", &symbol_conf.time_quantum, "time (ms|us|ns|s)", + "Set time quantum for time sort key (default 100ms)", + parse_time_quantum), OPT_END() }; struct perf_data data = { diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 53f78cf3113f..61cfd8f70989 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -29,10 +29,12 @@ #include "util/time-utils.h" #include "util/path.h" #include "print_binary.h" +#include "archinsn.h" #include <linux/bitmap.h> #include <linux/kernel.h> #include <linux/stringify.h> #include <linux/time64.h> +#include <sys/utsname.h> #include "asm/bug.h" #include "util/mem-events.h" #include "util/dump-insn.h" @@ -51,6 +53,8 @@ static char const *script_name; static char const *generate_script_lang; +static bool reltime; +static u64 initial_time; static bool debug_mode; static u64 last_timestamp; static u64 nr_unordered; @@ -58,11 +62,11 @@ static bool no_callchain; static bool latency_format; static bool system_wide; static bool print_flags; -static bool nanosecs; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); static struct perf_stat_config stat_config; static int max_blocks; +static bool native_arch; unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; @@ -684,15 +688,21 @@ static int perf_sample__fprintf_start(struct perf_sample *sample, } if (PRINT_FIELD(TIME)) { - nsecs = sample->time; + u64 t = sample->time; + if (reltime) { + if (!initial_time) + initial_time = sample->time; + t = sample->time - initial_time; + } + nsecs = t; secs = nsecs / NSEC_PER_SEC; nsecs -= secs * NSEC_PER_SEC; - if (nanosecs) + if (symbol_conf.nanosecs) printed += fprintf(fp, "%5lu.%09llu: ", secs, nsecs); else { char sample_time[32]; - timestamp__scnprintf_usec(sample->time, sample_time, sizeof(sample_time)); + timestamp__scnprintf_usec(t, sample_time, sizeof(sample_time)); printed += fprintf(fp, "%12s: ", sample_time); } } @@ -1227,6 +1237,12 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, return len + dlen; } +__weak void arch_fetch_insn(struct perf_sample *sample __maybe_unused, + struct thread *thread __maybe_unused, + struct machine *machine __maybe_unused) +{ +} + static int perf_sample__fprintf_insn(struct perf_sample *sample, struct perf_event_attr *attr, struct thread *thread, @@ -1234,9 +1250,12 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample, { int printed = 0; + if (sample->insn_len == 0 && native_arch) + arch_fetch_insn(sample, thread, machine); + if (PRINT_FIELD(INSNLEN)) printed += fprintf(fp, " ilen: %d", sample->insn_len); - if (PRINT_FIELD(INSN)) { + if (PRINT_FIELD(INSN) && sample->insn_len) { int i; printed += fprintf(fp, " insn:"); @@ -1922,6 +1941,13 @@ static int cleanup_scripting(void) return scripting_ops ? scripting_ops->stop_script() : 0; } +static bool filter_cpu(struct perf_sample *sample) +{ + if (cpu_list) + return !test_bit(sample->cpu, cpu_bitmap); + return false; +} + static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -1956,7 +1982,7 @@ static int process_sample_event(struct perf_tool *tool, if (al.filtered) goto out_put; - if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) + if (filter_cpu(sample)) goto out_put; if (scripting_ops) @@ -2041,9 +2067,11 @@ static int process_comm_event(struct perf_tool *tool, sample->tid = event->comm.tid; sample->pid = event->comm.pid; } - perf_sample__fprintf_start(sample, thread, evsel, + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, PERF_RECORD_COMM, stdout); - perf_event__fprintf(event, stdout); + perf_event__fprintf(event, stdout); + } ret = 0; out: thread__put(thread); @@ -2077,9 +2105,11 @@ static int process_namespaces_event(struct perf_tool *tool, sample->tid = event->namespaces.tid; sample->pid = event->namespaces.pid; } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_NAMESPACES, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_NAMESPACES, stdout); + perf_event__fprintf(event, stdout); + } ret = 0; out: thread__put(thread); @@ -2111,9 +2141,11 @@ static int process_fork_event(struct perf_tool *tool, sample->tid = event->fork.tid; sample->pid = event->fork.pid; } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_FORK, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_FORK, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; @@ -2141,9 +2173,11 @@ static int process_exit_event(struct perf_tool *tool, sample->tid = event->fork.tid; sample->pid = event->fork.pid; } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_EXIT, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_EXIT, stdout); + perf_event__fprintf(event, stdout); + } if (perf_event__process_exit(tool, event, sample, machine) < 0) err = -1; @@ -2177,9 +2211,11 @@ static int process_mmap_event(struct perf_tool *tool, sample->tid = event->mmap.tid; sample->pid = event->mmap.pid; } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_MMAP, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_MMAP, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; } @@ -2209,9 +2245,11 @@ static int process_mmap2_event(struct perf_tool *tool, sample->tid = event->mmap2.tid; sample->pid = event->mmap2.pid; } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_MMAP2, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_MMAP2, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; } @@ -2236,9 +2274,11 @@ static int process_switch_event(struct perf_tool *tool, return -1; } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_SWITCH, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_SWITCH, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; } @@ -2259,9 +2299,11 @@ process_lost_event(struct perf_tool *tool, if (thread == NULL) return -1; - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_LOST, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_LOST, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; } @@ -2948,7 +2990,8 @@ static int check_ev_match(char *dir_name, char *scriptname, * will list all statically runnable scripts, select one, execute it and * show the output in a perf browser. */ -int find_scripts(char **scripts_array, char **scripts_path_array) +int find_scripts(char **scripts_array, char **scripts_path_array, int num, + int pathlen) { struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN]; @@ -2993,7 +3036,10 @@ int find_scripts(char **scripts_array, char **scripts_path_array) /* Skip those real time scripts: xxxtop.p[yl] */ if (strstr(script_dirent->d_name, "top.")) continue; - sprintf(scripts_path_array[i], "%s/%s", lang_path, + if (i >= num) + break; + snprintf(scripts_path_array[i], pathlen, "%s/%s", + lang_path, script_dirent->d_name); temp = strchr(script_dirent->d_name, '.'); snprintf(scripts_array[i], @@ -3232,7 +3278,7 @@ static int parse_insn_trace(const struct option *opt __maybe_unused, { parse_output_fields(NULL, "+insn,-event,-period", 0); itrace_parse_synth_opts(opt, "i0ns", 0); - nanosecs = true; + symbol_conf.nanosecs = true; return 0; } @@ -3250,7 +3296,7 @@ static int parse_call_trace(const struct option *opt __maybe_unused, { parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0); itrace_parse_synth_opts(opt, "cewp", 0); - nanosecs = true; + symbol_conf.nanosecs = true; return 0; } @@ -3260,7 +3306,7 @@ static int parse_callret_trace(const struct option *opt __maybe_unused, { parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent,+flags", 0); itrace_parse_synth_opts(opt, "crewp", 0); - nanosecs = true; + symbol_conf.nanosecs = true; return 0; } @@ -3277,6 +3323,7 @@ int cmd_script(int argc, const char **argv) .set = false, .default_no_sample = true, }; + struct utsname uts; char *script_path = NULL; const char **__argv; int i, j, err = 0; @@ -3374,6 +3421,7 @@ int cmd_script(int argc, const char **argv) "Set the maximum stack depth when parsing the callchain, " "anything beyond the specified depth will be ignored. " "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)), + OPT_BOOLEAN(0, "reltime", &reltime, "Show time stamps relative to start"), OPT_BOOLEAN('I', "show-info", &show_full_info, "display extended information from perf.data file"), OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path, @@ -3395,7 +3443,7 @@ int cmd_script(int argc, const char **argv) OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"), OPT_INTEGER(0, "max-blocks", &max_blocks, "Maximum number of code blocks to dump with brstackinsn"), - OPT_BOOLEAN(0, "ns", &nanosecs, + OPT_BOOLEAN(0, "ns", &symbol_conf.nanosecs, "Use 9 decimal places when displaying time"), OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts", "Instruction Tracing options\n" ITRACE_HELP, @@ -3448,6 +3496,11 @@ int cmd_script(int argc, const char **argv) } } + if (script.time_str && reltime) { + fprintf(stderr, "Don't combine --reltime with --time\n"); + return -1; + } + if (itrace_synth_opts.callchain && itrace_synth_opts.callchain_sz > scripting_max_stack) scripting_max_stack = itrace_synth_opts.callchain_sz; @@ -3615,6 +3668,12 @@ int cmd_script(int argc, const char **argv) if (symbol__init(&session->header.env) < 0) goto out_delete; + uname(&uts); + if (!strcmp(uts.machine, session->header.env.arch) || + (!strcmp(uts.machine, "x86_64") && + !strcmp(session->header.env.arch, "i386"))) + native_arch = true; + script.session = session; script__setup_sample_type(&script); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 7b8f09b0b8bf..a3c060878faa 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -244,11 +244,25 @@ perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread, process_synthesized_event, NULL); } +static int read_single_counter(struct perf_evsel *counter, int cpu, + int thread, struct timespec *rs) +{ + if (counter->tool_event == PERF_TOOL_DURATION_TIME) { + u64 val = rs->tv_nsec + rs->tv_sec*1000000000ULL; + struct perf_counts_values *count = + perf_counts(counter->counts, cpu, thread); + count->ena = count->run = val; + count->val = val; + return 0; + } + return perf_evsel__read_counter(counter, cpu, thread); +} + /* * Read out the results of a single counter: * do not aggregate counts across CPUs in system-wide mode */ -static int read_counter(struct perf_evsel *counter) +static int read_counter(struct perf_evsel *counter, struct timespec *rs) { int nthreads = thread_map__nr(evsel_list->threads); int ncpus, cpu, thread; @@ -275,7 +289,7 @@ static int read_counter(struct perf_evsel *counter) * (via perf_evsel__read_counter) and sets threir count->loaded. */ if (!count->loaded && - perf_evsel__read_counter(counter, cpu, thread)) { + read_single_counter(counter, cpu, thread, rs)) { counter->counts->scaled = -1; perf_counts(counter->counts, cpu, thread)->ena = 0; perf_counts(counter->counts, cpu, thread)->run = 0; @@ -304,13 +318,13 @@ static int read_counter(struct perf_evsel *counter) return 0; } -static void read_counters(void) +static void read_counters(struct timespec *rs) { struct perf_evsel *counter; int ret; evlist__for_each_entry(evsel_list, counter) { - ret = read_counter(counter); + ret = read_counter(counter, rs); if (ret) pr_debug("failed to read counter %s\n", counter->name); @@ -323,11 +337,11 @@ static void process_interval(void) { struct timespec ts, rs; - read_counters(); - clock_gettime(CLOCK_MONOTONIC, &ts); diff_timespec(&rs, &ts, &ref_time); + read_counters(&rs); + if (STAT_RECORD) { if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSEC_PER_SEC + rs.tv_nsec, INTERVAL)) pr_err("failed to write stat round event\n"); @@ -593,7 +607,7 @@ try_again: * avoid arbitrary skew, we must read all counters before closing any * group leaders. */ - read_counters(); + read_counters(&(struct timespec) { .tv_nsec = t1-t0 }); perf_evlist__close(evsel_list); return WEXITSTATUS(status); @@ -718,7 +732,8 @@ static struct option stat_options[] = { "system-wide collection from all CPUs"), OPT_BOOLEAN('g', "group", &group, "put the counters into a counter group"), - OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"), + OPT_BOOLEAN(0, "scale", &stat_config.scale, + "Use --no-scale to disable counter scaling for multiplexing"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_INTEGER('r', "repeat", &stat_config.run_count, @@ -1307,6 +1322,7 @@ static void init_features(struct perf_session *session) for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++) perf_header__set_feat(&session->header, feat); + perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT); perf_header__clear_feat(&session->header, HEADER_BUILD_ID); perf_header__clear_feat(&session->header, HEADER_TRACING_DATA); perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 231a90daa958..fbbb0da43abb 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1189,30 +1189,26 @@ static int __cmd_top(struct perf_top *top) pthread_t thread, thread_process; int ret; - top->session = perf_session__new(NULL, false, NULL); - if (top->session == NULL) - return -1; - if (!top->annotation_opts.objdump_path) { ret = perf_env__lookup_objdump(&top->session->header.env, &top->annotation_opts.objdump_path); if (ret) - goto out_delete; + return ret; } ret = callchain_param__setup_sample_type(&callchain_param); if (ret) - goto out_delete; + return ret; if (perf_session__register_idle_thread(top->session) < 0) - goto out_delete; + return ret; if (top->nr_threads_synthesize > 1) perf_set_multithreaded(); init_process_thread(top); - ret = perf_event__synthesize_bpf_events(&top->tool, perf_event__process, + ret = perf_event__synthesize_bpf_events(top->session, perf_event__process, &top->session->machines.host, &top->record_opts); if (ret < 0) @@ -1227,13 +1223,18 @@ static int __cmd_top(struct perf_top *top) if (perf_hpp_list.socket) { ret = perf_env__read_cpu_topology_map(&perf_env); - if (ret < 0) - goto out_err_cpu_topo; + if (ret < 0) { + char errbuf[BUFSIZ]; + const char *err = str_error_r(-ret, errbuf, sizeof(errbuf)); + + ui__error("Could not read the CPU topology map: %s\n", err); + return ret; + } } ret = perf_top__start_counters(top); if (ret) - goto out_delete; + return ret; top->session->evlist = top->evlist; perf_session__set_id_hdr_size(top->session); @@ -1252,7 +1253,7 @@ static int __cmd_top(struct perf_top *top) ret = -1; if (pthread_create(&thread_process, NULL, process_thread, top)) { ui__error("Could not create process thread.\n"); - goto out_delete; + return ret; } if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui : @@ -1296,19 +1297,7 @@ out_join: out_join_thread: pthread_cond_signal(&top->qe.cond); pthread_join(thread_process, NULL); -out_delete: - perf_session__delete(top->session); - top->session = NULL; - return ret; - -out_err_cpu_topo: { - char errbuf[BUFSIZ]; - const char *err = str_error_r(-ret, errbuf, sizeof(errbuf)); - - ui__error("Could not read the CPU topology map: %s\n", err); - goto out_delete; -} } static int @@ -1388,6 +1377,7 @@ int cmd_top(int argc, const char **argv) * */ .overwrite = 0, .sample_time = true, + .sample_time_set = true, }, .max_stack = sysctl__max_stack(), .annotation_opts = annotation__default_options, @@ -1480,6 +1470,7 @@ int cmd_top(int argc, const char **argv) "Display raw encoding of assembly instructions (default)"), OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), + OPT_BOOLEAN(0, "no-bpf-event", &top.record_opts.no_bpf_event, "do not record bpf events"), OPT_STRING(0, "objdump", &top.annotation_opts.objdump_path, "path", "objdump binary to use for disassembly and annotations"), OPT_STRING('M', "disassembler-style", &top.annotation_opts.disassembler_style, "disassembler style", @@ -1511,6 +1502,7 @@ int cmd_top(int argc, const char **argv) "number of thread to run event synthesize"), OPT_END() }; + struct perf_evlist *sb_evlist = NULL; const char * const top_usage[] = { "perf top [<options>]", NULL @@ -1628,8 +1620,9 @@ int cmd_top(int argc, const char **argv) annotation_config__init(); symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); - if (symbol__init(NULL) < 0) - return -1; + status = symbol__init(NULL); + if (status < 0) + goto out_delete_evlist; sort__setup_elide(stdout); @@ -1639,10 +1632,28 @@ int cmd_top(int argc, const char **argv) signal(SIGWINCH, winch_sig); } + top.session = perf_session__new(NULL, false, NULL); + if (top.session == NULL) { + status = -1; + goto out_delete_evlist; + } + + if (!top.record_opts.no_bpf_event) + bpf_event__add_sb_event(&sb_evlist, &perf_env); + + if (perf_evlist__start_sb_thread(sb_evlist, target)) { + pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n"); + opts->no_bpf_event = true; + } + status = __cmd_top(&top); + if (!opts->no_bpf_event) + perf_evlist__stop_sb_thread(sb_evlist); + out_delete_evlist: perf_evlist__delete(top.evlist); + perf_session__delete(top.session); return status; } diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index 50df168be326..f470144d1a70 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -78,6 +78,8 @@ static void library_status(void) STATUS(HAVE_LZMA_SUPPORT, lzma); STATUS(HAVE_AUXTRACE_SUPPORT, get_cpuid); STATUS(HAVE_LIBBPF_SUPPORT, bpf); + STATUS(HAVE_AIO_SUPPORT, aio); + STATUS(HAVE_ZSTD_SUPPORT, zstd); } int cmd_version(int argc, const char **argv) diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index 05745f3ce912..999fe9170122 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -40,5 +40,6 @@ int cmd_mem(int argc, const char **argv); int cmd_data(int argc, const char **argv); int cmd_ftrace(int argc, const char **argv); -int find_scripts(char **scripts_array, char **scripts_path_array); +int find_scripts(char **scripts_array, char **scripts_path_array, int num, + int pathlen); #endif diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 7b55613924de..c68ee06cae63 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -103,7 +103,7 @@ done # diff with extra ignore lines check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' -check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"' +check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"' check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' # diff non-symmetric files diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c index f9b2161e1ca4..2422894a8194 100644 --- a/tools/perf/examples/bpf/augmented_raw_syscalls.c +++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c @@ -15,6 +15,7 @@ */ #include <unistd.h> +#include <linux/limits.h> #include <pid_filter.h> /* bpf-output associated map */ @@ -41,32 +42,110 @@ struct syscall_exit_args { struct augmented_filename { unsigned int size; int reserved; - char value[256]; + char value[PATH_MAX]; }; -#define SYS_OPEN 2 -#define SYS_ACCESS 21 -#define SYS_OPENAT 257 +/* syscalls where the first arg is a string */ +#define SYS_OPEN 2 +#define SYS_STAT 4 +#define SYS_LSTAT 6 +#define SYS_ACCESS 21 +#define SYS_EXECVE 59 +#define SYS_TRUNCATE 76 +#define SYS_CHDIR 80 +#define SYS_RENAME 82 +#define SYS_MKDIR 83 +#define SYS_RMDIR 84 +#define SYS_CREAT 85 +#define SYS_LINK 86 +#define SYS_UNLINK 87 +#define SYS_SYMLINK 88 +#define SYS_READLINK 89 +#define SYS_CHMOD 90 +#define SYS_CHOWN 92 +#define SYS_LCHOWN 94 +#define SYS_MKNOD 133 +#define SYS_STATFS 137 +#define SYS_PIVOT_ROOT 155 +#define SYS_CHROOT 161 +#define SYS_ACCT 163 +#define SYS_SWAPON 167 +#define SYS_SWAPOFF 168 +#define SYS_DELETE_MODULE 176 +#define SYS_SETXATTR 188 +#define SYS_LSETXATTR 189 +#define SYS_GETXATTR 191 +#define SYS_LGETXATTR 192 +#define SYS_LISTXATTR 194 +#define SYS_LLISTXATTR 195 +#define SYS_REMOVEXATTR 197 +#define SYS_LREMOVEXATTR 198 +#define SYS_MQ_OPEN 240 +#define SYS_MQ_UNLINK 241 +#define SYS_ADD_KEY 248 +#define SYS_REQUEST_KEY 249 +#define SYS_SYMLINKAT 266 +#define SYS_MEMFD_CREATE 319 + +/* syscalls where the first arg is a string */ + +#define SYS_PWRITE64 18 +#define SYS_EXECVE 59 +#define SYS_RENAME 82 +#define SYS_QUOTACTL 179 +#define SYS_FSETXATTR 190 +#define SYS_FGETXATTR 193 +#define SYS_FREMOVEXATTR 199 +#define SYS_MQ_TIMEDSEND 242 +#define SYS_REQUEST_KEY 249 +#define SYS_INOTIFY_ADD_WATCH 254 +#define SYS_OPENAT 257 +#define SYS_MKDIRAT 258 +#define SYS_MKNODAT 259 +#define SYS_FCHOWNAT 260 +#define SYS_FUTIMESAT 261 +#define SYS_NEWFSTATAT 262 +#define SYS_UNLINKAT 263 +#define SYS_RENAMEAT 264 +#define SYS_LINKAT 265 +#define SYS_READLINKAT 267 +#define SYS_FCHMODAT 268 +#define SYS_FACCESSAT 269 +#define SYS_UTIMENSAT 280 +#define SYS_NAME_TO_HANDLE_AT 303 +#define SYS_FINIT_MODULE 313 +#define SYS_RENAMEAT2 316 +#define SYS_EXECVEAT 322 +#define SYS_STATX 332 pid_filter(pids_filtered); +struct augmented_args_filename { + struct syscall_enter_args args; + struct augmented_filename filename; +}; + +bpf_map(augmented_filename_map, PERCPU_ARRAY, int, struct augmented_args_filename, 1); + SEC("raw_syscalls:sys_enter") int sys_enter(struct syscall_enter_args *args) { - struct { - struct syscall_enter_args args; - struct augmented_filename filename; - } augmented_args; - struct syscall *syscall; - unsigned int len = sizeof(augmented_args); + struct augmented_args_filename *augmented_args; + unsigned int len = sizeof(*augmented_args); const void *filename_arg = NULL; + struct syscall *syscall; + int key = 0; + + augmented_args = bpf_map_lookup_elem(&augmented_filename_map, &key); + if (augmented_args == NULL) + return 1; if (pid_filter__has(&pids_filtered, getpid())) return 0; - probe_read(&augmented_args.args, sizeof(augmented_args.args), args); + probe_read(&augmented_args->args, sizeof(augmented_args->args), args); - syscall = bpf_map_lookup_elem(&syscalls, &augmented_args.args.syscall_nr); + syscall = bpf_map_lookup_elem(&syscalls, &augmented_args->args.syscall_nr); if (syscall == NULL || !syscall->enabled) return 0; /* @@ -109,30 +188,105 @@ int sys_enter(struct syscall_enter_args *args) * * after the ctx memory access to prevent their down stream merging. */ - switch (augmented_args.args.syscall_nr) { + /* + * This table of what args are strings will be provided by userspace, + * in the syscalls map, i.e. we will already have to do the lookup to + * see if this specific syscall is filtered, so we can as well get more + * info about what syscall args are strings or pointers, and how many + * bytes to copy, per arg, etc. + * + * For now hard code it, till we have all the basic mechanisms in place + * to automate everything and make the kernel part be completely driven + * by information obtained in userspace for each kernel version and + * processor architecture, making the kernel part the same no matter what + * kernel version or processor architecture it runs on. + */ + switch (augmented_args->args.syscall_nr) { + case SYS_ACCT: + case SYS_ADD_KEY: + case SYS_CHDIR: + case SYS_CHMOD: + case SYS_CHOWN: + case SYS_CHROOT: + case SYS_CREAT: + case SYS_DELETE_MODULE: + case SYS_EXECVE: + case SYS_GETXATTR: + case SYS_LCHOWN: + case SYS_LGETXATTR: + case SYS_LINK: + case SYS_LISTXATTR: + case SYS_LLISTXATTR: + case SYS_LREMOVEXATTR: + case SYS_LSETXATTR: + case SYS_LSTAT: + case SYS_MEMFD_CREATE: + case SYS_MKDIR: + case SYS_MKNOD: + case SYS_MQ_OPEN: + case SYS_MQ_UNLINK: + case SYS_PIVOT_ROOT: + case SYS_READLINK: + case SYS_REMOVEXATTR: + case SYS_RENAME: + case SYS_REQUEST_KEY: + case SYS_RMDIR: + case SYS_SETXATTR: + case SYS_STAT: + case SYS_STATFS: + case SYS_SWAPOFF: + case SYS_SWAPON: + case SYS_SYMLINK: + case SYS_SYMLINKAT: + case SYS_TRUNCATE: + case SYS_UNLINK: case SYS_ACCESS: case SYS_OPEN: filename_arg = (const void *)args->args[0]; __asm__ __volatile__("": : :"memory"); break; + case SYS_EXECVEAT: + case SYS_FACCESSAT: + case SYS_FCHMODAT: + case SYS_FCHOWNAT: + case SYS_FGETXATTR: + case SYS_FINIT_MODULE: + case SYS_FREMOVEXATTR: + case SYS_FSETXATTR: + case SYS_FUTIMESAT: + case SYS_INOTIFY_ADD_WATCH: + case SYS_LINKAT: + case SYS_MKDIRAT: + case SYS_MKNODAT: + case SYS_MQ_TIMEDSEND: + case SYS_NAME_TO_HANDLE_AT: + case SYS_NEWFSTATAT: + case SYS_PWRITE64: + case SYS_QUOTACTL: + case SYS_READLINKAT: + case SYS_RENAMEAT: + case SYS_RENAMEAT2: + case SYS_STATX: + case SYS_UNLINKAT: + case SYS_UTIMENSAT: case SYS_OPENAT: filename_arg = (const void *)args->args[1]; break; } if (filename_arg != NULL) { - augmented_args.filename.reserved = 0; - augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, - sizeof(augmented_args.filename.value), + augmented_args->filename.reserved = 0; + augmented_args->filename.size = probe_read_str(&augmented_args->filename.value, + sizeof(augmented_args->filename.value), filename_arg); - if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) { - len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size; - len &= sizeof(augmented_args.filename.value) - 1; + if (augmented_args->filename.size < sizeof(augmented_args->filename.value)) { + len -= sizeof(augmented_args->filename.value) - augmented_args->filename.size; + len &= sizeof(augmented_args->filename.value) - 1; } } else { - len = sizeof(augmented_args.args); + len = sizeof(augmented_args->args); } /* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */ - return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len); + return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len); } SEC("raw_syscalls:sys_exit") diff --git a/tools/perf/perf.c b/tools/perf/perf.c index a11cb006f968..72df4b6fa36f 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -298,6 +298,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) use_pager = 1; commit_pager_choice(); + perf_env__init(&perf_env); perf_env__set_cmdline(&perf_env, argc, argv); status = p->fn(argc, argv); perf_config__exit(); diff --git a/tools/perf/perf.h b/tools/perf/perf.h index b120e547ddc7..369eae61068d 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -66,7 +66,7 @@ struct record_opts { bool ignore_missing_thread; bool strict_freq; bool sample_id; - bool bpf_event; + bool no_bpf_event; unsigned int freq; unsigned int mmap_pages; unsigned int auxtrace_mmap_pages; @@ -85,6 +85,7 @@ struct record_opts { u64 clockid_res_ns; int nr_cblocks; int affinity; + int mmap_flush; }; enum perf_affinity { diff --git a/tools/perf/pmu-events/arch/powerpc/power8/other.json b/tools/perf/pmu-events/arch/powerpc/power8/other.json index 704302c3e67d..9dc2f6b70354 100644 --- a/tools/perf/pmu-events/arch/powerpc/power8/other.json +++ b/tools/perf/pmu-events/arch/powerpc/power8/other.json @@ -348,18 +348,6 @@ "PublicDescription": "" }, {, - "EventCode": "0x517082", - "EventName": "PM_CO_DISP_FAIL", - "BriefDescription": "CO dispatch failed due to all CO machines being busy", - "PublicDescription": "" - }, - {, - "EventCode": "0x527084", - "EventName": "PM_CO_TM_SC_FOOTPRINT", - "BriefDescription": "L2 did a cleanifdirty CO to the L3 (ie created an SC line in the L3)", - "PublicDescription": "" - }, - {, "EventCode": "0x3608a", "EventName": "PM_CO_USAGE", "BriefDescription": "Continuous 16 cycle(2to1) window where this signals rotates thru sampling each L2 CO machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running", @@ -1578,36 +1566,12 @@ "PublicDescription": "" }, {, - "EventCode": "0x617082", - "EventName": "PM_ISIDE_DISP", - "BriefDescription": "All i-side dispatch attempts", - "PublicDescription": "" - }, - {, - "EventCode": "0x627084", - "EventName": "PM_ISIDE_DISP_FAIL", - "BriefDescription": "All i-side dispatch attempts that failed due to a addr collision with another machine", - "PublicDescription": "" - }, - {, - "EventCode": "0x627086", - "EventName": "PM_ISIDE_DISP_FAIL_OTHER", - "BriefDescription": "All i-side dispatch attempts that failed due to a reason other than addrs collision", - "PublicDescription": "" - }, - {, "EventCode": "0x4608e", "EventName": "PM_ISIDE_L2MEMACC", "BriefDescription": "valid when first beat of data comes in for an i-side fetch where data came from mem(or L4)", "PublicDescription": "" }, {, - "EventCode": "0x44608e", - "EventName": "PM_ISIDE_MRU_TOUCH", - "BriefDescription": "Iside L2 MRU touch", - "PublicDescription": "" - }, - {, "EventCode": "0x30ac", "EventName": "PM_ISU_REF_FX0", "BriefDescription": "FX0 ISU reject", @@ -1734,222 +1698,36 @@ "PublicDescription": "" }, {, - "EventCode": "0x417080", - "EventName": "PM_L2_CASTOUT_MOD", - "BriefDescription": "L2 Castouts - Modified (M, Mu, Me)", - "PublicDescription": "" - }, - {, - "EventCode": "0x417082", - "EventName": "PM_L2_CASTOUT_SHR", - "BriefDescription": "L2 Castouts - Shared (T, Te, Si, S)", - "PublicDescription": "" - }, - {, "EventCode": "0x27084", "EventName": "PM_L2_CHIP_PUMP", "BriefDescription": "RC requests that were local on chip pump attempts", "PublicDescription": "" }, {, - "EventCode": "0x427086", - "EventName": "PM_L2_DC_INV", - "BriefDescription": "Dcache invalidates from L2", - "PublicDescription": "" - }, - {, - "EventCode": "0x44608c", - "EventName": "PM_L2_DISP_ALL_L2MISS", - "BriefDescription": "All successful Ld/St dispatches for this thread that were an L2miss", - "PublicDescription": "" - }, - {, "EventCode": "0x27086", "EventName": "PM_L2_GROUP_PUMP", "BriefDescription": "RC requests that were on Node Pump attempts", "PublicDescription": "" }, {, - "EventCode": "0x626084", - "EventName": "PM_L2_GRP_GUESS_CORRECT", - "BriefDescription": "L2 guess grp and guess was correct (data intra-6chip AND ^on-chip)", - "PublicDescription": "" - }, - {, - "EventCode": "0x626086", - "EventName": "PM_L2_GRP_GUESS_WRONG", - "BriefDescription": "L2 guess grp and guess was not correct (ie data on-chip OR beyond-6chip)", - "PublicDescription": "" - }, - {, - "EventCode": "0x427084", - "EventName": "PM_L2_IC_INV", - "BriefDescription": "Icache Invalidates from L2", - "PublicDescription": "" - }, - {, - "EventCode": "0x436088", - "EventName": "PM_L2_INST", - "BriefDescription": "All successful I-side dispatches for this thread (excludes i_l2mru_tch reqs)", - "PublicDescription": "" - }, - {, - "EventCode": "0x43608a", - "EventName": "PM_L2_INST_MISS", - "BriefDescription": "All successful i-side dispatches that were an L2miss for this thread (excludes i_l2mru_tch reqs)", - "PublicDescription": "" - }, - {, - "EventCode": "0x416080", - "EventName": "PM_L2_LD", - "BriefDescription": "All successful D-side Load dispatches for this thread", - "PublicDescription": "" - }, - {, - "EventCode": "0x437088", - "EventName": "PM_L2_LD_DISP", - "BriefDescription": "All successful load dispatches", - "PublicDescription": "" - }, - {, - "EventCode": "0x43708a", - "EventName": "PM_L2_LD_HIT", - "BriefDescription": "All successful load dispatches that were L2 hits", - "PublicDescription": "" - }, - {, - "EventCode": "0x426084", - "EventName": "PM_L2_LD_MISS", - "BriefDescription": "All successful D-Side Load dispatches that were an L2miss for this thread", - "PublicDescription": "" - }, - {, - "EventCode": "0x616080", - "EventName": "PM_L2_LOC_GUESS_CORRECT", - "BriefDescription": "L2 guess loc and guess was correct (ie data local)", - "PublicDescription": "" - }, - {, - "EventCode": "0x616082", - "EventName": "PM_L2_LOC_GUESS_WRONG", - "BriefDescription": "L2 guess loc and guess was not correct (ie data not on chip)", - "PublicDescription": "" - }, - {, - "EventCode": "0x516080", - "EventName": "PM_L2_RCLD_DISP", - "BriefDescription": "L2 RC load dispatch attempt", - "PublicDescription": "" - }, - {, - "EventCode": "0x516082", - "EventName": "PM_L2_RCLD_DISP_FAIL_ADDR", - "BriefDescription": "L2 RC load dispatch attempt failed due to address collision with RC/CO/SN/SQ", - "PublicDescription": "" - }, - {, - "EventCode": "0x526084", - "EventName": "PM_L2_RCLD_DISP_FAIL_OTHER", - "BriefDescription": "L2 RC load dispatch attempt failed due to other reasons", - "PublicDescription": "" - }, - {, - "EventCode": "0x536088", - "EventName": "PM_L2_RCST_DISP", - "BriefDescription": "L2 RC store dispatch attempt", - "PublicDescription": "" - }, - {, - "EventCode": "0x53608a", - "EventName": "PM_L2_RCST_DISP_FAIL_ADDR", - "BriefDescription": "L2 RC store dispatch attempt failed due to address collision with RC/CO/SN/SQ", - "PublicDescription": "" - }, - {, - "EventCode": "0x54608c", - "EventName": "PM_L2_RCST_DISP_FAIL_OTHER", - "BriefDescription": "L2 RC store dispatch attempt failed due to other reasons", - "PublicDescription": "" - }, - {, - "EventCode": "0x537088", - "EventName": "PM_L2_RC_ST_DONE", - "BriefDescription": "RC did st to line that was Tx or Sx", - "PublicDescription": "" - }, - {, - "EventCode": "0x63708a", - "EventName": "PM_L2_RTY_LD", - "BriefDescription": "RC retries on PB for any load from core", - "PublicDescription": "" - }, - {, "EventCode": "0x3708a", "EventName": "PM_L2_RTY_ST", "BriefDescription": "RC retries on PB for any store from core", "PublicDescription": "" }, {, - "EventCode": "0x54708c", - "EventName": "PM_L2_SN_M_RD_DONE", - "BriefDescription": "SNP dispatched for a read and was M", - "PublicDescription": "" - }, - {, - "EventCode": "0x54708e", - "EventName": "PM_L2_SN_M_WR_DONE", - "BriefDescription": "SNP dispatched for a write and was M", - "PublicDescription": "" - }, - {, - "EventCode": "0x53708a", - "EventName": "PM_L2_SN_SX_I_DONE", - "BriefDescription": "SNP dispatched and went from Sx or Tx to Ix", - "PublicDescription": "" - }, - {, "EventCode": "0x17080", "EventName": "PM_L2_ST", "BriefDescription": "All successful D-side store dispatches for this thread", "PublicDescription": "" }, {, - "EventCode": "0x44708c", - "EventName": "PM_L2_ST_DISP", - "BriefDescription": "All successful store dispatches", - "PublicDescription": "" - }, - {, - "EventCode": "0x44708e", - "EventName": "PM_L2_ST_HIT", - "BriefDescription": "All successful store dispatches that were L2Hits", - "PublicDescription": "" - }, - {, "EventCode": "0x17082", "EventName": "PM_L2_ST_MISS", "BriefDescription": "All successful D-side store dispatches for this thread that were L2 Miss", "PublicDescription": "" }, {, - "EventCode": "0x636088", - "EventName": "PM_L2_SYS_GUESS_CORRECT", - "BriefDescription": "L2 guess sys and guess was correct (ie data beyond-6chip)", - "PublicDescription": "" - }, - {, - "EventCode": "0x63608a", - "EventName": "PM_L2_SYS_GUESS_WRONG", - "BriefDescription": "L2 guess sys and guess was not correct (ie data ^beyond-6chip)", - "PublicDescription": "" - }, - {, - "EventCode": "0x617080", - "EventName": "PM_L2_SYS_PUMP", - "BriefDescription": "RC requests that were system pump attempts", - "PublicDescription": "" - }, - {, "EventCode": "0x1e05e", "EventName": "PM_L2_TM_REQ_ABORT", "BriefDescription": "TM abort", @@ -1962,36 +1740,12 @@ "PublicDescription": "" }, {, - "EventCode": "0x23808a", - "EventName": "PM_L3_CINJ", - "BriefDescription": "l3 ci of cache inject", - "PublicDescription": "" - }, - {, - "EventCode": "0x128084", - "EventName": "PM_L3_CI_HIT", - "BriefDescription": "L3 Castins Hit (total count", - "PublicDescription": "" - }, - {, - "EventCode": "0x128086", - "EventName": "PM_L3_CI_MISS", - "BriefDescription": "L3 castins miss (total count", - "PublicDescription": "" - }, - {, "EventCode": "0x819082", "EventName": "PM_L3_CI_USAGE", "BriefDescription": "rotating sample of 16 CI or CO actives", "PublicDescription": "" }, {, - "EventCode": "0x438088", - "EventName": "PM_L3_CO", - "BriefDescription": "l3 castout occurring ( does not include casthrough or log writes (cinj/dmaw)", - "PublicDescription": "" - }, - {, "EventCode": "0x83908b", "EventName": "PM_L3_CO0_ALLOC", "BriefDescription": "lifetime, sample of CO machine 0 valid", @@ -2010,120 +1764,18 @@ "PublicDescription": "" }, {, - "EventCode": "0x238088", - "EventName": "PM_L3_CO_LCO", - "BriefDescription": "Total L3 castouts occurred on LCO", - "PublicDescription": "" - }, - {, "EventCode": "0x28084", "EventName": "PM_L3_CO_MEM", "BriefDescription": "L3 CO to memory OR of port 0 and 1 ( lossy)", "PublicDescription": "" }, {, - "EventCode": "0xb19082", - "EventName": "PM_L3_GRP_GUESS_CORRECT", - "BriefDescription": "Initial scope=group and data from same group (near) (pred successful)", - "PublicDescription": "" - }, - {, - "EventCode": "0xb3908a", - "EventName": "PM_L3_GRP_GUESS_WRONG_HIGH", - "BriefDescription": "Initial scope=group but data from local node. Predition too high", - "PublicDescription": "" - }, - {, - "EventCode": "0xb39088", - "EventName": "PM_L3_GRP_GUESS_WRONG_LOW", - "BriefDescription": "Initial scope=group but data from outside group (far or rem). Prediction too Low", - "PublicDescription": "" - }, - {, - "EventCode": "0x218080", - "EventName": "PM_L3_HIT", - "BriefDescription": "L3 Hits", - "PublicDescription": "" - }, - {, - "EventCode": "0x138088", - "EventName": "PM_L3_L2_CO_HIT", - "BriefDescription": "L2 castout hits", - "PublicDescription": "" - }, - {, - "EventCode": "0x13808a", - "EventName": "PM_L3_L2_CO_MISS", - "BriefDescription": "L2 castout miss", - "PublicDescription": "" - }, - {, - "EventCode": "0x14808c", - "EventName": "PM_L3_LAT_CI_HIT", - "BriefDescription": "L3 Lateral Castins Hit", - "PublicDescription": "" - }, - {, - "EventCode": "0x14808e", - "EventName": "PM_L3_LAT_CI_MISS", - "BriefDescription": "L3 Lateral Castins Miss", - "PublicDescription": "" - }, - {, - "EventCode": "0x228084", - "EventName": "PM_L3_LD_HIT", - "BriefDescription": "L3 demand LD Hits", - "PublicDescription": "" - }, - {, - "EventCode": "0x228086", - "EventName": "PM_L3_LD_MISS", - "BriefDescription": "L3 demand LD Miss", - "PublicDescription": "" - }, - {, "EventCode": "0x1e052", "EventName": "PM_L3_LD_PREF", "BriefDescription": "L3 Load Prefetches", "PublicDescription": "" }, {, - "EventCode": "0xb19080", - "EventName": "PM_L3_LOC_GUESS_CORRECT", - "BriefDescription": "initial scope=node/chip and data from local node (local) (pred successful)", - "PublicDescription": "" - }, - {, - "EventCode": "0xb29086", - "EventName": "PM_L3_LOC_GUESS_WRONG", - "BriefDescription": "Initial scope=node but data from out side local node (near or far or rem). Prediction too Low", - "PublicDescription": "" - }, - {, - "EventCode": "0x218082", - "EventName": "PM_L3_MISS", - "BriefDescription": "L3 Misses", - "PublicDescription": "" - }, - {, - "EventCode": "0x54808c", - "EventName": "PM_L3_P0_CO_L31", - "BriefDescription": "l3 CO to L3.1 (lco) port 0", - "PublicDescription": "" - }, - {, - "EventCode": "0x538088", - "EventName": "PM_L3_P0_CO_MEM", - "BriefDescription": "l3 CO to memory port 0", - "PublicDescription": "" - }, - {, - "EventCode": "0x929084", - "EventName": "PM_L3_P0_CO_RTY", - "BriefDescription": "L3 CO received retry port 0", - "PublicDescription": "" - }, - {, "EventCode": "0xa29084", "EventName": "PM_L3_P0_GRP_PUMP", "BriefDescription": "L3 pf sent with grp scope port 0", @@ -2148,120 +1800,6 @@ "PublicDescription": "" }, {, - "EventCode": "0xa19080", - "EventName": "PM_L3_P0_NODE_PUMP", - "BriefDescription": "L3 pf sent with nodal scope port 0", - "PublicDescription": "" - }, - {, - "EventCode": "0x919080", - "EventName": "PM_L3_P0_PF_RTY", - "BriefDescription": "L3 PF received retry port 0", - "PublicDescription": "" - }, - {, - "EventCode": "0x939088", - "EventName": "PM_L3_P0_SN_HIT", - "BriefDescription": "L3 snoop hit port 0", - "PublicDescription": "" - }, - {, - "EventCode": "0x118080", - "EventName": "PM_L3_P0_SN_INV", - "BriefDescription": "Port0 snooper detects someone doing a store to a line thats Sx", - "PublicDescription": "" - }, - {, - "EventCode": "0x94908c", - "EventName": "PM_L3_P0_SN_MISS", - "BriefDescription": "L3 snoop miss port 0", - "PublicDescription": "" - }, - {, - "EventCode": "0xa39088", - "EventName": "PM_L3_P0_SYS_PUMP", - "BriefDescription": "L3 pf sent with sys scope port 0", - "PublicDescription": "" - }, - {, - "EventCode": "0x54808e", - "EventName": "PM_L3_P1_CO_L31", - "BriefDescription": "l3 CO to L3.1 (lco) port 1", - "PublicDescription": "" - }, - {, - "EventCode": "0x53808a", - "EventName": "PM_L3_P1_CO_MEM", - "BriefDescription": "l3 CO to memory port 1", - "PublicDescription": "" - }, - {, - "EventCode": "0x929086", - "EventName": "PM_L3_P1_CO_RTY", - "BriefDescription": "L3 CO received retry port 1", - "PublicDescription": "" - }, - {, - "EventCode": "0xa29086", - "EventName": "PM_L3_P1_GRP_PUMP", - "BriefDescription": "L3 pf sent with grp scope port 1", - "PublicDescription": "" - }, - {, - "EventCode": "0x528086", - "EventName": "PM_L3_P1_LCO_DATA", - "BriefDescription": "lco sent with data port 1", - "PublicDescription": "" - }, - {, - "EventCode": "0x518082", - "EventName": "PM_L3_P1_LCO_NO_DATA", - "BriefDescription": "dataless l3 lco sent port 1", - "PublicDescription": "" - }, - {, - "EventCode": "0xa4908e", - "EventName": "PM_L3_P1_LCO_RTY", - "BriefDescription": "L3 LCO received retry port 1", - "PublicDescription": "" - }, - {, - "EventCode": "0xa19082", - "EventName": "PM_L3_P1_NODE_PUMP", - "BriefDescription": "L3 pf sent with nodal scope port 1", - "PublicDescription": "" - }, - {, - "EventCode": "0x919082", - "EventName": "PM_L3_P1_PF_RTY", - "BriefDescription": "L3 PF received retry port 1", - "PublicDescription": "" - }, - {, - "EventCode": "0x93908a", - "EventName": "PM_L3_P1_SN_HIT", - "BriefDescription": "L3 snoop hit port 1", - "PublicDescription": "" - }, - {, - "EventCode": "0x118082", - "EventName": "PM_L3_P1_SN_INV", - "BriefDescription": "Port1 snooper detects someone doing a store to a line thats Sx", - "PublicDescription": "" - }, - {, - "EventCode": "0x94908e", - "EventName": "PM_L3_P1_SN_MISS", - "BriefDescription": "L3 snoop miss port 1", - "PublicDescription": "" - }, - {, - "EventCode": "0xa3908a", - "EventName": "PM_L3_P1_SYS_PUMP", - "BriefDescription": "L3 pf sent with sys scope port 1", - "PublicDescription": "" - }, - {, "EventCode": "0x84908d", "EventName": "PM_L3_PF0_ALLOC", "BriefDescription": "lifetime, sample of PF machine 0 valid", @@ -2274,12 +1812,6 @@ "PublicDescription": "" }, {, - "EventCode": "0x428084", - "EventName": "PM_L3_PF_HIT_L3", - "BriefDescription": "l3 pf hit in l3", - "PublicDescription": "" - }, - {, "EventCode": "0x18080", "EventName": "PM_L3_PF_MISS_L3", "BriefDescription": "L3 Prefetch missed in L3", @@ -2370,42 +1902,12 @@ "PublicDescription": "" }, {, - "EventCode": "0xb29084", - "EventName": "PM_L3_SYS_GUESS_CORRECT", - "BriefDescription": "Initial scope=system and data from outside group (far or rem)(pred successful)", - "PublicDescription": "" - }, - {, - "EventCode": "0xb4908c", - "EventName": "PM_L3_SYS_GUESS_WRONG", - "BriefDescription": "Initial scope=system but data from local or near. Predction too high", - "PublicDescription": "" - }, - {, - "EventCode": "0x24808e", - "EventName": "PM_L3_TRANS_PF", - "BriefDescription": "L3 Transient prefetch", - "PublicDescription": "" - }, - {, "EventCode": "0x18081", "EventName": "PM_L3_WI0_ALLOC", "BriefDescription": "lifetime, sample of Write Inject machine 0 valid", "PublicDescription": "0.0" }, {, - "EventCode": "0x418080", - "EventName": "PM_L3_WI0_BUSY", - "BriefDescription": "lifetime, sample of Write Inject machine 0 valid", - "PublicDescription": "" - }, - {, - "EventCode": "0x418082", - "EventName": "PM_L3_WI_USAGE", - "BriefDescription": "rotating sample of 8 WI actives", - "PublicDescription": "" - }, - {, "EventCode": "0xc080", "EventName": "PM_LD_REF_L1_LSU0", "BriefDescription": "LS0 L1 D cache load references counted at finish, gated by reject", @@ -3312,12 +2814,6 @@ "PublicDescription": "" }, {, - "EventCode": "0x328084", - "EventName": "PM_NON_TM_RST_SC", - "BriefDescription": "non tm snp rst tm sc", - "PublicDescription": "" - }, - {, "EventCode": "0x2001a", "EventName": "PM_NTCG_ALL_FIN", "BriefDescription": "Cycles after all instructions have finished to group completed", @@ -3420,24 +2916,6 @@ "PublicDescription": "" }, {, - "EventCode": "0x34808e", - "EventName": "PM_RD_CLEARING_SC", - "BriefDescription": "rd clearing sc", - "PublicDescription": "" - }, - {, - "EventCode": "0x34808c", - "EventName": "PM_RD_FORMING_SC", - "BriefDescription": "rd forming sc", - "PublicDescription": "" - }, - {, - "EventCode": "0x428086", - "EventName": "PM_RD_HIT_PF", - "BriefDescription": "rd machine hit l3 pf machine", - "PublicDescription": "" - }, - {, "EventCode": "0x20004", "EventName": "PM_REAL_SRQ_FULL", "BriefDescription": "Out of real srq entries", @@ -3504,18 +2982,6 @@ "PublicDescription": "TLBIE snoopSnoop TLBIE" }, {, - "EventCode": "0x338088", - "EventName": "PM_SNP_TM_HIT_M", - "BriefDescription": "snp tm st hit m mu", - "PublicDescription": "" - }, - {, - "EventCode": "0x33808a", - "EventName": "PM_SNP_TM_HIT_T", - "BriefDescription": "snp tm_st_hit t tn te", - "PublicDescription": "" - }, - {, "EventCode": "0x4608c", "EventName": "PM_SN_USAGE", "BriefDescription": "Continuous 16 cycle(2to1) window where this signals rotates thru sampling each L2 SN machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running", @@ -3534,12 +3000,6 @@ "PublicDescription": "STCX executed reported at sent to nest42" }, {, - "EventCode": "0x717080", - "EventName": "PM_ST_CAUSED_FAIL", - "BriefDescription": "Non TM St caused any thread to fail", - "PublicDescription": "" - }, - {, "EventCode": "0x3090", "EventName": "PM_SWAP_CANCEL", "BriefDescription": "SWAP cancel , rtag not available", @@ -3624,18 +3084,6 @@ "PublicDescription": "" }, {, - "EventCode": "0x318082", - "EventName": "PM_TM_CAM_OVERFLOW", - "BriefDescription": "l3 tm cam overflow during L2 co of SC", - "PublicDescription": "" - }, - {, - "EventCode": "0x74708c", - "EventName": "PM_TM_CAP_OVERFLOW", - "BriefDescription": "TM Footprint Capactiy Overflow", - "PublicDescription": "" - }, - {, "EventCode": "0x20ba", "EventName": "PM_TM_END_ALL", "BriefDescription": "Tm any tend", @@ -3690,48 +3138,6 @@ "PublicDescription": "Transactional conflict from LSU, whatever gets reported to texas 42" }, {, - "EventCode": "0x727086", - "EventName": "PM_TM_FAV_CAUSED_FAIL", - "BriefDescription": "TM Load (fav) caused another thread to fail", - "PublicDescription": "" - }, - {, - "EventCode": "0x717082", - "EventName": "PM_TM_LD_CAUSED_FAIL", - "BriefDescription": "Non TM Ld caused any thread to fail", - "PublicDescription": "" - }, - {, - "EventCode": "0x727084", - "EventName": "PM_TM_LD_CONF", - "BriefDescription": "TM Load (fav or non-fav) ran into conflict (failed)", - "PublicDescription": "" - }, - {, - "EventCode": "0x328086", - "EventName": "PM_TM_RST_SC", - "BriefDescription": "tm snp rst tm sc", - "PublicDescription": "" - }, - {, - "EventCode": "0x318080", - "EventName": "PM_TM_SC_CO", - "BriefDescription": "l3 castout tm Sc line", - "PublicDescription": "" - }, - {, - "EventCode": "0x73708a", - "EventName": "PM_TM_ST_CAUSED_FAIL", - "BriefDescription": "TM Store (fav or non-fav) caused another thread to fail", - "PublicDescription": "" - }, - {, - "EventCode": "0x737088", - "EventName": "PM_TM_ST_CONF", - "BriefDescription": "TM Store (fav or non-fav) ran into conflict (failed)", - "PublicDescription": "" - }, - {, "EventCode": "0x20bc", "EventName": "PM_TM_TBEGIN", "BriefDescription": "Tm nested tbegin", diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json index e7a3524b748f..68618152ea2c 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json @@ -4,7 +4,7 @@ "EventCode": "128", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", - "PublicDescription": "Counter:128 Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" + "PublicDescription": "L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { "Unit": "CPU-M-CF", diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/branch.json b/tools/perf/pmu-events/arch/x86/amdfam17h/branch.json new file mode 100644 index 000000000000..93ddfd8053ca --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdfam17h/branch.json @@ -0,0 +1,12 @@ +[ + { + "EventName": "bp_l1_btb_correct", + "EventCode": "0x8a", + "BriefDescription": "L1 BTB Correction." + }, + { + "EventName": "bp_l2_btb_correct", + "EventCode": "0x8b", + "BriefDescription": "L2 BTB Correction." + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json b/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json new file mode 100644 index 000000000000..fad4af9142cb --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json @@ -0,0 +1,287 @@ +[ + { + "EventName": "ic_fw32", + "EventCode": "0x80", + "BriefDescription": "The number of 32B fetch windows transferred from IC pipe to DE instruction decoder (includes non-cacheable and cacheable fill responses)." + }, + { + "EventName": "ic_fw32_miss", + "EventCode": "0x81", + "BriefDescription": "The number of 32B fetch windows tried to read the L1 IC and missed in the full tag." + }, + { + "EventName": "ic_cache_fill_l2", + "EventCode": "0x82", + "BriefDescription": "The number of 64 byte instruction cache line was fulfilled from the L2 cache." + }, + { + "EventName": "ic_cache_fill_sys", + "EventCode": "0x83", + "BriefDescription": "The number of 64 byte instruction cache line fulfilled from system memory or another cache." + }, + { + "EventName": "bp_l1_tlb_miss_l2_hit", + "EventCode": "0x84", + "BriefDescription": "The number of instruction fetches that miss in the L1 ITLB but hit in the L2 ITLB." + }, + { + "EventName": "bp_l1_tlb_miss_l2_miss", + "EventCode": "0x85", + "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs." + }, + { + "EventName": "bp_snp_re_sync", + "EventCode": "0x86", + "BriefDescription": "The number of pipeline restarts caused by invalidating probes that hit on the instruction stream currently being executed. This would happen if the active instruction stream was being modified by another processor in an MP system - typically a highly unlikely event." + }, + { + "EventName": "ic_fetch_stall.ic_stall_any", + "EventCode": "0x87", + "BriefDescription": "IC pipe was stalled during this clock cycle for any reason (nothing valid in pipe ICM1).", + "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle for any reason (nothing valid in pipe ICM1).", + "UMask": "0x4" + }, + { + "EventName": "ic_fetch_stall.ic_stall_dq_empty", + "EventCode": "0x87", + "BriefDescription": "IC pipe was stalled during this clock cycle (including IC to OC fetches) due to DQ empty.", + "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to DQ empty.", + "UMask": "0x2" + }, + { + "EventName": "ic_fetch_stall.ic_stall_back_pressure", + "EventCode": "0x87", + "BriefDescription": "IC pipe was stalled during this clock cycle (including IC to OC fetches) due to back-pressure.", + "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to back-pressure.", + "UMask": "0x1" + }, + { + "EventName": "ic_cache_inval.l2_invalidating_probe", + "EventCode": "0x8c", + "BriefDescription": "IC line invalidated due to L2 invalidating probe (external or LS).", + "PublicDescription": "The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core. IC line invalidated due to L2 invalidating probe (external or LS).", + "UMask": "0x2" + }, + { + "EventName": "ic_cache_inval.fill_invalidated", + "EventCode": "0x8c", + "BriefDescription": "IC line invalidated due to overwriting fill response.", + "PublicDescription": "The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core. IC line invalidated due to overwriting fill response.", + "UMask": "0x1" + }, + { + "EventName": "bp_tlb_rel", + "EventCode": "0x99", + "BriefDescription": "The number of ITLB reload requests." + }, + { + "EventName": "l2_request_g1.rd_blk_l", + "EventCode": "0x60", + "BriefDescription": "Requests to L2 Group1.", + "PublicDescription": "Requests to L2 Group1.", + "UMask": "0x80" + }, + { + "EventName": "l2_request_g1.rd_blk_x", + "EventCode": "0x60", + "BriefDescription": "Requests to L2 Group1.", + "PublicDescription": "Requests to L2 Group1.", + "UMask": "0x40" + }, + { + "EventName": "l2_request_g1.ls_rd_blk_c_s", + "EventCode": "0x60", + "BriefDescription": "Requests to L2 Group1.", + "PublicDescription": "Requests to L2 Group1.", + "UMask": "0x20" + }, + { + "EventName": "l2_request_g1.cacheable_ic_read", + "EventCode": "0x60", + "BriefDescription": "Requests to L2 Group1.", + "PublicDescription": "Requests to L2 Group1.", + "UMask": "0x10" + }, + { + "EventName": "l2_request_g1.change_to_x", + "EventCode": "0x60", + "BriefDescription": "Requests to L2 Group1.", + "PublicDescription": "Requests to L2 Group1.", + "UMask": "0x8" + }, + { + "EventName": "l2_request_g1.prefetch_l2", + "EventCode": "0x60", + "BriefDescription": "Requests to L2 Group1.", + "PublicDescription": "Requests to L2 Group1.", + "UMask": "0x4" + }, + { + "EventName": "l2_request_g1.l2_hw_pf", + "EventCode": "0x60", + "BriefDescription": "Requests to L2 Group1.", + "PublicDescription": "Requests to L2 Group1.", + "UMask": "0x2" + }, + { + "EventName": "l2_request_g1.other_requests", + "EventCode": "0x60", + "BriefDescription": "Events covered by l2_request_g2.", + "PublicDescription": "Requests to L2 Group1. Events covered by l2_request_g2.", + "UMask": "0x1" + }, + { + "EventName": "l2_request_g2.group1", + "EventCode": "0x61", + "BriefDescription": "All Group 1 commands not in unit0.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. All Group 1 commands not in unit0.", + "UMask": "0x80" + }, + { + "EventName": "l2_request_g2.ls_rd_sized", + "EventCode": "0x61", + "BriefDescription": "RdSized, RdSized32, RdSized64.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. RdSized, RdSized32, RdSized64.", + "UMask": "0x40" + }, + { + "EventName": "l2_request_g2.ls_rd_sized_nc", + "EventCode": "0x61", + "BriefDescription": "RdSizedNC, RdSized32NC, RdSized64NC.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. RdSizedNC, RdSized32NC, RdSized64NC.", + "UMask": "0x20" + }, + { + "EventName": "l2_request_g2.ic_rd_sized", + "EventCode": "0x61", + "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "UMask": "0x10" + }, + { + "EventName": "l2_request_g2.ic_rd_sized_nc", + "EventCode": "0x61", + "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "UMask": "0x8" + }, + { + "EventName": "l2_request_g2.smc_inval", + "EventCode": "0x61", + "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "UMask": "0x4" + }, + { + "EventName": "l2_request_g2.bus_locks_originator", + "EventCode": "0x61", + "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "UMask": "0x2" + }, + { + "EventName": "l2_request_g2.bus_locks_responses", + "EventCode": "0x61", + "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", + "UMask": "0x1" + }, + { + "EventName": "l2_latency.l2_cycles_waiting_on_fills", + "EventCode": "0x62", + "BriefDescription": "Total cycles spent waiting for L2 fills to complete from L3 or memory, divided by four. Event counts are for both threads. To calculate average latency, the number of fills from both threads must be used.", + "PublicDescription": "Total cycles spent waiting for L2 fills to complete from L3 or memory, divided by four. Event counts are for both threads. To calculate average latency, the number of fills from both threads must be used.", + "UMask": "0x1" + }, + { + "EventName": "l2_wcb_req.wcb_write", + "EventCode": "0x63", + "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) write requests.", + "BriefDescription": "LS to L2 WCB write requests.", + "UMask": "0x40" + }, + { + "EventName": "l2_wcb_req.wcb_close", + "EventCode": "0x63", + "BriefDescription": "LS to L2 WCB close requests.", + "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) close requests.", + "UMask": "0x20" + }, + { + "EventName": "l2_wcb_req.zero_byte_store", + "EventCode": "0x63", + "BriefDescription": "LS to L2 WCB zero byte store requests.", + "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) zero byte store requests.", + "UMask": "0x4" + }, + { + "EventName": "l2_wcb_req.cl_zero", + "EventCode": "0x63", + "PublicDescription": "LS to L2 WCB cache line zeroing requests.", + "BriefDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) cache line zeroing requests.", + "UMask": "0x1" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_cs", + "EventCode": "0x64", + "BriefDescription": "LS ReadBlock C/S Hit.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS ReadBlock C/S Hit.", + "UMask": "0x80" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_x", + "EventCode": "0x64", + "BriefDescription": "LS Read Block L Hit X.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS Read Block L Hit X.", + "UMask": "0x40" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_s", + "EventCode": "0x64", + "BriefDescription": "LsRdBlkL Hit Shared.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LsRdBlkL Hit Shared.", + "UMask": "0x20" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_x", + "EventCode": "0x64", + "BriefDescription": "LsRdBlkX/ChgToX Hit X. Count RdBlkX finding Shared as a Miss.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LsRdBlkX/ChgToX Hit X. Count RdBlkX finding Shared as a Miss.", + "UMask": "0x10" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_c", + "EventCode": "0x64", + "BriefDescription": "LS Read Block C S L X Change to X Miss.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS Read Block C S L X Change to X Miss.", + "UMask": "0x8" + }, + { + "EventName": "l2_cache_req_stat.ic_fill_hit_x", + "EventCode": "0x64", + "BriefDescription": "IC Fill Hit Exclusive Stale.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Hit Exclusive Stale.", + "UMask": "0x4" + }, + { + "EventName": "l2_cache_req_stat.ic_fill_hit_s", + "EventCode": "0x64", + "BriefDescription": "IC Fill Hit Shared.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Hit Shared.", + "UMask": "0x2" + }, + { + "EventName": "l2_cache_req_stat.ic_fill_miss", + "EventCode": "0x64", + "BriefDescription": "IC Fill Miss.", + "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Miss.", + "UMask": "0x1" + }, + { + "EventName": "l2_fill_pending.l2_fill_busy", + "EventCode": "0x6d", + "BriefDescription": "Total cycles spent with one or more fill requests in flight from L2.", + "PublicDescription": "Total cycles spent with one or more fill requests in flight from L2.", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/core.json b/tools/perf/pmu-events/arch/x86/amdfam17h/core.json new file mode 100644 index 000000000000..7b285b0a7f35 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdfam17h/core.json @@ -0,0 +1,134 @@ +[ + { + "EventName": "ex_ret_instr", + "EventCode": "0xc0", + "BriefDescription": "Retired Instructions." + }, + { + "EventName": "ex_ret_cops", + "EventCode": "0xc1", + "BriefDescription": "Retired Uops.", + "PublicDescription": "The number of uOps retired. This includes all processor activity (instructions, exceptions, interrupts, microcode assists, etc.). The number of events logged per cycle can vary from 0 to 4." + }, + { + "EventName": "ex_ret_brn", + "EventCode": "0xc2", + "BriefDescription": "[Retired Branch Instructions.", + "PublicDescription": "The number of branch instructions retired. This includes all types of architectural control flow changes, including exceptions and interrupts." + }, + { + "EventName": "ex_ret_brn_misp", + "EventCode": "0xc3", + "BriefDescription": "Retired Branch Instructions Mispredicted.", + "PublicDescription": "The number of branch instructions retired, of any type, that were not correctly predicted. This includes those for which prediction is not attempted (far control transfers, exceptions and interrupts)." + }, + { + "EventName": "ex_ret_brn_tkn", + "EventCode": "0xc4", + "BriefDescription": "Retired Taken Branch Instructions.", + "PublicDescription": "The number of taken branches that were retired. This includes all types of architectural control flow changes, including exceptions and interrupts." + }, + { + "EventName": "ex_ret_brn_tkn_misp", + "EventCode": "0xc5", + "BriefDescription": "Retired Taken Branch Instructions Mispredicted.", + "PublicDescription": "The number of retired taken branch instructions that were mispredicted." + }, + { + "EventName": "ex_ret_brn_far", + "EventCode": "0xc6", + "BriefDescription": "Retired Far Control Transfers.", + "PublicDescription": "The number of far control transfers retired including far call/jump/return, IRET, SYSCALL and SYSRET, plus exceptions and interrupts. Far control transfers are not subject to branch prediction." + }, + { + "EventName": "ex_ret_brn_resync", + "EventCode": "0xc7", + "BriefDescription": "Retired Branch Resyncs.", + "PublicDescription": "The number of resync branches. These reflect pipeline restarts due to certain microcode assists and events such as writes to the active instruction stream, among other things. Each occurrence reflects a restart penalty similar to a branch mispredict. This is relatively rare." + }, + { + "EventName": "ex_ret_near_ret", + "EventCode": "0xc8", + "BriefDescription": "Retired Near Returns.", + "PublicDescription": "The number of near return instructions (RET or RET Iw) retired." + }, + { + "EventName": "ex_ret_near_ret_mispred", + "EventCode": "0xc9", + "BriefDescription": "Retired Near Returns Mispredicted.", + "PublicDescription": "The number of near returns retired that were not correctly predicted by the return address predictor. Each such mispredict incurs the same penalty as a mispredicted conditional branch instruction." + }, + { + "EventName": "ex_ret_brn_ind_misp", + "EventCode": "0xca", + "BriefDescription": "Retired Indirect Branch Instructions Mispredicted.", + "PublicDescription": "Retired Indirect Branch Instructions Mispredicted." + }, + { + "EventName": "ex_ret_mmx_fp_instr.sse_instr", + "EventCode": "0xcb", + "BriefDescription": "SSE instructions (SSE, SSE2, SSE3, SSSE3, SSE4A, SSE41, SSE42, AVX).", + "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. SSE instructions (SSE, SSE2, SSE3, SSSE3, SSE4A, SSE41, SSE42, AVX).", + "UMask": "0x4" + }, + { + "EventName": "ex_ret_mmx_fp_instr.mmx_instr", + "EventCode": "0xcb", + "BriefDescription": "MMX instructions.", + "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. MMX instructions.", + "UMask": "0x2" + }, + { + "EventName": "ex_ret_mmx_fp_instr.x87_instr", + "EventCode": "0xcb", + "BriefDescription": "x87 instructions.", + "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. x87 instructions.", + "UMask": "0x1" + }, + { + "EventName": "ex_ret_cond", + "EventCode": "0xd1", + "BriefDescription": "Retired Conditional Branch Instructions." + }, + { + "EventName": "ex_ret_cond_misp", + "EventCode": "0xd2", + "BriefDescription": "Retired Conditional Branch Instructions Mispredicted." + }, + { + "EventName": "ex_div_busy", + "EventCode": "0xd3", + "BriefDescription": "Div Cycles Busy count." + }, + { + "EventName": "ex_div_count", + "EventCode": "0xd4", + "BriefDescription": "Div Op Count." + }, + { + "EventName": "ex_tagged_ibs_ops.ibs_count_rollover", + "EventCode": "0x1cf", + "BriefDescription": "Number of times an op could not be tagged by IBS because of a previous tagged op that has not retired.", + "PublicDescription": "Tagged IBS Ops. Number of times an op could not be tagged by IBS because of a previous tagged op that has not retired.", + "UMask": "0x4" + }, + { + "EventName": "ex_tagged_ibs_ops.ibs_tagged_ops_ret", + "EventCode": "0x1cf", + "BriefDescription": "Number of Ops tagged by IBS that retired.", + "PublicDescription": "Tagged IBS Ops. Number of Ops tagged by IBS that retired.", + "UMask": "0x2" + }, + { + "EventName": "ex_tagged_ibs_ops.ibs_tagged_ops", + "EventCode": "0x1cf", + "BriefDescription": "Number of Ops tagged by IBS.", + "PublicDescription": "Tagged IBS Ops. Number of Ops tagged by IBS.", + "UMask": "0x1" + }, + { + "EventName": "ex_ret_fus_brnch_inst", + "EventCode": "0x1d0", + "BriefDescription": "The number of fused retired branch instructions retired per cycle. The number of events logged per cycle can vary from 0 to 3." + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json b/tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json new file mode 100644 index 000000000000..ea4711983d1d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json @@ -0,0 +1,168 @@ +[ + { + "EventName": "fpu_pipe_assignment.dual", + "EventCode": "0x00", + "BriefDescription": "Total number multi-pipe uOps.", + "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to Pipe 3.", + "UMask": "0xf0" + }, + { + "EventName": "fpu_pipe_assignment.total", + "EventCode": "0x00", + "BriefDescription": "Total number uOps.", + "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to Pipe 3.", + "UMask": "0xf" + }, + { + "EventName": "fp_sched_empty", + "EventCode": "0x01", + "BriefDescription": "This is a speculative event. The number of cycles in which the FPU scheduler is empty. Note that some Ops like FP loads bypass the scheduler." + }, + { + "EventName": "fp_retx87_fp_ops.all", + "EventCode": "0x02", + "BriefDescription": "All Ops.", + "PublicDescription": "The number of x87 floating-point Ops that have retired. The number of events logged per cycle can vary from 0 to 8.", + "UMask": "0x7" + }, + { + "EventName": "fp_retx87_fp_ops.div_sqr_r_ops", + "EventCode": "0x02", + "BriefDescription": "Divide and square root Ops.", + "PublicDescription": "The number of x87 floating-point Ops that have retired. The number of events logged per cycle can vary from 0 to 8. Divide and square root Ops.", + "UMask": "0x4" + }, + { + "EventName": "fp_retx87_fp_ops.mul_ops", + "EventCode": "0x02", + "BriefDescription": "Multiply Ops.", + "PublicDescription": "The number of x87 floating-point Ops that have retired. The number of events logged per cycle can vary from 0 to 8. Multiply Ops.", + "UMask": "0x2" + }, + { + "EventName": "fp_retx87_fp_ops.add_sub_ops", + "EventCode": "0x02", + "BriefDescription": "Add/subtract Ops.", + "PublicDescription": "The number of x87 floating-point Ops that have retired. The number of events logged per cycle can vary from 0 to 8. Add/subtract Ops.", + "UMask": "0x1" + }, + { + "EventName": "fp_ret_sse_avx_ops.all", + "EventCode": "0x03", + "BriefDescription": "All FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15.", + "UMask": "0xff" + }, + { + "EventName": "fp_ret_sse_avx_ops.dp_mult_add_flops", + "EventCode": "0x03", + "BriefDescription": "Double precision multiply-add FLOPS. Multiply-add counts as 2 FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Double precision multiply-add FLOPS. Multiply-add counts as 2 FLOPS.", + "UMask": "0x80" + }, + { + "EventName": "fp_ret_sse_avx_ops.dp_div_flops", + "EventCode": "0x03", + "BriefDescription": "Double precision divide/square root FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Double precision divide/square root FLOPS.", + "UMask": "0x40" + }, + { + "EventName": "fp_ret_sse_avx_ops.dp_mult_flops", + "EventCode": "0x03", + "BriefDescription": "Double precision multiply FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Double precision multiply FLOPS.", + "UMask": "0x20" + }, + { + "EventName": "fp_ret_sse_avx_ops.dp_add_sub_flops", + "EventCode": "0x03", + "BriefDescription": "Double precision add/subtract FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Double precision add/subtract FLOPS.", + "UMask": "0x10" + }, + { + "EventName": "fp_ret_sse_avx_ops.sp_mult_add_flops", + "EventCode": "0x03", + "BriefDescription": "Single precision multiply-add FLOPS. Multiply-add counts as 2 FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Single precision multiply-add FLOPS. Multiply-add counts as 2 FLOPS.", + "UMask": "0x8" + }, + { + "EventName": "fp_ret_sse_avx_ops.sp_div_flops", + "EventCode": "0x03", + "BriefDescription": "Single-precision divide/square root FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Single-precision divide/square root FLOPS.", + "UMask": "0x4" + }, + { + "EventName": "fp_ret_sse_avx_ops.sp_mult_flops", + "EventCode": "0x03", + "BriefDescription": "Single-precision multiply FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Single-precision multiply FLOPS.", + "UMask": "0x2" + }, + { + "EventName": "fp_ret_sse_avx_ops.sp_add_sub_flops", + "EventCode": "0x03", + "BriefDescription": "Single-precision add/subtract FLOPS.", + "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Single-precision add/subtract FLOPS.", + "UMask": "0x1" + }, + { + "EventName": "fp_num_mov_elim_scal_op.optimized", + "EventCode": "0x04", + "BriefDescription": "Number of Scalar Ops optimized.", + "PublicDescription": "This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number of Scalar Ops optimized.", + "UMask": "0x8" + }, + { + "EventName": "fp_num_mov_elim_scal_op.opt_potential", + "EventCode": "0x04", + "BriefDescription": "Number of Ops that are candidates for optimization (have Z-bit either set or pass).", + "PublicDescription": "This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number of Ops that are candidates for optimization (have Z-bit either set or pass).", + "UMask": "0x4" + }, + { + "EventName": "fp_num_mov_elim_scal_op.sse_mov_ops_elim", + "EventCode": "0x04", + "BriefDescription": "Number of SSE Move Ops eliminated.", + "PublicDescription": "This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number of SSE Move Ops eliminated.", + "UMask": "0x2" + }, + { + "EventName": "fp_num_mov_elim_scal_op.sse_mov_ops", + "EventCode": "0x04", + "BriefDescription": "Number of SSE Move Ops.", + "PublicDescription": "This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number of SSE Move Ops.", + "UMask": "0x1" + }, + { + "EventName": "fp_retired_ser_ops.x87_ctrl_ret", + "EventCode": "0x05", + "BriefDescription": "x87 control word mispredict traps due to mispredictions in RC or PC, or changes in mask bits.", + "PublicDescription": "The number of serializing Ops retired. x87 control word mispredict traps due to mispredictions in RC or PC, or changes in mask bits.", + "UMask": "0x8" + }, + { + "EventName": "fp_retired_ser_ops.x87_bot_ret", + "EventCode": "0x05", + "BriefDescription": "x87 bottom-executing uOps retired.", + "PublicDescription": "The number of serializing Ops retired. x87 bottom-executing uOps retired.", + "UMask": "0x4" + }, + { + "EventName": "fp_retired_ser_ops.sse_ctrl_ret", + "EventCode": "0x05", + "BriefDescription": "SSE control word mispredict traps due to mispredictions in RC, FTZ or DAZ, or changes in mask bits.", + "PublicDescription": "The number of serializing Ops retired. SSE control word mispredict traps due to mispredictions in RC, FTZ or DAZ, or changes in mask bits.", + "UMask": "0x2" + }, + { + "EventName": "fp_retired_ser_ops.sse_bot_ret", + "EventCode": "0x05", + "BriefDescription": "SSE bottom-executing uOps retired.", + "PublicDescription": "The number of serializing Ops retired. SSE bottom-executing uOps retired.", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/memory.json b/tools/perf/pmu-events/arch/x86/amdfam17h/memory.json new file mode 100644 index 000000000000..fa2d60d4def0 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdfam17h/memory.json @@ -0,0 +1,162 @@ +[ + { + "EventName": "ls_locks.bus_lock", + "EventCode": "0x25", + "BriefDescription": "Bus lock when a locked operations crosses a cache boundary or is done on an uncacheable memory type.", + "PublicDescription": "Bus lock when a locked operations crosses a cache boundary or is done on an uncacheable memory type.", + "UMask": "0x1" + }, + { + "EventName": "ls_dispatch.ld_st_dispatch", + "EventCode": "0x29", + "BriefDescription": "Load-op-Stores.", + "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed. Load-op-Stores.", + "UMask": "0x4" + }, + { + "EventName": "ls_dispatch.store_dispatch", + "EventCode": "0x29", + "BriefDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.", + "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.", + "UMask": "0x2" + }, + { + "EventName": "ls_dispatch.ld_dispatch", + "EventCode": "0x29", + "BriefDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.", + "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.", + "UMask": "0x1" + }, + { + "EventName": "ls_stlf", + "EventCode": "0x35", + "BriefDescription": "Number of STLF hits." + }, + { + "EventName": "ls_dc_accesses", + "EventCode": "0x40", + "BriefDescription": "The number of accesses to the data cache for load and store references. This may include certain microcode scratchpad accesses, although these are generally rare. Each increment represents an eight-byte access, although the instruction may only be accessing a portion of that. This event is a speculative event." + }, + { + "EventName": "ls_l1_d_tlb_miss.all", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss or Reload off all sizes.", + "PublicDescription": "L1 DTLB Miss or Reload off all sizes.", + "UMask": "0xff" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_1g_l2_miss", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss of a page of 1G size.", + "PublicDescription": "L1 DTLB Miss of a page of 1G size.", + "UMask": "0x80" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_2m_l2_miss", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss of a page of 2M size.", + "PublicDescription": "L1 DTLB Miss of a page of 2M size.", + "UMask": "0x40" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_32k_l2_miss", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss of a page of 32K size.", + "PublicDescription": "L1 DTLB Miss of a page of 32K size.", + "UMask": "0x20" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_4k_l2_miss", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss of a page of 4K size.", + "PublicDescription": "L1 DTLB Miss of a page of 4K size.", + "UMask": "0x10" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_1g_l2_hit", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Reload of a page of 1G size.", + "PublicDescription": "L1 DTLB Reload of a page of 1G size.", + "UMask": "0x8" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_2m_l2_hit", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Reload of a page of 2M size.", + "PublicDescription": "L1 DTLB Reload of a page of 2M size.", + "UMask": "0x4" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_32k_l2_hit", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Reload of a page of 32K size.", + "PublicDescription": "L1 DTLB Reload of a page of 32K size.", + "UMask": "0x2" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_4k_l2_hit", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Reload of a page of 4K size.", + "PublicDescription": "L1 DTLB Reload of a page of 4K size.", + "UMask": "0x1" + }, + { + "EventName": "ls_tablewalker.perf_mon_tablewalk_alloc_iside", + "EventCode": "0x46", + "BriefDescription": "Tablewalker allocation.", + "PublicDescription": "Tablewalker allocation.", + "UMask": "0xc" + }, + { + "EventName": "ls_tablewalker.perf_mon_tablewalk_alloc_dside", + "EventCode": "0x46", + "BriefDescription": "Tablewalker allocation.", + "PublicDescription": "Tablewalker allocation.", + "UMask": "0x3" + }, + { + "EventName": "ls_misal_accesses", + "EventCode": "0x47", + "BriefDescription": "Misaligned loads." + }, + { + "EventName": "ls_pref_instr_disp.prefetch_nta", + "EventCode": "0x4b", + "BriefDescription": "Software Prefetch Instructions (PREFETCHNTA instruction) Dispatched.", + "PublicDescription": "Software Prefetch Instructions (PREFETCHNTA instruction) Dispatched.", + "UMask": "0x4" + }, + { + "EventName": "ls_pref_instr_disp.store_prefetch_w", + "EventCode": "0x4b", + "BriefDescription": "Software Prefetch Instructions (3DNow PREFETCHW instruction) Dispatched.", + "PublicDescription": "Software Prefetch Instructions (3DNow PREFETCHW instruction) Dispatched.", + "UMask": "0x2" + }, + { + "EventName": "ls_pref_instr_disp.load_prefetch_w", + "EventCode": "0x4b", + "BriefDescription": "Prefetch, Prefetch_T0_T1_T2.", + "PublicDescription": "Software Prefetch Instructions Dispatched. Prefetch, Prefetch_T0_T1_T2.", + "UMask": "0x1" + }, + { + "EventName": "ls_inef_sw_pref.mab_mch_cnt", + "EventCode": "0x52", + "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core.", + "PublicDescription": "The number of software prefetches that did not fetch data outside of the processor core.", + "UMask": "0x2" + }, + { + "EventName": "ls_inef_sw_pref.data_pipe_sw_pf_dc_hit", + "EventCode": "0x52", + "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core.", + "PublicDescription": "The number of software prefetches that did not fetch data outside of the processor core.", + "UMask": "0x1" + }, + { + "EventName": "ls_not_halted_cyc", + "EventCode": "0x76", + "BriefDescription": "Cycles not in Halt." + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/other.json b/tools/perf/pmu-events/arch/x86/amdfam17h/other.json new file mode 100644 index 000000000000..b26a00d05a2e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdfam17h/other.json @@ -0,0 +1,65 @@ +[ + { + "EventName": "ic_oc_mode_switch.oc_ic_mode_switch", + "EventCode": "0x28a", + "BriefDescription": "OC to IC mode switch.", + "PublicDescription": "OC Mode Switch. OC to IC mode switch.", + "UMask": "0x2" + }, + { + "EventName": "ic_oc_mode_switch.ic_oc_mode_switch", + "EventCode": "0x28a", + "BriefDescription": "IC to OC mode switch.", + "PublicDescription": "OC Mode Switch. IC to OC mode switch.", + "UMask": "0x1" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.retire_token_stall", + "EventCode": "0xaf", + "BriefDescription": "RETIRE Tokens unavailable.", + "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. RETIRE Tokens unavailable.", + "UMask": "0x40" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.agsq_token_stall", + "EventCode": "0xaf", + "BriefDescription": "AGSQ Tokens unavailable.", + "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. AGSQ Tokens unavailable.", + "UMask": "0x20" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alu_token_stall", + "EventCode": "0xaf", + "BriefDescription": "ALU tokens total unavailable.", + "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALU tokens total unavailable.", + "UMask": "0x10" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq3_0_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall.", + "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall.", + "UMask": "0x8" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq3_token_stall", + "EventCode": "0xaf", + "BriefDescription": "ALSQ 3 Tokens unavailable.", + "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 3 Tokens unavailable.", + "UMask": "0x4" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq2_token_stall", + "EventCode": "0xaf", + "BriefDescription": "ALSQ 2 Tokens unavailable.", + "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 2 Tokens unavailable.", + "UMask": "0x2" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq1_token_stall", + "EventCode": "0xaf", + "BriefDescription": "ALSQ 1 Tokens unavailable.", + "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 1 Tokens unavailable.", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/bonnell/frontend.json b/tools/perf/pmu-events/arch/x86/bonnell/frontend.json index 935b7dcf067d..ef69540ab61d 100644 --- a/tools/perf/pmu-events/arch/x86/bonnell/frontend.json +++ b/tools/perf/pmu-events/arch/x86/bonnell/frontend.json @@ -77,7 +77,7 @@ "UMask": "0x1", "EventName": "UOPS.MS_CYCLES", "SampleAfterValue": "2000000", - "BriefDescription": "This event counts the cycles where 1 or more uops are issued by the micro-sequencer (MS), including microcode assists and inserted flows, and written to the IQ. ", + "BriefDescription": "This event counts the cycles where 1 or more uops are issued by the micro-sequencer (MS), including microcode assists and inserted flows, and written to the IQ.", "CounterMask": "1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json b/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json index b2e681c78466..09c6de13de20 100644 --- a/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json @@ -189,7 +189,7 @@ "UMask": "0x8", "EventName": "BR_MISSP_TYPE_RETIRED.IND_CALL", "SampleAfterValue": "200000", - "BriefDescription": "Mispredicted indirect calls, including both register and memory indirect. " + "BriefDescription": "Mispredicted indirect calls, including both register and memory indirect." }, { "EventCode": "0x89", diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index 00bfdb5c5acb..212b117a8ffb 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -1,164 +1,352 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )", - "MetricGroup": "Frontend", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "Branch_Misprediction_Cost" }, { + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts_SMT", + "MetricName": "Branch_Misprediction_Cost_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" + }, + { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / cycles", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/broadwell/cache.json b/tools/perf/pmu-events/arch/x86/broadwell/cache.json index 0b080b0352d8..7938bf5689ab 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/cache.json @@ -56,10 +56,10 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x41", + "UMask": "0xc1", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", "SampleAfterValue": "200003", "BriefDescription": "Demand Data Read requests that hit L2 cache", @@ -68,7 +68,7 @@ { "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x42", + "UMask": "0xc2", "EventName": "L2_RQSTS.RFO_HIT", "SampleAfterValue": "200003", "BriefDescription": "RFO requests that hit L2 cache.", @@ -77,7 +77,7 @@ { "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x44", + "UMask": "0xc4", "EventName": "L2_RQSTS.CODE_RD_HIT", "SampleAfterValue": "200003", "BriefDescription": "L2 cache hits when fetching instructions, code reads.", @@ -87,7 +87,7 @@ "PublicDescription": "This event counts the number of requests from the L2 hardware prefetchers that hit L2 cache. L3 prefetch new types.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x50", + "UMask": "0xd0", "EventName": "L2_RQSTS.L2_PF_HIT", "SampleAfterValue": "200003", "BriefDescription": "L2 prefetch requests that hit L2 cache", @@ -433,7 +433,7 @@ }, { "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "EventCode": "0xD0", "Counter": "0,1,2,3", "UMask": "0x41", @@ -445,7 +445,7 @@ }, { "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "EventCode": "0xD0", "Counter": "0,1,2,3", "UMask": "0x42", @@ -771,2628 +771,2628 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010001 ", + "MSRValue": "0x0000010001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that have any response type.", + "BriefDescription": "Counts demand data reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020001 ", + "MSRValue": "0x0080020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020001 ", + "MSRValue": "0x0100020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020001 ", + "MSRValue": "0x0200020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020001 ", + "MSRValue": "0x0400020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020001 ", + "MSRValue": "0x1000020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020001 ", + "MSRValue": "0x3F80020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0001 ", + "MSRValue": "0x00803C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0001 ", + "MSRValue": "0x01003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0001 ", + "MSRValue": "0x02003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0001 ", + "MSRValue": "0x04003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0001 ", + "MSRValue": "0x10003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0001 ", + "MSRValue": "0x3F803C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010002 ", + "MSRValue": "0x0000010002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.", + "BriefDescription": "Counts all demand data writes (RFOs) have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0002 ", + "MSRValue": "0x00803C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0002 ", + "MSRValue": "0x01003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0002 ", + "MSRValue": "0x02003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0002 ", + "MSRValue": "0x04003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0002 ", + "MSRValue": "0x10003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0002 ", + "MSRValue": "0x3F803C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010004 ", + "MSRValue": "0x0000010004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that have any response type.", + "BriefDescription": "Counts all demand code reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020004 ", + "MSRValue": "0x0080020004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020004 ", + "MSRValue": "0x0100020004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020004 ", + "MSRValue": "0x0200020004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020004 ", + "MSRValue": "0x0400020004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020004 ", + "MSRValue": "0x1000020004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020004 ", + "MSRValue": "0x3F80020004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0004 ", + "MSRValue": "0x00803C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0004 ", + "MSRValue": "0x01003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0004 ", + "MSRValue": "0x02003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0004 ", + "MSRValue": "0x04003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0004 ", + "MSRValue": "0x10003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0004 ", + "MSRValue": "0x3F803C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive) have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010008 ", + "MSRValue": "0x0000010008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that have any response type.", + "BriefDescription": "Counts writebacks (modified to exclusive) have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020008 ", + "MSRValue": "0x0080020008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020008 ", + "MSRValue": "0x0100020008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020008 ", + "MSRValue": "0x0200020008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020008 ", + "MSRValue": "0x0400020008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020008 ", + "MSRValue": "0x1000020008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020008 ", + "MSRValue": "0x3F80020008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0008 ", + "MSRValue": "0x00803C0008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0008 ", + "MSRValue": "0x01003C0008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0008 ", + "MSRValue": "0x02003C0008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0008 ", + "MSRValue": "0x04003C0008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0008 ", + "MSRValue": "0x10003C0008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0008 ", + "MSRValue": "0x3F803C0008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010010 ", + "MSRValue": "0x0000010010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020010 ", + "MSRValue": "0x0080020010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020010 ", + "MSRValue": "0x0100020010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020010 ", + "MSRValue": "0x0200020010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020010 ", + "MSRValue": "0x0400020010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020010 ", + "MSRValue": "0x1000020010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020010 ", + "MSRValue": "0x3F80020010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0010 ", + "MSRValue": "0x00803C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0010 ", + "MSRValue": "0x01003C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0010 ", + "MSRValue": "0x02003C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0010 ", + "MSRValue": "0x04003C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0010 ", + "MSRValue": "0x10003C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0010 ", + "MSRValue": "0x3F803C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010020 ", + "MSRValue": "0x0000010020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020020 ", + "MSRValue": "0x0080020020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020020 ", + "MSRValue": "0x0100020020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020020 ", + "MSRValue": "0x0200020020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020020 ", + "MSRValue": "0x0400020020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020020 ", + "MSRValue": "0x1000020020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020020 ", + "MSRValue": "0x3F80020020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0020 ", + "MSRValue": "0x00803C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0020 ", + "MSRValue": "0x01003C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0020 ", + "MSRValue": "0x02003C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0020 ", + "MSRValue": "0x04003C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0020 ", + "MSRValue": "0x10003C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0020 ", + "MSRValue": "0x3F803C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010040 ", + "MSRValue": "0x0000010040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that have any response type.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020040 ", + "MSRValue": "0x0080020040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020040 ", + "MSRValue": "0x0100020040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020040 ", + "MSRValue": "0x0200020040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020040 ", + "MSRValue": "0x0400020040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020040 ", + "MSRValue": "0x1000020040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020040 ", + "MSRValue": "0x3F80020040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0040 ", + "MSRValue": "0x00803C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0040 ", + "MSRValue": "0x01003C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0040 ", + "MSRValue": "0x02003C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0040 ", + "MSRValue": "0x04003C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0040 ", + "MSRValue": "0x10003C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0040 ", + "MSRValue": "0x3F803C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010080 ", + "MSRValue": "0x0000010080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020080 ", + "MSRValue": "0x0080020080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020080 ", + "MSRValue": "0x0100020080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020080 ", + "MSRValue": "0x0200020080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020080 ", + "MSRValue": "0x0400020080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020080 ", + "MSRValue": "0x1000020080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020080 ", + "MSRValue": "0x3F80020080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0080 ", + "MSRValue": "0x00803C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0080 ", + "MSRValue": "0x01003C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0080 ", + "MSRValue": "0x02003C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0080 ", + "MSRValue": "0x04003C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0080 ", + "MSRValue": "0x10003C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0080 ", + "MSRValue": "0x3F803C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010100 ", + "MSRValue": "0x0000010100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020100 ", + "MSRValue": "0x0080020100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020100 ", + "MSRValue": "0x0100020100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020100 ", + "MSRValue": "0x0200020100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020100 ", + "MSRValue": "0x0400020100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020100 ", + "MSRValue": "0x1000020100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020100 ", + "MSRValue": "0x3F80020100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0100 ", + "MSRValue": "0x00803C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0100 ", + "MSRValue": "0x01003C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0100 ", + "MSRValue": "0x02003C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0100 ", + "MSRValue": "0x04003C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0100 ", + "MSRValue": "0x10003C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0100 ", + "MSRValue": "0x3F803C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010200 ", + "MSRValue": "0x0000010200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that have any response type.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020200 ", + "MSRValue": "0x0080020200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020200 ", + "MSRValue": "0x0100020200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020200 ", + "MSRValue": "0x0200020200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020200 ", + "MSRValue": "0x0400020200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020200 ", + "MSRValue": "0x1000020200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020200 ", + "MSRValue": "0x3F80020200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0200 ", + "MSRValue": "0x00803C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0200 ", + "MSRValue": "0x01003C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0200 ", + "MSRValue": "0x02003C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0200 ", + "MSRValue": "0x04003C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0200 ", + "MSRValue": "0x10003C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0200 ", + "MSRValue": "0x3F803C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000018000 ", + "MSRValue": "0x0000018000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that have any response type.", + "BriefDescription": "Counts any other requests have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080028000 ", + "MSRValue": "0x0080028000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100028000 ", + "MSRValue": "0x0100028000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200028000 ", + "MSRValue": "0x0200028000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400028000 ", + "MSRValue": "0x0400028000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000028000 ", + "MSRValue": "0x1000028000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80028000 ", + "MSRValue": "0x3F80028000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c8000 ", + "MSRValue": "0x00803C8000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c8000 ", + "MSRValue": "0x01003C8000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c8000 ", + "MSRValue": "0x02003C8000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c8000 ", + "MSRValue": "0x04003C8000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c8000 ", + "MSRValue": "0x10003C8000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c8000 ", + "MSRValue": "0x3F803C8000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that hit in the L3.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010090 ", + "MSRValue": "0x0000010090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that have any response type.", + "BriefDescription": "Counts all prefetch data reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020090 ", + "MSRValue": "0x0080020090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020090 ", + "MSRValue": "0x0100020090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020090 ", + "MSRValue": "0x0200020090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020090 ", + "MSRValue": "0x0400020090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020090 ", + "MSRValue": "0x1000020090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020090 ", + "MSRValue": "0x3F80020090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0090 ", + "MSRValue": "0x00803C0090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0090 ", + "MSRValue": "0x01003C0090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0090 ", + "MSRValue": "0x02003C0090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0090 ", + "MSRValue": "0x04003C0090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0090 ", + "MSRValue": "0x10003C0090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0090 ", + "MSRValue": "0x3F803C0090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that hit in the L3.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010120 ", + "MSRValue": "0x0000010120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that have any response type.", + "BriefDescription": "Counts prefetch RFOs have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020120 ", + "MSRValue": "0x0080020120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020120 ", + "MSRValue": "0x0100020120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020120 ", + "MSRValue": "0x0200020120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020120 ", + "MSRValue": "0x0400020120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020120 ", + "MSRValue": "0x1000020120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020120 ", + "MSRValue": "0x3F80020120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0120 ", + "MSRValue": "0x00803C0120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0120 ", + "MSRValue": "0x01003C0120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0120 ", + "MSRValue": "0x02003C0120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0120 ", + "MSRValue": "0x04003C0120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0120 ", + "MSRValue": "0x10003C0120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0120 ", + "MSRValue": "0x3F803C0120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that hit in the L3.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010240 ", + "MSRValue": "0x0000010240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that have any response type.", + "BriefDescription": "Counts all prefetch code reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020240 ", + "MSRValue": "0x0080020240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020240 ", + "MSRValue": "0x0100020240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020240 ", + "MSRValue": "0x0200020240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020240 ", + "MSRValue": "0x0400020240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020240 ", + "MSRValue": "0x1000020240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020240 ", + "MSRValue": "0x3F80020240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0240 ", + "MSRValue": "0x00803C0240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0240 ", + "MSRValue": "0x01003C0240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0240 ", + "MSRValue": "0x02003C0240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0240 ", + "MSRValue": "0x04003C0240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0240 ", + "MSRValue": "0x10003C0240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0240 ", + "MSRValue": "0x3F803C0240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that hit in the L3.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010091 ", + "MSRValue": "0x0000010091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that have any response type.", + "BriefDescription": "Counts all demand & prefetch data reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020091 ", + "MSRValue": "0x0080020091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020091 ", + "MSRValue": "0x0100020091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020091 ", + "MSRValue": "0x0200020091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020091 ", + "MSRValue": "0x0400020091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020091 ", + "MSRValue": "0x1000020091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020091 ", + "MSRValue": "0x3F80020091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0091 ", + "MSRValue": "0x00803C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0091 ", + "MSRValue": "0x01003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0091 ", + "MSRValue": "0x02003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0091 ", + "MSRValue": "0x04003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0091 ", + "MSRValue": "0x10003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0091 ", + "MSRValue": "0x3F803C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010122 ", + "MSRValue": "0x0000010122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.", + "BriefDescription": "Counts all demand & prefetch RFOs have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020122 ", + "MSRValue": "0x0080020122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020122 ", + "MSRValue": "0x0100020122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020122 ", + "MSRValue": "0x0200020122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020122 ", + "MSRValue": "0x0400020122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020122 ", + "MSRValue": "0x1000020122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f80020122 ", + "MSRValue": "0x3F80020122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00803c0122 ", + "MSRValue": "0x00803C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01003c0122 ", + "MSRValue": "0x01003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02003c0122 ", + "MSRValue": "0x02003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0122 ", + "MSRValue": "0x04003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0122 ", + "MSRValue": "0x10003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0122 ", + "MSRValue": "0x3F803C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json index 689d478dae93..15291239c128 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json @@ -1,24 +1,26 @@ [ { - "PublicDescription": "This event counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x8", "Errata": "BDM30", "EventName": "OTHER_ASSISTS.AVX_TO_SSE", "SampleAfterValue": "100003", - "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", + "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable (Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x10", "Errata": "BDM30", "EventName": "OTHER_ASSISTS.SSE_TO_AVX", "SampleAfterValue": "100003", - "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", + "BriefDescription": "Number of transitions from legacy SSE to AVX-256 when penalty applicable (Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -45,7 +47,7 @@ "UMask": "0x3", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single precision?)", "CounterHTOff": "0,1,2,3" }, { @@ -54,7 +56,7 @@ "UMask": "0x4", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "CounterHTOff": "0,1,2,3" }, { @@ -63,7 +65,7 @@ "UMask": "0x8", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "CounterHTOff": "0,1,2,3" }, { @@ -72,7 +74,7 @@ "UMask": "0x10", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "CounterHTOff": "0,1,2,3" }, { @@ -81,7 +83,7 @@ "UMask": "0x15", "EventName": "FP_ARITH_INST_RETIRED.DOUBLE", "SampleAfterValue": "2000006", - "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.", + "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "CounterHTOff": "0,1,2,3" }, { @@ -90,7 +92,7 @@ "UMask": "0x20", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "CounterHTOff": "0,1,2,3" }, { @@ -99,7 +101,7 @@ "UMask": "0x2a", "EventName": "FP_ARITH_INST_RETIRED.SINGLE", "SampleAfterValue": "2000005", - "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.", + "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "CounterHTOff": "0,1,2,3" }, { @@ -108,57 +110,62 @@ "UMask": "0x3c", "EventName": "FP_ARITH_INST_RETIRED.PACKED", "SampleAfterValue": "2000004", - "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single-precision?)", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "This event counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x2", "EventName": "FP_ASSIST.X87_OUTPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of X87 assists due to output value.", + "BriefDescription": "output - Numeric Overflow, Numeric Underflow, Inexact Result (Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x4", "EventName": "FP_ASSIST.X87_INPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of X87 assists due to input value.", + "BriefDescription": "input - Invalid Operation, Denormal Operand, SNaN Operand (Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x8", "EventName": "FP_ASSIST.SIMD_OUTPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of SIMD FP assists due to Output values", + "BriefDescription": "SSE* FP micro-code assist when output value is invalid. (Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts any input SSE* floating-point (FP) assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x10", "EventName": "FP_ASSIST.SIMD_INPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of SIMD FP assists due to input values", + "BriefDescription": "Any input SSE* FP Assist - (Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.", + "PEBS": "1", + "PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1. Uses PEBS.", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x1e", "EventName": "FP_ASSIST.ANY", "SampleAfterValue": "100003", - "BriefDescription": "Cycles with any input/output SSE or FP assist", + "BriefDescription": "Counts any FP_ASSIST umask was incrementing (Precise Event)", "CounterMask": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json index 7142c76d7f11..aa4a5d762f21 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json @@ -211,7 +211,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.", + "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.", "EventCode": "0x9C", "Counter": "0,1,2,3", "UMask": "0x1", @@ -274,7 +274,7 @@ "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", + "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.", "EventCode": "0xAB", "Counter": "0,1,2,3", "UMask": "0x2", diff --git a/tools/perf/pmu-events/arch/x86/broadwell/memory.json b/tools/perf/pmu-events/arch/x86/broadwell/memory.json index c9154cebbdf0..b6b5247d3d5a 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/memory.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/memory.json @@ -311,7 +311,7 @@ }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above four.", + "PublicDescription": "Counts randomly selected loads with latency value being above four.", "EventCode": "0xCD", "MSRValue": "0x4", "Counter": "3", @@ -320,13 +320,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "SampleAfterValue": "100003", - "BriefDescription": "Loads with latency value being above 4", + "BriefDescription": "Randomly selected loads with latency value being above 4", "TakenAlone": "1", "CounterHTOff": "3" }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above eight.", + "PublicDescription": "Counts randomly selected loads with latency value being above eight.", "EventCode": "0xCD", "MSRValue": "0x8", "Counter": "3", @@ -335,13 +335,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "SampleAfterValue": "50021", - "BriefDescription": "Loads with latency value being above 8", + "BriefDescription": "Randomly selected loads with latency value being above 8", "TakenAlone": "1", "CounterHTOff": "3" }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 16.", + "PublicDescription": "Counts randomly selected loads with latency value being above 16.", "EventCode": "0xCD", "MSRValue": "0x10", "Counter": "3", @@ -350,13 +350,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "SampleAfterValue": "20011", - "BriefDescription": "Loads with latency value being above 16", + "BriefDescription": "Randomly selected loads with latency value being above 16", "TakenAlone": "1", "CounterHTOff": "3" }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 32.", + "PublicDescription": "Counts randomly selected loads with latency value being above 32.", "EventCode": "0xCD", "MSRValue": "0x20", "Counter": "3", @@ -365,13 +365,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "SampleAfterValue": "100007", - "BriefDescription": "Loads with latency value being above 32", + "BriefDescription": "Randomly selected loads with latency value being above 32", "TakenAlone": "1", "CounterHTOff": "3" }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 64.", + "PublicDescription": "Counts randomly selected loads with latency value being above 64.", "EventCode": "0xCD", "MSRValue": "0x40", "Counter": "3", @@ -380,13 +380,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "SampleAfterValue": "2003", - "BriefDescription": "Loads with latency value being above 64", + "BriefDescription": "Randomly selected loads with latency value being above 64", "TakenAlone": "1", "CounterHTOff": "3" }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 128.", + "PublicDescription": "Counts randomly selected loads with latency value being above 128.", "EventCode": "0xCD", "MSRValue": "0x80", "Counter": "3", @@ -395,13 +395,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "SampleAfterValue": "1009", - "BriefDescription": "Loads with latency value being above 128", + "BriefDescription": "Randomly selected loads with latency value being above 128", "TakenAlone": "1", "CounterHTOff": "3" }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 256.", + "PublicDescription": "Counts randomly selected loads with latency value being above 256.", "EventCode": "0xCD", "MSRValue": "0x100", "Counter": "3", @@ -410,13 +410,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "SampleAfterValue": "503", - "BriefDescription": "Loads with latency value being above 256", + "BriefDescription": "Randomly selected loads with latency value being above 256", "TakenAlone": "1", "CounterHTOff": "3" }, { "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 512.", + "PublicDescription": "Counts randomly selected loads with latency value being above 512.", "EventCode": "0xCD", "MSRValue": "0x200", "Counter": "3", @@ -425,2620 +425,2620 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "SampleAfterValue": "101", - "BriefDescription": "Loads with latency value being above 512", + "BriefDescription": "Randomly selected loads with latency value being above 512", "TakenAlone": "1", "CounterHTOff": "3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020001 ", + "MSRValue": "0x2000020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0001 ", + "MSRValue": "0x20003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000001 ", + "MSRValue": "0x0084000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000001 ", + "MSRValue": "0x0104000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000001 ", + "MSRValue": "0x0204000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000001 ", + "MSRValue": "0x0404000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000001 ", + "MSRValue": "0x1004000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000001 ", + "MSRValue": "0x2004000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000001 ", + "MSRValue": "0x3F84000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000001 ", + "MSRValue": "0x00BC000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000001 ", + "MSRValue": "0x013C000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000001 ", + "MSRValue": "0x023C000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000001 ", + "MSRValue": "0x043C000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0002 ", + "MSRValue": "0x20003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000002 ", + "MSRValue": "0x3F84000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000002 ", + "MSRValue": "0x00BC000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000002 ", + "MSRValue": "0x013C000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000002 ", + "MSRValue": "0x023C000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000002 ", + "MSRValue": "0x043C000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand data writes (RFOs)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020004 ", + "MSRValue": "0x2000020004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0004 ", + "MSRValue": "0x20003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000004 ", + "MSRValue": "0x0084000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000004 ", + "MSRValue": "0x0104000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000004 ", + "MSRValue": "0x0204000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000004 ", + "MSRValue": "0x0404000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000004 ", + "MSRValue": "0x1004000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000004 ", + "MSRValue": "0x2004000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000004 ", + "MSRValue": "0x3F84000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000004 ", + "MSRValue": "0x00BC000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000004 ", + "MSRValue": "0x013C000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000004 ", + "MSRValue": "0x023C000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000004 ", + "MSRValue": "0x043C000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020008 ", + "MSRValue": "0x2000020008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0008 ", + "MSRValue": "0x20003C0008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000008 ", + "MSRValue": "0x0084000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000008 ", + "MSRValue": "0x0104000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000008 ", + "MSRValue": "0x0204000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000008 ", + "MSRValue": "0x0404000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000008 ", + "MSRValue": "0x1004000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000008 ", + "MSRValue": "0x2004000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000008 ", + "MSRValue": "0x3F84000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000008 ", + "MSRValue": "0x00BC000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000008 ", + "MSRValue": "0x013C000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts writebacks (modified to exclusive) that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000008 ", + "MSRValue": "0x023C000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts writebacks (modified to exclusive) that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts writebacks (modified to exclusive)", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000008 ", + "MSRValue": "0x043C000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "COREWB & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts writebacks (modified to exclusive)", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020010 ", + "MSRValue": "0x2000020010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0010 ", + "MSRValue": "0x20003C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000010 ", + "MSRValue": "0x0084000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000010 ", + "MSRValue": "0x0104000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000010 ", + "MSRValue": "0x0204000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000010 ", + "MSRValue": "0x0404000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000010 ", + "MSRValue": "0x1004000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000010 ", + "MSRValue": "0x2004000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000010 ", + "MSRValue": "0x3F84000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000010 ", + "MSRValue": "0x00BC000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000010 ", + "MSRValue": "0x013C000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000010 ", + "MSRValue": "0x023C000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000010 ", + "MSRValue": "0x043C000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020020 ", + "MSRValue": "0x2000020020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0020 ", + "MSRValue": "0x20003C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000020 ", + "MSRValue": "0x0084000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000020 ", + "MSRValue": "0x0104000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000020 ", + "MSRValue": "0x0204000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000020 ", + "MSRValue": "0x0404000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000020 ", + "MSRValue": "0x1004000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000020 ", + "MSRValue": "0x2004000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000020 ", + "MSRValue": "0x3F84000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000020 ", + "MSRValue": "0x00BC000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000020 ", + "MSRValue": "0x013C000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000020 ", + "MSRValue": "0x023C000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000020 ", + "MSRValue": "0x043C000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_RFO & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020040 ", + "MSRValue": "0x2000020040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0040 ", + "MSRValue": "0x20003C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000040 ", + "MSRValue": "0x0084000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000040 ", + "MSRValue": "0x0104000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000040 ", + "MSRValue": "0x0204000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000040 ", + "MSRValue": "0x0404000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000040 ", + "MSRValue": "0x1004000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000040 ", + "MSRValue": "0x2004000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000040 ", + "MSRValue": "0x3F84000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000040 ", + "MSRValue": "0x00BC000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000040 ", + "MSRValue": "0x013C000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000040 ", + "MSRValue": "0x023C000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000040 ", + "MSRValue": "0x043C000040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L2_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020080 ", + "MSRValue": "0x2000020080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0080 ", + "MSRValue": "0x20003C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000080 ", + "MSRValue": "0x0084000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000080 ", + "MSRValue": "0x0104000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000080 ", + "MSRValue": "0x0204000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000080 ", + "MSRValue": "0x0404000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000080 ", + "MSRValue": "0x1004000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000080 ", + "MSRValue": "0x2004000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000080 ", + "MSRValue": "0x3F84000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000080 ", + "MSRValue": "0x00BC000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000080 ", + "MSRValue": "0x013C000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000080 ", + "MSRValue": "0x023C000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000080 ", + "MSRValue": "0x043C000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020100 ", + "MSRValue": "0x2000020100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0100 ", + "MSRValue": "0x20003C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000100 ", + "MSRValue": "0x0084000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000100 ", + "MSRValue": "0x0104000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000100 ", + "MSRValue": "0x0204000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000100 ", + "MSRValue": "0x0404000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000100 ", + "MSRValue": "0x1004000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000100 ", + "MSRValue": "0x2004000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000100 ", + "MSRValue": "0x3F84000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000100 ", + "MSRValue": "0x00BC000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000100 ", + "MSRValue": "0x013C000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000100 ", + "MSRValue": "0x023C000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000100 ", + "MSRValue": "0x043C000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020200 ", + "MSRValue": "0x2000020200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0200 ", + "MSRValue": "0x20003C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000200 ", + "MSRValue": "0x0084000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000200 ", + "MSRValue": "0x0104000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000200 ", + "MSRValue": "0x0204000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000200 ", + "MSRValue": "0x0404000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000200 ", + "MSRValue": "0x1004000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000200 ", + "MSRValue": "0x2004000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000200 ", + "MSRValue": "0x3F84000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000200 ", + "MSRValue": "0x00BC000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000200 ", + "MSRValue": "0x013C000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000200 ", + "MSRValue": "0x023C000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000200 ", + "MSRValue": "0x043C000200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "PF_L3_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000028000 ", + "MSRValue": "0x2000028000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c8000 ", + "MSRValue": "0x20003C8000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084008000 ", + "MSRValue": "0x0084008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104008000 ", + "MSRValue": "0x0104008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204008000 ", + "MSRValue": "0x0204008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404008000 ", + "MSRValue": "0x0404008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004008000 ", + "MSRValue": "0x1004008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004008000 ", + "MSRValue": "0x2004008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84008000 ", + "MSRValue": "0x3F84008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc008000 ", + "MSRValue": "0x00BC008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c008000 ", + "MSRValue": "0x013C008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts any other requests that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c008000 ", + "MSRValue": "0x023C008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c008000 ", + "MSRValue": "0x043C008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "OTHER & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts any other requests", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020090 ", + "MSRValue": "0x2000020090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0090 ", + "MSRValue": "0x20003C0090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000090 ", + "MSRValue": "0x0084000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000090 ", + "MSRValue": "0x0104000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000090 ", + "MSRValue": "0x0204000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000090 ", + "MSRValue": "0x0404000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000090 ", + "MSRValue": "0x1004000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000090 ", + "MSRValue": "0x2004000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000090 ", + "MSRValue": "0x3F84000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000090 ", + "MSRValue": "0x00BC000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000090 ", + "MSRValue": "0x013C000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000090 ", + "MSRValue": "0x023C000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch data reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000090 ", + "MSRValue": "0x043C000090", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020120 ", + "MSRValue": "0x2000020120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0120 ", + "MSRValue": "0x20003C0120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000120 ", + "MSRValue": "0x0084000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000120 ", + "MSRValue": "0x0104000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000120 ", + "MSRValue": "0x0204000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000120 ", + "MSRValue": "0x0404000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000120 ", + "MSRValue": "0x1004000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000120 ", + "MSRValue": "0x2004000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000120 ", + "MSRValue": "0x3F84000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000120 ", + "MSRValue": "0x00BC000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000120 ", + "MSRValue": "0x013C000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000120 ", + "MSRValue": "0x023C000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch RFOs that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000120 ", + "MSRValue": "0x043C000120", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_RFO & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020240 ", + "MSRValue": "0x2000020240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0240 ", + "MSRValue": "0x20003C0240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000240 ", + "MSRValue": "0x0084000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000240 ", + "MSRValue": "0x0104000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000240 ", + "MSRValue": "0x0204000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000240 ", + "MSRValue": "0x0404000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000240 ", + "MSRValue": "0x1004000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000240 ", + "MSRValue": "0x2004000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000240 ", + "MSRValue": "0x3F84000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000240 ", + "MSRValue": "0x00BC000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000240 ", + "MSRValue": "0x013C000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000240 ", + "MSRValue": "0x023C000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch code reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch code reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000240 ", + "MSRValue": "0x043C000240", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_PF_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all prefetch code reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020091 ", + "MSRValue": "0x2000020091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0091 ", + "MSRValue": "0x20003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000091 ", + "MSRValue": "0x0084000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000091 ", + "MSRValue": "0x0104000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000091 ", + "MSRValue": "0x0204000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000091 ", + "MSRValue": "0x0404000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000091 ", + "MSRValue": "0x1004000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000091 ", + "MSRValue": "0x2004000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000091 ", + "MSRValue": "0x3F84000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000091 ", + "MSRValue": "0x00BC000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000091 ", + "MSRValue": "0x013C000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000091 ", + "MSRValue": "0x023C000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000091 ", + "MSRValue": "0x043C000091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand & prefetch data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020122 ", + "MSRValue": "0x2000020122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20003c0122 ", + "MSRValue": "0x20003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the target was non-DRAM system address.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000122 ", + "MSRValue": "0x0084000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000122 ", + "MSRValue": "0x0104000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000122 ", + "MSRValue": "0x0204000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000122 ", + "MSRValue": "0x0404000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000122 ", + "MSRValue": "0x1004000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000122 ", + "MSRValue": "0x2004000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f84000122 ", + "MSRValue": "0x3F84000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000122 ", + "MSRValue": "0x00BC000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 with no details on snoop-related information.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000122 ", + "MSRValue": "0x013C000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000122 ", + "MSRValue": "0x023C000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 with a snoop miss response.", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000122 ", + "MSRValue": "0x043C000122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "ALL_RFO & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts all demand & prefetch RFOs", "Offcore": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json index 999cf3066363..bb25574b8d21 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json @@ -1,7 +1,6 @@ [ { "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. \nNotes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. \nCounting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -11,7 +10,6 @@ }, { "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -20,7 +18,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "AnyThread": "1", @@ -31,7 +28,6 @@ }, { "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. \nNote: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", @@ -317,7 +313,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", + "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", "EventCode": "0x87", "Counter": "0,1,2,3", "UMask": "0x1", @@ -786,8 +782,8 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts resource-related stall cycles. Reasons for stalls can be as follows:\n - *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots)\n - *any* u-arch structure got empty (like INT/SIMD FreeLists)\n - FPU control word (FPCW), MXCSR\nand others. This counts cycles that the pipeline backend blocked uop delivery from the front end.", - "EventCode": "0xA2", + "PublicDescription": "This event counts resource-related stall cycles.", + "EventCode": "0xa2", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "RESOURCE_STALLS.ANY", @@ -973,6 +969,7 @@ "CounterHTOff": "2" }, { + "PublicDescription": "Number of Uops delivered by the LSD.", "EventCode": "0xA8", "Counter": "0,1,2,3", "UMask": "0x1", @@ -1147,7 +1144,8 @@ "CounterHTOff": "1" }, { - "PublicDescription": "This event counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.", "EventCode": "0xC0", "Counter": "0,1,2,3", "UMask": "0x2", @@ -1157,12 +1155,12 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PEBS": "1", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x40", "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST", "SampleAfterValue": "100003", - "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -1178,26 +1176,28 @@ "Data_LA": "1" }, { - "PublicDescription": "This event counts cycles without actually retired uops.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts cycles without actually retired uops.", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "UOPS_RETIRED.STALL_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles without actually retired uops.", + "BriefDescription": "Cycles no executable uops retired (Precise Event)", "CounterMask": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", + "PEBS": "1", + "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to PEBS uops retired event.", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "UOPS_RETIRED.TOTAL_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with less than 10 actually retired uops.", + "BriefDescription": "Number of cycles using always true condition applied to PEBS uops retired event.", "CounterMask": "10", "CounterHTOff": "0,1,2,3" }, @@ -1320,13 +1320,14 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts not taken branch instructions retired.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x10", "EventName": "BR_INST_RETIRED.NOT_TAKEN", "SampleAfterValue": "400009", - "BriefDescription": "Not taken branch instructions retired.", + "BriefDescription": "Counts all not taken macro branch instructions retired. (Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -1341,14 +1342,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts far branch instructions retired.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts far branch instructions retired.", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x40", "Errata": "BDW98", "EventName": "BR_INST_RETIRED.FAR_BRANCH", "SampleAfterValue": "100007", - "BriefDescription": "Far branch instructions retired.", + "BriefDescription": "Counts the number of far branch instructions retired.(Precise Event)", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/cache.json index 4ad425312bdc..bf243fe2a0ec 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/cache.json @@ -439,7 +439,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -451,7 +451,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "SampleAfterValue": "100003", "L1_Hit_Indication": "1", "CounterHTOff": "0,1,2,3" diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json index 0d04bf9db000..e2f0540625a2 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json @@ -1,6 +1,5 @@ [ { - "EventCode": "0x00", "UMask": "0x1", "BriefDescription": "Instructions retired from execution.", "Counter": "Fixed counter 0", @@ -10,7 +9,6 @@ "CounterHTOff": "Fixed counter 0" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when the thread is not in halt state", "Counter": "Fixed counter 1", @@ -20,7 +18,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "Counter": "Fixed counter 1", @@ -30,7 +27,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x3", "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", @@ -322,7 +318,7 @@ "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "Counter": "0,1,2,3", "EventName": "ILD_STALL.LCP", - "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", + "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 5a7f1ec24200..c6f9762f32c0 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -1,164 +1,370 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )", - "MetricGroup": "Frontend", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "Branch_Misprediction_Cost" + }, + { + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts_SMT", + "MetricName": "Branch_Misprediction_Cost_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( 2 * cycles )", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED) ) / (2*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles))", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "MetricExpr": "1000000000 * ( cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x35\\,umask\\=0x3\\,filter_opc\\=0x182@ ) / ( cbox_0@event\\=0x0@ / duration_time )", + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_Lat", + "MetricName": "DRAM_Read_Latency" + }, + { + "MetricExpr": "cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182\\,thresh\\=1@", + "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_Parallel_Reads" + }, + { + "MetricExpr": "cbox_0@event\\=0x0@", + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricGroup": "", + "MetricName": "Socket_CLKS" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json index 141b1080429d..75a3098d5775 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json @@ -57,17 +57,17 @@ }, { "EventCode": "0x24", - "UMask": "0x41", + "UMask": "0xc1", "BriefDescription": "Demand Data Read requests that hit L2 cache", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache.", "SampleAfterValue": "200003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x24", - "UMask": "0x42", + "UMask": "0xc2", "BriefDescription": "RFO requests that hit L2 cache.", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.RFO_HIT", @@ -76,7 +76,7 @@ }, { "EventCode": "0x24", - "UMask": "0x44", + "UMask": "0xc4", "BriefDescription": "L2 cache hits when fetching instructions, code reads.", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.CODE_RD_HIT", @@ -85,7 +85,7 @@ }, { "EventCode": "0x24", - "UMask": "0x50", + "UMask": "0xd0", "BriefDescription": "L2 prefetch requests that hit L2 cache", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.L2_PF_HIT", @@ -396,24 +396,24 @@ { "EventCode": "0xD0", "UMask": "0x11", - "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops that miss the STLB.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.", + "PublicDescription": "This event counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x12", - "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS)", + "BriefDescription": "Retired store uops that miss the STLB.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.", + "PublicDescription": "This event counts store uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.", "SampleAfterValue": "100003", "L1_Hit_Indication": "1", "CounterHTOff": "0,1,2,3" @@ -421,37 +421,37 @@ { "EventCode": "0xD0", "UMask": "0x21", - "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops with locked access.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", "Errata": "BDM35", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with locked access retired to the architected path.", + "PublicDescription": "This event counts load uops with locked access retired to the architected path.", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x41", - "BriefDescription": "Retired load uops that split across a cacheline boundary.(Precise Event - PEBS)", + "BriefDescription": "Retired load uops that split across a cacheline boundary.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x42", - "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)", + "BriefDescription": "Retired store uops that split across a cacheline boundary.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "SampleAfterValue": "100003", "L1_Hit_Indication": "1", "CounterHTOff": "0,1,2,3" @@ -459,24 +459,24 @@ { "EventCode": "0xD0", "UMask": "0x81", - "BriefDescription": "All retired load uops. (Precise Event - PEBS)", + "BriefDescription": "All retired load uops.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.", + "PublicDescription": "This event counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x82", - "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)", + "BriefDescription": "All retired store uops.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement.", + "PublicDescription": "This event counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement.", "SampleAfterValue": "2000003", "L1_Hit_Indication": "1", "CounterHTOff": "0,1,2,3" @@ -484,69 +484,69 @@ { "EventCode": "0xD1", "UMask": "0x1", - "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops with L1 cache hits as data sources.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data source were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.", + "PublicDescription": "This event counts retired load uops which data sources were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x2", - "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops with L2 cache hits as data sources.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", "Errata": "BDM35", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the mid-level (L2) cache.", + "PublicDescription": "This event counts retired load uops which data sources were hits in the mid-level (L2) cache.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x4", - "BriefDescription": "Hit in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", "Errata": "BDM100", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.", + "PublicDescription": "This event counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.", "SampleAfterValue": "50021", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x8", - "BriefDescription": "Retired load uops misses in L1 cache as data sources. Uses PEBS.", + "BriefDescription": "Retired load uops misses in L1 cache as data sources.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.", + "PublicDescription": "This event counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x10", - "BriefDescription": "Retired load uops with L2 cache misses as data sources. Uses PEBS.", + "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.", + "PublicDescription": "This event counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.", "SampleAfterValue": "50021", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x20", - "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS).", + "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -558,83 +558,84 @@ { "EventCode": "0xD1", "UMask": "0x40", - "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.", + "PublicDescription": "This event counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD2", "UMask": "0x1", - "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS", "Errata": "BDM100", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.", + "PublicDescription": "This event counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.", "SampleAfterValue": "20011", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD2", "UMask": "0x2", - "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT", "Errata": "BDM100", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.", + "PublicDescription": "This event counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.", "SampleAfterValue": "20011", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD2", "UMask": "0x4", - "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM", "Errata": "BDM100", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).", + "PublicDescription": "This event counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).", "SampleAfterValue": "20011", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD2", "UMask": "0x8", - "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_NONE", "Errata": "BDM100", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.", + "PublicDescription": "This event counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD3", "UMask": "0x1", + "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", "Errata": "BDE70, BDM100", - "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.", + "PublicDescription": "Retired load uop whose Data Source was: local DRAM either Snoop not needed or Snoop Miss (RspI).", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD3", "UMask": "0x4", - "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -646,7 +647,7 @@ { "EventCode": "0xD3", "UMask": "0x10", - "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -658,7 +659,7 @@ { "EventCode": "0xD3", "UMask": "0x20", - "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -810,12 +811,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all requests that hit in the L3", - "MSRValue": "0x3f803c8fff", + "BriefDescription": "Counts all requests hit in the L3", + "MSRValue": "0x3F803C8FFF", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all requests hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -823,12 +824,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c07f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C07F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -836,12 +837,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c07f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C07F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -849,12 +850,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0244", + "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0244", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -862,12 +863,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0122", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -875,12 +876,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0122", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -888,12 +889,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0091", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -901,12 +902,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0091", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -914,12 +915,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3", - "MSRValue": "0x3f803c0200", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", + "MSRValue": "0x3F803C0200", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -927,12 +928,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3", - "MSRValue": "0x3f803c0100", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", + "MSRValue": "0x3F803C0100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -940,12 +941,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0002", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -953,12 +954,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3", - "MSRValue": "0x3f803c0002", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3", + "MSRValue": "0x3F803C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json index d7b9d9c9c518..ba0e0c4e74eb 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json @@ -42,7 +42,7 @@ { "EventCode": "0xC7", "UMask": "0x3", - "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single precision?)", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", "SampleAfterValue": "2000003", @@ -51,7 +51,7 @@ { "EventCode": "0xC7", "UMask": "0x4", - "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", "SampleAfterValue": "2000003", @@ -60,7 +60,7 @@ { "EventCode": "0xC7", "UMask": "0x8", - "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", "SampleAfterValue": "2000003", @@ -69,7 +69,7 @@ { "EventCode": "0xC7", "UMask": "0x10", - "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", "SampleAfterValue": "2000003", @@ -78,7 +78,7 @@ { "EventCode": "0xC7", "UMask": "0x15", - "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.", + "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.DOUBLE", "SampleAfterValue": "2000006", @@ -87,7 +87,7 @@ { "EventCode": "0xc7", "UMask": "0x20", - "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", "SampleAfterValue": "2000003", @@ -96,7 +96,7 @@ { "EventCode": "0xC7", "UMask": "0x2a", - "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.", + "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.SINGLE", "SampleAfterValue": "2000005", @@ -105,7 +105,7 @@ { "EventCode": "0xC7", "UMask": "0x3c", - "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single-precision?)", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.PACKED", "SampleAfterValue": "2000004", diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/memory.json index d79a5cfea44b..ecb413bb67ca 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/memory.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/memory.json @@ -170,11 +170,11 @@ { "EventCode": "0xc8", "UMask": "0x4", - "BriefDescription": "Number of times HLE abort was triggered (PEBS)", + "BriefDescription": "Number of times HLE abort was triggered", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "HLE_RETIRED.ABORTED", - "PublicDescription": "Number of times HLE abort was triggered (PEBS).", + "PublicDescription": "Number of times HLE abort was triggered.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -251,11 +251,11 @@ { "EventCode": "0xc9", "UMask": "0x4", - "BriefDescription": "Number of times RTM abort was triggered (PEBS)", + "BriefDescription": "Number of times RTM abort was triggered", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "RTM_RETIRED.ABORTED", - "PublicDescription": "Number of times RTM abort was triggered (PEBS).", + "PublicDescription": "Number of times RTM abort was triggered .", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, @@ -312,14 +312,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 4", + "BriefDescription": "Randomly selected loads with latency value being above 4", "PEBS": "2", "MSRValue": "0x4", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above four.", + "PublicDescription": "Counts randomly selected loads with latency value being above four.", "TakenAlone": "1", "SampleAfterValue": "100003", "CounterHTOff": "3" @@ -327,14 +327,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 8", + "BriefDescription": "Randomly selected loads with latency value being above 8", "PEBS": "2", "MSRValue": "0x8", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above eight.", + "PublicDescription": "Counts randomly selected loads with latency value being above eight.", "TakenAlone": "1", "SampleAfterValue": "50021", "CounterHTOff": "3" @@ -342,14 +342,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 16", + "BriefDescription": "Randomly selected loads with latency value being above 16", "PEBS": "2", "MSRValue": "0x10", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above 16.", + "PublicDescription": "Counts randomly selected loads with latency value being above 16.", "TakenAlone": "1", "SampleAfterValue": "20011", "CounterHTOff": "3" @@ -357,14 +357,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 32", + "BriefDescription": "Randomly selected loads with latency value being above 32", "PEBS": "2", "MSRValue": "0x20", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above 32.", + "PublicDescription": "Counts randomly selected loads with latency value being above 32.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "3" @@ -372,14 +372,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 64", + "BriefDescription": "Randomly selected loads with latency value being above 64", "PEBS": "2", "MSRValue": "0x40", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above 64.", + "PublicDescription": "Counts randomly selected loads with latency value being above 64.", "TakenAlone": "1", "SampleAfterValue": "2003", "CounterHTOff": "3" @@ -387,14 +387,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 128", + "BriefDescription": "Randomly selected loads with latency value being above 128", "PEBS": "2", "MSRValue": "0x80", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above 128.", + "PublicDescription": "Counts randomly selected loads with latency value being above 128.", "TakenAlone": "1", "SampleAfterValue": "1009", "CounterHTOff": "3" @@ -402,14 +402,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 256", + "BriefDescription": "Randomly selected loads with latency value being above 256", "PEBS": "2", "MSRValue": "0x100", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above 256.", + "PublicDescription": "Counts randomly selected loads with latency value being above 256.", "TakenAlone": "1", "SampleAfterValue": "503", "CounterHTOff": "3" @@ -417,14 +417,14 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 512", + "BriefDescription": "Randomly selected loads with latency value being above 512", "PEBS": "2", "MSRValue": "0x200", "Counter": "3", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "Errata": "BDM100, BDM35", - "PublicDescription": "This event counts loads with latency value being above 512.", + "PublicDescription": "Counts randomly selected loads with latency value being above 512.", "TakenAlone": "1", "SampleAfterValue": "101", "CounterHTOff": "3" @@ -433,12 +433,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all requests that miss in the L3", - "MSRValue": "0x3fbfc08fff", + "BriefDescription": "Counts all requests miss in the L3", + "MSRValue": "0x3FBFC08FFF", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all requests miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -446,12 +446,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache", - "MSRValue": "0x087fc007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache", + "MSRValue": "0x087FC007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -459,12 +459,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache", - "MSRValue": "0x103fc007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache", + "MSRValue": "0x103FC007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -472,12 +472,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram", - "MSRValue": "0x063bc007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram", + "MSRValue": "0x063BC007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -485,12 +485,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram", - "MSRValue": "0x06040007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram", + "MSRValue": "0x06040007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -498,12 +498,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3", - "MSRValue": "0x3fbfc007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3", + "MSRValue": "0x3FBFC007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -511,12 +511,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "MSRValue": "0x0604000244", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -524,12 +524,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3", - "MSRValue": "0x3fbfc00244", + "BriefDescription": "Counts all demand & prefetch code reads miss in the L3", + "MSRValue": "0x3FBFC00244", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -537,12 +537,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "MSRValue": "0x0604000122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -550,12 +550,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3", - "MSRValue": "0x3fbfc00122", + "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3", + "MSRValue": "0x3FBFC00122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -563,12 +563,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache", - "MSRValue": "0x087fc00091", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache", + "MSRValue": "0x087FC00091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -576,12 +576,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache", - "MSRValue": "0x103fc00091", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache", + "MSRValue": "0x103FC00091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -589,12 +589,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram", - "MSRValue": "0x063bc00091", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram", + "MSRValue": "0x063BC00091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -602,12 +602,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "MSRValue": "0x0604000091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -615,12 +615,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3", - "MSRValue": "0x3fbfc00091", + "BriefDescription": "Counts all demand & prefetch data reads miss in the L3", + "MSRValue": "0x3FBFC00091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -628,12 +628,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3", - "MSRValue": "0x3fbfc00200", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", + "MSRValue": "0x3FBFC00200", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -641,12 +641,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3", - "MSRValue": "0x3fbfc00100", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", + "MSRValue": "0x3FBFC00100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -654,12 +654,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache", - "MSRValue": "0x103fc00002", + "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache", + "MSRValue": "0x103FC00002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -667,12 +667,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3", - "MSRValue": "0x3fbfc00002", + "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3", + "MSRValue": "0x3FBFC00002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json index 0d04bf9db000..c2f6932a5817 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json @@ -1,6 +1,5 @@ [ { - "EventCode": "0x00", "UMask": "0x1", "BriefDescription": "Instructions retired from execution.", "Counter": "Fixed counter 0", @@ -10,7 +9,6 @@ "CounterHTOff": "Fixed counter 0" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when the thread is not in halt state", "Counter": "Fixed counter 1", @@ -20,7 +18,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "Counter": "Fixed counter 1", @@ -30,7 +27,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x3", "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", @@ -322,7 +318,7 @@ "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "Counter": "0,1,2,3", "EventName": "ILD_STALL.LCP", - "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", + "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -786,12 +782,12 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0xa2", "UMask": "0x1", "BriefDescription": "Resource-related stall cycles", "Counter": "0,1,2,3", "EventName": "RESOURCE_STALLS.ANY", - "PublicDescription": "This event counts resource-related stall cycles. Reasons for stalls can be as follows:\n - *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots)\n - *any* u-arch structure got empty (like INT/SIMD FreeLists)\n - FPU control word (FPCW), MXCSR\nand others. This counts cycles that the pipeline backend blocked uop delivery from the front end.", + "PublicDescription": "This event counts resource-related stall cycles.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1168,12 +1164,12 @@ { "EventCode": "0xC2", "UMask": "0x1", - "BriefDescription": "Actually retired uops. (Precise Event - PEBS)", + "BriefDescription": "Actually retired uops.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "UOPS_RETIRED.ALL", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.", + "PublicDescription": "This event counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1204,11 +1200,11 @@ { "EventCode": "0xC2", "UMask": "0x2", - "BriefDescription": "Retirement slots used. (Precise Event - PEBS)", + "BriefDescription": "Retirement slots used.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "UOPS_RETIRED.RETIRE_SLOTS", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of retirement slots used.", + "PublicDescription": "This event counts the number of retirement slots used.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1266,33 +1262,33 @@ { "EventCode": "0xC4", "UMask": "0x1", - "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Conditional branch instructions retired.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.CONDITIONAL", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.", + "PublicDescription": "This event counts conditional branch instructions retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xC4", "UMask": "0x2", - "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Direct and indirect near call instructions retired.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.", + "PublicDescription": "This event counts both direct and indirect near call instructions retired.", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xC4", "UMask": "0x2", - "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS)", + "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3).", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_CALL_R3", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect macro near call instructions retired (captured in ring 3).", + "PublicDescription": "This event counts both direct and indirect macro near call instructions retired (captured in ring 3).", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1311,11 +1307,11 @@ { "EventCode": "0xC4", "UMask": "0x8", - "BriefDescription": "Return instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Return instructions retired.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.", + "PublicDescription": "This event counts return instructions retired.", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1332,11 +1328,11 @@ { "EventCode": "0xC4", "UMask": "0x20", - "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Taken branch instructions retired.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.", + "PublicDescription": "This event counts taken branch instructions retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1364,11 +1360,11 @@ { "EventCode": "0xC5", "UMask": "0x1", - "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Mispredicted conditional branch instructions retired.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_MISP_RETIRED.CONDITIONAL", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.", + "PublicDescription": "This event counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1386,22 +1382,22 @@ { "EventCode": "0xC5", "UMask": "0x8", - "BriefDescription": "This event counts the number of mispredicted ret instructions retired.(Precise Event)", + "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_MISP_RETIRED.RET", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted return instructions retired.", + "PublicDescription": "This event counts mispredicted return instructions retired.", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xC5", "UMask": "0x20", - "BriefDescription": "number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).", + "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).", + "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 71e9737f4614..1a1a3501180a 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -1,164 +1,394 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )", - "MetricGroup": "Frontend", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "Branch_Misprediction_Cost" + }, + { + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts_SMT", + "MetricName": "Branch_Misprediction_Cost_SMT" }, { + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" + }, + { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Access_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x35\\\\\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )", + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_Lat", + "MetricName": "DRAM_Read_Latency" + }, + { + "MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1@", + "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_Parallel_Reads" + }, + { + "MetricExpr": "( 1000000000 * ( imc@event\\=0xe0\\\\\\,umask\\=0x1@ / imc@event\\=0xe3@ ) / imc_0@event\\=0x0@ ) if 1 if 1 == 1 else 0 else 0", + "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", + "MetricGroup": "Memory_Lat", + "MetricName": "MEM_PMM_Read_Latency" + }, + { + "MetricExpr": "( ( 64 * imc@event\\=0xe3@ / 1000000000 ) / duration_time ) if 1 if 1 == 1 else 0 else 0", + "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "PMM_Read_BW" + }, + { + "MetricExpr": "( ( 64 * imc@event\\=0xe7@ / 1000000000 ) / duration_time ) if 1 if 1 == 1 else 0 else 0", + "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "PMM_Write_BW" + }, + { + "MetricExpr": "cha_0@event\\=0x0@", + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricGroup": "", + "MetricName": "Socket_CLKS" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/goldmont/cache.json b/tools/perf/pmu-events/arch/x86/goldmont/cache.json index f8bbe087b0f8..52a105666afc 100644 --- a/tools/perf/pmu-events/arch/x86/goldmont/cache.json +++ b/tools/perf/pmu-events/arch/x86/goldmont/cache.json @@ -77,7 +77,8 @@ "UMask": "0x21", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Locked load uops retired (Precise event capable)" + "BriefDescription": "Locked load uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -88,7 +89,8 @@ "UMask": "0x41", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)" + "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -99,7 +101,8 @@ "UMask": "0x42", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", "SampleAfterValue": "200003", - "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)" + "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -110,7 +113,8 @@ "UMask": "0x43", "EventName": "MEM_UOPS_RETIRED.SPLIT", "SampleAfterValue": "200003", - "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)" + "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -121,7 +125,8 @@ "UMask": "0x81", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired (Precise event capable)" + "BriefDescription": "Load uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -132,7 +137,8 @@ "UMask": "0x82", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "SampleAfterValue": "200003", - "BriefDescription": "Store uops retired (Precise event capable)" + "BriefDescription": "Store uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -143,7 +149,8 @@ "UMask": "0x83", "EventName": "MEM_UOPS_RETIRED.ALL", "SampleAfterValue": "200003", - "BriefDescription": "Memory uops retired (Precise event capable)" + "BriefDescription": "Memory uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -154,7 +161,8 @@ "UMask": "0x1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)" + "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -165,7 +173,8 @@ "UMask": "0x2", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that hit L2 (Precise event capable)" + "BriefDescription": "Load uops retired that hit L2 (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -176,7 +185,8 @@ "UMask": "0x8", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)" + "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -187,7 +197,8 @@ "UMask": "0x10", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that missed L2 (Precise event capable)" + "BriefDescription": "Load uops retired that missed L2 (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -198,7 +209,8 @@ "UMask": "0x20", "EventName": "MEM_LOAD_UOPS_RETIRED.HITM", "SampleAfterValue": "200003", - "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)" + "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -209,7 +221,8 @@ "UMask": "0x40", "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Loads retired that hit WCB (Precise event capable)" + "BriefDescription": "Loads retired that hit WCB (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -220,26 +233,14 @@ "UMask": "0x80", "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Loads retired that came from DRAM (Precise event capable)" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x40000032b7 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" + "BriefDescription": "Loads retired that came from DRAM (Precise event capable)", + "Data_LA": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x36000032b7 ", + "MSRValue": "0x36000032b7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.ANY", @@ -252,7 +253,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x10000032b7 ", + "MSRValue": "0x10000032b7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.HITM_OTHER_CORE", @@ -265,7 +266,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x04000032b7 ", + "MSRValue": "0x04000032b7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -278,20 +279,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x02000032b7 ", + "MSRValue": "0x02000032b7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x00000432b7 ", + "MSRValue": "0x00000432b7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT", @@ -302,35 +303,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x00000132b7 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_READ.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000022 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000022 ", + "MSRValue": "0x3600000022", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.ANY", @@ -343,7 +318,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000000022 ", + "MSRValue": "0x1000000022", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.HITM_OTHER_CORE", @@ -356,7 +331,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000022 ", + "MSRValue": "0x0400000022", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -369,20 +344,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000022 ", + "MSRValue": "0x0200000022", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040022 ", + "MSRValue": "0x0000040022", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT", @@ -393,32 +368,6 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010022 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data reads (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000003091", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", "MSRValue": "0x3600003091", @@ -466,7 +415,7 @@ "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data reads (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -484,35 +433,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts data reads (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000013091", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads (demand & prefetch) that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000003010 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600003010 ", + "MSRValue": "0x3600003010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.ANY", @@ -525,7 +448,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000003010 ", + "MSRValue": "0x1000003010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.HITM_OTHER_CORE", @@ -538,7 +461,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400003010 ", + "MSRValue": "0x0400003010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -551,20 +474,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200003010 ", + "MSRValue": "0x0200003010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000043010 ", + "MSRValue": "0x0000043010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_HIT", @@ -575,48 +498,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000013010 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts requests to the uncore subsystem that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000008000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts requests to the uncore subsystem that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x3600008000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.ANY", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000008000 ", + "MSRValue": "0x1000008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.HITM_OTHER_CORE", @@ -629,7 +513,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400008000 ", + "MSRValue": "0x0400008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -642,20 +526,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200008000 ", + "MSRValue": "0x0200008000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts requests to the uncore subsystem that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000048000 ", + "MSRValue": "0x0000048000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT", @@ -668,7 +552,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts requests to the uncore subsystem that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000018000 ", + "MSRValue": "0x0000018000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.ANY_RESPONSE", @@ -679,22 +563,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000004800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600004800 ", + "MSRValue": "0x3600004800", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.ANY", @@ -705,48 +576,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x1000004800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0400004800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0200004800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. ", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000044800 ", + "MSRValue": "0x0000044800", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_HIT", @@ -757,35 +589,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000014800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000004000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600004000 ", + "MSRValue": "0x3600004000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.ANY", @@ -798,7 +604,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000004000 ", + "MSRValue": "0x1000004000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.HITM_OTHER_CORE", @@ -811,7 +617,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400004000 ", + "MSRValue": "0x0400004000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -824,20 +630,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200004000 ", + "MSRValue": "0x0200004000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000044000 ", + "MSRValue": "0x0000044000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_HIT", @@ -848,35 +654,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000014000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000002000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600002000 ", + "MSRValue": "0x3600002000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.ANY", @@ -889,7 +669,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000002000 ", + "MSRValue": "0x1000002000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.HITM_OTHER_CORE", @@ -902,7 +682,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400002000 ", + "MSRValue": "0x0400002000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -915,20 +695,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200002000 ", + "MSRValue": "0x0200002000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000042000 ", + "MSRValue": "0x0000042000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT", @@ -939,35 +719,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000012000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cache lines requests by software prefetch instructions that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000001000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache lines requests by software prefetch instructions that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600001000 ", + "MSRValue": "0x3600001000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.ANY", @@ -980,7 +734,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000001000 ", + "MSRValue": "0x1000001000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.HITM_OTHER_CORE", @@ -993,7 +747,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400001000 ", + "MSRValue": "0x0400001000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -1006,20 +760,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200001000 ", + "MSRValue": "0x0200001000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts data cache lines requests by software prefetch instructions that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000041000 ", + "MSRValue": "0x0000041000", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_HIT", @@ -1030,35 +784,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cache lines requests by software prefetch instructions that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000011000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache lines requests by software prefetch instructions that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000800 ", + "MSRValue": "0x3600000800", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.ANY", @@ -1071,7 +799,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000000800 ", + "MSRValue": "0x1000000800", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.HITM_OTHER_CORE", @@ -1084,7 +812,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000800 ", + "MSRValue": "0x0400000800", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -1097,20 +825,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000800 ", + "MSRValue": "0x0200000800", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040800 ", + "MSRValue": "0x0000040800", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_HIT", @@ -1121,100 +849,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts bus lock and split lock requests that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000400 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x3600000400 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.ANY", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x1000000400 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0400000400 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts bus lock and split lock requests that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0200000400 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests that true miss for the L2 cache with a snoop miss in the other processor module. ", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts bus lock and split lock requests that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000040400 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests that hit the L2 cache.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts bus lock and split lock requests that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000010400 ", + "MSRValue": "0x0000010400", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.ANY_RESPONSE", @@ -1225,113 +862,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x3600000200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.ANY", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x1000000200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0400000200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0200000200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. ", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000040200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_HIT", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that hit the L2 cache.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000100 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000100 ", + "MSRValue": "0x3600000100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.ANY", @@ -1342,87 +875,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x1000000100 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0400000100 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0200000100 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that true miss for the L2 cache with a snoop miss in the other processor module. ", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000040100 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that hit the L2 cache.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010100 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000080 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000080 ", + "MSRValue": "0x3600000080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.ANY", @@ -1433,87 +888,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x1000000080 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0400000080 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0200000080 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that true miss for the L2 cache with a snoop miss in the other processor module. ", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000040080 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that hit the L2 cache.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010080 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000020 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000020 ", + "MSRValue": "0x3600000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.ANY", @@ -1526,7 +903,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000000020 ", + "MSRValue": "0x1000000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.HITM_OTHER_CORE", @@ -1539,7 +916,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000020 ", + "MSRValue": "0x0400000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -1552,20 +929,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000020 ", + "MSRValue": "0x0200000020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040020 ", + "MSRValue": "0x0000040020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT", @@ -1576,35 +953,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010020 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000010 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000010 ", + "MSRValue": "0x3600000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.ANY", @@ -1617,7 +968,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000000010 ", + "MSRValue": "0x1000000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.HITM_OTHER_CORE", @@ -1630,7 +981,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000010 ", + "MSRValue": "0x0400000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -1643,20 +994,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000010 ", + "MSRValue": "0x0200000010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040010 ", + "MSRValue": "0x0000040010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_HIT", @@ -1667,35 +1018,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010010 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x4000000008 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.COREWB.OUTSTANDING", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that are outstanding, per cycle, from the time of the L2 miss to when any response is received.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000008 ", + "MSRValue": "0x3600000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.ANY", @@ -1708,7 +1033,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000000008 ", + "MSRValue": "0x1000000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.HITM_OTHER_CORE", @@ -1721,7 +1046,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000008 ", + "MSRValue": "0x0400000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -1734,20 +1059,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000008 ", + "MSRValue": "0x0200000008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040008 ", + "MSRValue": "0x0000040008", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.COREWB.L2_HIT", @@ -1758,22 +1083,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010008 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x4000000004 ", + "MSRValue": "0x4000000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING", @@ -1786,7 +1098,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000004 ", + "MSRValue": "0x3600000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.ANY", @@ -1797,22 +1109,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x1000000004 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000004 ", + "MSRValue": "0x0400000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -1825,20 +1124,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000004 ", + "MSRValue": "0x0200000004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040004 ", + "MSRValue": "0x0000040004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT", @@ -1849,22 +1148,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010004 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x4000000002 ", + "MSRValue": "0x4000000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING", @@ -1877,7 +1163,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000002 ", + "MSRValue": "0x3600000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.ANY", @@ -1890,7 +1176,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000000002 ", + "MSRValue": "0x1000000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.HITM_OTHER_CORE", @@ -1903,7 +1189,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000002 ", + "MSRValue": "0x0400000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -1916,20 +1202,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000002 ", + "MSRValue": "0x0200000002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040002 ", + "MSRValue": "0x0000040002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT", @@ -1940,22 +1226,9 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010002 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that have any transaction responses from the uncore subsystem.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", "PublicDescription": "Counts demand cacheable data reads of full cache lines that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x4000000001 ", + "MSRValue": "0x4000000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING", @@ -1968,7 +1241,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x3600000001 ", + "MSRValue": "0x3600000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.ANY", @@ -1981,7 +1254,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x1000000001 ", + "MSRValue": "0x1000000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.HITM_OTHER_CORE", @@ -1994,7 +1267,7 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0400000001 ", + "MSRValue": "0x0400000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD", @@ -2007,20 +1280,20 @@ "CollectPEBSRecord": "1", "PublicDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0200000001 ", + "MSRValue": "0x0200000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { "CollectPEBSRecord": "1", "PublicDescription": "Counts demand cacheable data reads of full cache lines that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", "EventCode": "0xB7", - "MSRValue": "0x0000040001 ", + "MSRValue": "0x0000040001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT", @@ -2028,18 +1301,5 @@ "SampleAfterValue": "100007", "BriefDescription": "Counts demand cacheable data reads of full cache lines that hit the L2 cache.", "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand cacheable data reads of full cache lines that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x0000010001 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data reads of full cache lines that have any transaction responses from the uncore subsystem.", - "Offcore": "1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/goldmont/memory.json b/tools/perf/pmu-events/arch/x86/goldmont/memory.json index 690cebd12a94..197dc76d49dd 100644 --- a/tools/perf/pmu-events/arch/x86/goldmont/memory.json +++ b/tools/perf/pmu-events/arch/x86/goldmont/memory.json @@ -30,265 +30,5 @@ "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", "SampleAfterValue": "200003", "BriefDescription": "Machine clears due to memory ordering issue" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x20000032b7 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000022 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000003091", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000003010 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000008000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000004800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000004000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000002000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000001000 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000800 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000400 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000200 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000100 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000080 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000020 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000010 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000008 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000004 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000002 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" - }, - { - "CollectPEBSRecord": "1", - "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)", - "EventCode": "0xB7", - "MSRValue": "0x2000000001 ", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.NON_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache and targets non-DRAM system address.", - "Offcore": "1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json b/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json index 254788af8ab6..6342368accf8 100644 --- a/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json @@ -1,7 +1,6 @@ [ { "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. You cannot collect a PEBs record for this event.", - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -10,7 +9,6 @@ }, { "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. This event uses fixed counter 1. You cannot collect a PEBs record for this event.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.CORE", @@ -19,7 +17,6 @@ }, { "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. This event uses fixed counter 2. You cannot collect a PEBs record for this event.", - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", @@ -188,7 +185,7 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.", + "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel\u00ae architecture processors.", "EventCode": "0xC3", "Counter": "0,1,2,3", "UMask": "0x1", diff --git a/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json b/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json index 9805198d3f5f..343d66bbd777 100644 --- a/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json @@ -48,7 +48,8 @@ "UMask": "0x11", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)" + "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -59,7 +60,8 @@ "UMask": "0x12", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES", "SampleAfterValue": "200003", - "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)" + "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -70,6 +72,7 @@ "UMask": "0x13", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS", "SampleAfterValue": "200003", - "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)" + "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)", + "Data_LA": "1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json b/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json index b4791b443a66..5a6ac8285ad4 100644 --- a/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json +++ b/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json @@ -92,7 +92,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Locked load uops retired (Precise event capable)" + "BriefDescription": "Locked load uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -104,7 +105,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)" + "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -116,7 +118,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", "SampleAfterValue": "200003", - "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)" + "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -128,7 +131,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT", "SampleAfterValue": "200003", - "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)" + "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -140,7 +144,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired (Precise event capable)" + "BriefDescription": "Load uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -152,7 +157,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "SampleAfterValue": "200003", - "BriefDescription": "Store uops retired (Precise event capable)" + "BriefDescription": "Store uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -164,7 +170,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL", "SampleAfterValue": "200003", - "BriefDescription": "Memory uops retired (Precise event capable)" + "BriefDescription": "Memory uops retired (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -176,7 +183,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)" + "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -188,7 +196,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that hit L2 (Precise event capable)" + "BriefDescription": "Load uops retired that hit L2 (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -200,7 +209,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)" + "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -212,7 +222,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that missed L2 (Precise event capable)" + "BriefDescription": "Load uops retired that missed L2 (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -224,7 +235,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.HITM", "SampleAfterValue": "200003", - "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)" + "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -236,7 +248,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Loads retired that hit WCB (Precise event capable)" + "BriefDescription": "Loads retired that hit WCB (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -248,7 +261,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Loads retired that came from DRAM (Precise event capable)" + "BriefDescription": "Loads retired that came from DRAM (Precise event capable)", + "Data_LA": "1" }, { "CollectPEBSRecord": "1", @@ -292,7 +306,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data reads of full cache lines true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts demand cacheable data reads of full cache lines true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -367,7 +381,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -442,7 +456,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -517,7 +531,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -592,7 +606,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -667,7 +681,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -742,7 +756,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts bus lock and split lock requests true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts bus lock and split lock requests true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -817,7 +831,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -892,7 +906,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache lines requests by software prefetch instructions true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data cache lines requests by software prefetch instructions true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -967,7 +981,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -1042,7 +1056,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -1117,7 +1131,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts requests to the uncore subsystem true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts requests to the uncore subsystem true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -1192,7 +1206,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -1267,7 +1281,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data reads (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data reads (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -1342,7 +1356,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { @@ -1417,7 +1431,7 @@ "PDIR_COUNTER": "na", "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ", + "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.", "Offcore": "1" }, { diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json b/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json index ccf1aed69197..e3fa1a0ba71b 100644 --- a/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json @@ -3,7 +3,6 @@ "PEBS": "2", "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. You cannot collect a PEBs record for this event.", - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "PEBScounters": "32", @@ -15,7 +14,6 @@ { "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. This event uses fixed counter 1. You cannot collect a PEBs record for this event.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "PEBScounters": "33", @@ -27,7 +25,6 @@ { "CollectPEBSRecord": "1", "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. This event uses fixed counter 2. You cannot collect a PEBs record for this event.", - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "PEBScounters": "34", @@ -231,7 +228,7 @@ }, { "CollectPEBSRecord": "1", - "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.", + "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel\u00ae architecture processors.", "EventCode": "0xC3", "Counter": "0,1,2,3", "UMask": "0x1", diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json b/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json index 0b53a3b0dfb8..0d32fd26ded1 100644 --- a/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json @@ -189,7 +189,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS", "SampleAfterValue": "200003", - "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)" + "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -201,7 +202,8 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES", "SampleAfterValue": "200003", - "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)" + "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)", + "Data_LA": "1" }, { "PEBS": "2", @@ -213,6 +215,7 @@ "PEBScounters": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS", "SampleAfterValue": "200003", - "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)" + "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)", + "Data_LA": "1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/haswell/cache.json b/tools/perf/pmu-events/arch/x86/haswell/cache.json index da4d6ddd4f92..7fb0ad8d8ca1 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/cache.json +++ b/tools/perf/pmu-events/arch/x86/haswell/cache.json @@ -63,10 +63,10 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Demand data read requests that hit L2 cache.", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x41", + "UMask": "0xc1", "Errata": "HSD78", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", "SampleAfterValue": "200003", @@ -77,7 +77,7 @@ "PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x42", + "UMask": "0xc2", "EventName": "L2_RQSTS.RFO_HIT", "SampleAfterValue": "200003", "BriefDescription": "RFO requests that hit L2 cache", @@ -87,7 +87,7 @@ "PublicDescription": "Number of instruction fetches that hit the L2 cache.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x44", + "UMask": "0xc4", "EventName": "L2_RQSTS.CODE_RD_HIT", "SampleAfterValue": "200003", "BriefDescription": "L2 cache hits when fetching instructions, code reads.", @@ -97,7 +97,7 @@ "PublicDescription": "Counts all L2 HW prefetcher requests that hit L2.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x50", + "UMask": "0xd0", "EventName": "L2_RQSTS.L2_PF_HIT", "SampleAfterValue": "200003", "BriefDescription": "L2 prefetch requests that hit L2 cache", @@ -610,7 +610,7 @@ "Errata": "HSD29, HSD25, HSM26, HSM30", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT", "SampleAfterValue": "20011", - "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. ", + "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, @@ -623,7 +623,7 @@ "Errata": "HSD29, HSD25, HSM26, HSM30", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM", "SampleAfterValue": "20011", - "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. ", + "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, @@ -792,7 +792,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "", "EventCode": "0xf4", "Counter": "0,1,2,3", "UMask": "0x10", @@ -802,262 +801,262 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all requests hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c8fff", + "MSRValue": "0x3F803C8FFF", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all requests that hit in the L3", + "BriefDescription": "Counts all requests hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c07f7", + "MSRValue": "0x10003C07F7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c07f7", + "MSRValue": "0x04003C07F7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0244", + "MSRValue": "0x04003C0244", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0122", + "MSRValue": "0x10003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0122", + "MSRValue": "0x04003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0091", + "MSRValue": "0x10003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0091", + "MSRValue": "0x04003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0200", + "MSRValue": "0x3F803C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0100", + "MSRValue": "0x3F803C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0080", + "MSRValue": "0x3F803C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0040", + "MSRValue": "0x3F803C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0020", + "MSRValue": "0x3F803C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0010", + "MSRValue": "0x3F803C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0004", + "MSRValue": "0x10003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0004", + "MSRValue": "0x04003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0002", + "MSRValue": "0x10003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0002", + "MSRValue": "0x04003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0001", + "MSRValue": "0x10003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0001", + "MSRValue": "0x04003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json index f9843e5a9b42..f5a3beaa19fc 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json @@ -1,22 +1,26 @@ [ { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x8", "Errata": "HSD56, HSM57", "EventName": "OTHER_ASSISTS.AVX_TO_SSE", "SampleAfterValue": "100003", - "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", + "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x10", "Errata": "HSD56, HSM57", "EventName": "OTHER_ASSISTS.SSE_TO_AVX", "SampleAfterValue": "100003", - "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", + "BriefDescription": "Number of transitions from legacy SSE to AVX-256 when penalty applicable", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -30,53 +34,58 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of X87 FP assists due to output values.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x2", "EventName": "FP_ASSIST.X87_OUTPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of X87 assists due to output value.", + "BriefDescription": "output - Numeric Overflow, Numeric Underflow, Inexact Result", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of X87 FP assists due to input values.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x4", "EventName": "FP_ASSIST.X87_INPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of X87 assists due to input value.", + "BriefDescription": "input - Invalid Operation, Denormal Operand, SNaN Operand", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of SIMD FP assists due to output values.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x8", "EventName": "FP_ASSIST.SIMD_OUTPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of SIMD FP assists due to Output values", + "BriefDescription": "SSE* FP micro-code assist when output value is invalid.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of SIMD FP assists due to input values.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x10", "EventName": "FP_ASSIST.SIMD_INPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of SIMD FP assists due to input values", + "BriefDescription": "Any input SSE* FP Assist", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Cycles with any input/output SSE* or FP assists.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x1e", "EventName": "FP_ASSIST.ANY", "SampleAfterValue": "100003", - "BriefDescription": "Cycles with any input/output SSE or FP assist", + "BriefDescription": "Counts any FP_ASSIST umask was incrementing", "CounterMask": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index 5ab5c78fe580..21b27488b621 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -1,158 +1,322 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )", - "MetricGroup": "Frontend", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/haswell/memory.json b/tools/perf/pmu-events/arch/x86/haswell/memory.json index e5f9fa6655b3..ef13ed88e2ea 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/memory.json +++ b/tools/perf/pmu-events/arch/x86/haswell/memory.json @@ -298,7 +298,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "SampleAfterValue": "100003", - "BriefDescription": "Loads with latency value being above 4.", + "BriefDescription": "Randomly selected loads with latency value being above 4.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -312,7 +312,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "SampleAfterValue": "50021", - "BriefDescription": "Loads with latency value being above 8.", + "BriefDescription": "Randomly selected loads with latency value being above 8.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -326,7 +326,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "SampleAfterValue": "20011", - "BriefDescription": "Loads with latency value being above 16.", + "BriefDescription": "Randomly selected loads with latency value being above 16.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -340,7 +340,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "SampleAfterValue": "100003", - "BriefDescription": "Loads with latency value being above 32.", + "BriefDescription": "Randomly selected loads with latency value being above 32.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -354,7 +354,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "SampleAfterValue": "2003", - "BriefDescription": "Loads with latency value being above 64.", + "BriefDescription": "Randomly selected loads with latency value being above 64.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -368,7 +368,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "SampleAfterValue": "1009", - "BriefDescription": "Loads with latency value being above 128.", + "BriefDescription": "Randomly selected loads with latency value being above 128.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -382,7 +382,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "SampleAfterValue": "503", - "BriefDescription": "Loads with latency value being above 256.", + "BriefDescription": "Randomly selected loads with latency value being above 256.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -396,280 +396,280 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "SampleAfterValue": "101", - "BriefDescription": "Loads with latency value being above 512.", + "BriefDescription": "Randomly selected loads with latency value being above 512.", "TakenAlone": "1", "CounterHTOff": "3" }, { - "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all requests miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc08fff", + "MSRValue": "0x3FFFC08FFF", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all requests that miss in the L3", + "BriefDescription": "Counts all requests miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01004007f7", + "MSRValue": "0x01004007F7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram", + "BriefDescription": "miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc007f7", + "MSRValue": "0x3FFFC007F7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3", + "BriefDescription": "miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400244", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00244", + "MSRValue": "0x3FFFC00244", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3", + "BriefDescription": "Counts all demand & prefetch code reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00122", + "MSRValue": "0x3FFFC00122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3", + "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00091", + "MSRValue": "0x3FFFC00091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3", + "BriefDescription": "Counts all demand & prefetch data reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00200", + "MSRValue": "0x3FFFC00200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00100", + "MSRValue": "0x3FFFC00100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00080", + "MSRValue": "0x3FFFC00080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00040", + "MSRValue": "0x3FFFC00040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00020", + "MSRValue": "0x3FFFC00020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00010", + "MSRValue": "0x3FFFC00010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00004", + "MSRValue": "0x3FFFC00004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that miss in the L3", + "BriefDescription": "Counts all demand code reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00002", + "MSRValue": "0x3FFFC00002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3", + "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts demand data reads miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00001", + "MSRValue": "0x3FFFC00001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that miss in the L3", + "BriefDescription": "Counts demand data reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json index a4dcfce4a512..734d3873729e 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json @@ -1,7 +1,6 @@ [ { "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. INST_RETIRED.ANY is counted by a designated fixed counter, leaving the programmable counters available for other events. Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "Errata": "HSD140, HSD143", @@ -12,7 +11,6 @@ }, { "PublicDescription": "This event counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -21,7 +19,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "AnyThread": "1", @@ -32,7 +29,6 @@ }, { "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state.", - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", @@ -1071,7 +1067,8 @@ "CounterHTOff": "1" }, { - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.", "EventCode": "0xC0", "Counter": "0,1,2,3", "UMask": "0x2", @@ -1081,13 +1078,13 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of microcode assists invoked by HW upon uop writeback.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x40", "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST", "SampleAfterValue": "100003", - "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -1102,28 +1099,34 @@ "Data_LA": "1" }, { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "UOPS_RETIRED.STALL_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles without actually retired uops.", + "BriefDescription": "Cycles no executable uops retired", "CounterMask": "1", "CounterHTOff": "0,1,2,3" }, { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "UOPS_RETIRED.TOTAL_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with less than 10 actually retired uops.", + "BriefDescription": "Number of cycles using always true condition applied to PEBS uops retired event.", "CounterMask": "10", "CounterHTOff": "0,1,2,3" }, { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", @@ -1131,7 +1134,7 @@ "AnyThread": "1", "EventName": "UOPS_RETIRED.CORE_STALL_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles without actually retired uops.", + "BriefDescription": "Cycles no executable uops retired on core", "CounterMask": "1", "CounterHTOff": "0,1,2,3" }, @@ -1245,13 +1248,14 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts the number of not taken branch instructions retired.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x10", "EventName": "BR_INST_RETIRED.NOT_TAKEN", "SampleAfterValue": "400009", - "BriefDescription": "Not taken branch instructions retired.", + "BriefDescription": "Counts all not taken macro branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -1265,13 +1269,14 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of far branches retired.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x40", "EventName": "BR_INST_RETIRED.FAR_BRANCH", "SampleAfterValue": "100003", - "BriefDescription": "Far branch instructions retired.", + "BriefDescription": "Counts the number of far branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { diff --git a/tools/perf/pmu-events/arch/x86/haswellx/cache.json b/tools/perf/pmu-events/arch/x86/haswellx/cache.json index b2fbd617306a..a9e62d4357af 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/cache.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/cache.json @@ -64,18 +64,18 @@ }, { "EventCode": "0x24", - "UMask": "0x41", + "UMask": "0xc1", "BriefDescription": "Demand Data Read requests that hit L2 cache", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", "Errata": "HSD78", - "PublicDescription": "Demand data read requests that hit L2 cache.", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", "SampleAfterValue": "200003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x24", - "UMask": "0x42", + "UMask": "0xc2", "BriefDescription": "RFO requests that hit L2 cache", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.RFO_HIT", @@ -85,7 +85,7 @@ }, { "EventCode": "0x24", - "UMask": "0x44", + "UMask": "0xc4", "BriefDescription": "L2 cache hits when fetching instructions, code reads.", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.CODE_RD_HIT", @@ -95,7 +95,7 @@ }, { "EventCode": "0x24", - "UMask": "0x50", + "UMask": "0xd0", "BriefDescription": "L2 prefetch requests that hit L2 cache", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.L2_PF_HIT", @@ -416,7 +416,7 @@ { "EventCode": "0xD0", "UMask": "0x11", - "BriefDescription": "Retired load uops that miss the STLB. (precise Event)", + "BriefDescription": "Retired load uops that miss the STLB.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -428,7 +428,7 @@ { "EventCode": "0xD0", "UMask": "0x12", - "BriefDescription": "Retired store uops that miss the STLB. (precise Event)", + "BriefDescription": "Retired store uops that miss the STLB.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -441,7 +441,7 @@ { "EventCode": "0xD0", "UMask": "0x21", - "BriefDescription": "Retired load uops with locked access. (precise Event)", + "BriefDescription": "Retired load uops with locked access.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -453,34 +453,32 @@ { "EventCode": "0xD0", "UMask": "0x41", - "BriefDescription": "Retired load uops that split across a cacheline boundary. (precise Event)", + "BriefDescription": "Retired load uops that split across a cacheline boundary.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", "Errata": "HSD29, HSM30", - "PublicDescription": "This event counts load uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x42", - "BriefDescription": "Retired store uops that split across a cacheline boundary. (precise Event)", + "BriefDescription": "Retired store uops that split across a cacheline boundary.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", "Errata": "HSD29, HSM30", "L1_Hit_Indication": "1", - "PublicDescription": "This event counts store uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x81", - "BriefDescription": "All retired load uops. (precise Event)", + "BriefDescription": "All retired load uops.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -492,14 +490,13 @@ { "EventCode": "0xD0", "UMask": "0x82", - "BriefDescription": "All retired store uops. (precise Event)", + "BriefDescription": "All retired store uops.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "Errata": "HSD29, HSM30", "L1_Hit_Indication": "1", - "PublicDescription": "This event counts all store uops retired. This is a precise event.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, @@ -530,13 +527,13 @@ { "EventCode": "0xD1", "UMask": "0x4", - "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.", + "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30", - "PublicDescription": "This event counts retired load uops in which data sources were data hits in the L3 cache without snoops required. This does not include hardware prefetches. This is a precise event.", + "PublicDescription": "Retired load uops with L3 cache hits as data sources.", "SampleAfterValue": "50021", "CounterHTOff": "0,1,2,3" }, @@ -549,19 +546,20 @@ "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", "Errata": "HSM30", - "PublicDescription": "This event counts retired load uops in which data sources missed in the L1 cache. This does not include hardware prefetches. This is a precise event.", + "PublicDescription": "Retired load uops missed L1 cache as data sources.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x10", - "BriefDescription": "Retired load uops with L2 cache misses as data sources.", + "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", "Errata": "HSD29, HSM30", + "PublicDescription": "Retired load uops missed L2. Unknown data source excluded.", "SampleAfterValue": "50021", "CounterHTOff": "0,1,2,3" }, @@ -574,6 +572,7 @@ "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_MISS", "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30", + "PublicDescription": "Retired load uops missed L3. Excludes unknown data source .", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -604,26 +603,24 @@ { "EventCode": "0xD2", "UMask": "0x2", - "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. ", + "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT", "Errata": "HSD29, HSD25, HSM26, HSM30", - "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HIT in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.", "SampleAfterValue": "20011", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD2", "UMask": "0x4", - "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. ", + "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM", "Errata": "HSD29, HSD25, HSM26, HSM30", - "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HITM (hit modified) in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.", "SampleAfterValue": "20011", "CounterHTOff": "0,1,2,3" }, @@ -642,19 +639,20 @@ { "EventCode": "0xD3", "UMask": "0x1", + "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", "Errata": "HSD74, HSD29, HSD25, HSM30", - "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.", + "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD3", "UMask": "0x4", - "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -666,7 +664,7 @@ { "EventCode": "0xD3", "UMask": "0x10", - "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -678,7 +676,7 @@ { "EventCode": "0xD3", "UMask": "0x20", - "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -833,7 +831,6 @@ "BriefDescription": "Split locks in SQ", "Counter": "0,1,2,3", "EventName": "SQ_MISC.SPLIT_LOCK", - "PublicDescription": "", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -841,12 +838,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0001", + "BriefDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -854,12 +851,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0001", + "BriefDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -867,12 +864,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0002", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -880,12 +877,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0002", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -893,12 +890,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0004", + "BriefDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -906,12 +903,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0004", + "BriefDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -919,12 +916,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3", - "MSRValue": "0x3f803c0010", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3", + "MSRValue": "0x3F803C0010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -932,12 +929,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3", - "MSRValue": "0x3f803c0020", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3", + "MSRValue": "0x3F803C0020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -945,12 +942,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3", - "MSRValue": "0x3f803c0040", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3", + "MSRValue": "0x3F803C0040", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -958,12 +955,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3", - "MSRValue": "0x3f803c0080", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3", + "MSRValue": "0x3F803C0080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -971,12 +968,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3", - "MSRValue": "0x3f803c0100", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", + "MSRValue": "0x3F803C0100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -984,12 +981,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3", - "MSRValue": "0x3f803c0200", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", + "MSRValue": "0x3F803C0200", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -997,12 +994,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0091", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1010,12 +1007,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0091", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1023,12 +1020,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0122", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1036,12 +1033,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c0122", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C0122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1049,12 +1046,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c0244", + "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C0244", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1062,12 +1059,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", - "MSRValue": "0x04003c07f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "MSRValue": "0x04003C07F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1075,12 +1072,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", - "MSRValue": "0x10003c07f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "MSRValue": "0x10003C07F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1088,12 +1085,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all requests that hit in the L3", - "MSRValue": "0x3f803c8fff", + "BriefDescription": "Counts all requests hit in the L3", + "MSRValue": "0x3F803C8FFF", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all requests hit in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index 5ab5c78fe580..e5aac148c941 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -1,158 +1,340 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )", - "MetricGroup": "Frontend", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "MetricExpr": "1000000000 * ( cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x35\\,umask\\=0x3\\,filter_opc\\=0x182@ ) / ( cbox_0@event\\=0x0@ / duration_time )", + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_Lat", + "MetricName": "DRAM_Read_Latency" + }, + { + "MetricExpr": "cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182\\,thresh\\=1@", + "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_Parallel_Reads" + }, + { + "MetricExpr": "cbox_0@event\\=0x0@", + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricGroup": "", + "MetricName": "Socket_CLKS" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/memory.json b/tools/perf/pmu-events/arch/x86/haswellx/memory.json index 56b0f24b8029..a42d5ce86b6f 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/memory.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/memory.json @@ -291,7 +291,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 4.", + "BriefDescription": "Randomly selected loads with latency value being above 4.", "PEBS": "2", "MSRValue": "0x4", "Counter": "3", @@ -305,7 +305,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 8.", + "BriefDescription": "Randomly selected loads with latency value being above 8.", "PEBS": "2", "MSRValue": "0x8", "Counter": "3", @@ -319,7 +319,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 16.", + "BriefDescription": "Randomly selected loads with latency value being above 16.", "PEBS": "2", "MSRValue": "0x10", "Counter": "3", @@ -333,7 +333,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 32.", + "BriefDescription": "Randomly selected loads with latency value being above 32.", "PEBS": "2", "MSRValue": "0x20", "Counter": "3", @@ -347,7 +347,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 64.", + "BriefDescription": "Randomly selected loads with latency value being above 64.", "PEBS": "2", "MSRValue": "0x40", "Counter": "3", @@ -361,7 +361,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 128.", + "BriefDescription": "Randomly selected loads with latency value being above 128.", "PEBS": "2", "MSRValue": "0x80", "Counter": "3", @@ -375,7 +375,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 256.", + "BriefDescription": "Randomly selected loads with latency value being above 256.", "PEBS": "2", "MSRValue": "0x100", "Counter": "3", @@ -389,7 +389,7 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Loads with latency value being above 512.", + "BriefDescription": "Randomly selected loads with latency value being above 512.", "PEBS": "2", "MSRValue": "0x200", "Counter": "3", @@ -404,12 +404,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss in the L3", - "MSRValue": "0x3fbfc00001", + "BriefDescription": "Counts demand data reads miss in the L3", + "MSRValue": "0x3FBFC00001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -417,12 +417,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts demand data reads miss the L3 and the data is returned from local dram", "MSRValue": "0x0600400001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -430,12 +430,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3", - "MSRValue": "0x3fbfc00002", + "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3", + "MSRValue": "0x3FBFC00002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -443,12 +443,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram", "MSRValue": "0x0600400002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -456,12 +456,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache", - "MSRValue": "0x103fc00002", + "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache", + "MSRValue": "0x103FC00002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -469,12 +469,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss in the L3", - "MSRValue": "0x3fbfc00004", + "BriefDescription": "Counts all demand code reads miss in the L3", + "MSRValue": "0x3FBFC00004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -482,12 +482,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram", "MSRValue": "0x0600400004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -495,12 +495,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3", - "MSRValue": "0x3fbfc00010", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3", + "MSRValue": "0x3FBFC00010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -508,12 +508,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3", - "MSRValue": "0x3fbfc00020", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3", + "MSRValue": "0x3FBFC00020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -521,12 +521,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3", - "MSRValue": "0x3fbfc00040", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3", + "MSRValue": "0x3FBFC00040", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -534,12 +534,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3", - "MSRValue": "0x3fbfc00080", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3", + "MSRValue": "0x3FBFC00080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -547,12 +547,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3", - "MSRValue": "0x3fbfc00100", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", + "MSRValue": "0x3FBFC00100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -560,12 +560,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3", - "MSRValue": "0x3fbfc00200", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", + "MSRValue": "0x3FBFC00200", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -573,12 +573,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3", - "MSRValue": "0x3fbfc00091", + "BriefDescription": "Counts all demand & prefetch data reads miss in the L3", + "MSRValue": "0x3FBFC00091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -586,12 +586,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "MSRValue": "0x0600400091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -599,12 +599,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram", - "MSRValue": "0x063f800091", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram", + "MSRValue": "0x063F800091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -612,12 +612,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache", - "MSRValue": "0x103fc00091", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache", + "MSRValue": "0x103FC00091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -625,12 +625,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache", - "MSRValue": "0x083fc00091", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache", + "MSRValue": "0x083FC00091", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -638,12 +638,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3", - "MSRValue": "0x3fbfc00122", + "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3", + "MSRValue": "0x3FBFC00122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -651,12 +651,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "MSRValue": "0x0600400122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -664,12 +664,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3", - "MSRValue": "0x3fbfc00244", + "BriefDescription": "Counts all demand & prefetch code reads miss in the L3", + "MSRValue": "0x3FBFC00244", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -677,12 +677,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "MSRValue": "0x0600400244", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -690,12 +690,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3", - "MSRValue": "0x3fbfc007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3", + "MSRValue": "0x3FBFC007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -703,12 +703,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram", - "MSRValue": "0x06004007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram", + "MSRValue": "0x06004007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -716,12 +716,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram", - "MSRValue": "0x063f8007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram", + "MSRValue": "0x063F8007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_DRAM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -729,12 +729,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache", - "MSRValue": "0x103fc007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache", + "MSRValue": "0x103FC007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -742,12 +742,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache", - "MSRValue": "0x083fc007f7", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache", + "MSRValue": "0x083FC007F7", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -755,12 +755,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all requests that miss in the L3", - "MSRValue": "0x3fbfc08fff", + "BriefDescription": "Counts all requests miss in the L3", + "MSRValue": "0x3FBFC08FFF", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all requests miss in the L3", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json b/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json index 8a18bfe9e3e4..26f2888341ee 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json @@ -1,6 +1,5 @@ [ { - "EventCode": "0x00", "UMask": "0x1", "BriefDescription": "Instructions retired from execution.", "Counter": "Fixed counter 0", @@ -11,7 +10,6 @@ "CounterHTOff": "Fixed counter 0" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when the thread is not in halt state.", "Counter": "Fixed counter 1", @@ -21,7 +19,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "Counter": "Fixed counter 1", @@ -31,7 +28,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x3", "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", @@ -1098,6 +1094,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "UOPS_RETIRED.ALL", + "PublicDescription": "Counts the number of micro-ops retired. Use Cmask=1 and invert to count active cycles or stalled cycles.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1142,6 +1139,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "PublicDescription": "This event counts the number of retirement slots used each cycle. There are potentially 4 slots that can be used each cycle - meaning, 4 uops or 4 instructions could retire each cycle.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1201,6 +1199,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.CONDITIONAL", + "PublicDescription": "Counts the number of conditional branch instructions retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1241,6 +1240,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PublicDescription": "Counts the number of near return instructions retired.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1261,6 +1261,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PublicDescription": "Number of near taken branches retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -1312,6 +1313,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PublicDescription": "Number of near branch instructions retired that were taken but mispredicted.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json index 999a01bc6467..5f6cb2abc384 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json @@ -1012,7 +1012,7 @@ "EventName": "OFFCORE_RESPONSE.SPLIT_LOCK_UC_LOCK.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address ", + "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address", "CounterHTOff": "0,1,2,3" }, { @@ -1036,7 +1036,7 @@ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data reads ", + "BriefDescription": "Counts all demand data reads", "CounterHTOff": "0,1,2,3" }, { @@ -1048,7 +1048,7 @@ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand rfo's ", + "BriefDescription": "Counts all demand rfo's", "CounterHTOff": "0,1,2,3" }, { @@ -1084,7 +1084,7 @@ "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch prefetch RFOs ", + "BriefDescription": "Counts all demand & prefetch prefetch RFOs", "CounterHTOff": "0,1,2,3" }, { @@ -1096,7 +1096,7 @@ "EventName": "OFFCORE_RESPONSE.ALL_READS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all data/code/rfo references (demand & prefetch) ", + "BriefDescription": "Counts all data/code/rfo references (demand & prefetch)", "CounterHTOff": "0,1,2,3" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index 7c2679514efb..bc4d5fc284a0 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -1,164 +1,340 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )", - "MetricGroup": "Frontend", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json b/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json index 0afbfd95ea30..2a0aad91d83d 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json @@ -1,6 +1,5 @@ [ { - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -9,7 +8,6 @@ "CounterHTOff": "Fixed counter 0" }, { - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -19,7 +17,6 @@ }, { "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "AnyThread": "1", @@ -29,7 +26,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 7c2679514efb..f3874b5f9995 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -1,164 +1,346 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )", - "MetricGroup": "Frontend", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "MetricExpr": "cbox_0@event\\=0x0@", + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricGroup": "", + "MetricName": "Socket_CLKS" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json b/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json index 0afbfd95ea30..2a0aad91d83d 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json @@ -1,6 +1,5 @@ [ { - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -9,7 +8,6 @@ "CounterHTOff": "Fixed counter 0" }, { - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -19,7 +17,6 @@ }, { "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "AnyThread": "1", @@ -29,7 +26,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/cache.json b/tools/perf/pmu-events/arch/x86/jaketown/cache.json index ee22e4a5e30d..52dc6ef40e63 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/cache.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/cache.json @@ -31,7 +31,7 @@ }, { "PEBS": "1", - "PublicDescription": "This event counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "EventCode": "0xD0", "Counter": "0,1,2,3", "UMask": "0x41", @@ -42,7 +42,7 @@ }, { "PEBS": "1", - "PublicDescription": "This event counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "EventCode": "0xD0", "Counter": "0,1,2,3", "UMask": "0x42", @@ -179,7 +179,7 @@ "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "This event counts L1D data line replacements. Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier. ", + "PublicDescription": "This event counts L1D data line replacements. Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.", "EventCode": "0x51", "Counter": "0,1,2,3", "UMask": "0x1", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index fd7d7c438226..98c73e430b05 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -1,140 +1,232 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )", - "MetricGroup": "Frontend", + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Average CPU Utilization", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "MetricExpr": "cbox_0@event\\=0x0@", + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricGroup": "", + "MetricName": "Socket_CLKS" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json b/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json index 34a519d9bfa0..783a5b4a67b1 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json @@ -1,7 +1,6 @@ [ { - "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. ", - "EventCode": "0x00", + "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers.", "Counter": "Fixed counter 1", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -10,8 +9,7 @@ "CounterHTOff": "Fixed counter 1" }, { - "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ", - "EventCode": "0x00", + "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", "Counter": "Fixed counter 2", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -20,8 +18,7 @@ "CounterHTOff": "Fixed counter 2" }, { - "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ", - "EventCode": "0x00", + "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", "Counter": "Fixed counter 3", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", @@ -778,7 +775,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.", + "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.", "EventCode": "0x03", "Counter": "0,1,2,3", "UMask": "0x2", @@ -1098,7 +1095,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x2", "AnyThread": "1", diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/cache.json b/tools/perf/pmu-events/arch/x86/knightslanding/cache.json index e434ec723001..e847b0fd696d 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/cache.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/cache.json @@ -32,16 +32,16 @@ "BriefDescription": "Counts the number of L2 cache misses" }, { - "PublicDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses. ", + "PublicDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses.", "EventCode": "0x86", "Counter": "0,1", "UMask": "0x4", "EventName": "FETCH_STALL.ICACHE_FILL_PENDING_CYCLES", "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of core cycles the fetch stalls because of an icache miss. This is a cummulative count of core cycles the fetch stalled for all icache misses. " + "BriefDescription": "Counts the number of core cycles the fetch stalls because of an icache miss. This is a cummulative count of core cycles the fetch stalled for all icache misses." }, { - "PublicDescription": "This event counts the number of load micro-ops retired that miss in L1 Data cache. Note that prefetch misses will not be counted. ", + "PublicDescription": "This event counts the number of load micro-ops retired that miss in L1 Data cache. Note that prefetch misses will not be counted.", "EventCode": "0x04", "Counter": "0,1", "UMask": "0x1", @@ -115,29 +115,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000070 ", + "MSRValue": "0x4000000070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400070 ", + "MSRValue": "0x1000400070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400070 ", + "MSRValue": "0x0800400070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE_E_F", @@ -148,29 +148,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080070 ", + "MSRValue": "0x1000080070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080070 ", + "MSRValue": "0x0800080070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010070 ", + "MSRValue": "0x0000010070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.ANY_RESPONSE", @@ -181,29 +181,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x40000032f7 ", + "MSRValue": "0x40000032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts any Read request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x10004032f7 ", + "MSRValue": "0x10004032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x08004032f7 ", + "MSRValue": "0x08004032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE_E_F", @@ -214,29 +214,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x10000832f7 ", + "MSRValue": "0x10000832f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x08000832f7 ", + "MSRValue": "0x08000832f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x00000132f7 ", + "MSRValue": "0x00000132f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.ANY_RESPONSE", @@ -247,29 +247,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000044 ", + "MSRValue": "0x4000000044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400044 ", + "MSRValue": "0x1000400044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400044 ", + "MSRValue": "0x0800400044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE_E_F", @@ -280,29 +280,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080044 ", + "MSRValue": "0x1000080044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080044 ", + "MSRValue": "0x0800080044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010044 ", + "MSRValue": "0x0000010044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.ANY_RESPONSE", @@ -313,29 +313,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000022 ", + "MSRValue": "0x4000000022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts Demand cacheable data write requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400022 ", + "MSRValue": "0x1000400022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400022 ", + "MSRValue": "0x0800400022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE_E_F", @@ -346,29 +346,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080022 ", + "MSRValue": "0x1000080022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080022 ", + "MSRValue": "0x0800080022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010022 ", + "MSRValue": "0x0000010022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.ANY_RESPONSE", @@ -379,29 +379,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000003091 ", + "MSRValue": "0x4000003091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000403091 ", + "MSRValue": "0x1000403091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800403091 ", + "MSRValue": "0x0800403091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE_E_F", @@ -412,29 +412,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000083091 ", + "MSRValue": "0x1000083091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800083091 ", + "MSRValue": "0x0800083091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000013091 ", + "MSRValue": "0x0000013091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.ANY_RESPONSE", @@ -445,29 +445,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000008000 ", + "MSRValue": "0x4000008000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000408000 ", + "MSRValue": "0x1000408000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800408000 ", + "MSRValue": "0x0800408000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE_E_F", @@ -478,29 +478,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000088000 ", + "MSRValue": "0x1000088000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800088000 ", + "MSRValue": "0x0800088000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000018000 ", + "MSRValue": "0x0000018000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.ANY_RESPONSE", @@ -511,7 +511,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0000014800 ", + "MSRValue": "0x0000014800", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE", @@ -522,7 +522,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0000014000 ", + "MSRValue": "0x0000014000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.ANY_RESPONSE", @@ -533,29 +533,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000002000 ", + "MSRValue": "0x4000002000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000402000 ", + "MSRValue": "0x1000402000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800402000 ", + "MSRValue": "0x0800402000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE_E_F", @@ -566,29 +566,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000082000 ", + "MSRValue": "0x1000082000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800082000 ", + "MSRValue": "0x0800082000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000012000 ", + "MSRValue": "0x0000012000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.ANY_RESPONSE", @@ -599,29 +599,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000001000 ", + "MSRValue": "0x4000001000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000401000 ", + "MSRValue": "0x1000401000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800401000 ", + "MSRValue": "0x0800401000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE_E_F", @@ -632,29 +632,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000081000 ", + "MSRValue": "0x1000081000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800081000 ", + "MSRValue": "0x0800081000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000011000 ", + "MSRValue": "0x0000011000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.ANY_RESPONSE", @@ -665,7 +665,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0000010800 ", + "MSRValue": "0x0000010800", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.ANY_RESPONSE", @@ -676,29 +676,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000400 ", + "MSRValue": "0x4000000400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400400 ", + "MSRValue": "0x1000400400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400400 ", + "MSRValue": "0x0800400400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE_E_F", @@ -709,29 +709,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080400 ", + "MSRValue": "0x1000080400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080400 ", + "MSRValue": "0x0800080400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010400 ", + "MSRValue": "0x0000010400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.ANY_RESPONSE", @@ -742,29 +742,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000200 ", + "MSRValue": "0x4000000200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400200 ", + "MSRValue": "0x1000400200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400200 ", + "MSRValue": "0x0800400200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_FAR_TILE_E_F", @@ -775,29 +775,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080200 ", + "MSRValue": "0x1000080200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080200 ", + "MSRValue": "0x0800080200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010200 ", + "MSRValue": "0x0000010200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.ANY_RESPONSE", @@ -808,18 +808,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000400100 ", + "MSRValue": "0x1000400100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400100 ", + "MSRValue": "0x0800400100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE_E_F", @@ -830,29 +830,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080100 ", + "MSRValue": "0x1000080100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080100 ", + "MSRValue": "0x0800080100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010100 ", + "MSRValue": "0x0000010100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.ANY_RESPONSE", @@ -863,29 +863,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000080 ", + "MSRValue": "0x4000000080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400080 ", + "MSRValue": "0x1000400080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400080 ", + "MSRValue": "0x0800400080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE_E_F", @@ -896,29 +896,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080080 ", + "MSRValue": "0x1000080080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080080 ", + "MSRValue": "0x0800080080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010080 ", + "MSRValue": "0x0000010080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.ANY_RESPONSE", @@ -929,29 +929,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000040 ", + "MSRValue": "0x4000000040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400040 ", + "MSRValue": "0x1000400040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400040 ", + "MSRValue": "0x0800400040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE_E_F", @@ -962,29 +962,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080040 ", + "MSRValue": "0x1000080040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080040 ", + "MSRValue": "0x0800080040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010040 ", + "MSRValue": "0x0000010040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.ANY_RESPONSE", @@ -995,18 +995,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000400020 ", + "MSRValue": "0x1000400020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400020 ", + "MSRValue": "0x0800400020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_FAR_TILE_E_F", @@ -1017,29 +1017,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080020 ", + "MSRValue": "0x1000080020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080020 ", + "MSRValue": "0x0800080020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000020020 ", + "MSRValue": "0x0000020020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE", @@ -1050,7 +1050,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0000010020 ", + "MSRValue": "0x0000010020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", @@ -1061,29 +1061,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000004 ", + "MSRValue": "0x4000000004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400004 ", + "MSRValue": "0x1000400004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400004 ", + "MSRValue": "0x0800400004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE_E_F", @@ -1094,29 +1094,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080004 ", + "MSRValue": "0x1000080004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080004 ", + "MSRValue": "0x0800080004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010004 ", + "MSRValue": "0x0000010004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", @@ -1127,29 +1127,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000002 ", + "MSRValue": "0x4000000002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400002 ", + "MSRValue": "0x1000400002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400002 ", + "MSRValue": "0x0800400002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE_E_F", @@ -1160,29 +1160,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080002 ", + "MSRValue": "0x1000080002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080002 ", + "MSRValue": "0x0800080002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010002 ", + "MSRValue": "0x0000010002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", @@ -1193,29 +1193,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x4000000001 ", + "MSRValue": "0x4000000001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING", "MSRIndex": "0x1a6", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1000400001 ", + "MSRValue": "0x1000400001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800400001 ", + "MSRValue": "0x0800400001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_FAR_TILE_E_F", @@ -1226,29 +1226,29 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1000080001 ", + "MSRValue": "0x1000080001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0800080001 ", + "MSRValue": "0x0800080001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0000010001 ", + "MSRValue": "0x0000010001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", @@ -1259,722 +1259,722 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0002000001 ", + "MSRValue": "0x0002000001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000002 ", + "MSRValue": "0x0002000002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000004 ", + "MSRValue": "0x0002000004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000020 ", + "MSRValue": "0x0002000020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000080 ", + "MSRValue": "0x0002000080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000100 ", + "MSRValue": "0x0002000100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000200 ", + "MSRValue": "0x0002000200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000400 ", + "MSRValue": "0x0002000400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002001000 ", + "MSRValue": "0x0002001000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002002000 ", + "MSRValue": "0x0002002000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002008000 ", + "MSRValue": "0x0002008000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002003091 ", + "MSRValue": "0x0002003091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000022 ", + "MSRValue": "0x0002000022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000044 ", + "MSRValue": "0x0002000044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x00020032f7 ", + "MSRValue": "0x00020032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0002000070 ", + "MSRValue": "0x0002000070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in M state ", + "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in M state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000001 ", + "MSRValue": "0x0004000001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000002 ", + "MSRValue": "0x0004000002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000004 ", + "MSRValue": "0x0004000004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000020 ", + "MSRValue": "0x0004000020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000040 ", + "MSRValue": "0x0004000040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000080 ", + "MSRValue": "0x0004000080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000100 ", + "MSRValue": "0x0004000100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000200 ", + "MSRValue": "0x0004000200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000400 ", + "MSRValue": "0x0004000400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004001000 ", + "MSRValue": "0x0004001000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004002000 ", + "MSRValue": "0x0004002000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004008000 ", + "MSRValue": "0x0004008000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004003091 ", + "MSRValue": "0x0004003091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000022 ", + "MSRValue": "0x0004000022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000044 ", + "MSRValue": "0x0004000044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x00040032f7 ", + "MSRValue": "0x00040032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0004000070 ", + "MSRValue": "0x0004000070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in E state ", + "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in E state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000001 ", + "MSRValue": "0x0008000001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000002 ", + "MSRValue": "0x0008000002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000004 ", + "MSRValue": "0x0008000004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000020 ", + "MSRValue": "0x0008000020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000080 ", + "MSRValue": "0x0008000080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000100 ", + "MSRValue": "0x0008000100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000200 ", + "MSRValue": "0x0008000200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000400 ", + "MSRValue": "0x0008000400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008001000 ", + "MSRValue": "0x0008001000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008002000 ", + "MSRValue": "0x0008002000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008008000 ", + "MSRValue": "0x0008008000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008003091 ", + "MSRValue": "0x0008003091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000022 ", + "MSRValue": "0x0008000022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0008000044 ", + "MSRValue": "0x0008000044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x00080032f7 ", + "MSRValue": "0x00080032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in S state ", + "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in S state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000001 ", + "MSRValue": "0x0010000001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000002 ", + "MSRValue": "0x0010000002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000004 ", + "MSRValue": "0x0010000004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000020 ", + "MSRValue": "0x0010000020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000040 ", + "MSRValue": "0x0010000040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000080 ", + "MSRValue": "0x0010000080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000100 ", + "MSRValue": "0x0010000100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000200 ", + "MSRValue": "0x0010000200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000400 ", + "MSRValue": "0x0010000400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010001000 ", + "MSRValue": "0x0010001000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010002000 ", + "MSRValue": "0x0010002000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010008000 ", + "MSRValue": "0x0010008000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010003091 ", + "MSRValue": "0x0010003091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000022 ", + "MSRValue": "0x0010000022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000044 ", + "MSRValue": "0x0010000044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x00100032f7 ", + "MSRValue": "0x00100032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0010000070 ", + "MSRValue": "0x0010000070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in F state ", + "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in F state", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x1800180002 ", + "MSRValue": "0x1800180002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE", @@ -1985,7 +1985,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180004 ", + "MSRValue": "0x1800180004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE", @@ -1996,7 +1996,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180020 ", + "MSRValue": "0x1800180020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE", @@ -2007,7 +2007,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180040 ", + "MSRValue": "0x1800180040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE", @@ -2018,7 +2018,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180080 ", + "MSRValue": "0x1800180080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE", @@ -2029,7 +2029,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180100 ", + "MSRValue": "0x1800180100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE", @@ -2040,7 +2040,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180200 ", + "MSRValue": "0x1800180200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE", @@ -2051,7 +2051,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180400 ", + "MSRValue": "0x1800180400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE", @@ -2062,7 +2062,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800181000 ", + "MSRValue": "0x1800181000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE", @@ -2073,7 +2073,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800182000 ", + "MSRValue": "0x1800182000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE", @@ -2084,7 +2084,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800188000 ", + "MSRValue": "0x1800188000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE", @@ -2095,7 +2095,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800183091 ", + "MSRValue": "0x1800183091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE", @@ -2106,7 +2106,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180022 ", + "MSRValue": "0x1800180022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE", @@ -2117,7 +2117,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180044 ", + "MSRValue": "0x1800180044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE", @@ -2128,7 +2128,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x18001832f7 ", + "MSRValue": "0x18001832f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE", @@ -2139,7 +2139,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800180070 ", + "MSRValue": "0x1800180070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE", @@ -2150,7 +2150,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400002 ", + "MSRValue": "0x1800400002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE", @@ -2161,7 +2161,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400004 ", + "MSRValue": "0x1800400004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE", @@ -2172,7 +2172,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400040 ", + "MSRValue": "0x1800400040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE", @@ -2183,7 +2183,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400080 ", + "MSRValue": "0x1800400080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE", @@ -2194,7 +2194,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400100 ", + "MSRValue": "0x1800400100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE", @@ -2205,7 +2205,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400400 ", + "MSRValue": "0x1800400400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE", @@ -2216,7 +2216,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800401000 ", + "MSRValue": "0x1800401000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE", @@ -2227,7 +2227,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800402000 ", + "MSRValue": "0x1800402000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE", @@ -2238,7 +2238,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800408000 ", + "MSRValue": "0x1800408000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE", @@ -2249,7 +2249,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800403091 ", + "MSRValue": "0x1800403091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE", @@ -2260,7 +2260,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400022 ", + "MSRValue": "0x1800400022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE", @@ -2271,7 +2271,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400044 ", + "MSRValue": "0x1800400044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE", @@ -2282,7 +2282,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x18004032f7 ", + "MSRValue": "0x18004032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE", @@ -2293,7 +2293,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x1800400070 ", + "MSRValue": "0x1800400070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE", diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/memory.json index 700652566200..c6bb16ba0f86 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/memory.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/memory.json @@ -9,18 +9,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400070 ", + "MSRValue": "0x0100400070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts any Prefetch requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200070 ", + "MSRValue": "0x0080200070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM_NEAR", @@ -31,18 +31,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000070 ", + "MSRValue": "0x0101000070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Prefetch requests that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts any Prefetch requests that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800070 ", + "MSRValue": "0x0080800070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.DDR_NEAR", @@ -53,18 +53,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x01004032f7 ", + "MSRValue": "0x01004032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts any Read request that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x00802032f7 ", + "MSRValue": "0x00802032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM_NEAR", @@ -75,18 +75,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x01010032f7 ", + "MSRValue": "0x01010032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any Read request that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts any Read request that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x00808032f7 ", + "MSRValue": "0x00808032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.DDR_NEAR", @@ -97,18 +97,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400044 ", + "MSRValue": "0x0100400044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200044 ", + "MSRValue": "0x0080200044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM_NEAR", @@ -119,18 +119,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000044 ", + "MSRValue": "0x0101000044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800044 ", + "MSRValue": "0x0080800044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR_NEAR", @@ -141,18 +141,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400022 ", + "MSRValue": "0x0100400022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200022 ", + "MSRValue": "0x0080200022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM_NEAR", @@ -163,18 +163,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000022 ", + "MSRValue": "0x0101000022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data write requests that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800022 ", + "MSRValue": "0x0080800022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR_NEAR", @@ -185,18 +185,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100403091 ", + "MSRValue": "0x0100403091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080203091 ", + "MSRValue": "0x0080203091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM_NEAR", @@ -207,18 +207,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101003091 ", + "MSRValue": "0x0101003091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080803091 ", + "MSRValue": "0x0080803091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR_NEAR", @@ -229,18 +229,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100408000 ", + "MSRValue": "0x0100408000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts any request that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080208000 ", + "MSRValue": "0x0080208000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM_NEAR", @@ -251,18 +251,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101008000 ", + "MSRValue": "0x0101008000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts any request that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts any request that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080808000 ", + "MSRValue": "0x0080808000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR_NEAR", @@ -273,18 +273,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100402000 ", + "MSRValue": "0x0100402000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080202000 ", + "MSRValue": "0x0080202000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.MCDRAM_NEAR", @@ -295,18 +295,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101002000 ", + "MSRValue": "0x0101002000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080802000 ", + "MSRValue": "0x0080802000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR_NEAR", @@ -317,18 +317,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100401000 ", + "MSRValue": "0x0100401000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Software Prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080201000 ", + "MSRValue": "0x0080201000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM_NEAR", @@ -339,18 +339,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101001000 ", + "MSRValue": "0x0101001000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Software Prefetches that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Software Prefetches that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080801000 ", + "MSRValue": "0x0080801000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR_NEAR", @@ -361,18 +361,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400400 ", + "MSRValue": "0x0100400400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200400 ", + "MSRValue": "0x0080200400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM_NEAR", @@ -383,18 +383,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000400 ", + "MSRValue": "0x0101000400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800400 ", + "MSRValue": "0x0080800400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR_NEAR", @@ -405,18 +405,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400200 ", + "MSRValue": "0x0100400200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200200 ", + "MSRValue": "0x0080200200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM_NEAR", @@ -427,18 +427,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000200 ", + "MSRValue": "0x0101000200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800200 ", + "MSRValue": "0x0080800200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR_NEAR", @@ -449,18 +449,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400100 ", + "MSRValue": "0x0100400100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM_FAR", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200100 ", + "MSRValue": "0x0080200100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM_NEAR", @@ -471,18 +471,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000100 ", + "MSRValue": "0x0101000100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.DDR_FAR", "MSRIndex": "0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800100 ", + "MSRValue": "0x0080800100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.DDR_NEAR", @@ -493,7 +493,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x2000020080 ", + "MSRValue": "0x2000020080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.NON_DRAM", @@ -504,18 +504,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400080 ", + "MSRValue": "0x0100400080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200080 ", + "MSRValue": "0x0080200080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM_NEAR", @@ -526,18 +526,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000080 ", + "MSRValue": "0x0101000080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800080 ", + "MSRValue": "0x0080800080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR_NEAR", @@ -548,18 +548,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400040 ", + "MSRValue": "0x0100400040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200040 ", + "MSRValue": "0x0080200040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.MCDRAM_NEAR", @@ -570,18 +570,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000040 ", + "MSRValue": "0x0101000040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800040 ", + "MSRValue": "0x0080800040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR_NEAR", @@ -592,7 +592,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x2000020020 ", + "MSRValue": "0x2000020020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.NON_DRAM", @@ -603,18 +603,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400020 ", + "MSRValue": "0x0100400020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200020 ", + "MSRValue": "0x0080200020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM_NEAR", @@ -625,18 +625,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000020 ", + "MSRValue": "0x0101000020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800020 ", + "MSRValue": "0x0080800020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR_NEAR", @@ -647,18 +647,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400004 ", + "MSRValue": "0x0100400004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200004 ", + "MSRValue": "0x0080200004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM_NEAR", @@ -669,18 +669,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000004 ", + "MSRValue": "0x0101000004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800004 ", + "MSRValue": "0x0080800004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR_NEAR", @@ -691,18 +691,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400002 ", + "MSRValue": "0x0100400002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200002 ", + "MSRValue": "0x0080200002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM_NEAR", @@ -713,18 +713,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000002 ", + "MSRValue": "0x0101000002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800002 ", + "MSRValue": "0x0080800002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR_NEAR", @@ -735,18 +735,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0100400001 ", + "MSRValue": "0x0100400001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080200001 ", + "MSRValue": "0x0080200001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM_NEAR", @@ -757,18 +757,18 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0101000001 ", + "MSRValue": "0x0101000001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR_FAR", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100007", - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from DRAM Far. ", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from DRAM Far.", "Offcore": "1" }, { "EventCode": "0xB7", - "MSRValue": "0x0080800001 ", + "MSRValue": "0x0080800001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR_NEAR", @@ -779,7 +779,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600001 ", + "MSRValue": "0x0180600001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM", @@ -790,7 +790,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600002 ", + "MSRValue": "0x0180600002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM", @@ -801,7 +801,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600004 ", + "MSRValue": "0x0180600004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM", @@ -812,7 +812,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600020 ", + "MSRValue": "0x0180600020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM", @@ -823,7 +823,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600080 ", + "MSRValue": "0x0180600080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM", @@ -834,7 +834,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600100 ", + "MSRValue": "0x0180600100", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM", @@ -845,7 +845,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600200 ", + "MSRValue": "0x0180600200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM", @@ -856,7 +856,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600400 ", + "MSRValue": "0x0180600400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM", @@ -867,7 +867,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180601000 ", + "MSRValue": "0x0180601000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM", @@ -878,7 +878,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180608000 ", + "MSRValue": "0x0180608000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM", @@ -889,7 +889,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180603091 ", + "MSRValue": "0x0180603091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM", @@ -900,7 +900,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600022 ", + "MSRValue": "0x0180600022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM", @@ -911,7 +911,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600044 ", + "MSRValue": "0x0180600044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM", @@ -922,7 +922,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x01806032f7 ", + "MSRValue": "0x01806032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM", @@ -933,7 +933,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0180600070 ", + "MSRValue": "0x0180600070", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM", @@ -944,7 +944,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800001 ", + "MSRValue": "0x0181800001", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR", @@ -955,7 +955,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800002 ", + "MSRValue": "0x0181800002", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR", @@ -966,7 +966,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800004 ", + "MSRValue": "0x0181800004", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR", @@ -977,7 +977,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800020 ", + "MSRValue": "0x0181800020", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR", @@ -988,7 +988,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800040 ", + "MSRValue": "0x0181800040", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR", @@ -999,7 +999,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800080 ", + "MSRValue": "0x0181800080", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR", @@ -1010,7 +1010,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800200 ", + "MSRValue": "0x0181800200", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR", @@ -1021,7 +1021,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800400 ", + "MSRValue": "0x0181800400", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR", @@ -1032,7 +1032,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181801000 ", + "MSRValue": "0x0181801000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR", @@ -1043,7 +1043,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181802000 ", + "MSRValue": "0x0181802000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR", @@ -1054,7 +1054,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181808000 ", + "MSRValue": "0x0181808000", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR", @@ -1065,7 +1065,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181803091 ", + "MSRValue": "0x0181803091", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR", @@ -1076,7 +1076,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800022 ", + "MSRValue": "0x0181800022", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR", @@ -1087,7 +1087,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x0181800044 ", + "MSRValue": "0x0181800044", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR", @@ -1098,7 +1098,7 @@ }, { "EventCode": "0xB7", - "MSRValue": "0x01818032f7 ", + "MSRValue": "0x01818032f7", "Counter": "0,1", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ANY_READ.DDR", diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json b/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json index bb5494cfb5ae..92e4ef2e22c6 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json @@ -144,7 +144,7 @@ "BriefDescription": "Counts the number of micro-ops retired that are from the complex flows issued by the micro-sequencer (MS)." }, { - "PublicDescription": "This event counts the number of micro-ops (uops) retired. The processor decodes complex macro instructions into a sequence of simpler uops. Most instructions are composed of one or two uops. Some instructions are decoded into longer sequences such as repeat instructions, floating point transcendental instructions, and assists. ", + "PublicDescription": "This event counts the number of micro-ops (uops) retired. The processor decodes complex macro instructions into a sequence of simpler uops. Most instructions are composed of one or two uops. Some instructions are decoded into longer sequences such as repeat instructions, floating point transcendental instructions, and assists.", "EventCode": "0xC2", "Counter": "0,1", "UMask": "0x10", @@ -218,7 +218,7 @@ "UMask": "0x20", "EventName": "NO_ALLOC_CYCLES.RAT_STALL", "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of core cycles when no micro-ops are allocated and a RATstall (caused by reservation station full) is asserted. " + "BriefDescription": "Counts the number of core cycles when no micro-ops are allocated and a RATstall (caused by reservation station full) is asserted." }, { "PublicDescription": "This event counts the number of core cycles when no uops are allocated, the instruction queue is empty and the alloc pipe is stalled waiting for instructions to be fetched.", @@ -251,7 +251,7 @@ "UMask": "0x1f", "EventName": "RS_FULL_STALL.ALL", "SampleAfterValue": "200003", - "BriefDescription": "Counts the total number of core cycles the Alloc pipeline is stalled when any one of the reservation stations is full. " + "BriefDescription": "Counts the total number of core cycles the Alloc pipeline is stalled when any one of the reservation stations is full." }, { "EventCode": "0xC0", @@ -268,11 +268,10 @@ "UMask": "0x1", "EventName": "CYCLES_DIV_BUSY.ALL", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles the number of core cycles when divider is busy. Does not imply a stall waiting for the divider. " + "BriefDescription": "Cycles the number of core cycles when divider is busy. Does not imply a stall waiting for the divider." }, { "PublicDescription": "This event counts the number of instructions that retire. For instructions that consist of multiple micro-ops, this event counts exactly once, as the last micro-op of the instruction retires. The event continues counting while instructions retire, including during interrupt service routines caused by hardware interrupts, faults or traps.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -296,8 +295,7 @@ "BriefDescription": "Counts the number of unhalted reference clock cycles" }, { - "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter\r\n", - "EventCode": "0x00", + "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter", "Counter": "Fixed counter 2", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -305,7 +303,6 @@ "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles" }, { - "EventCode": "0x00", "Counter": "Fixed counter 3", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", @@ -343,7 +340,7 @@ "UMask": "0x1", "EventName": "RECYCLEQ.LD_BLOCK_ST_FORWARD", "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of occurences a retired load gets blocked because its address partially overlaps with a store ", + "BriefDescription": "Counts the number of occurences a retired load gets blocked because its address partially overlaps with a store", "Data_LA": "1" }, { diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json index f31594507f8c..9e493977771f 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json @@ -36,7 +36,7 @@ "EdgeDetect": "1" }, { - "PublicDescription": "This event counts every cycle when an I-side (walks due to an instruction fetch) page walk is in progress. ", + "PublicDescription": "This event counts every cycle when an I-side (walks due to an instruction fetch) page walk is in progress.", "EventCode": "0x05", "Counter": "0,1", "UMask": "0x2", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index e05c2c8458fc..d6984a3017e0 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -33,3 +33,4 @@ GenuineIntel-6-25,v2,westmereep-sp,core GenuineIntel-6-2F,v2,westmereex,core GenuineIntel-6-55-[01234],v1,skylakex,core GenuineIntel-6-55-[56789ABCDEF],v1,cascadelakex,core +AuthenticAMD-23-[[:xdigit:]]+,v1,amdfam17h,core diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/cache.json b/tools/perf/pmu-events/arch/x86/sandybridge/cache.json index 16b04a20bc12..bb79e89c2049 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/cache.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/cache.json @@ -1,207 +1,200 @@ [ { - "PEBS": "1", - "EventCode": "0xD0", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x11", - "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load uops that miss the STLB.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "Demand Data Read requests that hit L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xD0", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x12", - "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", - "SampleAfterValue": "100003", - "BriefDescription": "Retired store uops that miss the STLB.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x3", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "SampleAfterValue": "200003", + "BriefDescription": "Demand Data Read requests.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xD0", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x21", - "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", - "SampleAfterValue": "100007", - "BriefDescription": "Retired load uops with locked access.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x4", + "EventName": "L2_RQSTS.RFO_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests that hit L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", - "EventCode": "0xD0", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x41", - "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load uops that split across a cacheline boundary.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x8", + "EventName": "L2_RQSTS.RFO_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests that miss L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", - "EventCode": "0xD0", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x42", - "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", - "SampleAfterValue": "100003", - "BriefDescription": "Retired store uops that split across a cacheline boundary.", - "CounterHTOff": "0,1,2,3" + "UMask": "0xc", + "EventName": "L2_RQSTS.ALL_RFO", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests to L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts the number of load uops retired", - "EventCode": "0xD0", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x81", - "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", - "SampleAfterValue": "2000003", - "BriefDescription": "All retired load uops.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x10", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts the number of store uops retired.", - "EventCode": "0xD0", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x82", - "EventName": "MEM_UOPS_RETIRED.ALL_STORES", - "SampleAfterValue": "2000003", - "BriefDescription": "All retired store uops.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x20", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "L2 cache misses when fetching instructions.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xD1", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", - "SampleAfterValue": "2000003", - "BriefDescription": "Retired load uops with L1 cache hits as data sources.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x30", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "SampleAfterValue": "200003", + "BriefDescription": "L2 code requests.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xD1", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load uops with L2 cache hits as data sources.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x40", + "EventName": "L2_RQSTS.PF_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts retired load uops that hit in the last-level (L3) cache without snoops required.", - "EventCode": "0xD1", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT", - "SampleAfterValue": "50021", - "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x80", + "EventName": "L2_RQSTS.PF_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xD1", + "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.", - "CounterHTOff": "0,1,2,3" + "UMask": "0xc0", + "EventName": "L2_RQSTS.ALL_PF", + "SampleAfterValue": "200003", + "BriefDescription": "Requests from L2 hardware prefetchers.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xD2", + "EventCode": "0x27", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS", - "SampleAfterValue": "20011", - "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache.", - "CounterHTOff": "0,1,2,3" - }, - { - "PEBS": "1", - "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a non-modified state.", - "EventCode": "0xD2", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT", - "SampleAfterValue": "20011", - "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache.", - "CounterHTOff": "0,1,2,3" + "EventName": "L2_STORE_LOCK_RQSTS.MISS", + "SampleAfterValue": "200003", + "BriefDescription": "RFOs that miss cache lines.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a modified state, so the line had to be invalidated in that L2 cache and transferred to the requesting L2.", - "EventCode": "0xD2", + "EventCode": "0x27", "Counter": "0,1,2,3", "UMask": "0x4", - "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM", - "SampleAfterValue": "20011", - "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC.", - "CounterHTOff": "0,1,2,3" + "EventName": "L2_STORE_LOCK_RQSTS.HIT_E", + "SampleAfterValue": "200003", + "BriefDescription": "RFOs that hit cache lines in E state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xD2", + "EventCode": "0x27", "Counter": "0,1,2,3", "UMask": "0x8", - "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required.", - "CounterHTOff": "0,1,2,3" + "EventName": "L2_STORE_LOCK_RQSTS.HIT_M", + "SampleAfterValue": "200003", + "BriefDescription": "RFOs that hit cache lines in M state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts retired demand loads that missed the last-level (L3) cache. This means that the load is usually satisfied from memory in a client system or possibly from the remote socket in a server. Demand loads are non speculative load uops.", - "EventCode": "0xD4", + "EventCode": "0x27", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS", - "SampleAfterValue": "100007", - "BriefDescription": "Retired load uops with unknown information as data source in cache serviced the load.", - "CounterHTOff": "0,1,2,3" + "UMask": "0xf", + "EventName": "L2_STORE_LOCK_RQSTS.ALL", + "SampleAfterValue": "200003", + "BriefDescription": "RFOs that access cache lines in any state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts L1D data line replacements. Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier. ", - "EventCode": "0x51", + "EventCode": "0x28", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "L1D.REPLACEMENT", - "SampleAfterValue": "2000003", - "BriefDescription": "L1D data line replacements.", + "EventName": "L2_L1D_WB_RQSTS.MISS", + "SampleAfterValue": "200003", + "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x51", + "EventCode": "0x28", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "L1D.ALLOCATED_IN_M", - "SampleAfterValue": "2000003", - "BriefDescription": "Allocated L1D data cache lines in M state.", + "EventName": "L2_L1D_WB_RQSTS.HIT_S", + "SampleAfterValue": "200003", + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in S state.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x51", + "EventCode": "0x28", "Counter": "0,1,2,3", "UMask": "0x4", - "EventName": "L1D.EVICTION", - "SampleAfterValue": "2000003", - "BriefDescription": "L1D data cache lines in M state evicted due to replacement.", + "EventName": "L2_L1D_WB_RQSTS.HIT_E", + "SampleAfterValue": "200003", + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x51", + "EventCode": "0x28", "Counter": "0,1,2,3", "UMask": "0x8", - "EventName": "L1D.ALL_M_REPLACEMENT", - "SampleAfterValue": "2000003", - "BriefDescription": "Cache lines in M state evicted out of L1D due to Snoop HitM or dirty line replacement.", + "EventName": "L2_L1D_WB_RQSTS.HIT_M", + "SampleAfterValue": "200003", + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x28", + "Counter": "0,1,2,3", + "UMask": "0xf", + "EventName": "L2_L1D_WB_RQSTS.ALL", + "SampleAfterValue": "200003", + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x2E", + "Counter": "0,1,2,3", + "UMask": "0x41", + "EventName": "LONGEST_LAT_CACHE.MISS", + "SampleAfterValue": "100003", + "BriefDescription": "Core-originated cacheable demand requests missed LLC.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x2E", + "Counter": "0,1,2,3", + "UMask": "0x4f", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "SampleAfterValue": "100003", + "BriefDescription": "Core-originated cacheable demand requests that refer to LLC.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -224,12 +217,61 @@ "CounterHTOff": "2" }, { - "EventCode": "0x63", + "EventCode": "0x48", + "Counter": "2", + "UMask": "0x1", + "AnyThread": "1", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", + "CounterMask": "1", + "CounterHTOff": "2" + }, + { + "EventCode": "0x48", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", + "EventName": "L1D_PEND_MISS.FB_FULL", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when L1D is locked.", + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "This event counts L1D data line replacements. Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.", + "EventCode": "0x51", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "L1D.REPLACEMENT", + "SampleAfterValue": "2000003", + "BriefDescription": "L1D data line replacements.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x51", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "L1D.ALLOCATED_IN_M", + "SampleAfterValue": "2000003", + "BriefDescription": "Allocated L1D data cache lines in M state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x51", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "L1D.EVICTION", + "SampleAfterValue": "2000003", + "BriefDescription": "L1D data cache lines in M state evicted due to replacement.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x51", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "L1D.ALL_M_REPLACEMENT", + "SampleAfterValue": "2000003", + "BriefDescription": "Cache lines in M state evicted out of L1D due to Snoop HitM or dirty line replacement.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -254,6 +296,16 @@ { "EventCode": "0x60", "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_C6", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "CounterMask": "6", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "Counter": "0,1,2,3", "UMask": "0x4", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", "SampleAfterValue": "2000003", @@ -263,6 +315,16 @@ { "EventCode": "0x60", "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "SampleAfterValue": "2000003", + "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "Counter": "0,1,2,3", "UMask": "0x8", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", "SampleAfterValue": "2000003", @@ -280,6 +342,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x63", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when L1D is locked.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xB0", "Counter": "0,1,2,3", "UMask": "0x1", @@ -325,148 +396,182 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x24", + "EventCode": "0xBF", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "Demand Data Read requests that hit L2 cache.", + "UMask": "0x5", + "EventName": "L1D_BLOCKS.BANK_CONFLICT_CYCLES", + "SampleAfterValue": "100003", + "BriefDescription": "Cycles when dispatched loads are cancelled due to L1D bank conflicts with other load ports.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x24", + "PEBS": "1", + "EventCode": "0xD0", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "L2_RQSTS.RFO_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "RFO requests that hit L2 cache.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x11", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x24", + "PEBS": "1", + "EventCode": "0xD0", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "L2_RQSTS.RFO_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "RFO requests that miss L2 cache.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x12", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "SampleAfterValue": "100003", + "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x24", + "PEBS": "1", + "EventCode": "0xD0", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "L2_RQSTS.CODE_RD_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "L2 cache hits when fetching instructions, code reads.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x21", + "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", + "SampleAfterValue": "100007", + "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x24", + "PEBS": "1", + "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K). (Precise Event - PEBS)", + "EventCode": "0xD0", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "L2_RQSTS.CODE_RD_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "L2 cache misses when fetching instructions.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x41", + "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops that split across a cacheline boundary. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x24", + "PEBS": "1", + "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K). (Precise Event - PEBS)", + "EventCode": "0xD0", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "L2_RQSTS.PF_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x42", + "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", + "SampleAfterValue": "100003", + "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x24", + "PEBS": "1", + "PublicDescription": "This event counts the number of load uops retired (Precise Event)", + "EventCode": "0xD0", "Counter": "0,1,2,3", - "UMask": "0x80", - "EventName": "L2_RQSTS.PF_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x81", + "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", + "SampleAfterValue": "2000003", + "BriefDescription": "All retired load uops. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x27", + "PEBS": "1", + "PublicDescription": "This event counts the number of store uops retired. (Precise Event - PEBS)", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x82", + "EventName": "MEM_UOPS_RETIRED.ALL_STORES", + "SampleAfterValue": "2000003", + "BriefDescription": "All retired store uops. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "EventCode": "0xD1", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "L2_STORE_LOCK_RQSTS.MISS", - "SampleAfterValue": "200003", - "BriefDescription": "RFOs that miss cache lines.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", + "SampleAfterValue": "2000003", + "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x27", + "PEBS": "1", + "EventCode": "0xD1", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "L2_STORE_LOCK_RQSTS.HIT_E", - "SampleAfterValue": "200003", - "BriefDescription": "RFOs that hit cache lines in E state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x27", + "PEBS": "1", + "PublicDescription": "This event counts retired load uops that hit in the last-level (L3) cache without snoops required. (Precise Event - PEBS)", + "EventCode": "0xD1", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "L2_STORE_LOCK_RQSTS.HIT_M", - "SampleAfterValue": "200003", - "BriefDescription": "RFOs that hit cache lines in M state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4", + "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT", + "SampleAfterValue": "50021", + "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x27", + "PEBS": "1", + "EventCode": "0xD1", "Counter": "0,1,2,3", - "UMask": "0xf", - "EventName": "L2_STORE_LOCK_RQSTS.ALL", - "SampleAfterValue": "200003", - "BriefDescription": "RFOs that access cache lines in any state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x40", + "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x28", + "PEBS": "1", + "EventCode": "0xD2", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "L2_L1D_WB_RQSTS.MISS", - "SampleAfterValue": "200003", - "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x28", + "PEBS": "1", + "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a non-modified state. (Precise Event - PEBS)", + "EventCode": "0xD2", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "L2_L1D_WB_RQSTS.HIT_S", - "SampleAfterValue": "200003", - "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in S state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x28", + "PEBS": "1", + "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a modified state, so the line had to be invalidated in that L2 cache and transferred to the requesting L2. (Precise Event - PEBS)", + "EventCode": "0xD2", "Counter": "0,1,2,3", "UMask": "0x4", - "EventName": "L2_L1D_WB_RQSTS.HIT_E", - "SampleAfterValue": "200003", - "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x28", + "PEBS": "1", + "EventCode": "0xD2", "Counter": "0,1,2,3", "UMask": "0x8", - "EventName": "L2_L1D_WB_RQSTS.HIT_M", - "SampleAfterValue": "200003", - "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x28", + "PEBS": "1", + "PublicDescription": "This event counts retired demand loads that missed the last-level (L3) cache. This means that the load is usually satisfied from memory in a client system or possibly from the remote socket in a server. Demand loads are non speculative load uops. (Precise Event - PEBS)", + "EventCode": "0xD4", "Counter": "0,1,2,3", - "UMask": "0xf", - "EventName": "L2_L1D_WB_RQSTS.ALL", - "SampleAfterValue": "200003", - "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2", + "EventName": "MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS", + "SampleAfterValue": "100007", + "BriefDescription": "Retired load uops with unknown information as data source in cache serviced the load. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xF0", @@ -623,24 +728,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x2E", - "Counter": "0,1,2,3", - "UMask": "0x41", - "EventName": "LONGEST_LAT_CACHE.MISS", - "SampleAfterValue": "100003", - "BriefDescription": "Core-originated cacheable demand requests missed LLC.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x2E", - "Counter": "0,1,2,3", - "UMask": "0x4f", - "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "SampleAfterValue": "100003", - "BriefDescription": "Core-originated cacheable demand requests that refer to LLC.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0xF4", "Counter": "0,1,2,3", "UMask": "0x10", @@ -650,93 +737,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0x3", - "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "SampleAfterValue": "200003", - "BriefDescription": "Demand Data Read requests.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0xc", - "EventName": "L2_RQSTS.ALL_RFO", - "SampleAfterValue": "200003", - "BriefDescription": "RFO requests to L2 cache.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0x30", - "EventName": "L2_RQSTS.ALL_CODE_RD", - "SampleAfterValue": "200003", - "BriefDescription": "L2 code requests.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0xc0", - "EventName": "L2_RQSTS.ALL_PF", - "SampleAfterValue": "200003", - "BriefDescription": "Requests from L2 hardware prefetchers.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xBF", - "Counter": "0,1,2,3", - "UMask": "0x5", - "EventName": "L1D_BLOCKS.BANK_CONFLICT_CYCLES", - "SampleAfterValue": "100003", - "BriefDescription": "Cycles when dispatched loads are cancelled due to L1D bank conflicts with other load ports.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x60", - "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "SampleAfterValue": "2000003", - "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x60", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_C6", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", - "CounterMask": "6", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x48", - "Counter": "2", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", - "CounterMask": "1", - "CounterHTOff": "2" - }, - { - "EventCode": "0x48", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "L1D_PEND_MISS.FB_FULL", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0xB7, 0xBB", "MSRValue": "0x10003c0244", "Counter": "0,1,2,3", @@ -1825,7 +1825,7 @@ "EventName": "OFFCORE_RESPONSE.DATA_IN.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = DATA_INTO_CORE and RESPONSE = ANY_RESPONSE", + "BriefDescription": "REQUEST = DATA_INTO_CORE and RESPONSE = ANY_RESPONSE", "CounterHTOff": "0,1,2,3" }, { @@ -1837,7 +1837,7 @@ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT_M.HITM", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = DEMAND_RFO and RESPONSE = LLC_HIT_M and SNOOP = HITM", + "BriefDescription": "REQUEST = DEMAND_RFO and RESPONSE = LLC_HIT_M and SNOOP = HITM", "CounterHTOff": "0,1,2,3" }, { @@ -1849,7 +1849,7 @@ "EventName": "OFFCORE_RESPONSE.PF_IFETCH.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = PF_RFO and RESPONSE = ANY_RESPONSE", + "BriefDescription": "REQUEST = PF_RFO and RESPONSE = ANY_RESPONSE", "CounterHTOff": "0,1,2,3" }, { @@ -1861,7 +1861,7 @@ "EventName": "OFFCORE_RESPONSE.PF_L_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = PF_LLC_DATA_RD and RESPONSE = ANY_RESPONSE", + "BriefDescription": "REQUEST = PF_LLC_DATA_RD and RESPONSE = ANY_RESPONSE", "CounterHTOff": "0,1,2,3" }, { @@ -1873,7 +1873,7 @@ "EventName": "OFFCORE_RESPONSE.PF_L_IFETCH.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = PF_LLC_IFETCH and RESPONSE = ANY_RESPONSE", + "BriefDescription": "REQUEST = PF_LLC_IFETCH and RESPONSE = ANY_RESPONSE", "CounterHTOff": "0,1,2,3" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json b/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json index 982eda48785e..ce26537c7d47 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json @@ -1,68 +1,5 @@ [ { - "EventCode": "0xC1", - "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "OTHER_ASSISTS.AVX_STORE", - "SampleAfterValue": "100003", - "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xC1", - "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "OTHER_ASSISTS.AVX_TO_SSE", - "SampleAfterValue": "100003", - "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xC1", - "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "OTHER_ASSISTS.SSE_TO_AVX", - "SampleAfterValue": "100003", - "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xCA", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "FP_ASSIST.X87_OUTPUT", - "SampleAfterValue": "100003", - "BriefDescription": "Number of X87 assists due to output value.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xCA", - "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "FP_ASSIST.X87_INPUT", - "SampleAfterValue": "100003", - "BriefDescription": "Number of X87 assists due to input value.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xCA", - "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "FP_ASSIST.SIMD_OUTPUT", - "SampleAfterValue": "100003", - "BriefDescription": "Number of SIMD FP assists due to Output values.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xCA", - "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "FP_ASSIST.SIMD_INPUT", - "SampleAfterValue": "100003", - "BriefDescription": "Number of SIMD FP assists due to input values.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0x10", "Counter": "0,1,2,3", "UMask": "0x1", @@ -126,6 +63,69 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0xC1", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "OTHER_ASSISTS.AVX_STORE", + "SampleAfterValue": "100003", + "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC1", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "OTHER_ASSISTS.AVX_TO_SSE", + "SampleAfterValue": "100003", + "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC1", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "OTHER_ASSISTS.SSE_TO_AVX", + "SampleAfterValue": "100003", + "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCA", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "FP_ASSIST.X87_OUTPUT", + "SampleAfterValue": "100003", + "BriefDescription": "Number of X87 assists due to output value.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCA", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "FP_ASSIST.X87_INPUT", + "SampleAfterValue": "100003", + "BriefDescription": "Number of X87 assists due to input value.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCA", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "FP_ASSIST.SIMD_OUTPUT", + "SampleAfterValue": "100003", + "BriefDescription": "Number of SIMD FP assists due to Output values.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCA", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "FP_ASSIST.SIMD_INPUT", + "SampleAfterValue": "100003", + "BriefDescription": "Number of SIMD FP assists due to input values.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x1e", diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json index 1b7b1dd36c68..e58ed14a204c 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json @@ -1,24 +1,5 @@ [ { - "EventCode": "0x80", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "ICACHE.HIT", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes unchacheable accesses.", - "EventCode": "0x80", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "ICACHE.MISSES", - "SampleAfterValue": "200003", - "BriefDescription": "Instruction cache, streaming buffer and victim cache misses.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0x79", "Counter": "0,1,2,3", "UMask": "0x2", @@ -39,159 +20,201 @@ { "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "IDQ.DSB_UOPS", + "UMask": "0x4", + "EventName": "IDQ.MITE_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "IDQ.MS_DSB_UOPS", + "UMask": "0x8", + "EventName": "IDQ.DSB_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "IDQ.MS_MITE_UOPS", + "UMask": "0x8", + "EventName": "IDQ.DSB_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x30", - "EventName": "IDQ.MS_UOPS", + "UMask": "0x10", + "EventName": "IDQ.MS_DSB_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance. See the Intel? 64 and IA-32 Architectures Optimization Reference Manual for more information.", "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x30", - "EventName": "IDQ.MS_CYCLES", + "UMask": "0x10", + "EventName": "IDQ.MS_DSB_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of uops not delivered to the back-end per cycle, per thread, when the back-end was not stalled. In the ideal case 4 uops can be delivered each cycle. The event counts the undelivered uops - so if 3 were delivered in one cycle, the counter would be incremented by 1 for that cycle (4 - 3). If the back-end is stalled, the count for this event is not incremented even when uops were not delivered, because the back-end would not have been able to accept them. This event is used in determining the front-end bound category of the top-down pipeline slots characterization.", - "EventCode": "0x9C", + "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "UMask": "0x10", + "EdgeDetect": "1", + "EventName": "IDQ.MS_DSB_OCCUR", "SampleAfterValue": "2000003", - "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled .", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x9C", + "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "UMask": "0x18", + "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops.", "CounterMask": "4", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x9C", + "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "UMask": "0x18", + "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", - "CounterMask": "3", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xAB", + "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "DSB2MITE_SWITCHES.COUNT", + "UMask": "0x20", + "EventName": "IDQ.MS_MITE_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches.", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the cycles attributed to a switch from the Decoded Stream Buffer (DSB), which holds decoded instructions, to the legacy decode pipeline. It excludes cycles when the back-end cannot accept new micro-ops. The penalty for these switches is potentially several cycles of instruction starvation, where no micro-ops are delivered to the back-end.", - "EventCode": "0xAB", + "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "UMask": "0x24", + "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", + "BriefDescription": "Cycles MITE is delivering 4 Uops.", + "CounterMask": "4", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xAC", + "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "DSB_FILL.OTHER_CANCEL", + "UMask": "0x24", + "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cases of cancelling valid DSB fill not because of exceeding way limit.", + "BriefDescription": "Cycles MITE is delivering any Uop.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xAC", + "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "DSB_FILL.EXCEED_DSB_LINES", + "UMask": "0x30", + "EventName": "IDQ.MS_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines.", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance. See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual for more information.", "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "IDQ.MITE_CYCLES", + "UMask": "0x30", + "EventName": "IDQ.MS_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "IDQ.DSB_CYCLES", + "UMask": "0x30", + "EdgeDetect": "1", + "EventName": "IDQ.MS_SWITCHES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.", + "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "IDQ.MS_DSB_CYCLES", + "UMask": "0x3c", + "EventName": "IDQ.MITE_ALL_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", - "CounterMask": "1", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x79", + "EventCode": "0x80", "Counter": "0,1,2,3", - "UMask": "0x10", - "EdgeDetect": "1", - "EventName": "IDQ.MS_DSB_OCCUR", + "UMask": "0x1", + "EventName": "ICACHE.HIT", "SampleAfterValue": "2000003", - "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.", - "CounterMask": "1", + "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes unchacheable accesses.", + "EventCode": "0x80", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "ICACHE.MISSES", + "SampleAfterValue": "200003", + "BriefDescription": "Instruction cache, streaming buffer and victim cache misses.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "This event counts the number of uops not delivered to the back-end per cycle, per thread, when the back-end was not stalled. In the ideal case 4 uops can be delivered each cycle. The event counts the undelivered uops - so if 3 were delivered in one cycle, the counter would be incremented by 1 for that cycle (4 - 3). If the back-end is stalled, the count for this event is not incremented even when uops were not delivered, because the back-end would not have been able to accept them. This event is used in determining the front-end bound category of the top-down pipeline slots characterization.", + "EventCode": "0x9C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled .", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0x9C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "CounterMask": "4", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0x9C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "CounterMask": "3", + "CounterHTOff": "0,1,2,3" + }, + { "EventCode": "0x9C", "Counter": "0,1,2,3", "UMask": "0x1", @@ -223,83 +246,60 @@ "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x79", - "Counter": "0,1,2,3", - "UMask": "0x18", - "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops.", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x79", + "EventCode": "0x9C", + "Invert": "1", "Counter": "0,1,2,3", - "UMask": "0x18", - "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop.", + "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x79", + "EventCode": "0xAB", "Counter": "0,1,2,3", - "UMask": "0x24", - "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", + "UMask": "0x1", + "EventName": "DSB2MITE_SWITCHES.COUNT", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles MITE is delivering 4 Uops.", - "CounterMask": "4", + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x79", + "PublicDescription": "This event counts the cycles attributed to a switch from the Decoded Stream Buffer (DSB), which holds decoded instructions, to the legacy decode pipeline. It excludes cycles when the back-end cannot accept new micro-ops. The penalty for these switches is potentially several cycles of instruction starvation, where no micro-ops are delivered to the back-end.", + "EventCode": "0xAB", "Counter": "0,1,2,3", - "UMask": "0x24", - "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "UMask": "0x2", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles MITE is delivering any Uop.", - "CounterMask": "1", + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xAC", "Counter": "0,1,2,3", - "UMask": "0xa", - "EventName": "DSB_FILL.ALL_CANCEL", + "UMask": "0x2", + "EventName": "DSB_FILL.OTHER_CANCEL", "SampleAfterValue": "2000003", - "BriefDescription": "Cases of cancelling valid Decode Stream Buffer (DSB) fill not because of exceeding way limit.", + "BriefDescription": "Cases of cancelling valid DSB fill not because of exceeding way limit.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x9C", - "Invert": "1", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0x79", + "EventCode": "0xAC", "Counter": "0,1,2,3", - "UMask": "0x3c", - "EventName": "IDQ.MITE_ALL_UOPS", + "UMask": "0x8", + "EventName": "DSB_FILL.EXCEED_DSB_LINES", "SampleAfterValue": "2000003", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path.", + "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x79", + "EventCode": "0xAC", "Counter": "0,1,2,3", - "UMask": "0x30", - "EdgeDetect": "1", - "EventName": "IDQ.MS_SWITCHES", + "UMask": "0xa", + "EventName": "DSB_FILL.ALL_CANCEL", "SampleAfterValue": "2000003", - "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", - "CounterMask": "1", + "BriefDescription": "Cases of cancelling valid Decode Stream Buffer (DSB) fill not because of exceeding way limit.", "CounterHTOff": "0,1,2,3,4,5,6,7" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/memory.json b/tools/perf/pmu-events/arch/x86/sandybridge/memory.json index e6dfa89d00f3..78c1a987f9a2 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/memory.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/memory.json @@ -1,5 +1,32 @@ [ { + "EventCode": "0x05", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "MISALIGN_MEM_REF.LOADS", + "SampleAfterValue": "2000003", + "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x05", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "MISALIGN_MEM_REF.STORES", + "SampleAfterValue": "2000003", + "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xBE", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "PAGE_WALKS.LLC_MISS", + "SampleAfterValue": "100003", + "BriefDescription": "Number of any page walk that had a miss in LLC. Does not necessary cause a SUSPEND.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from memory disambiguation, external snoops, or cross SMT-HW-thread snoop (stores) hitting load buffers. Machine clears can have a significant performance impact if they are happening frequently.", "EventCode": "0xC3", "Counter": "0,1,2,3", @@ -126,33 +153,6 @@ "CounterHTOff": "3" }, { - "EventCode": "0xBE", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "PAGE_WALKS.LLC_MISS", - "SampleAfterValue": "100003", - "BriefDescription": "Number of any page walk that had a miss in LLC. Does not necessary cause a SUSPEND.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x05", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MISALIGN_MEM_REF.LOADS", - "SampleAfterValue": "2000003", - "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x05", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "MISALIGN_MEM_REF.STORES", - "SampleAfterValue": "2000003", - "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0xB7, 0xBB", "MSRValue": "0x300400244", "Counter": "0,1,2,3", @@ -367,7 +367,7 @@ "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.LLC_MISS_LOCAL.DRAM", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = ANY_REQUEST and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", + "BriefDescription": "REQUEST = ANY_REQUEST and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", "CounterHTOff": "0,1,2,3" }, { @@ -379,7 +379,7 @@ "EventName": "OFFCORE_RESPONSE.DATA_IN_SOCKET.LLC_MISS_LOCAL.ANY_LLC_HIT", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = DATA_IN_SOCKET and RESPONSE = LLC_MISS_LOCAL and SNOOP = ANY_LLC_HIT", + "BriefDescription": "REQUEST = DATA_IN_SOCKET and RESPONSE = LLC_MISS_LOCAL and SNOOP = ANY_LLC_HIT", "CounterHTOff": "0,1,2,3" }, { @@ -391,7 +391,7 @@ "EventName": "OFFCORE_RESPONSE.DEMAND_IFETCH.LLC_MISS_LOCAL.DRAM", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = DEMAND_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", + "BriefDescription": "REQUEST = DEMAND_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", "CounterHTOff": "0,1,2,3" }, { @@ -403,7 +403,7 @@ "EventName": "OFFCORE_RESPONSE.PF_DATA_RD.LLC_MISS_LOCAL.DRAM", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = PF_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", + "BriefDescription": "REQUEST = PF_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", "CounterHTOff": "0,1,2,3" }, { @@ -415,7 +415,7 @@ "EventName": "OFFCORE_RESPONSE.PF_IFETCH.LLC_MISS_LOCAL.DRAM", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = PF_RFO and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", + "BriefDescription": "REQUEST = PF_RFO and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", "CounterHTOff": "0,1,2,3" }, { @@ -427,7 +427,7 @@ "EventName": "OFFCORE_RESPONSE.PF_L_DATA_RD.LLC_MISS_LOCAL.DRAM", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = PF_LLC_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", + "BriefDescription": "REQUEST = PF_LLC_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", "CounterHTOff": "0,1,2,3" }, { @@ -439,7 +439,7 @@ "EventName": "OFFCORE_RESPONSE.PF_L_IFETCH.LLC_MISS_LOCAL.DRAM", "MSRIndex": "0x1a6,0x1a7", "SampleAfterValue": "100003", - "BriefDescription": " REQUEST = PF_LLC_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", + "BriefDescription": "REQUEST = PF_LLC_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM", "CounterHTOff": "0,1,2,3" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/other.json b/tools/perf/pmu-events/arch/x86/sandybridge/other.json index 64b195b82c50..874eb40a2e0f 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/other.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/other.json @@ -9,6 +9,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x4E", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "HW_PRE_REQ.DL1_MISS", + "SampleAfterValue": "2000003", + "BriefDescription": "Hardware Prefetch requests that miss the L1D cache. This accounts for both L1 streamer and IP-based (IPP) HW prefetchers. A request is being counted each time it access the cache & miss it, including if a block is applicable or if hit the Fill Buffer for .", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x5C", "Counter": "0,1,2,3", "UMask": "0x1", @@ -38,15 +47,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x4E", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "HW_PRE_REQ.DL1_MISS", - "SampleAfterValue": "2000003", - "BriefDescription": "Hardware Prefetch requests that miss the L1D cache. This accounts for both L1 streamer and IP-based (IPP) HW prefetchers. A request is being counted each time it access the cache & miss it, including if a block is applicable or if hit the Fill Buffer for .", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0x63", "Counter": "0,1,2,3", "UMask": "0x1", diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json b/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json index 34a519d9bfa0..b7150f65f16d 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json @@ -1,289 +1,307 @@ [ { - "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. ", - "EventCode": "0x00", - "Counter": "Fixed counter 1", + "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", + "Counter": "Fixed counter 2", + "UMask": "0x3", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "SampleAfterValue": "2000003", + "BriefDescription": "Reference cycles when the core is not in halt state.", + "CounterHTOff": "Fixed counter 2" + }, + { + "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers.", + "Counter": "Fixed counter 0", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", "SampleAfterValue": "2000003", "BriefDescription": "Instructions retired from execution.", - "CounterHTOff": "Fixed counter 1" + "CounterHTOff": "Fixed counter 0" }, { - "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ", - "EventCode": "0x00", - "Counter": "Fixed counter 2", + "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", + "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", "SampleAfterValue": "2000003", "BriefDescription": "Core cycles when the thread is not in halt state.", - "CounterHTOff": "Fixed counter 2" + "CounterHTOff": "Fixed counter 1" }, { - "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ", - "EventCode": "0x00", - "Counter": "Fixed counter 3", - "UMask": "0x3", - "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "Counter": "Fixed counter 1", + "UMask": "0x2", + "AnyThread": "1", + "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the core is not in halt state.", - "CounterHTOff": "Fixed counter 3" - }, - { - "EventCode": "0x88", - "Counter": "0,1,2,3", - "UMask": "0x41", - "EventName": "BR_INST_EXEC.NONTAKEN_CONDITIONAL", - "SampleAfterValue": "200003", - "BriefDescription": "Not taken macro-conditional branches.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x88", + "EventCode": "0x03", "Counter": "0,1,2,3", - "UMask": "0x81", - "EventName": "BR_INST_EXEC.TAKEN_CONDITIONAL", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired macro-conditional branches.", + "UMask": "0x1", + "EventName": "LD_BLOCKS.DATA_UNKNOWN", + "SampleAfterValue": "100003", + "BriefDescription": "Loads delayed due to SB blocks, preceding store operations with known addresses but unknown data.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store. See the table of not supported store forwards in the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.", + "EventCode": "0x03", "Counter": "0,1,2,3", - "UMask": "0x82", - "EventName": "BR_INST_EXEC.TAKEN_DIRECT_JUMP", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired macro-conditional branch instructions excluding calls and indirects.", + "UMask": "0x2", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "SampleAfterValue": "100003", + "BriefDescription": "Cases when loads get true Block-on-Store blocking code preventing store forwarding.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0x03", "Counter": "0,1,2,3", - "UMask": "0x84", - "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired indirect branches excluding calls and returns.", + "UMask": "0x8", + "EventName": "LD_BLOCKS.NO_SR", + "SampleAfterValue": "100003", + "BriefDescription": "This event counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0x03", "Counter": "0,1,2,3", - "UMask": "0x88", - "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_RETURN", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired indirect branches with return mnemonic.", + "UMask": "0x10", + "EventName": "LD_BLOCKS.ALL_BLOCK", + "SampleAfterValue": "100003", + "BriefDescription": "Number of cases where any load ends up with a valid block-code written to the load buffer (including blocks due to Memory Order Buffer (MOB), Data Cache Unit (DCU), TLB, but load has no DCU miss).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "PublicDescription": "Aliasing occurs when a load is issued after a store and their memory addresses are offset by 4K. This event counts the number of loads that aliased with a preceding store, resulting in an extended address check in the pipeline. The enhanced address check typically has a performance penalty of 5 cycles.", + "EventCode": "0x07", "Counter": "0,1,2,3", - "UMask": "0x90", - "EventName": "BR_INST_EXEC.TAKEN_DIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired direct near calls.", + "UMask": "0x1", + "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", + "SampleAfterValue": "100003", + "BriefDescription": "False dependencies in MOB due to partial compare.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0x07", "Counter": "0,1,2,3", - "UMask": "0xa0", - "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired indirect calls.", + "UMask": "0x8", + "EventName": "LD_BLOCKS_PARTIAL.ALL_STA_BLOCK", + "SampleAfterValue": "100003", + "BriefDescription": "This event counts the number of times that load operations are temporarily blocked because of older stores, with addresses that are not yet known. A load operation may incur more than one block of this type.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0x0D", "Counter": "0,1,2,3", - "UMask": "0xc1", - "EventName": "BR_INST_EXEC.ALL_CONDITIONAL", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired macro-conditional branches.", + "UMask": "0x3", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0x0D", "Counter": "0,1,2,3", - "UMask": "0xc2", - "EventName": "BR_INST_EXEC.ALL_DIRECT_JMP", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired macro-unconditional branches excluding calls and indirects.", + "UMask": "0x3", + "EdgeDetect": "1", + "EventName": "INT_MISC.RECOVERY_STALLS_COUNT", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of occurences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0x0D", "Counter": "0,1,2,3", - "UMask": "0xc4", - "EventName": "BR_INST_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired indirect branches excluding calls and returns.", + "UMask": "0x3", + "AnyThread": "1", + "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0x0D", "Counter": "0,1,2,3", - "UMask": "0xc8", - "EventName": "BR_INST_EXEC.ALL_INDIRECT_NEAR_RETURN", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired indirect return branches.", + "UMask": "0x40", + "EventName": "INT_MISC.RAT_STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "PublicDescription": "This event counts the number of Uops issued by the front-end of the pipeilne to the back-end.", + "EventCode": "0x0E", "Counter": "0,1,2,3", - "UMask": "0xd0", - "EventName": "BR_INST_EXEC.ALL_DIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired direct near calls.", + "UMask": "0x1", + "EventName": "UOPS_ISSUED.ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x89", + "EventCode": "0x0E", + "Invert": "1", "Counter": "0,1,2,3", - "UMask": "0x41", - "EventName": "BR_MISP_EXEC.NONTAKEN_CONDITIONAL", - "SampleAfterValue": "200003", - "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x89", + "EventCode": "0x0E", + "Invert": "1", "Counter": "0,1,2,3", - "UMask": "0x81", - "EventName": "BR_MISP_EXEC.TAKEN_CONDITIONAL", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired mispredicted macro conditional branches.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1", + "AnyThread": "1", + "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x89", + "EventCode": "0x14", "Counter": "0,1,2,3", - "UMask": "0x84", - "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired mispredicted indirect branches excluding calls and returns.", + "UMask": "0x1", + "EventName": "ARITH.FPU_DIV_ACTIVE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when divider is busy executing divide operations.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x89", + "PublicDescription": "This event counts the number of the divide operations executed.", + "EventCode": "0x14", "Counter": "0,1,2,3", - "UMask": "0x88", - "EventName": "BR_MISP_EXEC.TAKEN_RETURN_NEAR", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired mispredicted indirect branches with return mnemonic.", + "UMask": "0x1", + "EdgeDetect": "1", + "EventName": "ARITH.FPU_DIV", + "SampleAfterValue": "100003", + "BriefDescription": "Divide operations executed.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x89", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0x90", - "EventName": "BR_MISP_EXEC.TAKEN_DIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired mispredicted direct near calls.", + "UMask": "0x0", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "SampleAfterValue": "2000003", + "BriefDescription": "Thread cycles when thread is not in halt state.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x89", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0xa0", - "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired mispredicted indirect calls.", + "UMask": "0x0", + "AnyThread": "1", + "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x89", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0xc1", - "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired mispredicted macro conditional branches.", + "UMask": "0x1", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", + "SampleAfterValue": "2000003", + "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x89", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0xc4", - "EventName": "BR_MISP_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET", - "SampleAfterValue": "200003", - "BriefDescription": "Mispredicted indirect branches excluding calls and returns.", + "UMask": "0x1", + "AnyThread": "1", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x89", + "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0xd0", - "EventName": "BR_MISP_EXEC.ALL_DIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired mispredicted direct near calls.", + "UMask": "0x1", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "SampleAfterValue": "2000003", + "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0x0", - "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "UMask": "0x1", + "AnyThread": "1", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", "SampleAfterValue": "2000003", - "BriefDescription": "Thread cycles when thread is not in halt state.", + "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA8", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LSD.UOPS", + "UMask": "0x2", + "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of Uops delivered by the LSD.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "BriefDescription": "Count XClk pulses when this thread is unhalted and the other is halted.", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xA8", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LSD.CYCLES_ACTIVE", + "UMask": "0x2", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", - "CounterMask": "1", + "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x87", + "EventCode": "0x4C", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "ILD_STALL.LCP", - "SampleAfterValue": "2000003", - "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "EventName": "LOAD_HIT_PRE.SW_PF", + "SampleAfterValue": "100003", + "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x87", + "EventCode": "0x4C", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "ILD_STALL.IQ_FULL", - "SampleAfterValue": "2000003", - "BriefDescription": "Stall cycles because IQ is full.", + "UMask": "0x2", + "EventName": "LOAD_HIT_PRE.HW_PF", + "SampleAfterValue": "100003", + "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for hardware prefetch.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x0D", + "EventCode": "0x59", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "INT_MISC.RAT_STALL_CYCLES", + "UMask": "0x20", + "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread.", + "BriefDescription": "Increments the number of flags-merge uops in flight each cycle.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "This event counts the number of cycles spent executing performance-sensitive flags-merging uops. For example, shift CL (merge_arith_flags). For more details, See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual.", "EventCode": "0x59", "Counter": "0,1,2,3", "UMask": "0x20", - "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP", + "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Increments the number of flags-merge uops in flight each cycle.", + "BriefDescription": "Performance sensitive flags-merging uops added by Sandy Bridge u-arch.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of cycles with at least one slow LEA uop being allocated. A uop is generally considered as slow LEA if it has three sources (for example, two sources and immediate) regardless of whether it is a result of LEA instruction or not. Examples of the slow LEA uop are or uops with base, index, and offset source operands using base and index reqisters, where base is EBR/RBP/R13, using RIP relative or 16-bit addressing modes. See the Intel? 64 and IA-32 Architectures Optimization Reference Manual for more details about slow LEA instructions.", + "PublicDescription": "This event counts the number of cycles with at least one slow LEA uop being allocated. A uop is generally considered as slow LEA if it has three sources (for example, two sources and immediate) regardless of whether it is a result of LEA instruction or not. Examples of the slow LEA uop are or uops with base, index, and offset source operands using base and index reqisters, where base is EBR/RBP/R13, using RIP relative or 16-bit addressing modes. See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual for more details about slow LEA instructions.", "EventCode": "0x59", "Counter": "0,1,2,3", "UMask": "0x40", @@ -302,48 +320,21 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "RESOURCE_STALLS.ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Resource-related stall cycles.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA2", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "RESOURCE_STALLS.LB", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts the cycles of stall due to lack of load buffers.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA2", - "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "RESOURCE_STALLS.RS", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles stalled due to no eligible RS entry available.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA2", + "EventCode": "0x5B", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "RESOURCE_STALLS.SB", + "UMask": "0xc", + "EventName": "RESOURCE_STALLS2.ALL_FL_EMPTY", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "BriefDescription": "Cycles with either free list is empty.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0x5B", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "RESOURCE_STALLS.ROB", + "UMask": "0xf", + "EventName": "RESOURCE_STALLS2.ALL_PRF_CONTROL", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles stalled due to re-order buffer full.", + "BriefDescription": "Resource stalls2 control structures full for physical registers.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -356,702 +347,663 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of Uops issued by the front-end of the pipeilne to the back-end.", - "EventCode": "0x0E", + "EventCode": "0x5B", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_ISSUED.ANY", + "UMask": "0x4f", + "EventName": "RESOURCE_STALLS2.OOO_RSRC", "SampleAfterValue": "2000003", - "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS).", + "BriefDescription": "Resource stalls out of order resources full.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x0E", - "Invert": "1", + "EventCode": "0x5E", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "UOPS_ISSUED.STALL_CYCLES", + "EventName": "RS_EVENTS.EMPTY_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x0E", + "EventCode": "0x5E", "Invert": "1", "Counter": "0,1,2,3", "UMask": "0x1", - "AnyThread": "1", - "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES", + "EdgeDetect": "1", + "EventName": "RS_EVENTS.EMPTY_END", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.", + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", "CounterMask": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x5E", + "EventCode": "0x87", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "RS_EVENTS.EMPTY_CYCLES", + "EventName": "ILD_STALL.LCP", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xCC", + "EventCode": "0x87", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", + "UMask": "0x4", + "EventName": "ILD_STALL.IQ_FULL", "SampleAfterValue": "2000003", - "BriefDescription": "Count cases of saving new LBR.", + "BriefDescription": "Stall cycles because IQ is full.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event is incremented when self-modifying code (SMC) is detected, which causes a machine clear. Machine clears can have a significant performance impact if they are happening frequently.", - "EventCode": "0xC3", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "MACHINE_CLEARS.SMC", - "SampleAfterValue": "100003", - "BriefDescription": "Self-modifying code (SMC) detected.", + "UMask": "0x41", + "EventName": "BR_INST_EXEC.NONTAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Not taken macro-conditional branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Maskmov false fault - counts number of time ucode passes through Maskmov flow due to instruction's mask being 0 while the flow was completed without raising a fault.", - "EventCode": "0xC3", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "MACHINE_CLEARS.MASKMOV", - "SampleAfterValue": "100003", - "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0.", + "UMask": "0x81", + "EventName": "BR_INST_EXEC.TAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired macro-conditional branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC0", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x0", - "EventName": "INST_RETIRED.ANY_P", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of instructions retired. General Counter - architectural event.", + "UMask": "0x82", + "EventName": "BR_INST_EXEC.TAKEN_DIRECT_JUMP", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired macro-conditional branch instructions excluding calls and indirects.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts the number of micro-ops retired.", - "EventCode": "0xC2", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_RETIRED.ALL", - "SampleAfterValue": "2000003", - "BriefDescription": "Actually retired uops.", + "UMask": "0x84", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired indirect branches excluding calls and returns.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "PublicDescription": "This event counts the number of retirement slots used each cycle. There are potentially 4 slots that can be used each cycle - meaning, 4 micro-ops or 4 instructions could retire each cycle. This event is used in determining the 'Retiring' category of the Top-Down pipeline slots characterization.", - "EventCode": "0xC2", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_RETIRED.RETIRE_SLOTS", - "SampleAfterValue": "2000003", - "BriefDescription": "Retirement slots used.", + "UMask": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_RETURN", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired indirect branches with return mnemonic.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC2", - "Invert": "1", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_RETIRED.STALL_CYCLES", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles without actually retired uops.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x90", + "EventName": "BR_INST_EXEC.TAKEN_DIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired direct near calls.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC2", - "Invert": "1", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_RETIRED.TOTAL_CYCLES", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with less than 10 actually retired uops.", - "CounterMask": "10", - "CounterHTOff": "0,1,2,3" + "UMask": "0xa0", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired indirect calls.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC4", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "BR_INST_RETIRED.CONDITIONAL", - "SampleAfterValue": "400009", - "BriefDescription": "Conditional branch instructions retired.", + "UMask": "0xc1", + "EventName": "BR_INST_EXEC.ALL_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired macro-conditional branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC4", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "BR_INST_RETIRED.NEAR_CALL", - "SampleAfterValue": "100007", - "BriefDescription": "Direct and indirect near call instructions retired.", + "UMask": "0xc2", + "EventName": "BR_INST_EXEC.ALL_DIRECT_JMP", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired macro-unconditional branches excluding calls and indirects.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC4", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x0", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "SampleAfterValue": "400009", - "BriefDescription": "All (macro) branch instructions retired.", + "UMask": "0xc4", + "EventName": "BR_INST_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired indirect branches excluding calls and returns.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC4", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "SampleAfterValue": "100007", - "BriefDescription": "Return instructions retired.", + "UMask": "0xc8", + "EventName": "BR_INST_EXEC.ALL_INDIRECT_NEAR_RETURN", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired indirect return branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC4", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "BR_INST_RETIRED.NOT_TAKEN", - "SampleAfterValue": "400009", - "BriefDescription": "Not taken branch instructions retired.", + "UMask": "0xd0", + "EventName": "BR_INST_EXEC.ALL_DIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired direct near calls.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC4", + "EventCode": "0x88", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "SampleAfterValue": "400009", - "BriefDescription": "Taken branch instructions retired.", + "UMask": "0xff", + "EventName": "BR_INST_EXEC.ALL_BRANCHES", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC4", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "SampleAfterValue": "100007", - "BriefDescription": "Far branch instructions retired.", + "UMask": "0x41", + "EventName": "BR_MISP_EXEC.NONTAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "2", - "EventCode": "0xC4", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", - "SampleAfterValue": "400009", - "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS).", - "CounterHTOff": "0,1,2,3" + "UMask": "0x81", + "EventName": "BR_MISP_EXEC.TAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted macro conditional branches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC5", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "BR_MISP_RETIRED.CONDITIONAL", - "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted conditional branch instructions retired.", + "UMask": "0x84", + "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted indirect branches excluding calls and returns.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC5", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "BR_MISP_RETIRED.NEAR_CALL", - "SampleAfterValue": "100007", - "BriefDescription": "Direct and indirect mispredicted near call instructions retired.", + "UMask": "0x88", + "EventName": "BR_MISP_EXEC.TAKEN_RETURN_NEAR", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted indirect branches with return mnemonic.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC5", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x0", - "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "SampleAfterValue": "400009", - "BriefDescription": "All mispredicted macro branch instructions retired.", + "UMask": "0x90", + "EventName": "BR_MISP_EXEC.TAKEN_DIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted direct near calls.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC5", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "BR_MISP_RETIRED.NOT_TAKEN", - "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted not taken branch instructions retired.", + "UMask": "0xa0", + "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted indirect calls.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "1", - "EventCode": "0xC5", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "BR_MISP_RETIRED.TAKEN", - "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted taken branch instructions retired.", + "UMask": "0xc1", + "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired mispredicted macro conditional branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "2", - "PublicDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS)", - "EventCode": "0xC5", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", - "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS).", - "CounterHTOff": "0,1,2,3" + "UMask": "0xc4", + "EventName": "BR_MISP_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "BriefDescription": "Mispredicted indirect branches excluding calls and returns.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC1", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "OTHER_ASSISTS.ITLB_MISS_RETIRED", - "SampleAfterValue": "100003", - "BriefDescription": "Retired instructions experiencing ITLB misses.", + "UMask": "0xd0", + "EventName": "BR_MISP_EXEC.ALL_DIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired mispredicted direct near calls.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x14", + "EventCode": "0x89", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "ARITH.FPU_DIV_ACTIVE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when divider is busy executing divide operations.", + "UMask": "0xff", + "EventName": "BR_MISP_EXEC.ALL_BRANCHES", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired mispredicted macro conditional branches.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of the divide operations executed.", - "EventCode": "0x14", + "EventCode": "0xA1", "Counter": "0,1,2,3", "UMask": "0x1", - "EdgeDetect": "1", - "EventName": "ARITH.FPU_DIV", - "SampleAfterValue": "100003", - "BriefDescription": "Divide operations executed.", - "CounterMask": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_0", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when uops are dispatched to port 0.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", + "EventCode": "0xA1", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "UOPS_DISPATCHED.THREAD", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Uops dispatched per thread.", + "BriefDescription": "Cycles per core when uops are dispatched to port 0.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", + "EventCode": "0xA1", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "UOPS_DISPATCHED.CORE", + "EventName": "UOPS_DISPATCHED_PORT.PORT_1", "SampleAfterValue": "2000003", - "BriefDescription": "Uops dispatched from any thread.", + "BriefDescription": "Cycles per thread when uops are dispatched to port 1.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_0", + "UMask": "0x2", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are dispatched to port 0.", + "BriefDescription": "Cycles per core when uops are dispatched to port 1.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_DISPATCHED_PORT.PORT_1", + "UMask": "0xc", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are dispatched to port 1.", + "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "UOPS_DISPATCHED_PORT.PORT_4", + "UMask": "0xc", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are dispatched to port 4.", + "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 2.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x80", - "EventName": "UOPS_DISPATCHED_PORT.PORT_5", + "UMask": "0x30", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are dispatched to port 5.", + "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA3", + "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "CYCLE_ACTIVITY.CYCLES_NO_DISPATCH", + "UMask": "0x30", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Each cycle there was no dispatch for this thread, increment by 1. Note this is connect to Umask 2. No dispatch can be deduced from the UOPS_EXECUTED event.", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA3", - "Counter": "2", - "UMask": "0x2", - "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING", + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4", "SampleAfterValue": "2000003", - "BriefDescription": "Each cycle there was a miss-pending demand load this thread, increment by 1. Note this is in DCU and connected to Umask 1. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.", - "CounterMask": "2", - "CounterHTOff": "2" + "BriefDescription": "Cycles per thread when uops are dispatched to port 4.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA3", + "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING", + "UMask": "0x40", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Each cycle there was a MLC-miss pending demand load this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0.", - "CounterMask": "1", + "BriefDescription": "Cycles per core when uops are dispatched to port 4.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA3", - "Counter": "2", - "UMask": "0x6", - "EventName": "CYCLE_ACTIVITY.STALLS_L1D_PENDING", + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x80", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5", "SampleAfterValue": "2000003", - "BriefDescription": "Each cycle there was a miss-pending demand load this thread and no uops dispatched, increment by 1. Note this is in DCU and connected to Umask 1 and 2. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.", - "CounterMask": "6", - "CounterHTOff": "2" + "BriefDescription": "Cycles per thread when uops are dispatched to port 5.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA3", + "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x5", - "EventName": "CYCLE_ACTIVITY.STALLS_L2_PENDING", + "UMask": "0x80", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Each cycle there was a MLC-miss pending demand load and no uops dispatched on this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0 and 2.", - "CounterMask": "5", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "Cycles per core when uops are dispatched to port 5.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x4C", + "EventCode": "0xA2", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "LOAD_HIT_PRE.SW_PF", - "SampleAfterValue": "100003", - "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch.", + "EventName": "RESOURCE_STALLS.ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Resource-related stall cycles.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x4C", + "EventCode": "0xA2", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "LOAD_HIT_PRE.HW_PF", - "SampleAfterValue": "100003", - "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for hardware prefetch.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x03", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LD_BLOCKS.DATA_UNKNOWN", - "SampleAfterValue": "100003", - "BriefDescription": "Loads delayed due to SB blocks, preceding store operations with known addresses but unknown data.", + "EventName": "RESOURCE_STALLS.LB", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts the cycles of stall due to lack of load buffers.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.", - "EventCode": "0x03", + "EventCode": "0xA2", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "LD_BLOCKS.STORE_FORWARD", - "SampleAfterValue": "100003", - "BriefDescription": "Cases when loads get true Block-on-Store blocking code preventing store forwarding.", + "UMask": "0x4", + "EventName": "RESOURCE_STALLS.RS", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles stalled due to no eligible RS entry available.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x03", + "EventCode": "0xA2", "Counter": "0,1,2,3", "UMask": "0x8", - "EventName": "LD_BLOCKS.NO_SR", - "SampleAfterValue": "100003", - "BriefDescription": "This event counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "EventName": "RESOURCE_STALLS.SB", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x03", + "EventCode": "0xA2", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "LD_BLOCKS.ALL_BLOCK", - "SampleAfterValue": "100003", - "BriefDescription": "Number of cases where any load ends up with a valid block-code written to the load buffer (including blocks due to Memory Order Buffer (MOB), Data Cache Unit (DCU), TLB, but load has no DCU miss).", + "UMask": "0xa", + "EventName": "RESOURCE_STALLS.LB_SB", + "SampleAfterValue": "2000003", + "BriefDescription": "Resource stalls due to load or store buffers all being in use.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Aliasing occurs when a load is issued after a store and their memory addresses are offset by 4K. This event counts the number of loads that aliased with a preceding store, resulting in an extended address check in the pipeline. The enhanced address check typically has a performance penalty of 5 cycles.", - "EventCode": "0x07", + "EventCode": "0xA2", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", - "SampleAfterValue": "100003", - "BriefDescription": "False dependencies in MOB due to partial compare.", + "UMask": "0xe", + "EventName": "RESOURCE_STALLS.MEM_RS", + "SampleAfterValue": "2000003", + "BriefDescription": "Resource stalls due to memory buffers or Reservation Station (RS) being fully utilized.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x07", + "EventCode": "0xA2", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "LD_BLOCKS_PARTIAL.ALL_STA_BLOCK", - "SampleAfterValue": "100003", - "BriefDescription": "This event counts the number of times that load operations are temporarily blocked because of older stores, with addresses that are not yet known. A load operation may incur more than one block of this type.", + "UMask": "0x10", + "EventName": "RESOURCE_STALLS.ROB", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles stalled due to re-order buffer full.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB6", + "EventCode": "0xA2", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "AGU_BYPASS_CANCEL.COUNT", - "SampleAfterValue": "100003", - "BriefDescription": "This event counts executed load operations with all the following traits: 1. addressing of the format [base + offset], 2. the offset is between 1 and 2047, 3. the address specified in the base register is in one page and the address [base+offset] is in an.", + "UMask": "0xf0", + "EventName": "RESOURCE_STALLS.OOO_RSRC", + "SampleAfterValue": "2000003", + "BriefDescription": "Resource stalls due to Rob being full, FCSW, MXCSR and OTHER.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x3C", + "EventCode": "0xA3", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING", "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).", + "BriefDescription": "Each cycle there was a MLC-miss pending demand load this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x3C", - "Counter": "0,1,2,3", + "EventCode": "0xA3", + "Counter": "2", "UMask": "0x2", - "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING", "SampleAfterValue": "2000003", - "BriefDescription": "Count XClk pulses when this thread is unhalted and the other is halted.", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "Each cycle there was a miss-pending demand load this thread, increment by 1. Note this is in DCU and connected to Umask 1. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.", + "CounterMask": "2", + "CounterHTOff": "2" }, { - "EventCode": "0xA1", + "EventCode": "0xA3", "Counter": "0,1,2,3", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE", + "UMask": "0x4", + "EventName": "CYCLE_ACTIVITY.CYCLES_NO_DISPATCH", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are dispatched to port 0.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "BriefDescription": "Each cycle there was no dispatch for this thread, increment by 1. Note this is connect to Umask 2. No dispatch can be deduced from the UOPS_EXECUTED event.", + "CounterMask": "4", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xA1", + "EventCode": "0xA3", "Counter": "0,1,2,3", - "UMask": "0x2", - "AnyThread": "1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE", + "UMask": "0x5", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_PENDING", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are dispatched to port 1.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "BriefDescription": "Each cycle there was a MLC-miss pending demand load and no uops dispatched on this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0 and 2.", + "CounterMask": "5", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x40", - "AnyThread": "1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE", + "EventCode": "0xA3", + "Counter": "2", + "UMask": "0x6", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_PENDING", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are dispatched to port 4.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "BriefDescription": "Each cycle there was a miss-pending demand load this thread and no uops dispatched, increment by 1. Note this is in DCU and connected to Umask 1 and 2. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.", + "CounterMask": "6", + "CounterHTOff": "2" }, { - "EventCode": "0xA1", + "EventCode": "0xA8", "Counter": "0,1,2,3", - "UMask": "0x80", - "AnyThread": "1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE", + "UMask": "0x1", + "EventName": "LSD.UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are dispatched to port 5.", + "BriefDescription": "Number of Uops delivered by the LSD.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA1", + "EventCode": "0xA8", "Counter": "0,1,2,3", - "UMask": "0xc", - "EventName": "UOPS_DISPATCHED_PORT.PORT_2", + "UMask": "0x1", + "EventName": "LSD.CYCLES_ACTIVE", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2.", + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA1", + "EventCode": "0xA8", "Counter": "0,1,2,3", - "UMask": "0x30", - "EventName": "UOPS_DISPATCHED_PORT.PORT_3", + "UMask": "0x1", + "EventName": "LSD.CYCLES_4_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3.", + "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", + "CounterMask": "4", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA1", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0xc", - "AnyThread": "1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE", + "UMask": "0x1", + "EventName": "UOPS_DISPATCHED.THREAD", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 2.", + "BriefDescription": "Uops dispatched per thread.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA1", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0x30", - "AnyThread": "1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE", + "UMask": "0x2", + "EventName": "UOPS_DISPATCHED.CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3.", + "BriefDescription": "Uops dispatched from any thread.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "2", - "EventCode": "0xC0", - "Counter": "1", - "UMask": "0x1", - "EventName": "INST_RETIRED.PREC_DIST", - "SampleAfterValue": "2000003", - "BriefDescription": "Instructions retired. (Precise Event - PEBS).", - "TakenAlone": "1", - "CounterHTOff": "1" - }, - { - "EventCode": "0x5B", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0xf", - "EventName": "RESOURCE_STALLS2.ALL_PRF_CONTROL", + "UMask": "0x2", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", "SampleAfterValue": "2000003", - "BriefDescription": "Resource stalls2 control structures full for physical registers.", + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x5B", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0xc", - "EventName": "RESOURCE_STALLS2.ALL_FL_EMPTY", + "UMask": "0x2", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with either free list is empty.", + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "CounterMask": "2", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0xe", - "EventName": "RESOURCE_STALLS.MEM_RS", + "UMask": "0x2", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", "SampleAfterValue": "2000003", - "BriefDescription": "Resource stalls due to memory buffers or Reservation Station (RS) being fully utilized.", + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "CounterMask": "3", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0xf0", - "EventName": "RESOURCE_STALLS.OOO_RSRC", + "UMask": "0x2", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", "SampleAfterValue": "2000003", - "BriefDescription": "Resource stalls due to Rob being full, FCSW, MXCSR and OTHER.", + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "CounterMask": "4", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x5B", + "EventCode": "0xB1", + "Invert": "1", "Counter": "0,1,2,3", - "UMask": "0x4f", - "EventName": "RESOURCE_STALLS2.OOO_RSRC", + "UMask": "0x2", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", "SampleAfterValue": "2000003", - "BriefDescription": "Resource stalls out of order resources full.", + "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0xB6", "Counter": "0,1,2,3", - "UMask": "0xa", - "EventName": "RESOURCE_STALLS.LB_SB", - "SampleAfterValue": "2000003", - "BriefDescription": "Resource stalls due to load or store buffers all being in use.", + "UMask": "0x1", + "EventName": "AGU_BYPASS_CANCEL.COUNT", + "SampleAfterValue": "100003", + "BriefDescription": "This event counts executed load operations with all the following traits: 1. addressing of the format [base + offset], 2. the offset is between 1 and 2047, 3. the address specified in the base register is in one page and the address [base+offset] is in an.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x0D", + "EventCode": "0xC0", "Counter": "0,1,2,3", - "UMask": "0x3", - "EventName": "INT_MISC.RECOVERY_CYCLES", + "UMask": "0x0", + "EventName": "INST_RETIRED.ANY_P", "SampleAfterValue": "2000003", - "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).", - "CounterMask": "1", + "BriefDescription": "Number of instructions retired. General Counter - architectural event.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts the number of cycles spent executing performance-sensitive flags-merging uops. For example, shift CL (merge_arith_flags). For more details, See the Intel? 64 and IA-32 Architectures Optimization Reference Manual.", - "EventCode": "0x59", - "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP_CYCLES", + "PEBS": "2", + "EventCode": "0xC0", + "Counter": "1", + "UMask": "0x1", + "EventName": "INST_RETIRED.PREC_DIST", "SampleAfterValue": "2000003", - "BriefDescription": "Performance sensitive flags-merging uops added by Sandy Bridge u-arch.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "BriefDescription": "Instructions retired. (Precise Event - PEBS).", + "TakenAlone": "1", + "CounterHTOff": "1" }, { - "EventCode": "0x0D", + "EventCode": "0xC1", "Counter": "0,1,2,3", - "UMask": "0x3", - "EdgeDetect": "1", - "EventName": "INT_MISC.RECOVERY_STALLS_COUNT", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of occurences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).", - "CounterMask": "1", + "UMask": "0x2", + "EventName": "OTHER_ASSISTS.ITLB_MISS_RETIRED", + "SampleAfterValue": "100003", + "BriefDescription": "Retired instructions experiencing ITLB misses.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xE6", + "PEBS": "1", + "PublicDescription": "This event counts the number of micro-ops retired. (Precise Event)", + "EventCode": "0xC2", "Counter": "0,1,2,3", - "UMask": "0x1f", - "EventName": "BACLEARS.ANY", - "SampleAfterValue": "100003", - "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "UMask": "0x1", + "EventName": "UOPS_RETIRED.ALL", + "SampleAfterValue": "2000003", + "BriefDescription": "Actually retired uops. (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x88", + "EventCode": "0xC2", + "Invert": "1", "Counter": "0,1,2,3", - "UMask": "0xff", - "EventName": "BR_INST_EXEC.ALL_BRANCHES", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired branches.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1", + "EventName": "UOPS_RETIRED.STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles without actually retired uops.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0x89", + "EventCode": "0xC2", + "Invert": "1", "Counter": "0,1,2,3", - "UMask": "0xff", - "EventName": "BR_MISP_EXEC.ALL_BRANCHES", - "SampleAfterValue": "200003", - "BriefDescription": "Speculative and retired mispredicted macro conditional branches.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with less than 10 actually retired uops.", + "CounterMask": "10", + "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xC2", @@ -1065,13 +1017,14 @@ "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xA8", + "PEBS": "1", + "PublicDescription": "This event counts the number of retirement slots used each cycle. There are potentially 4 slots that can be used each cycle - meaning, 4 micro-ops or 4 instructions could retire each cycle. This event is used in determining the 'Retiring' category of the Top-Down pipeline slots characterization. (Precise Event - PEBS)", + "EventCode": "0xC2", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LSD.CYCLES_4_UOPS", + "UMask": "0x2", + "EventName": "UOPS_RETIRED.RETIRE_SLOTS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", - "CounterMask": "4", + "BriefDescription": "Retirement slots used. (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -1086,135 +1039,188 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x5E", - "Invert": "1", + "PublicDescription": "This event is incremented when self-modifying code (SMC) is detected, which causes a machine clear. Machine clears can have a significant performance impact if they are happening frequently.", + "EventCode": "0xC3", "Counter": "0,1,2,3", - "UMask": "0x1", - "EdgeDetect": "1", - "EventName": "RS_EVENTS.EMPTY_END", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", - "CounterMask": "1", + "UMask": "0x4", + "EventName": "MACHINE_CLEARS.SMC", + "SampleAfterValue": "100003", + "BriefDescription": "Self-modifying code (SMC) detected.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x00", - "Counter": "Fixed counter 2", - "UMask": "0x2", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "CounterHTOff": "Fixed counter 2" + "PublicDescription": "Maskmov false fault - counts number of time ucode passes through Maskmov flow due to instruction's mask being 0 while the flow was completed without raising a fault.", + "EventCode": "0xC3", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "MACHINE_CLEARS.MASKMOV", + "SampleAfterValue": "100003", + "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x3C", + "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x0", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "SampleAfterValue": "400009", + "BriefDescription": "All (macro) branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x3C", + "PEBS": "1", + "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x1", - "AnyThread": "1", - "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", + "EventName": "BR_INST_RETIRED.CONDITIONAL", + "SampleAfterValue": "400009", + "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x0D", + "PEBS": "1", + "EventCode": "0xC4", "Counter": "0,1,2,3", - "UMask": "0x3", - "AnyThread": "1", - "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", - "CounterMask": "1", + "UMask": "0x2", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "SampleAfterValue": "100007", + "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", + "PEBS": "1", + "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", - "CounterMask": "1", + "EventName": "BR_INST_RETIRED.NEAR_CALL_R3", + "SampleAfterValue": "100007", + "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", + "PEBS": "2", + "EventCode": "0xC4", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", - "CounterMask": "2", + "UMask": "0x4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "SampleAfterValue": "400009", + "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "EventCode": "0xC4", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "SampleAfterValue": "100007", + "BriefDescription": "Return instructions retired. (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", + "EventCode": "0xC4", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", - "CounterMask": "3", + "UMask": "0x10", + "EventName": "BR_INST_RETIRED.NOT_TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Not taken branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", + "PEBS": "1", + "EventCode": "0xC4", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", - "CounterMask": "4", + "UMask": "0x20", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", - "Invert": "1", + "EventCode": "0xC4", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", + "UMask": "0x40", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "SampleAfterValue": "100007", + "BriefDescription": "Far branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", - "EventCode": "0x3C", + "EventCode": "0xC5", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK", - "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).", + "UMask": "0x0", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "SampleAfterValue": "400009", + "BriefDescription": "All mispredicted macro branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x3C", + "PEBS": "1", + "EventCode": "0xC5", "Counter": "0,1,2,3", "UMask": "0x1", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", + "EventName": "BR_MISP_RETIRED.CONDITIONAL", + "SampleAfterValue": "400009", + "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x3C", + "PEBS": "1", + "EventCode": "0xC5", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "EventName": "BR_MISP_RETIRED.NEAR_CALL", + "SampleAfterValue": "100007", + "BriefDescription": "Direct and indirect mispredicted near call instructions retired. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PEBS": "2", + "PublicDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS)", + "EventCode": "0xC5", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", + "SampleAfterValue": "400009", + "BriefDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "EventCode": "0xC5", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "BR_MISP_RETIRED.NOT_TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Mispredicted not taken branch instructions retired.(Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PEBS": "1", + "EventCode": "0xC5", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "BR_MISP_RETIRED.TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Mispredicted taken branch instructions retired. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCC", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", "SampleAfterValue": "2000003", - "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", + "BriefDescription": "Count cases of saving new LBR.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xE6", + "Counter": "0,1,2,3", + "UMask": "0x1f", + "EventName": "BACLEARS.ANY", + "SampleAfterValue": "100003", + "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", "CounterHTOff": "0,1,2,3,4,5,6,7" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index fd7d7c438226..cfeba5067bab 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -1,140 +1,226 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )", - "MetricGroup": "Frontend", + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Average CPU Utilization", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json b/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json index a654ab771fce..b8eccce5d75d 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json @@ -1,131 +1,131 @@ [ { - "EventCode": "0xAE", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "ITLB.ITLB_FLUSH", - "SampleAfterValue": "100007", - "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x4F", - "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "EPT.WALK_CYCLES", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycle count for an Extended Page table walk. The Extended Page Directory cache is used by Virtual Machine operating systems while the guest operating systems use the standard TLB caches.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x85", + "EventCode": "0x08", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", "SampleAfterValue": "100003", - "BriefDescription": "Misses at all ITLB levels that cause page walks.", + "BriefDescription": "Load misses in all DTLB levels that cause page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x85", + "EventCode": "0x08", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "ITLB_MISSES.WALK_COMPLETED", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", "SampleAfterValue": "100003", - "BriefDescription": "Misses in all ITLB levels that cause completed page walks.", + "BriefDescription": "Load misses at all DTLB levels that cause completed page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event count cycles when Page Miss Handler (PMH) is servicing page walks caused by ITLB misses.", - "EventCode": "0x85", + "PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB load misses.", + "EventCode": "0x08", "Counter": "0,1,2,3", "UMask": "0x4", - "EventName": "ITLB_MISSES.WALK_DURATION", + "EventName": "DTLB_LOAD_MISSES.WALK_DURATION", "SampleAfterValue": "2000003", "BriefDescription": "Cycles when PMH is busy with page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x85", + "PublicDescription": "This event counts load operations that miss the first DTLB level but hit the second and do not cause any page walks. The penalty in this case is approximately 7 cycles.", + "EventCode": "0x08", "Counter": "0,1,2,3", "UMask": "0x10", - "EventName": "ITLB_MISSES.STLB_HIT", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", "SampleAfterValue": "100003", - "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.", + "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x08", + "EventCode": "0x49", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", "SampleAfterValue": "100003", - "BriefDescription": "Load misses in all DTLB levels that cause page walks.", + "BriefDescription": "Store misses in all DTLB levels that cause page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x08", + "EventCode": "0x49", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", "SampleAfterValue": "100003", - "BriefDescription": "Load misses at all DTLB levels that cause completed page walks.", + "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB load misses.", - "EventCode": "0x08", + "EventCode": "0x49", "Counter": "0,1,2,3", "UMask": "0x4", - "EventName": "DTLB_LOAD_MISSES.WALK_DURATION", + "EventName": "DTLB_STORE_MISSES.WALK_DURATION", "SampleAfterValue": "2000003", "BriefDescription": "Cycles when PMH is busy with page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts load operations that miss the first DTLB level but hit the second and do not cause any page walks. The penalty in this case is approximately 7 cycles.", - "EventCode": "0x08", + "EventCode": "0x49", "Counter": "0,1,2,3", "UMask": "0x10", - "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", "SampleAfterValue": "100003", - "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.", + "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x49", + "EventCode": "0x4F", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "EPT.WALK_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycle count for an Extended Page table walk. The Extended Page Directory cache is used by Virtual Machine operating systems while the guest operating systems use the standard TLB caches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", + "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", "SampleAfterValue": "100003", - "BriefDescription": "Store misses in all DTLB levels that cause page walks.", + "BriefDescription": "Misses at all ITLB levels that cause page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x49", + "EventCode": "0x85", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "EventName": "ITLB_MISSES.WALK_COMPLETED", "SampleAfterValue": "100003", - "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.", + "BriefDescription": "Misses in all ITLB levels that cause completed page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x49", + "PublicDescription": "This event count cycles when Page Miss Handler (PMH) is servicing page walks caused by ITLB misses.", + "EventCode": "0x85", "Counter": "0,1,2,3", "UMask": "0x4", - "EventName": "DTLB_STORE_MISSES.WALK_DURATION", + "EventName": "ITLB_MISSES.WALK_DURATION", "SampleAfterValue": "2000003", "BriefDescription": "Cycles when PMH is busy with page walks.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x49", + "EventCode": "0x85", "Counter": "0,1,2,3", "UMask": "0x10", - "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "EventName": "ITLB_MISSES.STLB_HIT", "SampleAfterValue": "100003", - "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.", + "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xAE", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "ITLB.ITLB_FLUSH", + "SampleAfterValue": "100007", + "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { diff --git a/tools/perf/pmu-events/arch/x86/silvermont/cache.json b/tools/perf/pmu-events/arch/x86/silvermont/cache.json index 82be7d1b8b81..805ef1436539 100644 --- a/tools/perf/pmu-events/arch/x86/silvermont/cache.json +++ b/tools/perf/pmu-events/arch/x86/silvermont/cache.json @@ -36,7 +36,7 @@ "BriefDescription": "L2 cache request misses" }, { - "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ICache miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ICache miss. Note: this event is not the same as the total number of cycles spent retrieving instruction cache lines from the memory hierarchy.\r\nCounts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes. This will include cycles due to an ITLB miss, ICache miss and other events. \r\n", + "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ICache miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ICache miss. Note: this event is not the same as the total number of cycles spent retrieving instruction cache lines from the memory hierarchy.\r\nCounts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes. This will include cycles due to an ITLB miss, ICache miss and other events.", "EventCode": "0x86", "Counter": "0,1", "UMask": "0x4", diff --git a/tools/perf/pmu-events/arch/x86/silvermont/other.json b/tools/perf/pmu-events/arch/x86/silvermont/other.json new file mode 100644 index 000000000000..47814046fa9d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/silvermont/other.json @@ -0,0 +1,20 @@ +[ + { + "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ITLB miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ITLB miss. Note: this event is not the same as page walk cycles to retrieve an instruction translation.", + "EventCode": "0x86", + "Counter": "0,1", + "UMask": "0x2", + "EventName": "FETCH_STALL.ITLB_FILL_PENDING_CYCLES", + "SampleAfterValue": "200003", + "BriefDescription": "Cycles code-fetch stalled due to an outstanding ITLB miss." + }, + { + "PublicDescription": "Counts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes. This will include cycles due to an ITLB miss, ICache miss and other events.", + "EventCode": "0x86", + "Counter": "0,1", + "UMask": "0x3f", + "EventName": "FETCH_STALL.ALL", + "SampleAfterValue": "200003", + "BriefDescription": "Cycles code-fetch stalled due to any reason." + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json b/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json index 7468af99190a..1ed62ad4cf77 100644 --- a/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json @@ -210,7 +210,7 @@ "UMask": "0x4", "EventName": "NO_ALLOC_CYCLES.MISPREDICTS", "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of cycles when no uops are allocated and the alloc pipe is stalled waiting for a mispredicted jump to retire. After the misprediction is detected, the front end will start immediately but the allocate pipe stalls until the mispredicted " + "BriefDescription": "Counts the number of cycles when no uops are allocated and the alloc pipe is stalled waiting for a mispredicted jump to retire. After the misprediction is detected, the front end will start immediately but the allocate pipe stalls until the mispredicted" }, { "EventCode": "0xCA", @@ -275,7 +275,6 @@ }, { "PublicDescription": "This event counts the number of instructions that retire. For instructions that consist of multiple micro-ops, this event counts exactly once, as the last micro-op of the instruction retires. The event continues counting while instructions retire, including during interrupt service routines caused by hardware interrupts, faults or traps. Background: Modern microprocessors employ extensive pipelining and speculative techniques. Since sometimes an instruction is started but never completed, the notion of \"retirement\" is introduced. A retired instruction is one that commits its states. Or stated differently, an instruction might be abandoned at some point. No instruction is truly finished until it retires. This counter measures the number of completed instructions. The fixed event is INST_RETIRED.ANY and the programmable event is INST_RETIRED.ANY_P.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -284,7 +283,6 @@ }, { "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. In systems with a constant core frequency, this event can give you a measurement of the elapsed time while the core was not in halt state by dividing the event count by the core frequency. This event is architecturally defined and is a designated fixed counter. CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.CORE_P use the core frequency which may change from time to time. CPU_CLK_UNHALTE.REF_TSC and CPU_CLK_UNHALTED.REF are not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. The fixed events are CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.REF_TSC and the programmable events are CPU_CLK_UNHALTED.CORE_P and CPU_CLK_UNHALTED.REF.", - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.CORE", @@ -293,7 +291,6 @@ }, { "PublicDescription": "Counts the number of reference cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. Divide this event count by core frequency to determine the elapsed time while the core was not in halt state. Divide this event count by core frequency to determine the elapsed time while the core was not in halt state. This event is architecturally defined and is a designated fixed counter. CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.CORE_P use the core frequency which may change from time to time. CPU_CLK_UNHALTE.REF_TSC and CPU_CLK_UNHALTED.REF are not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. The fixed events are CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.REF_TSC and the programmable events are CPU_CLK_UNHALTED.CORE_P and CPU_CLK_UNHALTED.REF.", - "EventCode": "0x00", "Counter": "Fixed counter 3", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", diff --git a/tools/perf/pmu-events/arch/x86/skylake/cache.json b/tools/perf/pmu-events/arch/x86/skylake/cache.json index 54bfe9e4045c..720458139049 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/cache.json +++ b/tools/perf/pmu-events/arch/x86/skylake/cache.json @@ -60,10 +60,10 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts the number of demand Data Read requests that hit L2 cache. Only non rejected loads are counted.", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x41", + "UMask": "0xc1", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", "SampleAfterValue": "200003", "BriefDescription": "Demand Data Read requests that hit L2 cache", @@ -73,7 +73,7 @@ "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x42", + "UMask": "0xc2", "EventName": "L2_RQSTS.RFO_HIT", "SampleAfterValue": "200003", "BriefDescription": "RFO requests that hit L2 cache", @@ -83,7 +83,7 @@ "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x44", + "UMask": "0xc4", "EventName": "L2_RQSTS.CODE_RD_HIT", "SampleAfterValue": "200003", "BriefDescription": "L2 cache hits when fetching instructions, code reads.", @@ -482,7 +482,7 @@ }, { "PEBS": "1", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.\r\n", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", "EventCode": "0xD1", "Counter": "0,1,2,3", "UMask": "0x1", @@ -554,7 +554,7 @@ }, { "PEBS": "1", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. \r\n", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", "EventCode": "0xD1", "Counter": "0,1,2,3", "UMask": "0x40", @@ -661,13 +661,13 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.", + "PublicDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", "EventCode": "0xF2", "Counter": "0,1,2,3", "UMask": "0x4", "EventName": "L2_LINES_OUT.USELESS_PREF", "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", + "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -690,249 +690,2238 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC01C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10001C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x04001C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x02001C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x01001C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00801C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00401C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fc0400001 ", + "MSRValue": "0x0200028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests have any response type.", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0000018000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests have any response type.", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC01C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10001C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x04001C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x02001C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x01001C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00801C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00401C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0000010004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC01C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10001C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x04001C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x02001C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x01001C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00801C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00401C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs) have any response type.", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0000010002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs) have any response type.", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & ANY_SNOOP", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000400001 ", + "MSRValue": "0x1000400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400400001 ", + "MSRValue": "0x0400400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200400001 ", + "MSRValue": "0x0200400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_MISS", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100400001 ", + "MSRValue": "0x0100400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080400001 ", + "MSRValue": "0x0080400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040400001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_NONE", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fc01c0001 ", + "MSRValue": "0x3FC01C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_HIT & ANY_SNOOP", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10001c0001 ", + "MSRValue": "0x10001C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04001c0001 ", + "MSRValue": "0x04001C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops sent to sibling cores return clean response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02001c0001 ", + "MSRValue": "0x02001C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops sent to sibling cores return clean response.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01001c0001 ", + "MSRValue": "0x01001C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00801c0001 ", + "MSRValue": "0x00801C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00401C0001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_NONE", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fc0020001 ", + "MSRValue": "0x0080100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1000040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0400040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0200040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0100040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0080040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC0020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020001 ", + "MSRValue": "0x1000020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020001 ", + "MSRValue": "0x0400020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020001 ", + "MSRValue": "0x0200020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020001 ", + "MSRValue": "0x0100020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020001 ", + "MSRValue": "0x0080020001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0040020001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads have any response type.", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010001 ", + "MSRValue": "0x0000010001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that have any response type.", + "BriefDescription": "Counts demand data reads have any response type.", "Offcore": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/skylake/frontend.json b/tools/perf/pmu-events/arch/x86/skylake/frontend.json index 578dff5bd823..7fa95a35e3ca 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/skylake/frontend.json @@ -177,7 +177,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", + "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", "EventCode": "0x9C", "Counter": "0,1,2,3", "UMask": "0x1", @@ -242,7 +242,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", + "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.", "EventCode": "0xAB", "Counter": "0,1,2,3", "UMask": "0x2", @@ -253,7 +253,7 @@ }, { "PEBS": "1", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. \r\n", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", "EventCode": "0xC6", "MSRValue": "0x11", "Counter": "0,1,2,3", @@ -360,7 +360,7 @@ }, { "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. \r\n", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "EventCode": "0xC6", "MSRValue": "0x400806", "Counter": "0,1,2,3", @@ -374,7 +374,7 @@ }, { "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.\r\n", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", "EventCode": "0xC6", "MSRValue": "0x401006", "Counter": "0,1,2,3", @@ -388,7 +388,7 @@ }, { "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.\r\n", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "EventCode": "0xC6", "MSRValue": "0x402006", "Counter": "0,1,2,3", @@ -454,7 +454,7 @@ }, { "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.\r\n", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "EventCode": "0xC6", "MSRValue": "0x100206", "Counter": "0,1,2,3", diff --git a/tools/perf/pmu-events/arch/x86/skylake/memory.json b/tools/perf/pmu-events/arch/x86/skylake/memory.json index 3bd8b712c889..f197b4c7695b 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/memory.json +++ b/tools/perf/pmu-events/arch/x86/skylake/memory.json @@ -215,7 +215,7 @@ "UMask": "0x4", "EventName": "HLE_RETIRED.ABORTED", "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one). ", + "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -237,6 +237,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", "EventCode": "0xC8", "Counter": "0,1,2,3", "UMask": "0x20", @@ -292,7 +293,7 @@ "UMask": "0x4", "EventName": "RTM_RETIRED.ABORTED", "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one). ", + "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -346,7 +347,7 @@ }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x4", "Counter": "0,1,2,3", @@ -354,13 +355,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "SampleAfterValue": "100003", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x8", "Counter": "0,1,2,3", @@ -368,13 +369,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "SampleAfterValue": "50021", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x10", "Counter": "0,1,2,3", @@ -382,13 +383,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "SampleAfterValue": "20011", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x20", "Counter": "0,1,2,3", @@ -396,13 +397,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "SampleAfterValue": "100007", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x40", "Counter": "0,1,2,3", @@ -410,13 +411,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "SampleAfterValue": "2003", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x80", "Counter": "0,1,2,3", @@ -424,13 +425,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "SampleAfterValue": "1009", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x100", "Counter": "0,1,2,3", @@ -438,13 +439,13 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "SampleAfterValue": "503", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { "PEBS": "2", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "EventCode": "0xCD", "MSRValue": "0x200", "Counter": "0,1,2,3", @@ -452,163 +453,1151 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "SampleAfterValue": "101", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", "TakenAlone": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts any other requests", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3ffc000001 ", + "MSRValue": "0x3FFC408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x203C408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x103C408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x043C408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x023C408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x013C408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00BC408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x007C408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC4008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2004008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1004008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0404008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0204008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0104008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0084008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0044008000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000408000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x20001C8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000108000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000088000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000048000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts any other requests", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000028000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts any other requests", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FFC400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x203C400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x103C400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x043C400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x023C400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x013C400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00BC400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x007C400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC4000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2004000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1004000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0404000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0204000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0104000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0084000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0044000004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x20001C0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000100004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000080004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000040004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000020004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FFC400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x203C400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x103C400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x043C400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x023C400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x013C400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00BC400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x007C400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC4000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2004000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1004000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0404000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0204000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0104000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0084000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0044000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000400002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x20001C0002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000100002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000080002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000040002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts all demand data writes (RFOs)", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000020002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data writes (RFOs)", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FFC400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x203C400001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & ANY_SNOOP", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x103c000001 ", + "MSRValue": "0x103C400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043c000001 ", + "MSRValue": "0x043C400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023c000001 ", + "MSRValue": "0x023C400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_MISS", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013c000001 ", + "MSRValue": "0x013C400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00bc000001 ", + "MSRValue": "0x00BC400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NONE", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fc4000001 ", + "MSRValue": "0x007C400001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FC4000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2004000001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000001 ", + "MSRValue": "0x1004000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000001 ", + "MSRValue": "0x0404000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000001 ", + "MSRValue": "0x0204000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000001 ", + "MSRValue": "0x0104000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000001 ", + "MSRValue": "0x0084000001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x0044000001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000400001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x20001C0001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000100001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000080001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000040001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads", + "Offcore": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "Counts demand data reads", + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2000020001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "Counts demand data reads", "Offcore": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json index bc6d2afbcd8a..4a891fbbc4bb 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json @@ -1,7 +1,6 @@ [ { "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "EventName": "INST_RETIRED.ANY", @@ -11,7 +10,6 @@ }, { "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -20,7 +18,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "AnyThread": "1", @@ -31,7 +28,6 @@ }, { "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", @@ -121,7 +117,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.", + "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.", "EventCode": "0x0E", "Counter": "0,1,2,3", "UMask": "0x2", @@ -248,6 +244,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.", + "EventCode": "0x59", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", "EventCode": "0x5E", "Counter": "0,1,2,3", @@ -361,8 +367,8 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts resource-related stall cycles. Reasons for stalls can be as follows:a. *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots).b. *any* u-arch structure got empty (like INT/SIMD FreeLists).c. FPU control word (FPCW), MXCSR.and others. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", - "EventCode": "0xA2", + "PublicDescription": "Counts resource-related stall cycles.", + "EventCode": "0xa2", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "RESOURCE_STALLS.ANY", @@ -735,7 +741,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.", + "PublicDescription": "This event counts cycles without actually retired uops.", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", @@ -759,6 +765,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Number of machine clears (nukes) of any type.", "EventCode": "0xC3", "Counter": "0,1,2,3", "UMask": "0x1", @@ -839,14 +846,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x10", "Errata": "SKL091", "EventName": "BR_INST_RETIRED.NOT_TAKEN", "SampleAfterValue": "400009", - "BriefDescription": "Not taken branch instructions retired.", + "BriefDescription": "Counts all not taken macro branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -924,7 +932,7 @@ "UMask": "0x20", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", "SampleAfterValue": "400009", - "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken. ", + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -938,6 +946,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0xCC", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "ROB_MISC_EVENTS.PAUSE_INST", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", "EventCode": "0xE6", "Counter": "0,1,2,3", diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index 71e9737f4614..2c95417a4dae 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -1,164 +1,364 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )", - "MetricGroup": "Frontend", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "Branch_Misprediction_Cost" }, { + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts_SMT", + "MetricName": "Branch_Misprediction_Cost_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" + }, + { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Access_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "MetricExpr": "arb@event\\=0x80\\,umask\\=0x2@ / arb@event\\=0x80\\,umask\\=0x2\\,thresh\\=1@", + "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_Parallel_Reads" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json index 5c9940866acd..24df183693fa 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/cache.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json @@ -61,17 +61,17 @@ }, { "EventCode": "0x24", - "UMask": "0x41", + "UMask": "0xc1", "BriefDescription": "Demand Data Read requests that hit L2 cache", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "Counts the number of demand Data Read requests that hit L2 cache. Only non rejected loads are counted.", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", "SampleAfterValue": "200003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x24", - "UMask": "0x42", + "UMask": "0xc2", "BriefDescription": "RFO requests that hit L2 cache", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.RFO_HIT", @@ -81,7 +81,7 @@ }, { "EventCode": "0x24", - "UMask": "0x44", + "UMask": "0xc4", "BriefDescription": "L2 cache hits when fetching instructions, code reads.", "Counter": "0,1,2,3", "EventName": "L2_RQSTS.CODE_RD_HIT", @@ -165,6 +165,7 @@ "BriefDescription": "Core-originated cacheable demand requests missed L3", "Counter": "0,1,2,3", "EventName": "LONGEST_LAT_CACHE.MISS", + "Errata": "SKL057", "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" @@ -175,28 +176,29 @@ "BriefDescription": "Core-originated cacheable demand requests that refer to L3", "Counter": "0,1,2,3", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all accesses to the L3.", + "Errata": "SKL057", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all accesses to the L3.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x48", "UMask": "0x1", - "BriefDescription": "L1D miss outstandings duration in cycles", + "BriefDescription": "Cycles with L1D load Misses outstanding.", "Counter": "0,1,2,3", - "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x48", "UMask": "0x1", - "BriefDescription": "Cycles with L1D load Misses outstanding.", + "BriefDescription": "L1D miss outstandings duration in cycles", "Counter": "0,1,2,3", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "CounterMask": "1", - "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "EventName": "L1D_PEND_MISS.PENDING", + "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -234,21 +236,21 @@ { "EventCode": "0x60", "UMask": "0x1", - "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", + "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "CounterMask": "1", + "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x60", "UMask": "0x1", - "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", + "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", - "CounterMask": "1", - "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -307,21 +309,21 @@ { "EventCode": "0x60", "UMask": "0x8", - "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", - "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "CounterMask": "1", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x60", "UMask": "0x8", - "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "CounterMask": "1", - "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -486,7 +488,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.\r\n", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, @@ -558,7 +560,7 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. \r\n", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" }, @@ -690,6 +692,7 @@ "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared state. A non-threaded event.", "Counter": "0,1,2,3", "EventName": "L2_LINES_OUT.SILENT", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -699,17 +702,18 @@ "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped", "Counter": "0,1,2,3", "EventName": "L2_LINES_OUT.NON_SILENT", - "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped.", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", "SampleAfterValue": "200003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xF2", "UMask": "0x4", - "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", + "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", + "Deprecated": "1", "Counter": "0,1,2,3", "EventName": "L2_LINES_OUT.USELESS_PREF", - "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.", + "PublicDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", "SampleAfterValue": "200003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -736,12 +740,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that have any response type.", - "MSRValue": "0x0000010001 ", + "BriefDescription": "Counts demand data reads have any response type.", + "MSRValue": "0x0000010001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -749,12 +753,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0001 ", + "BriefDescription": "Counts demand data reads TBD TBD", + "MSRValue": "0x01003C0001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -762,25 +766,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0001 ", + "BriefDescription": "Counts demand data reads TBD TBD", + "MSRValue": "0x04003C0001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0001 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -788,12 +779,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0001 ", + "BriefDescription": "Counts demand data reads TBD TBD", + "MSRValue": "0x10003C0001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -801,12 +792,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that hit in the L3.", - "MSRValue": "0x3f803c0001 ", + "BriefDescription": "Counts demand data reads TBD TBD", + "MSRValue": "0x3F803C0001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -814,12 +805,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.", - "MSRValue": "0x0000010002 ", + "BriefDescription": "Counts all demand data writes (RFOs) have any response type.", + "MSRValue": "0x0000010002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -827,12 +818,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", + "MSRValue": "0x01003C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -840,12 +831,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", + "MSRValue": "0x04003C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -853,25 +844,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0002 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", + "MSRValue": "0x10003C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -879,12 +857,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.", - "MSRValue": "0x3f803c0002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", + "MSRValue": "0x3F803C0002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -892,12 +870,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that have any response type.", - "MSRValue": "0x0000010004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.", + "MSRValue": "0x0000010004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -905,12 +883,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", + "MSRValue": "0x01003C0004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -918,12 +896,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", + "MSRValue": "0x04003C0004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -931,25 +909,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0004 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", + "MSRValue": "0x10003C0004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -957,12 +922,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that hit in the L3.", - "MSRValue": "0x3f803c0004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", + "MSRValue": "0x3F803C0004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -970,12 +935,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.", - "MSRValue": "0x0000010010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads have any response type.", + "MSRValue": "0x0000010010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -983,12 +948,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", + "MSRValue": "0x01003C0010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -996,12 +961,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", + "MSRValue": "0x04003C0010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1009,25 +974,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "PF_L2_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0010 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", + "MSRValue": "0x10003C0010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1035,12 +987,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.", - "MSRValue": "0x3f803c0010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", + "MSRValue": "0x3F803C0010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1048,12 +1000,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.", - "MSRValue": "0x0000010020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.", + "MSRValue": "0x0000010020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1061,12 +1013,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", + "MSRValue": "0x01003C0020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1074,12 +1026,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", + "MSRValue": "0x04003C0020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1087,25 +1039,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "PF_L2_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0020 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", + "MSRValue": "0x10003C0020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1113,12 +1052,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.", - "MSRValue": "0x3f803c0020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", + "MSRValue": "0x3F803C0020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1126,12 +1065,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.", - "MSRValue": "0x0000010080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.", + "MSRValue": "0x0000010080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1139,12 +1078,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", + "MSRValue": "0x01003C0080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1152,25 +1091,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", + "MSRValue": "0x04003C0080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0080 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1178,12 +1104,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", + "MSRValue": "0x10003C0080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1191,12 +1117,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.", - "MSRValue": "0x3f803c0080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", + "MSRValue": "0x3F803C0080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1204,12 +1130,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.", - "MSRValue": "0x0000010100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.", + "MSRValue": "0x0000010100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1217,12 +1143,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", + "MSRValue": "0x01003C0100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1230,12 +1156,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", + "MSRValue": "0x04003C0100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1243,12 +1169,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", + "MSRValue": "0x10003C0100", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1256,12 +1182,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", + "MSRValue": "0x3F803C0100", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1269,12 +1195,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.", - "MSRValue": "0x3f803c0100 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests have any response type.", + "MSRValue": "0x0000010400", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1282,12 +1208,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.", - "MSRValue": "0x0000010400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", + "MSRValue": "0x01003C0400", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1295,12 +1221,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", + "MSRValue": "0x04003C0400", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1308,12 +1234,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", + "MSRValue": "0x10003C0400", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1321,12 +1247,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "PF_L1D_AND_SW & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", + "MSRValue": "0x3F803C0400", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1334,12 +1260,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0400 ", + "BriefDescription": "TBD have any response type.", + "MSRValue": "0x0000010490", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1347,12 +1273,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.", - "MSRValue": "0x3f803c0400 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x01003C0490", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1360,12 +1286,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts any other requests that have any response type.", - "MSRValue": "0x0000018000 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x04003C0490", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1373,12 +1299,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c8000 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x10003C0490", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1386,12 +1312,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c8000 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3F803C0490", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1399,12 +1325,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "OTHER & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c8000 ", + "BriefDescription": "TBD have any response type.", + "MSRValue": "0x0000010120", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1412,12 +1338,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c8000 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x01003C0120", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1425,12 +1351,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts any other requests that hit in the L3.", - "MSRValue": "0x3f803c8000 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x04003C0120", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1438,12 +1364,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that have any response type.", - "MSRValue": "0x0000010490 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x10003C0120", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1451,12 +1377,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0490 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3F803C0120", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1464,12 +1390,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0490 ", + "BriefDescription": "TBD have any response type.", + "MSRValue": "0x0000010491", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1477,12 +1403,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0490 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x01003C0491", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1490,12 +1416,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0490 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x04003C0491", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1503,12 +1429,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that hit in the L3.", - "MSRValue": "0x3f803c0490 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x10003C0491", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1516,12 +1442,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that have any response type.", - "MSRValue": "0x0000010120 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3F803C0491", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1529,12 +1455,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0120 ", + "BriefDescription": "TBD have any response type.", + "MSRValue": "0x0000010122", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD have any response type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1542,12 +1468,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0120 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x01003C0122", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1555,12 +1481,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0120 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x04003C0122", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1568,12 +1494,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0120 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x10003C0122", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1581,12 +1507,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that hit in the L3.", - "MSRValue": "0x3f803c0120 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3F803C0122", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1594,12 +1520,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that have any response type.", - "MSRValue": "0x0000010491 ", + "BriefDescription": "Counts demand data reads", + "MSRValue": "0x08007C0001", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts demand data reads", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1607,12 +1532,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0491 ", + "BriefDescription": "Counts all demand data writes (RFOs)", + "MSRValue": "0x08007C0002", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts all demand data writes (RFOs)", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1620,12 +1544,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0491 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "MSRValue": "0x08007C0004", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1633,12 +1556,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0491 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads", + "MSRValue": "0x08007C0010", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1646,12 +1568,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0491 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", + "MSRValue": "0x08007C0020", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1659,12 +1580,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.", - "MSRValue": "0x3f803c0491 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", + "MSRValue": "0x08007C0080", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1672,12 +1592,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.", - "MSRValue": "0x0000010122 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", + "MSRValue": "0x08007C0100", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1685,12 +1604,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", - "MSRValue": "0x01003c0122 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests", + "MSRValue": "0x08007C0400", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1698,12 +1616,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x04003c0122 ", + "BriefDescription": "TBD", + "MSRValue": "0x08007C0490", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1711,12 +1628,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", - "MSRValue": "0x08003c0122 ", + "BriefDescription": "TBD", + "MSRValue": "0x08007C0120", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1724,12 +1640,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", - "MSRValue": "0x10003c0122 ", + "BriefDescription": "TBD", + "MSRValue": "0x08007C0491", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1737,12 +1652,11 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.", - "MSRValue": "0x3f803c0122 ", + "BriefDescription": "TBD", + "MSRValue": "0x08007C0122", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "PublicDescription": "TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json index 286ed1a37ec9..c5d0babe89fc 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json @@ -59,7 +59,6 @@ "BriefDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8)", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", - "PublicDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -69,7 +68,6 @@ "BriefDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16)", "Counter": "0,1,2,3", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", - "PublicDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, diff --git a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json index 403a4f89e9b2..4dc583cfb545 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json @@ -2,16 +2,6 @@ { "EventCode": "0x79", "UMask": "0x4", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", - "Counter": "0,1,2,3", - "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x79", - "UMask": "0x4", "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", "EventName": "IDQ.MITE_CYCLES", @@ -22,11 +12,11 @@ }, { "EventCode": "0x79", - "UMask": "0x8", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "UMask": "0x4", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", - "EventName": "IDQ.DSB_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -43,6 +33,16 @@ }, { "EventCode": "0x79", + "UMask": "0x8", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", "UMask": "0x10", "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", @@ -55,22 +55,22 @@ { "EventCode": "0x79", "UMask": "0x18", - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", "Counter": "0,1,2,3", - "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", - "CounterMask": "4", - "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", + "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", + "CounterMask": "1", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "UMask": "0x18", - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", "Counter": "0,1,2,3", - "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", - "CounterMask": "1", - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", + "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", + "CounterMask": "4", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -87,22 +87,22 @@ { "EventCode": "0x79", "UMask": "0x24", - "BriefDescription": "Cycles MITE is delivering 4 Uops", + "BriefDescription": "Cycles MITE is delivering any Uop", "Counter": "0,1,2,3", - "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", - "CounterMask": "4", - "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "CounterMask": "1", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "UMask": "0x24", - "BriefDescription": "Cycles MITE is delivering any Uop", + "BriefDescription": "Cycles MITE is delivering 4 Uops", "Counter": "0,1,2,3", - "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", - "CounterMask": "1", - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", + "CounterMask": "4", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -118,24 +118,24 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EdgeDetect": "1", "EventCode": "0x79", "UMask": "0x30", - "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "EventName": "IDQ.MS_SWITCHES", - "CounterMask": "1", - "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EdgeDetect": "1", "EventCode": "0x79", "UMask": "0x30", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", "Counter": "0,1,2,3", - "EventName": "IDQ.MS_UOPS", - "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", + "EventName": "IDQ.MS_SWITCHES", + "CounterMask": "1", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -177,67 +177,67 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "Invert": "1", "EventCode": "0x9C", "UMask": "0x1", - "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", + "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "CounterMask": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x9C", "UMask": "0x1", - "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", + "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "CounterMask": "4", - "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", + "CounterMask": "1", + "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x9C", "UMask": "0x1", - "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", + "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", - "CounterMask": "3", - "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", + "CounterMask": "2", + "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x9C", "UMask": "0x1", - "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", + "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", - "CounterMask": "2", - "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "CounterMask": "3", + "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x9C", "UMask": "0x1", - "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", - "CounterMask": "1", - "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "CounterMask": "4", + "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "Invert": "1", "EventCode": "0x9C", "UMask": "0x1", - "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", + "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", - "CounterMask": "1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -247,20 +247,19 @@ "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", "Counter": "0,1,2,3", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", + "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x11", + "MSRValue": "0x400406", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.DSB_MISS", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. \r\n", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -268,11 +267,11 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x12", + "MSRValue": "0x200206", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.L1I_MISS", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", "MSRIndex": "0x3F7", "TakenAlone": "1", "SampleAfterValue": "100007", @@ -281,11 +280,11 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x13", + "MSRValue": "0x400206", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.L2_MISS", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "TakenAlone": "1", "SampleAfterValue": "100007", @@ -294,13 +293,13 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.", + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.", "PEBS": "1", - "MSRValue": "0x14", + "MSRValue": "0x15", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -308,13 +307,13 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.", + "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.", "PEBS": "1", - "MSRValue": "0x15", + "MSRValue": "0x14", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.STLB_MISS", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -322,11 +321,11 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.", "PEBS": "1", - "MSRValue": "0x400206", + "MSRValue": "0x13", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", + "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "TakenAlone": "1", "SampleAfterValue": "100007", @@ -335,11 +334,11 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.", "PEBS": "1", - "MSRValue": "0x200206", + "MSRValue": "0x12", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", + "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "TakenAlone": "1", "SampleAfterValue": "100007", @@ -348,12 +347,13 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.", "PEBS": "1", - "MSRValue": "0x400406", + "MSRValue": "0x11", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", + "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -361,13 +361,12 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x400806", + "MSRValue": "0x300206", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. \r\n", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -375,13 +374,13 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x401006", + "MSRValue": "0x100206", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.\r\n", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -389,13 +388,12 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x402006", + "MSRValue": "0x420006", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.\r\n", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -403,11 +401,11 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x404006", + "MSRValue": "0x410006", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "TakenAlone": "1", "SampleAfterValue": "100007", @@ -429,11 +427,11 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x410006", + "MSRValue": "0x404006", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "TakenAlone": "1", "SampleAfterValue": "100007", @@ -442,12 +440,13 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x420006", + "MSRValue": "0x402006", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -455,13 +454,13 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.", "PEBS": "1", - "MSRValue": "0x100206", + "MSRValue": "0x401006", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.\r\n", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" @@ -469,12 +468,13 @@ { "EventCode": "0xC6", "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", "PEBS": "1", - "MSRValue": "0x300206", + "MSRValue": "0x400806", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "TakenAlone": "1", "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" diff --git a/tools/perf/pmu-events/arch/x86/skylakex/memory.json b/tools/perf/pmu-events/arch/x86/skylakex/memory.json index e7f1aa31226d..48a9cdf81307 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/memory.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/memory.json @@ -129,20 +129,20 @@ { "EventCode": "0x60", "UMask": "0x10", - "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", + "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", - "CounterMask": "1", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6", + "CounterMask": "6", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x60", "UMask": "0x10", - "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.", + "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6", - "CounterMask": "6", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", + "CounterMask": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -210,7 +210,7 @@ { "EventCode": "0xC8", "UMask": "0x4", - "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one). ", + "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "HLE_RETIRED.ABORTED", @@ -242,6 +242,7 @@ "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", "Counter": "0,1,2,3", "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY", + "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -287,7 +288,7 @@ { "EventCode": "0xC9", "UMask": "0x4", - "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one). ", + "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "RTM_RETIRED.ABORTED", @@ -347,125 +348,125 @@ { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", "PEBS": "2", - "MSRValue": "0x4", + "MSRValue": "0x200", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "100003", + "SampleAfterValue": "101", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", "PEBS": "2", - "MSRValue": "0x8", + "MSRValue": "0x100", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "50021", + "SampleAfterValue": "503", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", "PEBS": "2", - "MSRValue": "0x10", + "MSRValue": "0x80", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "20011", + "SampleAfterValue": "1009", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", "PEBS": "2", - "MSRValue": "0x20", + "MSRValue": "0x40", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "100007", + "SampleAfterValue": "2003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", "PEBS": "2", - "MSRValue": "0x40", + "MSRValue": "0x20", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "2003", + "SampleAfterValue": "100007", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", "PEBS": "2", - "MSRValue": "0x80", + "MSRValue": "0x10", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "1009", + "SampleAfterValue": "20011", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", "PEBS": "2", - "MSRValue": "0x100", + "MSRValue": "0x8", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "503", + "SampleAfterValue": "50021", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xCD", "UMask": "0x1", - "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", "PEBS": "2", - "MSRValue": "0x200", + "MSRValue": "0x4", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", - "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "TakenAlone": "1", - "SampleAfterValue": "101", + "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss in the L3.", - "MSRValue": "0x3fbc000001 ", + "BriefDescription": "Counts demand data reads TBD TBD", + "MSRValue": "0x3FBC000001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -473,12 +474,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00001 ", + "BriefDescription": "Counts demand data reads TBD", + "MSRValue": "0x083FC00001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -486,12 +487,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00001 ", + "BriefDescription": "Counts demand data reads TBD", + "MSRValue": "0x103FC00001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -499,12 +500,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00001 ", + "BriefDescription": "Counts demand data reads TBD", + "MSRValue": "0x063FC00001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -512,12 +513,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800001 ", + "BriefDescription": "Counts demand data reads TBD", + "MSRValue": "0x063B800001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -525,12 +526,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000001 ", + "BriefDescription": "Counts demand data reads TBD", + "MSRValue": "0x0604000001", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -538,12 +539,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3.", - "MSRValue": "0x3fbc000002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", + "MSRValue": "0x3FBC000002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -551,12 +552,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD", + "MSRValue": "0x083FC00002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -564,12 +565,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD", + "MSRValue": "0x103FC00002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -577,12 +578,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD", + "MSRValue": "0x063FC00002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -590,12 +591,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD", + "MSRValue": "0x063B800002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -603,12 +604,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000002 ", + "BriefDescription": "Counts all demand data writes (RFOs) TBD", + "MSRValue": "0x0604000002", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -616,12 +617,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss in the L3.", - "MSRValue": "0x3fbc000004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", + "MSRValue": "0x3FBC000004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -629,12 +630,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", + "MSRValue": "0x083FC00004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -642,12 +643,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", + "MSRValue": "0x103FC00004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -655,12 +656,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", + "MSRValue": "0x063FC00004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -668,12 +669,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", + "MSRValue": "0x063B800004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -681,12 +682,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000004 ", + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", + "MSRValue": "0x0604000004", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -694,12 +695,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3.", - "MSRValue": "0x3fbc000010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", + "MSRValue": "0x3FBC000010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -707,12 +708,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", + "MSRValue": "0x083FC00010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -720,12 +721,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", + "MSRValue": "0x103FC00010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -733,12 +734,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", + "MSRValue": "0x063FC00010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -746,12 +747,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", + "MSRValue": "0x063B800010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -759,12 +760,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000010 ", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", + "MSRValue": "0x0604000010", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -772,12 +773,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3.", - "MSRValue": "0x3fbc000020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", + "MSRValue": "0x3FBC000020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -785,12 +786,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", + "MSRValue": "0x083FC00020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -798,12 +799,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", + "MSRValue": "0x103FC00020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -811,12 +812,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", + "MSRValue": "0x063FC00020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -824,12 +825,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", + "MSRValue": "0x063B800020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -837,12 +838,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000020 ", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", + "MSRValue": "0x0604000020", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -850,12 +851,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3.", - "MSRValue": "0x3fbc000080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", + "MSRValue": "0x3FBC000080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -863,12 +864,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", + "MSRValue": "0x083FC00080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -876,12 +877,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", + "MSRValue": "0x103FC00080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -889,12 +890,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", + "MSRValue": "0x063FC00080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -902,12 +903,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", + "MSRValue": "0x063B800080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -915,12 +916,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000080 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", + "MSRValue": "0x0604000080", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -928,12 +929,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3.", - "MSRValue": "0x3fbc000100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", + "MSRValue": "0x3FBC000100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -941,12 +942,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", + "MSRValue": "0x083FC00100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -954,12 +955,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", + "MSRValue": "0x103FC00100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -967,12 +968,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", + "MSRValue": "0x063FC00100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -980,12 +981,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", + "MSRValue": "0x063B800100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -993,12 +994,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000100 ", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", + "MSRValue": "0x0604000100", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1006,12 +1007,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3.", - "MSRValue": "0x3fbc000400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", + "MSRValue": "0x3FBC000400", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1019,12 +1020,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", + "MSRValue": "0x083FC00400", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1032,12 +1033,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", + "MSRValue": "0x103FC00400", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1045,12 +1046,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", + "MSRValue": "0x063FC00400", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1058,12 +1059,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", + "MSRValue": "0x063B800400", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1071,90 +1072,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000400 ", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", + "MSRValue": "0x0604000400", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts any other requests that miss in the L3.", - "MSRValue": "0x3fbc008000 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts any other requests that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc08000 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts any other requests that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc08000 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc08000 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b808000 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604008000 ", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1162,12 +1085,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that miss in the L3.", - "MSRValue": "0x3fbc000490 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3FBC000490", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1175,12 +1098,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00490 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x083FC00490", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1188,12 +1111,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00490 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x103FC00490", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1201,12 +1124,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00490 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063FC00490", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1214,12 +1137,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800490 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063B800490", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1227,12 +1150,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000490 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x0604000490", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1240,12 +1163,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that miss in the L3.", - "MSRValue": "0x3fbc000120 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3FBC000120", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1253,12 +1176,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00120 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x083FC00120", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1266,12 +1189,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00120 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x103FC00120", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1279,12 +1202,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00120 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063FC00120", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1292,12 +1215,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800120 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063B800120", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1305,12 +1228,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000120 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x0604000120", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1318,12 +1241,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3.", - "MSRValue": "0x3fbc000491 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3FBC000491", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1331,12 +1254,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00491 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x083FC00491", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1344,12 +1267,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00491 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x103FC00491", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1357,12 +1280,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00491 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063FC00491", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1370,12 +1293,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800491 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063B800491", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1383,12 +1306,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000491 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x0604000491", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1396,12 +1319,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3.", - "MSRValue": "0x3fbc000122 ", + "BriefDescription": "TBD TBD TBD", + "MSRValue": "0x3FBC000122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1409,12 +1332,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.", - "MSRValue": "0x083fc00122 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x083FC00122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1422,12 +1345,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.", - "MSRValue": "0x103fc00122 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x103FC00122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1435,12 +1358,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram.", - "MSRValue": "0x063fc00122 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063FC00122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1448,12 +1371,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram.", - "MSRValue": "0x063b800122 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x063B800122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1461,12 +1384,12 @@ "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.", - "MSRValue": "0x0604000122 ", + "BriefDescription": "TBD TBD", + "MSRValue": "0x0604000122", "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "MSRIndex": "0x1a6, 0x1a7", + "PublicDescription": "TBD TBD", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json index f99f7ae27820..369f56c1d1b5 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json @@ -1,6 +1,5 @@ [ { - "EventCode": "0x00", "UMask": "0x1", "BriefDescription": "Instructions retired from execution.", "Counter": "Fixed counter 0", @@ -10,7 +9,6 @@ "CounterHTOff": "Fixed counter 0" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when the thread is not in halt state", "Counter": "Fixed counter 1", @@ -20,7 +18,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "Counter": "Fixed counter 1", @@ -30,7 +27,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "UMask": "0x3", "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", @@ -99,24 +95,24 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "Invert": "1", "EventCode": "0x0E", "UMask": "0x1", - "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", "Counter": "0,1,2,3", - "EventName": "UOPS_ISSUED.ANY", - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "Invert": "1", "EventCode": "0x0E", "UMask": "0x1", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", + "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", "Counter": "0,1,2,3", - "EventName": "UOPS_ISSUED.STALL_CYCLES", - "CounterMask": "1", - "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -126,7 +122,7 @@ "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.", "Counter": "0,1,2,3", "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH", - "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.", + "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -203,19 +199,19 @@ { "EventCode": "0x3C", "UMask": "0x1", - "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", + "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", + "AnyThread": "1", "SampleAfterValue": "2503", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x3C", "UMask": "0x1", - "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", - "AnyThread": "1", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", "SampleAfterValue": "2503", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -248,12 +244,12 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x5E", + "EventCode": "0x59", "UMask": "0x1", - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", + "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.", "Counter": "0,1,2,3", - "EventName": "RS_EVENTS.EMPTY_CYCLES", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", + "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD", + "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -271,6 +267,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x5E", + "UMask": "0x1", + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", + "Counter": "0,1,2,3", + "EventName": "RS_EVENTS.EMPTY_CYCLES", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x87", "UMask": "0x1", "BriefDescription": "Stalls caused by changing prefix length of the instruction.", @@ -361,12 +367,12 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0xa2", "UMask": "0x1", "BriefDescription": "Resource-related stall cycles", "Counter": "0,1,2,3", "EventName": "RESOURCE_STALLS.ANY", - "PublicDescription": "Counts resource-related stall cycles. Reasons for stalls can be as follows:a. *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots).b. *any* u-arch structure got empty (like INT/SIMD FreeLists).c. FPU control word (FPCW), MXCSR.and others. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "PublicDescription": "Counts resource-related stall cycles.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -522,6 +528,17 @@ { "EventCode": "0xA8", "UMask": "0x1", + "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", + "Counter": "0,1,2,3", + "EventName": "LSD.CYCLES_4_UOPS", + "CounterMask": "4", + "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA8", + "UMask": "0x1", "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", "Counter": "0,1,2,3", "EventName": "LSD.CYCLES_ACTIVE", @@ -531,35 +548,35 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA8", + "EventCode": "0xB1", "UMask": "0x1", - "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", "Counter": "0,1,2,3", - "EventName": "LSD.CYCLES_4_UOPS", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", "CounterMask": "4", - "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xB1", "UMask": "0x1", - "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.THREAD", - "PublicDescription": "Number of uops to be executed per-thread each cycle.", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "CounterMask": "3", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "Invert": "1", "EventCode": "0xB1", "UMask": "0x1", - "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.STALL_CYCLES", - "CounterMask": "1", - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", + "CounterMask": "2", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -575,35 +592,24 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "Invert": "1", "EventCode": "0xB1", "UMask": "0x1", - "BriefDescription": "Cycles where at least 2 uops were executed per-thread", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", - "CounterMask": "2", - "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", - "CounterMask": "3", - "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xB1", "UMask": "0x1", - "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", - "CounterMask": "4", - "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "EventName": "UOPS_EXECUTED.THREAD", + "PublicDescription": "Number of uops to be executed per-thread each cycle.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -618,11 +624,12 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "Invert": "1", "EventCode": "0xB1", "UMask": "0x2", - "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", "CounterMask": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" @@ -630,10 +637,10 @@ { "EventCode": "0xB1", "UMask": "0x2", - "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "CounterMask": "2", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", + "CounterMask": "4", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -650,20 +657,19 @@ { "EventCode": "0xB1", "UMask": "0x2", - "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "CounterMask": "4", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "CounterMask": "2", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "Invert": "1", "EventCode": "0xB1", "UMask": "0x2", - "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", "CounterMask": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" @@ -725,12 +731,14 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "Invert": "1", "EventCode": "0xC2", "UMask": "0x2", - "BriefDescription": "Retirement slots used.", + "BriefDescription": "Cycles with less than 10 actually retired uops.", "Counter": "0,1,2,3", - "EventName": "UOPS_RETIRED.RETIRE_SLOTS", - "PublicDescription": "Counts the retirement slots used.", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "CounterMask": "10", + "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -742,19 +750,17 @@ "Counter": "0,1,2,3", "EventName": "UOPS_RETIRED.STALL_CYCLES", "CounterMask": "1", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.", + "PublicDescription": "This event counts cycles without actually retired uops.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "Invert": "1", "EventCode": "0xC2", "UMask": "0x2", - "BriefDescription": "Cycles with less than 10 actually retired uops.", + "BriefDescription": "Retirement slots used.", "Counter": "0,1,2,3", - "EventName": "UOPS_RETIRED.TOTAL_CYCLES", - "CounterMask": "10", - "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", + "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "PublicDescription": "Counts the retirement slots used.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -766,6 +772,7 @@ "Counter": "0,1,2,3", "EventName": "MACHINE_CLEARS.COUNT", "CounterMask": "1", + "PublicDescription": "Number of machine clears (nukes) of any type.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -841,11 +848,12 @@ { "EventCode": "0xC4", "UMask": "0x10", - "BriefDescription": "Not taken branch instructions retired.", + "BriefDescription": "Counts all not taken macro branch instructions retired.", + "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NOT_TAKEN", "Errata": "SKL091", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -919,7 +927,7 @@ { "EventCode": "0xC5", "UMask": "0x20", - "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken. ", + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", @@ -938,6 +946,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0xCC", + "UMask": "0x40", + "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.", + "Counter": "0,1,2,3", + "EventName": "ROB_MISC_EVENTS.PAUSE_INST", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xE6", "UMask": "0x1", "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index 71e9737f4614..56e03ba771f4 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -1,164 +1,394 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )", - "MetricGroup": "Frontend", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / cycles", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "Branch_Misprediction_Cost" + }, + { + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)", + "MetricGroup": "Branch_Mispredicts_SMT", + "MetricName": "Branch_Misprediction_Cost_SMT" }, { + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" + }, + { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Access_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x35\\\\\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )", + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_Lat", + "MetricName": "DRAM_Read_Latency" + }, + { + "MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1@", + "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_Parallel_Reads" + }, + { + "MetricExpr": "( 1000000000 * ( imc@event\\=0xe0\\\\\\,umask\\=0x1@ / imc@event\\=0xe3@ ) / imc_0@event\\=0x0@ ) if 1 if 0 == 1 else 0 else 0", + "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", + "MetricGroup": "Memory_Lat", + "MetricName": "MEM_PMM_Read_Latency" + }, + { + "MetricExpr": "( ( 64 * imc@event\\=0xe3@ / 1000000000 ) / duration_time ) if 1 if 0 == 1 else 0 else 0", + "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "PMM_Read_BW" + }, + { + "MetricExpr": "( ( 64 * imc@event\\=0xe7@ / 1000000000 ) / duration_time ) if 1 if 0 == 1 else 0 else 0", + "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "PMM_Write_BW" + }, + { + "MetricExpr": "cha_0@event\\=0x0@", + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricGroup": "", + "MetricName": "Socket_CLKS" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py index 390a351d15ea..c3eae1d77d36 100644 --- a/tools/perf/scripts/python/export-to-postgresql.py +++ b/tools/perf/scripts/python/export-to-postgresql.py @@ -10,6 +10,8 @@ # FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for # more details. +from __future__ import print_function + import os import sys import struct @@ -199,6 +201,18 @@ import datetime from PySide.QtSql import * +if sys.version_info < (3, 0): + def toserverstr(str): + return str + def toclientstr(str): + return str +else: + # Assume UTF-8 server_encoding and client_encoding + def toserverstr(str): + return bytes(str, "UTF_8") + def toclientstr(str): + return bytes(str, "UTF_8") + # Need to access PostgreSQL C library directly to use COPY FROM STDIN from ctypes import * libpq = CDLL("libpq.so.5") @@ -234,12 +248,17 @@ perf_db_export_mode = True perf_db_export_calls = False perf_db_export_callchains = False +def printerr(*args, **kw_args): + print(*args, file=sys.stderr, **kw_args) + +def printdate(*args, **kw_args): + print(datetime.datetime.today(), *args, sep=' ', **kw_args) def usage(): - print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]" - print >> sys.stderr, "where: columns 'all' or 'branches'" - print >> sys.stderr, " calls 'calls' => create calls and call_paths table" - print >> sys.stderr, " callchains 'callchains' => create call_paths table" + printerr("Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]") + printerr("where: columns 'all' or 'branches'") + printerr(" calls 'calls' => create calls and call_paths table") + printerr(" callchains 'callchains' => create call_paths table") raise Exception("Too few arguments") if (len(sys.argv) < 2): @@ -273,7 +292,7 @@ def do_query(q, s): return raise Exception("Query failed: " + q.lastError().text()) -print datetime.datetime.today(), "Creating database..." +printdate("Creating database...") db = QSqlDatabase.addDatabase('QPSQL') query = QSqlQuery(db) @@ -506,12 +525,12 @@ do_query(query, 'CREATE VIEW samples_view AS ' ' FROM samples') -file_header = struct.pack("!11sii", "PGCOPY\n\377\r\n\0", 0, 0) -file_trailer = "\377\377" +file_header = struct.pack("!11sii", b"PGCOPY\n\377\r\n\0", 0, 0) +file_trailer = b"\377\377" def open_output_file(file_name): path_name = output_dir_name + "/" + file_name - file = open(path_name, "w+") + file = open(path_name, "wb+") file.write(file_header) return file @@ -526,13 +545,13 @@ def copy_output_file_direct(file, table_name): # Use COPY FROM STDIN because security may prevent postgres from accessing the files directly def copy_output_file(file, table_name): - conn = PQconnectdb("dbname = " + dbname) + conn = PQconnectdb(toclientstr("dbname = " + dbname)) if (PQstatus(conn)): raise Exception("COPY FROM STDIN PQconnectdb failed") file.write(file_trailer) file.seek(0) sql = "COPY " + table_name + " FROM STDIN (FORMAT 'binary')" - res = PQexec(conn, sql) + res = PQexec(conn, toclientstr(sql)) if (PQresultStatus(res) != 4): raise Exception("COPY FROM STDIN PQexec failed") data = file.read(65536) @@ -566,7 +585,7 @@ if perf_db_export_calls: call_file = open_output_file("call_table.bin") def trace_begin(): - print datetime.datetime.today(), "Writing to intermediate files..." + printdate("Writing to intermediate files...") # id == 0 means unknown. It is easier to create records for them than replace the zeroes with NULLs evsel_table(0, "unknown") machine_table(0, 0, "unknown") @@ -582,7 +601,7 @@ def trace_begin(): unhandled_count = 0 def trace_end(): - print datetime.datetime.today(), "Copying to database..." + printdate("Copying to database...") copy_output_file(evsel_file, "selected_events") copy_output_file(machine_file, "machines") copy_output_file(thread_file, "threads") @@ -597,7 +616,7 @@ def trace_end(): if perf_db_export_calls: copy_output_file(call_file, "calls") - print datetime.datetime.today(), "Removing intermediate files..." + printdate("Removing intermediate files...") remove_output_file(evsel_file) remove_output_file(machine_file) remove_output_file(thread_file) @@ -612,7 +631,7 @@ def trace_end(): if perf_db_export_calls: remove_output_file(call_file) os.rmdir(output_dir_name) - print datetime.datetime.today(), "Adding primary keys" + printdate("Adding primary keys") do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)') do_query(query, 'ALTER TABLE machines ADD PRIMARY KEY (id)') do_query(query, 'ALTER TABLE threads ADD PRIMARY KEY (id)') @@ -627,7 +646,7 @@ def trace_end(): if perf_db_export_calls: do_query(query, 'ALTER TABLE calls ADD PRIMARY KEY (id)') - print datetime.datetime.today(), "Adding foreign keys" + printdate("Adding foreign keys") do_query(query, 'ALTER TABLE threads ' 'ADD CONSTRAINT machinefk FOREIGN KEY (machine_id) REFERENCES machines (id),' 'ADD CONSTRAINT processfk FOREIGN KEY (process_id) REFERENCES threads (id)') @@ -663,8 +682,8 @@ def trace_end(): do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)') if (unhandled_count): - print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events" - print datetime.datetime.today(), "Done" + printdate("Warning: ", unhandled_count, " unhandled events") + printdate("Done") def trace_unhandled(event_name, context, event_fields_dict): global unhandled_count @@ -674,12 +693,14 @@ def sched__sched_switch(*x): pass def evsel_table(evsel_id, evsel_name, *x): + evsel_name = toserverstr(evsel_name) n = len(evsel_name) fmt = "!hiqi" + str(n) + "s" value = struct.pack(fmt, 2, 8, evsel_id, n, evsel_name) evsel_file.write(value) def machine_table(machine_id, pid, root_dir, *x): + root_dir = toserverstr(root_dir) n = len(root_dir) fmt = "!hiqiii" + str(n) + "s" value = struct.pack(fmt, 3, 8, machine_id, 4, pid, n, root_dir) @@ -690,6 +711,7 @@ def thread_table(thread_id, machine_id, process_id, pid, tid, *x): thread_file.write(value) def comm_table(comm_id, comm_str, *x): + comm_str = toserverstr(comm_str) n = len(comm_str) fmt = "!hiqi" + str(n) + "s" value = struct.pack(fmt, 2, 8, comm_id, n, comm_str) @@ -701,6 +723,9 @@ def comm_thread_table(comm_thread_id, comm_id, thread_id, *x): comm_thread_file.write(value) def dso_table(dso_id, machine_id, short_name, long_name, build_id, *x): + short_name = toserverstr(short_name) + long_name = toserverstr(long_name) + build_id = toserverstr(build_id) n1 = len(short_name) n2 = len(long_name) n3 = len(build_id) @@ -709,12 +734,14 @@ def dso_table(dso_id, machine_id, short_name, long_name, build_id, *x): dso_file.write(value) def symbol_table(symbol_id, dso_id, sym_start, sym_end, binding, symbol_name, *x): + symbol_name = toserverstr(symbol_name) n = len(symbol_name) fmt = "!hiqiqiqiqiii" + str(n) + "s" value = struct.pack(fmt, 6, 8, symbol_id, 8, dso_id, 8, sym_start, 8, sym_end, 4, binding, n, symbol_name) symbol_file.write(value) def branch_type_table(branch_type, name, *x): + name = toserverstr(name) n = len(name) fmt = "!hiii" + str(n) + "s" value = struct.pack(fmt, 2, 4, branch_type, n, name) diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py index eb63e6c7107f..bf271fbc3a88 100644 --- a/tools/perf/scripts/python/export-to-sqlite.py +++ b/tools/perf/scripts/python/export-to-sqlite.py @@ -10,6 +10,8 @@ # FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for # more details. +from __future__ import print_function + import os import sys import struct @@ -60,11 +62,17 @@ perf_db_export_mode = True perf_db_export_calls = False perf_db_export_callchains = False +def printerr(*args, **keyword_args): + print(*args, file=sys.stderr, **keyword_args) + +def printdate(*args, **kw_args): + print(datetime.datetime.today(), *args, sep=' ', **kw_args) + def usage(): - print >> sys.stderr, "Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>]" - print >> sys.stderr, "where: columns 'all' or 'branches'" - print >> sys.stderr, " calls 'calls' => create calls and call_paths table" - print >> sys.stderr, " callchains 'callchains' => create call_paths table" + printerr("Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>]"); + printerr("where: columns 'all' or 'branches'"); + printerr(" calls 'calls' => create calls and call_paths table"); + printerr(" callchains 'callchains' => create call_paths table"); raise Exception("Too few arguments") if (len(sys.argv) < 2): @@ -100,7 +108,7 @@ def do_query_(q): return raise Exception("Query failed: " + q.lastError().text()) -print datetime.datetime.today(), "Creating database..." +printdate("Creating database ...") db_exists = False try: @@ -323,7 +331,7 @@ if perf_db_export_calls: 'return_id,' 'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,' 'parent_call_path_id,' - 'parent_id' + 'calls.parent_id' ' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id') do_query(query, 'CREATE VIEW samples_view AS ' @@ -378,7 +386,7 @@ if perf_db_export_calls: call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)") def trace_begin(): - print datetime.datetime.today(), "Writing records..." + printdate("Writing records...") do_query(query, 'BEGIN TRANSACTION') # id == 0 means unknown. It is easier to create records for them than replace the zeroes with NULLs evsel_table(0, "unknown") @@ -397,14 +405,14 @@ unhandled_count = 0 def trace_end(): do_query(query, 'END TRANSACTION') - print datetime.datetime.today(), "Adding indexes" + printdate("Adding indexes") if perf_db_export_calls: do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)') do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)') if (unhandled_count): - print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events" - print datetime.datetime.today(), "Done" + printdate("Warning: ", unhandled_count, " unhandled events") + printdate("Done") def trace_unhandled(event_name, context, event_fields_dict): global unhandled_count diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index afec9479ca7f..74ef92f1d19a 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -88,20 +88,39 @@ # 7fab593ea956 48 89 15 3b 13 22 00 movq %rdx, 0x22133b(%rip) # 8107675243232 2 ls 22011 22011 hardware interrupt No 7fab593ea956 _dl_start+0x26 (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel]) +from __future__ import print_function + import sys import weakref import threading import string -import cPickle +try: + # Python2 + import cPickle as pickle + # size of pickled integer big enough for record size + glb_nsz = 8 +except ImportError: + import pickle + glb_nsz = 16 import re import os from PySide.QtCore import * from PySide.QtGui import * from PySide.QtSql import * +pyside_version_1 = True from decimal import * from ctypes import * from multiprocessing import Process, Array, Value, Event +# xrange is range in Python3 +try: + xrange +except NameError: + xrange = range + +def printerr(*args, **keyword_args): + print(*args, file=sys.stderr, **keyword_args) + # Data formatting helpers def tohex(ip): @@ -1004,10 +1023,6 @@ class ChildDataItemFinder(): glb_chunk_sz = 10000 -# size of pickled integer big enough for record size - -glb_nsz = 8 - # Background process for SQL data fetcher class SQLFetcherProcess(): @@ -1066,7 +1081,7 @@ class SQLFetcherProcess(): return True if space >= glb_nsz: # Use 0 (or space < glb_nsz) to mean there is no more at the top of the buffer - nd = cPickle.dumps(0, cPickle.HIGHEST_PROTOCOL) + nd = pickle.dumps(0, pickle.HIGHEST_PROTOCOL) self.buffer[self.local_head : self.local_head + len(nd)] = nd self.local_head = 0 if self.local_tail - self.local_head > sz: @@ -1084,9 +1099,9 @@ class SQLFetcherProcess(): self.wait_event.wait() def AddToBuffer(self, obj): - d = cPickle.dumps(obj, cPickle.HIGHEST_PROTOCOL) + d = pickle.dumps(obj, pickle.HIGHEST_PROTOCOL) n = len(d) - nd = cPickle.dumps(n, cPickle.HIGHEST_PROTOCOL) + nd = pickle.dumps(n, pickle.HIGHEST_PROTOCOL) sz = n + glb_nsz self.WaitForSpace(sz) pos = self.local_head @@ -1198,12 +1213,12 @@ class SQLFetcher(QObject): pos = self.local_tail if len(self.buffer) - pos < glb_nsz: pos = 0 - n = cPickle.loads(self.buffer[pos : pos + glb_nsz]) + n = pickle.loads(self.buffer[pos : pos + glb_nsz]) if n == 0: pos = 0 - n = cPickle.loads(self.buffer[0 : glb_nsz]) + n = pickle.loads(self.buffer[0 : glb_nsz]) pos += glb_nsz - obj = cPickle.loads(self.buffer[pos : pos + n]) + obj = pickle.loads(self.buffer[pos : pos + n]) self.local_tail = pos + n return obj @@ -1512,6 +1527,19 @@ def BranchDataPrep(query): " (" + dsoname(query.value(15)) + ")") return data +def BranchDataPrepWA(query): + data = [] + data.append(query.value(0)) + # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string + data.append("{:>19}".format(query.value(1))) + for i in xrange(2, 8): + data.append(query.value(i)) + data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) + + " (" + dsoname(query.value(11)) + ")" + " -> " + + tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) + + " (" + dsoname(query.value(15)) + ")") + return data + # Branch data model class BranchModel(TreeModel): @@ -1539,7 +1567,11 @@ class BranchModel(TreeModel): " AND evsel_id = " + str(self.event_id) + " ORDER BY samples.id" " LIMIT " + str(glb_chunk_sz)) - self.fetcher = SQLFetcher(glb, sql, BranchDataPrep, self.AddSample) + if pyside_version_1 and sys.version_info[0] == 3: + prep = BranchDataPrepWA + else: + prep = BranchDataPrep + self.fetcher = SQLFetcher(glb, sql, prep, self.AddSample) self.fetcher.done.connect(self.Update) self.fetcher.Fetch(glb_chunk_sz) @@ -2065,14 +2097,6 @@ def IsSelectable(db, table, sql = ""): return False return True -# SQL data preparation - -def SQLTableDataPrep(query, count): - data = [] - for i in xrange(count): - data.append(query.value(i)) - return data - # SQL table data model item class SQLTableItem(): @@ -2096,7 +2120,7 @@ class SQLTableModel(TableModel): self.more = True self.populated = 0 self.column_headers = column_headers - self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): SQLTableDataPrep(x, y), self.AddSample) + self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): self.SQLTableDataPrep(x, y), self.AddSample) self.fetcher.done.connect(self.Update) self.fetcher.Fetch(glb_chunk_sz) @@ -2140,6 +2164,12 @@ class SQLTableModel(TableModel): def columnHeader(self, column): return self.column_headers[column] + def SQLTableDataPrep(self, query, count): + data = [] + for i in xrange(count): + data.append(query.value(i)) + return data + # SQL automatic table data model class SQLAutoTableModel(SQLTableModel): @@ -2168,8 +2198,32 @@ class SQLAutoTableModel(SQLTableModel): QueryExec(query, "SELECT column_name FROM information_schema.columns WHERE table_schema = '" + schema + "' and table_name = '" + select_table_name + "'") while query.next(): column_headers.append(query.value(0)) + if pyside_version_1 and sys.version_info[0] == 3: + if table_name == "samples_view": + self.SQLTableDataPrep = self.samples_view_DataPrep + if table_name == "samples": + self.SQLTableDataPrep = self.samples_DataPrep super(SQLAutoTableModel, self).__init__(glb, sql, column_headers, parent) + def samples_view_DataPrep(self, query, count): + data = [] + data.append(query.value(0)) + # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string + data.append("{:>19}".format(query.value(1))) + for i in xrange(2, count): + data.append(query.value(i)) + return data + + def samples_DataPrep(self, query, count): + data = [] + for i in xrange(9): + data.append(query.value(i)) + # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string + data.append("{:>19}".format(query.value(9))) + for i in xrange(10, count): + data.append(query.value(i)) + return data + # Base class for custom ResizeColumnsToContents class ResizeColumnsToContentsBase(QObject): @@ -2854,9 +2908,13 @@ class LibXED(): ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0) if not ok: return 0, "" + if sys.version_info[0] == 2: + result = inst.buffer.value + else: + result = inst.buffer.value.decode() # Return instruction length and the disassembled instruction text # For now, assume the length is in byte 166 - return inst.xedd[166], inst.buffer.value + return inst.xedd[166], result def TryOpen(file_name): try: @@ -2872,9 +2930,14 @@ def Is64Bit(f): header = f.read(7) f.seek(pos) magic = header[0:4] - eclass = ord(header[4]) - encoding = ord(header[5]) - version = ord(header[6]) + if sys.version_info[0] == 2: + eclass = ord(header[4]) + encoding = ord(header[5]) + version = ord(header[6]) + else: + eclass = header[4] + encoding = header[5] + version = header[6] if magic == chr(127) + "ELF" and eclass > 0 and eclass < 3 and encoding > 0 and encoding < 3 and version == 1: result = True if eclass == 2 else False return result @@ -2973,7 +3036,7 @@ class DBRef(): def Main(): if (len(sys.argv) < 2): - print >> sys.stderr, "Usage is: exported-sql-viewer.py {<database name> | --help-only}" + printerr("Usage is: exported-sql-viewer.py {<database name> | --help-only}"); raise Exception("Too few arguments") dbname = sys.argv[1] @@ -2986,8 +3049,8 @@ def Main(): is_sqlite3 = False try: - f = open(dbname) - if f.read(15) == "SQLite format 3": + f = open(dbname, "rb") + if f.read(15) == b'SQLite format 3': is_sqlite3 = True f.close() except: diff --git a/tools/perf/tests/attr/test-record-C0 b/tools/perf/tests/attr/test-record-C0 index cb0a3138fa54..93818054ae20 100644 --- a/tools/perf/tests/attr/test-record-C0 +++ b/tools/perf/tests/attr/test-record-C0 @@ -1,6 +1,6 @@ [config] command = record -args = -C 0 kill >/dev/null 2>&1 +args = --no-bpf-event -C 0 kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-basic b/tools/perf/tests/attr/test-record-basic index 85a23cf35ba1..b0ca42a5ecc9 100644 --- a/tools/perf/tests/attr/test-record-basic +++ b/tools/perf/tests/attr/test-record-basic @@ -1,6 +1,6 @@ [config] command = record -args = kill >/dev/null 2>&1 +args = --no-bpf-event kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-branch-any b/tools/perf/tests/attr/test-record-branch-any index 81f839e2fad0..1a99b3ce6b89 100644 --- a/tools/perf/tests/attr/test-record-branch-any +++ b/tools/perf/tests/attr/test-record-branch-any @@ -1,6 +1,6 @@ [config] command = record -args = -b kill >/dev/null 2>&1 +args = --no-bpf-event -b kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-branch-filter-any b/tools/perf/tests/attr/test-record-branch-filter-any index 357421f4dfce..709768b508c6 100644 --- a/tools/perf/tests/attr/test-record-branch-filter-any +++ b/tools/perf/tests/attr/test-record-branch-filter-any @@ -1,6 +1,6 @@ [config] command = record -args = -j any kill >/dev/null 2>&1 +args = --no-bpf-event -j any kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_call b/tools/perf/tests/attr/test-record-branch-filter-any_call index dbc55f2ab845..f943221f7825 100644 --- a/tools/perf/tests/attr/test-record-branch-filter-any_call +++ b/tools/perf/tests/attr/test-record-branch-filter-any_call @@ -1,6 +1,6 @@ [config] command = record -args = -j any_call kill >/dev/null 2>&1 +args = --no-bpf-event -j any_call kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_ret b/tools/perf/tests/attr/test-record-branch-filter-any_ret index a0824ff8e131..fd4f5b4154a9 100644 --- a/tools/perf/tests/attr/test-record-branch-filter-any_ret +++ b/tools/perf/tests/attr/test-record-branch-filter-any_ret @@ -1,6 +1,6 @@ [config] command = record -args = -j any_ret kill >/dev/null 2>&1 +args = --no-bpf-event -j any_ret kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-branch-filter-hv b/tools/perf/tests/attr/test-record-branch-filter-hv index f34d6f120181..4e52d685ebe1 100644 --- a/tools/perf/tests/attr/test-record-branch-filter-hv +++ b/tools/perf/tests/attr/test-record-branch-filter-hv @@ -1,6 +1,6 @@ [config] command = record -args = -j hv kill >/dev/null 2>&1 +args = --no-bpf-event -j hv kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-branch-filter-ind_call b/tools/perf/tests/attr/test-record-branch-filter-ind_call index b86a35232248..e08c6ab3796e 100644 --- a/tools/perf/tests/attr/test-record-branch-filter-ind_call +++ b/tools/perf/tests/attr/test-record-branch-filter-ind_call @@ -1,6 +1,6 @@ [config] command = record -args = -j ind_call kill >/dev/null 2>&1 +args = --no-bpf-event -j ind_call kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-branch-filter-k b/tools/perf/tests/attr/test-record-branch-filter-k index d3fbc5e1858a..b4b98f84fc2f 100644 --- a/tools/perf/tests/attr/test-record-branch-filter-k +++ b/tools/perf/tests/attr/test-record-branch-filter-k @@ -1,6 +1,6 @@ [config] command = record -args = -j k kill >/dev/null 2>&1 +args = --no-bpf-event -j k kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-branch-filter-u b/tools/perf/tests/attr/test-record-branch-filter-u index a318f0dda173..fb9610edbb0d 100644 --- a/tools/perf/tests/attr/test-record-branch-filter-u +++ b/tools/perf/tests/attr/test-record-branch-filter-u @@ -1,6 +1,6 @@ [config] command = record -args = -j u kill >/dev/null 2>&1 +args = --no-bpf-event -j u kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-count b/tools/perf/tests/attr/test-record-count index 34f6cc577263..5e9b9019d786 100644 --- a/tools/perf/tests/attr/test-record-count +++ b/tools/perf/tests/attr/test-record-count @@ -1,6 +1,6 @@ [config] command = record -args = -c 123 kill >/dev/null 2>&1 +args = --no-bpf-event -c 123 kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-data b/tools/perf/tests/attr/test-record-data index a9cf2233b0ce..a99bb13149c2 100644 --- a/tools/perf/tests/attr/test-record-data +++ b/tools/perf/tests/attr/test-record-data @@ -1,6 +1,6 @@ [config] command = record -args = -d kill >/dev/null 2>&1 +args = --no-bpf-event -d kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-freq b/tools/perf/tests/attr/test-record-freq index bf4cb459f0d5..89e29f6b2ae0 100644 --- a/tools/perf/tests/attr/test-record-freq +++ b/tools/perf/tests/attr/test-record-freq @@ -1,6 +1,6 @@ [config] command = record -args = -F 100 kill >/dev/null 2>&1 +args = --no-bpf-event -F 100 kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-graph-default b/tools/perf/tests/attr/test-record-graph-default index 0b216e69760c..5d8234d50845 100644 --- a/tools/perf/tests/attr/test-record-graph-default +++ b/tools/perf/tests/attr/test-record-graph-default @@ -1,6 +1,6 @@ [config] command = record -args = -g kill >/dev/null 2>&1 +args = --no-bpf-event -g kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-graph-dwarf b/tools/perf/tests/attr/test-record-graph-dwarf index da2fa73bd0a2..ae92061d611d 100644 --- a/tools/perf/tests/attr/test-record-graph-dwarf +++ b/tools/perf/tests/attr/test-record-graph-dwarf @@ -1,6 +1,6 @@ [config] command = record -args = --call-graph dwarf -- kill >/dev/null 2>&1 +args = --no-bpf-event --call-graph dwarf -- kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-graph-fp b/tools/perf/tests/attr/test-record-graph-fp index 625d190bb798..5630521c0b0f 100644 --- a/tools/perf/tests/attr/test-record-graph-fp +++ b/tools/perf/tests/attr/test-record-graph-fp @@ -1,6 +1,6 @@ [config] command = record -args = --call-graph fp kill >/dev/null 2>&1 +args = --no-bpf-event --call-graph fp kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group index 618ba1c17474..14ee60fd3f41 100644 --- a/tools/perf/tests/attr/test-record-group +++ b/tools/perf/tests/attr/test-record-group @@ -1,6 +1,6 @@ [config] command = record -args = --group -e cycles,instructions kill >/dev/null 2>&1 +args = --no-bpf-event --group -e cycles,instructions kill >/dev/null 2>&1 ret = 1 [event-1:base-record] diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling index f0729c454f16..300b9f7e6d69 100644 --- a/tools/perf/tests/attr/test-record-group-sampling +++ b/tools/perf/tests/attr/test-record-group-sampling @@ -1,6 +1,6 @@ [config] command = record -args = -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1 +args = --no-bpf-event -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1 ret = 1 [event-1:base-record] diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1 index 48e8bd12fe46..3ffe246e0228 100644 --- a/tools/perf/tests/attr/test-record-group1 +++ b/tools/perf/tests/attr/test-record-group1 @@ -1,6 +1,6 @@ [config] command = record -args = -e '{cycles,instructions}' kill >/dev/null 2>&1 +args = --no-bpf-event -e '{cycles,instructions}' kill >/dev/null 2>&1 ret = 1 [event-1:base-record] diff --git a/tools/perf/tests/attr/test-record-no-buffering b/tools/perf/tests/attr/test-record-no-buffering index aa3956d8fe20..583dcbb078ba 100644 --- a/tools/perf/tests/attr/test-record-no-buffering +++ b/tools/perf/tests/attr/test-record-no-buffering @@ -1,6 +1,6 @@ [config] command = record -args = --no-buffering kill >/dev/null 2>&1 +args = --no-bpf-event --no-buffering kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/attr/test-record-no-inherit index 560943decb87..15d1dc162e1c 100644 --- a/tools/perf/tests/attr/test-record-no-inherit +++ b/tools/perf/tests/attr/test-record-no-inherit @@ -1,6 +1,6 @@ [config] command = record -args = -i kill >/dev/null 2>&1 +args = --no-bpf-event -i kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-no-samples b/tools/perf/tests/attr/test-record-no-samples index 8eb73ab639e0..596fbd6d5a2c 100644 --- a/tools/perf/tests/attr/test-record-no-samples +++ b/tools/perf/tests/attr/test-record-no-samples @@ -1,6 +1,6 @@ [config] command = record -args = -n kill >/dev/null 2>&1 +args = --no-bpf-event -n kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-period b/tools/perf/tests/attr/test-record-period index 69bc748f0f27..119101154c5e 100644 --- a/tools/perf/tests/attr/test-record-period +++ b/tools/perf/tests/attr/test-record-period @@ -1,6 +1,6 @@ [config] command = record -args = -c 100 -P kill >/dev/null 2>&1 +args = --no-bpf-event -c 100 -P kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-raw b/tools/perf/tests/attr/test-record-raw index a188a614a44c..13a5f7860c78 100644 --- a/tools/perf/tests/attr/test-record-raw +++ b/tools/perf/tests/attr/test-record-raw @@ -1,6 +1,6 @@ [config] command = record -args = -R kill >/dev/null 2>&1 +args = --no-bpf-event -R kill >/dev/null 2>&1 ret = 1 [event:base-record] diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index 6d598cc071ae..1a9c3becf5ff 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -18,7 +18,7 @@ static void testcase(void) int i; for (i = 0; i < NR_ITERS; i++) { - char proc_name[10]; + char proc_name[15]; snprintf(proc_name, sizeof(proc_name), "p:%d\n", i); prctl(PR_SET_NAME, proc_name); diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index ea7acf403727..71f60c0f9faa 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -85,5 +85,6 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes if (perf_evsel__test_field(evsel, "target_cpu", 4, true)) ret = -1; + perf_evsel__delete(evsel); return ret; } diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 01f0706995a9..9acc1e80b936 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -19,7 +19,7 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) const char *p; const char **other; double val; - int ret; + int i, ret; struct parse_ctx ctx; int num_other; @@ -56,6 +56,9 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) TEST_ASSERT_VAL("find other", !strcmp(other[1], "BAZ")); TEST_ASSERT_VAL("find other", !strcmp(other[2], "BOZO")); TEST_ASSERT_VAL("find other", other[3] == NULL); + + for (i = 0; i < num_other; i++) + free((void *)other[i]); free((void *)other); return 0; diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index c531e6deb104..493ecb611540 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -45,7 +45,7 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int if (IS_ERR(evsel)) { tracing_path__strerror_open_tp(errno, errbuf, sizeof(errbuf), "syscalls", "sys_enter_openat"); pr_debug("%s\n", errbuf); - goto out_thread_map_delete; + goto out_cpu_map_delete; } if (perf_evsel__open(evsel, cpus, threads) < 0) { @@ -119,6 +119,8 @@ out_close_fd: perf_evsel__close_fd(evsel); out_evsel_delete: perf_evsel__delete(evsel); +out_cpu_map_delete: + cpu_map__put(cpus); out_thread_map_delete: thread_map__put(threads); return err; diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh index 32bac9c0d694..5f5eefcb3c74 100755 --- a/tools/perf/trace/beauty/mmap_flags.sh +++ b/tools/perf/trace/beauty/mmap_flags.sh @@ -1,15 +1,18 @@ #!/bin/sh # SPDX-License-Identifier: LGPL-2.1 -if [ $# -ne 2 ] ; then +if [ $# -ne 3 ] ; then [ $# -eq 1 ] && hostarch=$1 || hostarch=`uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/` + linux_header_dir=tools/include/uapi/linux header_dir=tools/include/uapi/asm-generic arch_header_dir=tools/arch/${hostarch}/include/uapi/asm else - header_dir=$1 - arch_header_dir=$2 + linux_header_dir=$1 + header_dir=$2 + arch_header_dir=$3 fi +linux_mman=${linux_header_dir}/mman.h arch_mman=${arch_header_dir}/mman.h # those in egrep -vw are flags, we want just the bits @@ -20,6 +23,11 @@ egrep -q $regex ${arch_mman} && \ (egrep $regex ${arch_mman} | \ sed -r "s/$regex/\2 \1/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n") +egrep -q $regex ${linux_mman} && \ +(egrep $regex ${linux_mman} | \ + egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \ + sed -r "s/$regex/\2 \1/g" | \ + xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n") ([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman}) && (egrep $regex ${header_dir}/mman-common.h | \ egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \ diff --git a/tools/perf/trace/beauty/renameat.c b/tools/perf/trace/beauty/renameat.c index 6dab340cc506..852d2e271833 100644 --- a/tools/perf/trace/beauty/renameat.c +++ b/tools/perf/trace/beauty/renameat.c @@ -2,7 +2,6 @@ // Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> #include "trace/beauty/beauty.h" -#include <uapi/linux/fs.h> static size_t renameat2__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix) { diff --git a/tools/perf/trace/strace/groups/string b/tools/perf/trace/strace/groups/string new file mode 100644 index 000000000000..c87129a3e3c4 --- /dev/null +++ b/tools/perf/trace/strace/groups/string @@ -0,0 +1,65 @@ +access +acct +add_key +chdir +chmod +chown +chroot +creat +delete_module +execve +execveat +faccessat +fchmodat +fchownat +fgetxattr +finit_module +fremovexattr +fsetxattr +futimesat +getxattr +inotify_add_watch +lchown +lgetxattr +link +linkat +listxattr +llistxattr +lremovexattr +lsetxattr +lstat +memfd_create +mkdir +mkdirat +mknod +mknodat +mq_open +mq_timedsend +mq_unlink +name_to_handle_at +newfstatat +open +openat +pivot_root +pwrite64 +quotactl +readlink +readlinkat +removexattr +rename +renameat +renameat2 +request_key +rmdir +setxattr +stat +statfs +statx +swapoff +swapon +symlink +symlinkat +truncate +unlink +unlinkat +utimensat diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 4f75561424ed..4ad37d8c7d6a 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -611,14 +611,16 @@ void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence) browser->top = browser->entries; break; case SEEK_CUR: - browser->top = browser->top + browser->top_idx + offset; + browser->top = (char **)browser->top + offset; break; case SEEK_END: - browser->top = browser->top + browser->nr_entries - 1 + offset; + browser->top = (char **)browser->entries + browser->nr_entries - 1 + offset; break; default: return; } + assert((char **)browser->top < (char **)browser->entries + browser->nr_entries); + assert((char **)browser->top >= (char **)browser->entries); } unsigned int ui_browser__argv_refresh(struct ui_browser *browser) @@ -630,7 +632,9 @@ unsigned int ui_browser__argv_refresh(struct ui_browser *browser) browser->top = browser->entries; pos = (char **)browser->top; - while (idx < browser->nr_entries) { + while (idx < browser->nr_entries && + row < (unsigned)SLtt_Screen_Rows - 1) { + assert(pos < (char **)browser->entries + browser->nr_entries); if (!browser->filter || !browser->filter(browser, *pos)) { ui_browser__gotorc(browser, row, 0); browser->write(browser, pos, row); diff --git a/tools/perf/ui/browsers/Build b/tools/perf/ui/browsers/Build index 8fee56b46502..fdf86f7981ca 100644 --- a/tools/perf/ui/browsers/Build +++ b/tools/perf/ui/browsers/Build @@ -3,6 +3,7 @@ perf-y += hists.o perf-y += map.o perf-y += scripts.o perf-y += header.o +perf-y += res_sample.o CFLAGS_annotate.o += -DENABLE_SLFUTURE_CONST CFLAGS_hists.o += -DENABLE_SLFUTURE_CONST diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 35bdfd8b1e71..98d934a36d86 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -750,7 +750,7 @@ static int annotate_browser__run(struct annotate_browser *browser, continue; case 'r': { - script_browse(NULL); + script_browse(NULL, NULL); continue; } case 'k': diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index aef800d97ea1..3421ecbdd3f0 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -7,6 +7,7 @@ #include <string.h> #include <linux/rbtree.h> #include <sys/ttydefaults.h> +#include <linux/time64.h> #include "../../util/callchain.h" #include "../../util/evsel.h" @@ -30,6 +31,7 @@ #include "srcline.h" #include "string2.h" #include "units.h" +#include "time-utils.h" #include "sane_ctype.h" @@ -1224,6 +1226,8 @@ void hist_browser__init_hpp(void) hist_browser__hpp_color_overhead_guest_us; perf_hpp__format[PERF_HPP__OVERHEAD_ACC].color = hist_browser__hpp_color_overhead_acc; + + res_sample_init(); } static int hist_browser__show_entry(struct hist_browser *browser, @@ -2338,9 +2342,12 @@ close_file_and_continue: } struct popup_action { + unsigned long time; struct thread *thread; struct map_symbol ms; int socket; + struct perf_evsel *evsel; + enum rstype rstype; int (*fn)(struct hist_browser *browser, struct popup_action *act); }; @@ -2527,46 +2534,137 @@ static int do_run_script(struct hist_browser *browser __maybe_unused, struct popup_action *act) { - char script_opt[64]; - memset(script_opt, 0, sizeof(script_opt)); + char *script_opt; + int len; + int n = 0; + len = 100; + if (act->thread) + len += strlen(thread__comm_str(act->thread)); + else if (act->ms.sym) + len += strlen(act->ms.sym->name); + script_opt = malloc(len); + if (!script_opt) + return -1; + + script_opt[0] = 0; if (act->thread) { - scnprintf(script_opt, sizeof(script_opt), " -c %s ", + n = scnprintf(script_opt, len, " -c %s ", thread__comm_str(act->thread)); } else if (act->ms.sym) { - scnprintf(script_opt, sizeof(script_opt), " -S %s ", + n = scnprintf(script_opt, len, " -S %s ", act->ms.sym->name); } - script_browse(script_opt); + if (act->time) { + char start[32], end[32]; + unsigned long starttime = act->time; + unsigned long endtime = act->time + symbol_conf.time_quantum; + + if (starttime == endtime) { /* Display 1ms as fallback */ + starttime -= 1*NSEC_PER_MSEC; + endtime += 1*NSEC_PER_MSEC; + } + timestamp__scnprintf_usec(starttime, start, sizeof start); + timestamp__scnprintf_usec(endtime, end, sizeof end); + n += snprintf(script_opt + n, len - n, " --time %s,%s", start, end); + } + + script_browse(script_opt, act->evsel); + free(script_opt); return 0; } static int -add_script_opt(struct hist_browser *browser __maybe_unused, +do_res_sample_script(struct hist_browser *browser __maybe_unused, + struct popup_action *act) +{ + struct hist_entry *he; + + he = hist_browser__selected_entry(browser); + res_sample_browse(he->res_samples, he->num_res, act->evsel, act->rstype); + return 0; +} + +static int +add_script_opt_2(struct hist_browser *browser __maybe_unused, struct popup_action *act, char **optstr, - struct thread *thread, struct symbol *sym) + struct thread *thread, struct symbol *sym, + struct perf_evsel *evsel, const char *tstr) { + if (thread) { - if (asprintf(optstr, "Run scripts for samples of thread [%s]", - thread__comm_str(thread)) < 0) + if (asprintf(optstr, "Run scripts for samples of thread [%s]%s", + thread__comm_str(thread), tstr) < 0) return 0; } else if (sym) { - if (asprintf(optstr, "Run scripts for samples of symbol [%s]", - sym->name) < 0) + if (asprintf(optstr, "Run scripts for samples of symbol [%s]%s", + sym->name, tstr) < 0) return 0; } else { - if (asprintf(optstr, "Run scripts for all samples") < 0) + if (asprintf(optstr, "Run scripts for all samples%s", tstr) < 0) return 0; } act->thread = thread; act->ms.sym = sym; + act->evsel = evsel; act->fn = do_run_script; return 1; } static int +add_script_opt(struct hist_browser *browser, + struct popup_action *act, char **optstr, + struct thread *thread, struct symbol *sym, + struct perf_evsel *evsel) +{ + int n, j; + struct hist_entry *he; + + n = add_script_opt_2(browser, act, optstr, thread, sym, evsel, ""); + + he = hist_browser__selected_entry(browser); + if (sort_order && strstr(sort_order, "time")) { + char tstr[128]; + + optstr++; + act++; + j = sprintf(tstr, " in "); + j += timestamp__scnprintf_usec(he->time, tstr + j, + sizeof tstr - j); + j += sprintf(tstr + j, "-"); + timestamp__scnprintf_usec(he->time + symbol_conf.time_quantum, + tstr + j, sizeof tstr - j); + n += add_script_opt_2(browser, act, optstr, thread, sym, + evsel, tstr); + act->time = he->time; + } + return n; +} + +static int +add_res_sample_opt(struct hist_browser *browser __maybe_unused, + struct popup_action *act, char **optstr, + struct res_sample *res_sample, + struct perf_evsel *evsel, + enum rstype type) +{ + if (!res_sample) + return 0; + + if (asprintf(optstr, "Show context for individual samples %s", + type == A_ASM ? "with assembler" : + type == A_SOURCE ? "with source" : "") < 0) + return 0; + + act->fn = do_res_sample_script; + act->evsel = evsel; + act->rstype = type; + return 1; +} + +static int do_switch_data(struct hist_browser *browser __maybe_unused, struct popup_action *act __maybe_unused) { @@ -3031,7 +3129,7 @@ skip_annotation: nr_options += add_script_opt(browser, &actions[nr_options], &options[nr_options], - thread, NULL); + thread, NULL, evsel); } /* * Note that browser->selection != NULL @@ -3046,11 +3144,24 @@ skip_annotation: nr_options += add_script_opt(browser, &actions[nr_options], &options[nr_options], - NULL, browser->selection->sym); + NULL, browser->selection->sym, + evsel); } } nr_options += add_script_opt(browser, &actions[nr_options], - &options[nr_options], NULL, NULL); + &options[nr_options], NULL, NULL, evsel); + nr_options += add_res_sample_opt(browser, &actions[nr_options], + &options[nr_options], + hist_browser__selected_entry(browser)->res_samples, + evsel, A_NORMAL); + nr_options += add_res_sample_opt(browser, &actions[nr_options], + &options[nr_options], + hist_browser__selected_entry(browser)->res_samples, + evsel, A_ASM); + nr_options += add_res_sample_opt(browser, &actions[nr_options], + &options[nr_options], + hist_browser__selected_entry(browser)->res_samples, + evsel, A_SOURCE); nr_options += add_switch_opt(browser, &actions[nr_options], &options[nr_options]); skip_scripting: diff --git a/tools/perf/ui/browsers/res_sample.c b/tools/perf/ui/browsers/res_sample.c new file mode 100644 index 000000000000..c0dd73176d42 --- /dev/null +++ b/tools/perf/ui/browsers/res_sample.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Display a menu with individual samples to browse with perf script */ +#include "util.h" +#include "hist.h" +#include "evsel.h" +#include "hists.h" +#include "sort.h" +#include "config.h" +#include "time-utils.h" +#include <linux/time64.h> + +static u64 context_len = 10 * NSEC_PER_MSEC; + +static int res_sample_config(const char *var, const char *value, void *data __maybe_unused) +{ + if (!strcmp(var, "samples.context")) + return perf_config_u64(&context_len, var, value); + return 0; +} + +void res_sample_init(void) +{ + perf_config(res_sample_config, NULL); +} + +int res_sample_browse(struct res_sample *res_samples, int num_res, + struct perf_evsel *evsel, enum rstype rstype) +{ + char **names; + int i, n; + int choice; + char *cmd; + char pbuf[256], tidbuf[32], cpubuf[32]; + const char *perf = perf_exe(pbuf, sizeof pbuf); + char trange[128], tsample[64]; + struct res_sample *r; + char extra_format[256]; + + names = calloc(num_res, sizeof(char *)); + if (!names) + return -1; + for (i = 0; i < num_res; i++) { + char tbuf[64]; + + timestamp__scnprintf_nsec(res_samples[i].time, tbuf, sizeof tbuf); + if (asprintf(&names[i], "%s: CPU %d tid %d", tbuf, + res_samples[i].cpu, res_samples[i].tid) < 0) { + while (--i >= 0) + free(names[i]); + free(names); + return -1; + } + } + choice = ui__popup_menu(num_res, names); + for (i = 0; i < num_res; i++) + free(names[i]); + free(names); + + if (choice < 0 || choice >= num_res) + return -1; + r = &res_samples[choice]; + + n = timestamp__scnprintf_nsec(r->time - context_len, trange, sizeof trange); + trange[n++] = ','; + timestamp__scnprintf_nsec(r->time + context_len, trange + n, sizeof trange - n); + + timestamp__scnprintf_nsec(r->time, tsample, sizeof tsample); + + attr_to_script(extra_format, &evsel->attr); + + if (asprintf(&cmd, "%s script %s%s --time %s %s%s %s%s --ns %s %s %s %s %s | less +/%s", + perf, + input_name ? "-i " : "", + input_name ? input_name : "", + trange, + r->cpu >= 0 ? "--cpu " : "", + r->cpu >= 0 ? (sprintf(cpubuf, "%d", r->cpu), cpubuf) : "", + r->tid ? "--tid " : "", + r->tid ? (sprintf(tidbuf, "%d", r->tid), tidbuf) : "", + extra_format, + rstype == A_ASM ? "-F +insn --xed" : + rstype == A_SOURCE ? "-F +srcline,+srccode" : "", + symbol_conf.inline_name ? "--inline" : "", + "--show-lost-events ", + r->tid ? "--show-switch-events --show-task-events " : "", + tsample) < 0) + return -1; + run_script(cmd); + free(cmd); + return 0; +} diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c index 90a32ac69e76..27cf3ab88d13 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -1,34 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 -#include <elf.h> -#include <inttypes.h> -#include <sys/ttydefaults.h> -#include <string.h> #include "../../util/sort.h" #include "../../util/util.h" #include "../../util/hist.h" #include "../../util/debug.h" #include "../../util/symbol.h" #include "../browser.h" -#include "../helpline.h" #include "../libslang.h" - -/* 2048 lines should be enough for a script output */ -#define MAX_LINES 2048 - -/* 160 bytes for one output line */ -#define AVERAGE_LINE_LEN 160 - -struct script_line { - struct list_head node; - char line[AVERAGE_LINE_LEN]; -}; - -struct perf_script_browser { - struct ui_browser b; - struct list_head entries; - const char *script_name; - int nr_lines; -}; +#include "config.h" #define SCRIPT_NAMELEN 128 #define SCRIPT_MAX_NO 64 @@ -40,149 +18,169 @@ struct perf_script_browser { */ #define SCRIPT_FULLPATH_LEN 256 +struct script_config { + const char **names; + char **paths; + int index; + const char *perf; + char extra_format[256]; +}; + +void attr_to_script(char *extra_format, struct perf_event_attr *attr) +{ + extra_format[0] = 0; + if (attr->read_format & PERF_FORMAT_GROUP) + strcat(extra_format, " -F +metric"); + if (attr->sample_type & PERF_SAMPLE_BRANCH_STACK) + strcat(extra_format, " -F +brstackinsn --xed"); + if (attr->sample_type & PERF_SAMPLE_REGS_INTR) + strcat(extra_format, " -F +iregs"); + if (attr->sample_type & PERF_SAMPLE_REGS_USER) + strcat(extra_format, " -F +uregs"); + if (attr->sample_type & PERF_SAMPLE_PHYS_ADDR) + strcat(extra_format, " -F +phys_addr"); +} + +static int add_script_option(const char *name, const char *opt, + struct script_config *c) +{ + c->names[c->index] = name; + if (asprintf(&c->paths[c->index], + "%s script %s -F +metric %s %s", + c->perf, opt, symbol_conf.inline_name ? " --inline" : "", + c->extra_format) < 0) + return -1; + c->index++; + return 0; +} + +static int scripts_config(const char *var, const char *value, void *data) +{ + struct script_config *c = data; + + if (!strstarts(var, "scripts.")) + return -1; + if (c->index >= SCRIPT_MAX_NO) + return -1; + c->names[c->index] = strdup(var + 7); + if (!c->names[c->index]) + return -1; + if (asprintf(&c->paths[c->index], "%s %s", value, + c->extra_format) < 0) + return -1; + c->index++; + return 0; +} + /* * When success, will copy the full path of the selected script * into the buffer pointed by script_name, and return 0. * Return -1 on failure. */ -static int list_scripts(char *script_name) +static int list_scripts(char *script_name, bool *custom, + struct perf_evsel *evsel) { - char *buf, *names[SCRIPT_MAX_NO], *paths[SCRIPT_MAX_NO]; - int i, num, choice, ret = -1; + char *buf, *paths[SCRIPT_MAX_NO], *names[SCRIPT_MAX_NO]; + int i, num, choice; + int ret = 0; + int max_std, custom_perf; + char pbuf[256]; + const char *perf = perf_exe(pbuf, sizeof pbuf); + struct script_config scriptc = { + .names = (const char **)names, + .paths = paths, + .perf = perf + }; + + script_name[0] = 0; /* Preset the script name to SCRIPT_NAMELEN */ buf = malloc(SCRIPT_MAX_NO * (SCRIPT_NAMELEN + SCRIPT_FULLPATH_LEN)); if (!buf) - return ret; + return -1; - for (i = 0; i < SCRIPT_MAX_NO; i++) { - names[i] = buf + i * (SCRIPT_NAMELEN + SCRIPT_FULLPATH_LEN); + if (evsel) + attr_to_script(scriptc.extra_format, &evsel->attr); + add_script_option("Show individual samples", "", &scriptc); + add_script_option("Show individual samples with assembler", "-F +insn --xed", + &scriptc); + add_script_option("Show individual samples with source", "-F +srcline,+srccode", + &scriptc); + perf_config(scripts_config, &scriptc); + custom_perf = scriptc.index; + add_script_option("Show samples with custom perf script arguments", "", &scriptc); + i = scriptc.index; + max_std = i; + + for (; i < SCRIPT_MAX_NO; i++) { + names[i] = buf + (i - max_std) * (SCRIPT_NAMELEN + SCRIPT_FULLPATH_LEN); paths[i] = names[i] + SCRIPT_NAMELEN; } - num = find_scripts(names, paths); - if (num > 0) { - choice = ui__popup_menu(num, names); - if (choice < num && choice >= 0) { - strcpy(script_name, paths[choice]); - ret = 0; - } + num = find_scripts(names + max_std, paths + max_std, SCRIPT_MAX_NO - max_std, + SCRIPT_FULLPATH_LEN); + if (num < 0) + num = 0; + choice = ui__popup_menu(num + max_std, (char * const *)names); + if (choice < 0) { + ret = -1; + goto out; } + if (choice == custom_perf) { + char script_args[50]; + int key = ui_browser__input_window("perf script command", + "Enter perf script command line (without perf script prefix)", + script_args, "", 0); + if (key != K_ENTER) + return -1; + sprintf(script_name, "%s script %s", perf, script_args); + } else if (choice < num + max_std) { + strcpy(script_name, paths[choice]); + } + *custom = choice >= max_std; +out: free(buf); + for (i = 0; i < max_std; i++) + free(paths[i]); return ret; } -static void script_browser__write(struct ui_browser *browser, - void *entry, int row) +void run_script(char *cmd) { - struct script_line *sline = list_entry(entry, struct script_line, node); - bool current_entry = ui_browser__is_current_entry(browser, row); - - ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED : - HE_COLORSET_NORMAL); - - ui_browser__write_nstring(browser, sline->line, browser->width); + pr_debug("Running %s\n", cmd); + SLang_reset_tty(); + if (system(cmd) < 0) + pr_warning("Cannot run %s\n", cmd); + /* + * SLang doesn't seem to reset the whole terminal, so be more + * forceful to get back to the original state. + */ + printf("\033[c\033[H\033[J"); + fflush(stdout); + SLang_init_tty(0, 0, 0); + SLsmg_refresh(); } -static int script_browser__run(struct perf_script_browser *browser) +int script_browse(const char *script_opt, struct perf_evsel *evsel) { - int key; + char *cmd, script_name[SCRIPT_FULLPATH_LEN]; + bool custom = false; - if (ui_browser__show(&browser->b, browser->script_name, - "Press ESC to exit") < 0) + memset(script_name, 0, SCRIPT_FULLPATH_LEN); + if (list_scripts(script_name, &custom, evsel)) return -1; - while (1) { - key = ui_browser__run(&browser->b, 0); - - /* We can add some special key handling here if needed */ - break; - } - - ui_browser__hide(&browser->b); - return key; -} - - -int script_browse(const char *script_opt) -{ - char cmd[SCRIPT_FULLPATH_LEN*2], script_name[SCRIPT_FULLPATH_LEN]; - char *line = NULL; - size_t len = 0; - ssize_t retlen; - int ret = -1, nr_entries = 0; - FILE *fp; - void *buf; - struct script_line *sline; - - struct perf_script_browser script = { - .b = { - .refresh = ui_browser__list_head_refresh, - .seek = ui_browser__list_head_seek, - .write = script_browser__write, - }, - .script_name = script_name, - }; - - INIT_LIST_HEAD(&script.entries); - - /* Save each line of the output in one struct script_line object. */ - buf = zalloc((sizeof(*sline)) * MAX_LINES); - if (!buf) + if (asprintf(&cmd, "%s%s %s %s%s 2>&1 | less", + custom ? "perf script -s " : "", + script_name, + script_opt ? script_opt : "", + input_name ? "-i " : "", + input_name ? input_name : "") < 0) return -1; - sline = buf; - - memset(script_name, 0, SCRIPT_FULLPATH_LEN); - if (list_scripts(script_name)) - goto exit; - - sprintf(cmd, "perf script -s %s ", script_name); - if (script_opt) - strcat(cmd, script_opt); + run_script(cmd); + free(cmd); - if (input_name) { - strcat(cmd, " -i "); - strcat(cmd, input_name); - } - - strcat(cmd, " 2>&1"); - - fp = popen(cmd, "r"); - if (!fp) - goto exit; - - while ((retlen = getline(&line, &len, fp)) != -1) { - strncpy(sline->line, line, AVERAGE_LINE_LEN); - - /* If one output line is very large, just cut it short */ - if (retlen >= AVERAGE_LINE_LEN) { - sline->line[AVERAGE_LINE_LEN - 1] = '\0'; - sline->line[AVERAGE_LINE_LEN - 2] = '\n'; - } - list_add_tail(&sline->node, &script.entries); - - if (script.b.width < retlen) - script.b.width = retlen; - - if (nr_entries++ >= MAX_LINES - 1) - break; - sline++; - } - - if (script.b.width > AVERAGE_LINE_LEN) - script.b.width = AVERAGE_LINE_LEN; - - free(line); - pclose(fp); - - script.nr_lines = nr_entries; - script.b.nr_entries = nr_entries; - script.b.entries = &script.entries; - - ret = script_browser__run(&script); -exit: - free(buf); - return ret; + return 0; } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 5f6dbbf5d749..09762985c713 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -10,6 +10,10 @@ #include <errno.h> #include <inttypes.h> #include <libgen.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> +#include <linux/btf.h> #include "util.h" #include "ui/ui.h" #include "sort.h" @@ -24,6 +28,7 @@ #include "annotate.h" #include "evsel.h" #include "evlist.h" +#include "bpf-event.h" #include "block-range.h" #include "string2.h" #include "arch/common.h" @@ -31,6 +36,7 @@ #include <pthread.h> #include <linux/bitops.h> #include <linux/kernel.h> +#include <bpf/libbpf.h> /* FIXME: For the HE_COLORSET */ #include "ui/browser.h" @@ -1615,6 +1621,9 @@ int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map * " --vmlinux vmlinux\n", build_id_msg ?: ""); } break; + case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF: + scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation"); + break; default: scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum); break; @@ -1674,6 +1683,156 @@ fallback: return 0; } +#if defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) +#define PACKAGE "perf" +#include <bfd.h> +#include <dis-asm.h> + +static int symbol__disassemble_bpf(struct symbol *sym, + struct annotate_args *args) +{ + struct annotation *notes = symbol__annotation(sym); + struct annotation_options *opts = args->options; + struct bpf_prog_info_linear *info_linear; + struct bpf_prog_linfo *prog_linfo = NULL; + struct bpf_prog_info_node *info_node; + int len = sym->end - sym->start; + disassembler_ftype disassemble; + struct map *map = args->ms.map; + struct disassemble_info info; + struct dso *dso = map->dso; + int pc = 0, count, sub_id; + struct btf *btf = NULL; + char tpath[PATH_MAX]; + size_t buf_size; + int nr_skip = 0; + int ret = -1; + char *buf; + bfd *bfdf; + FILE *s; + + if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO) + return -1; + + pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__, + sym->name, sym->start, sym->end - sym->start); + + memset(tpath, 0, sizeof(tpath)); + perf_exe(tpath, sizeof(tpath)); + + bfdf = bfd_openr(tpath, NULL); + assert(bfdf); + assert(bfd_check_format(bfdf, bfd_object)); + + s = open_memstream(&buf, &buf_size); + if (!s) + goto out; + init_disassemble_info(&info, s, + (fprintf_ftype) fprintf); + + info.arch = bfd_get_arch(bfdf); + info.mach = bfd_get_mach(bfdf); + + info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env, + dso->bpf_prog.id); + if (!info_node) + goto out; + info_linear = info_node->info_linear; + sub_id = dso->bpf_prog.sub_id; + + info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns); + info.buffer_length = info_linear->info.jited_prog_len; + + if (info_linear->info.nr_line_info) + prog_linfo = bpf_prog_linfo__new(&info_linear->info); + + if (info_linear->info.btf_id) { + struct btf_node *node; + + node = perf_env__find_btf(dso->bpf_prog.env, + info_linear->info.btf_id); + if (node) + btf = btf__new((__u8 *)(node->data), + node->data_size); + } + + disassemble_init_for_target(&info); + +#ifdef DISASM_FOUR_ARGS_SIGNATURE + disassemble = disassembler(info.arch, + bfd_big_endian(bfdf), + info.mach, + bfdf); +#else + disassemble = disassembler(bfdf); +#endif + assert(disassemble); + + fflush(s); + do { + const struct bpf_line_info *linfo = NULL; + struct disasm_line *dl; + size_t prev_buf_size; + const char *srcline; + u64 addr; + + addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id]; + count = disassemble(pc, &info); + + if (prog_linfo) + linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo, + addr, sub_id, + nr_skip); + + if (linfo && btf) { + srcline = btf__name_by_offset(btf, linfo->line_off); + nr_skip++; + } else + srcline = NULL; + + fprintf(s, "\n"); + prev_buf_size = buf_size; + fflush(s); + + if (!opts->hide_src_code && srcline) { + args->offset = -1; + args->line = strdup(srcline); + args->line_nr = 0; + args->ms.sym = sym; + dl = disasm_line__new(args); + if (dl) { + annotation_line__add(&dl->al, + ¬es->src->source); + } + } + + args->offset = pc; + args->line = buf + prev_buf_size; + args->line_nr = 0; + args->ms.sym = sym; + dl = disasm_line__new(args); + if (dl) + annotation_line__add(&dl->al, ¬es->src->source); + + pc += count; + } while (count > 0 && pc < len); + + ret = 0; +out: + free(prog_linfo); + free(btf); + fclose(s); + bfd_close(bfdf); + return ret; +} +#else // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) +static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused, + struct annotate_args *args __maybe_unused) +{ + return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF; +} +#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) + static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) { struct annotation_options *opts = args->options; @@ -1701,7 +1860,9 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) pr_debug("annotating [%p] %30s : [%p] %30s\n", dso, dso->long_name, sym, sym->name); - if (dso__is_kcore(dso)) { + if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) { + return symbol__disassemble_bpf(sym, args); + } else if (dso__is_kcore(dso)) { kce.kcore_filename = symfs_filename; kce.addr = map__rip_2objdump(map, sym->start); kce.offs = sym->start; diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index df34fe483164..5bc0cf655d37 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -369,6 +369,7 @@ enum symbol_disassemble_errno { __SYMBOL_ANNOTATE_ERRNO__START = -10000, SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX = __SYMBOL_ANNOTATE_ERRNO__START, + SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF, __SYMBOL_ANNOTATE_ERRNO__END, }; diff --git a/tools/perf/util/archinsn.h b/tools/perf/util/archinsn.h new file mode 100644 index 000000000000..448cbb6b8d7e --- /dev/null +++ b/tools/perf/util/archinsn.h @@ -0,0 +1,12 @@ +#ifndef INSN_H +#define INSN_H 1 + +struct perf_sample; +struct machine; +struct thread; + +void arch_fetch_insn(struct perf_sample *sample, + struct thread *thread, + struct machine *machine); + +#endif diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 028c8ec1f62a..2a4a0da35632 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -3,11 +3,17 @@ #include <stdlib.h> #include <bpf/bpf.h> #include <bpf/btf.h> +#include <bpf/libbpf.h> #include <linux/btf.h> +#include <linux/err.h> #include "bpf-event.h" #include "debug.h" #include "symbol.h" #include "machine.h" +#include "env.h" +#include "session.h" +#include "map.h" +#include "evlist.h" #define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) @@ -21,15 +27,122 @@ static int snprintf_hex(char *buf, size_t size, unsigned char *data, size_t len) return ret; } +static int machine__process_bpf_event_load(struct machine *machine, + union perf_event *event, + struct perf_sample *sample __maybe_unused) +{ + struct bpf_prog_info_linear *info_linear; + struct bpf_prog_info_node *info_node; + struct perf_env *env = machine->env; + int id = event->bpf_event.id; + unsigned int i; + + /* perf-record, no need to handle bpf-event */ + if (env == NULL) + return 0; + + info_node = perf_env__find_bpf_prog_info(env, id); + if (!info_node) + return 0; + info_linear = info_node->info_linear; + + for (i = 0; i < info_linear->info.nr_jited_ksyms; i++) { + u64 *addrs = (u64 *)(uintptr_t)(info_linear->info.jited_ksyms); + u64 addr = addrs[i]; + struct map *map; + + map = map_groups__find(&machine->kmaps, addr); + + if (map) { + map->dso->binary_type = DSO_BINARY_TYPE__BPF_PROG_INFO; + map->dso->bpf_prog.id = id; + map->dso->bpf_prog.sub_id = i; + map->dso->bpf_prog.env = env; + } + } + return 0; +} + int machine__process_bpf_event(struct machine *machine __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused) { if (dump_trace) perf_event__fprintf_bpf_event(event, stdout); + + switch (event->bpf_event.type) { + case PERF_BPF_EVENT_PROG_LOAD: + return machine__process_bpf_event_load(machine, event, sample); + + case PERF_BPF_EVENT_PROG_UNLOAD: + /* + * Do not free bpf_prog_info and btf of the program here, + * as annotation still need them. They will be freed at + * the end of the session. + */ + break; + default: + pr_debug("unexpected bpf_event type of %d\n", + event->bpf_event.type); + break; + } return 0; } +static int perf_env__fetch_btf(struct perf_env *env, + u32 btf_id, + struct btf *btf) +{ + struct btf_node *node; + u32 data_size; + const void *data; + + data = btf__get_raw_data(btf, &data_size); + + node = malloc(data_size + sizeof(struct btf_node)); + if (!node) + return -1; + + node->id = btf_id; + node->data_size = data_size; + memcpy(node->data, data, data_size); + + perf_env__insert_btf(env, node); + return 0; +} + +static int synthesize_bpf_prog_name(char *buf, int size, + struct bpf_prog_info *info, + struct btf *btf, + u32 sub_id) +{ + u8 (*prog_tags)[BPF_TAG_SIZE] = (void *)(uintptr_t)(info->prog_tags); + void *func_infos = (void *)(uintptr_t)(info->func_info); + u32 sub_prog_cnt = info->nr_jited_ksyms; + const struct bpf_func_info *finfo; + const char *short_name = NULL; + const struct btf_type *t; + int name_len; + + name_len = snprintf(buf, size, "bpf_prog_"); + name_len += snprintf_hex(buf + name_len, size - name_len, + prog_tags[sub_id], BPF_TAG_SIZE); + if (btf) { + finfo = func_infos + sub_id * info->func_info_rec_size; + t = btf__type_by_id(btf, finfo->type_id); + short_name = btf__name_by_offset(btf, t->name_off); + } else if (sub_id == 0 && sub_prog_cnt == 1) { + /* no subprog */ + if (info->name[0]) + short_name = info->name; + } else + short_name = "F"; + if (short_name) + name_len += snprintf(buf + name_len, size - name_len, + "_%s", short_name); + return name_len; +} + /* * Synthesize PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT for one bpf * program. One PERF_RECORD_BPF_EVENT is generated for the program. And @@ -40,7 +153,7 @@ int machine__process_bpf_event(struct machine *machine __maybe_unused, * -1 for failures; * -2 for lack of kernel support. */ -static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool, +static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, perf_event__handler_t process, struct machine *machine, int fd, @@ -49,102 +162,71 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool, { struct ksymbol_event *ksymbol_event = &event->ksymbol_event; struct bpf_event *bpf_event = &event->bpf_event; - u32 sub_prog_cnt, i, func_info_rec_size = 0; - u8 (*prog_tags)[BPF_TAG_SIZE] = NULL; - struct bpf_prog_info info = { .type = 0, }; - u32 info_len = sizeof(info); - void *func_infos = NULL; - u64 *prog_addrs = NULL; + struct bpf_prog_info_linear *info_linear; + struct perf_tool *tool = session->tool; + struct bpf_prog_info_node *info_node; + struct bpf_prog_info *info; struct btf *btf = NULL; - u32 *prog_lens = NULL; - bool has_btf = false; - char errbuf[512]; + struct perf_env *env; + u32 sub_prog_cnt, i; int err = 0; + u64 arrays; + + /* + * for perf-record and perf-report use header.env; + * otherwise, use global perf_env. + */ + env = session->data ? &session->header.env : &perf_env; - /* Call bpf_obj_get_info_by_fd() to get sizes of arrays */ - err = bpf_obj_get_info_by_fd(fd, &info, &info_len); + arrays = 1UL << BPF_PROG_INFO_JITED_KSYMS; + arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS; + arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO; + arrays |= 1UL << BPF_PROG_INFO_PROG_TAGS; + arrays |= 1UL << BPF_PROG_INFO_JITED_INSNS; + arrays |= 1UL << BPF_PROG_INFO_LINE_INFO; + arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO; - if (err) { - pr_debug("%s: failed to get BPF program info: %s, aborting\n", - __func__, str_error_r(errno, errbuf, sizeof(errbuf))); + info_linear = bpf_program__get_prog_info_linear(fd, arrays); + if (IS_ERR_OR_NULL(info_linear)) { + info_linear = NULL; + pr_debug("%s: failed to get BPF program info. aborting\n", __func__); return -1; } - if (info_len < offsetof(struct bpf_prog_info, prog_tags)) { + + if (info_linear->info_len < offsetof(struct bpf_prog_info, prog_tags)) { pr_debug("%s: the kernel is too old, aborting\n", __func__); return -2; } + info = &info_linear->info; + /* number of ksyms, func_lengths, and tags should match */ - sub_prog_cnt = info.nr_jited_ksyms; - if (sub_prog_cnt != info.nr_prog_tags || - sub_prog_cnt != info.nr_jited_func_lens) + sub_prog_cnt = info->nr_jited_ksyms; + if (sub_prog_cnt != info->nr_prog_tags || + sub_prog_cnt != info->nr_jited_func_lens) return -1; /* check BTF func info support */ - if (info.btf_id && info.nr_func_info && info.func_info_rec_size) { + if (info->btf_id && info->nr_func_info && info->func_info_rec_size) { /* btf func info number should be same as sub_prog_cnt */ - if (sub_prog_cnt != info.nr_func_info) { + if (sub_prog_cnt != info->nr_func_info) { pr_debug("%s: mismatch in BPF sub program count and BTF function info count, aborting\n", __func__); - return -1; - } - if (btf__get_from_id(info.btf_id, &btf)) { - pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info.btf_id); - return -1; + err = -1; + goto out; } - func_info_rec_size = info.func_info_rec_size; - func_infos = calloc(sub_prog_cnt, func_info_rec_size); - if (!func_infos) { - pr_debug("%s: failed to allocate memory for func_infos, aborting\n", __func__); - return -1; + if (btf__get_from_id(info->btf_id, &btf)) { + pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info->btf_id); + err = -1; + btf = NULL; + goto out; } - has_btf = true; - } - - /* - * We need address, length, and tag for each sub program. - * Allocate memory and call bpf_obj_get_info_by_fd() again - */ - prog_addrs = calloc(sub_prog_cnt, sizeof(u64)); - if (!prog_addrs) { - pr_debug("%s: failed to allocate memory for prog_addrs, aborting\n", __func__); - goto out; - } - prog_lens = calloc(sub_prog_cnt, sizeof(u32)); - if (!prog_lens) { - pr_debug("%s: failed to allocate memory for prog_lens, aborting\n", __func__); - goto out; - } - prog_tags = calloc(sub_prog_cnt, BPF_TAG_SIZE); - if (!prog_tags) { - pr_debug("%s: failed to allocate memory for prog_tags, aborting\n", __func__); - goto out; - } - - memset(&info, 0, sizeof(info)); - info.nr_jited_ksyms = sub_prog_cnt; - info.nr_jited_func_lens = sub_prog_cnt; - info.nr_prog_tags = sub_prog_cnt; - info.jited_ksyms = ptr_to_u64(prog_addrs); - info.jited_func_lens = ptr_to_u64(prog_lens); - info.prog_tags = ptr_to_u64(prog_tags); - info_len = sizeof(info); - if (has_btf) { - info.nr_func_info = sub_prog_cnt; - info.func_info_rec_size = func_info_rec_size; - info.func_info = ptr_to_u64(func_infos); - } - - err = bpf_obj_get_info_by_fd(fd, &info, &info_len); - if (err) { - pr_debug("%s: failed to get BPF program info, aborting\n", __func__); - goto out; + perf_env__fetch_btf(env, info->btf_id, btf); } /* Synthesize PERF_RECORD_KSYMBOL */ for (i = 0; i < sub_prog_cnt; i++) { - const struct bpf_func_info *finfo; - const char *short_name = NULL; - const struct btf_type *t; + __u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens); + __u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms); int name_len; *ksymbol_event = (struct ksymbol_event){ @@ -157,26 +239,9 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool, .ksym_type = PERF_RECORD_KSYMBOL_TYPE_BPF, .flags = 0, }; - name_len = snprintf(ksymbol_event->name, KSYM_NAME_LEN, - "bpf_prog_"); - name_len += snprintf_hex(ksymbol_event->name + name_len, - KSYM_NAME_LEN - name_len, - prog_tags[i], BPF_TAG_SIZE); - if (has_btf) { - finfo = func_infos + i * info.func_info_rec_size; - t = btf__type_by_id(btf, finfo->type_id); - short_name = btf__name_by_offset(btf, t->name_off); - } else if (i == 0 && sub_prog_cnt == 1) { - /* no subprog */ - if (info.name[0]) - short_name = info.name; - } else - short_name = "F"; - if (short_name) - name_len += snprintf(ksymbol_event->name + name_len, - KSYM_NAME_LEN - name_len, - "_%s", short_name); + name_len = synthesize_bpf_prog_name(ksymbol_event->name, + KSYM_NAME_LEN, info, btf, i); ksymbol_event->header.size += PERF_ALIGN(name_len + 1, sizeof(u64)); @@ -186,8 +251,8 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool, machine, process); } - /* Synthesize PERF_RECORD_BPF_EVENT */ - if (opts->bpf_event) { + if (!opts->no_bpf_event) { + /* Synthesize PERF_RECORD_BPF_EVENT */ *bpf_event = (struct bpf_event){ .header = { .type = PERF_RECORD_BPF_EVENT, @@ -195,25 +260,38 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool, }, .type = PERF_BPF_EVENT_PROG_LOAD, .flags = 0, - .id = info.id, + .id = info->id, }; - memcpy(bpf_event->tag, prog_tags[i], BPF_TAG_SIZE); + memcpy(bpf_event->tag, info->tag, BPF_TAG_SIZE); memset((void *)event + event->header.size, 0, machine->id_hdr_size); event->header.size += machine->id_hdr_size; + + /* save bpf_prog_info to env */ + info_node = malloc(sizeof(struct bpf_prog_info_node)); + if (!info_node) { + err = -1; + goto out; + } + + info_node->info_linear = info_linear; + perf_env__insert_bpf_prog_info(env, info_node); + info_linear = NULL; + + /* + * process after saving bpf_prog_info to env, so that + * required information is ready for look up + */ err = perf_tool__process_synth_event(tool, event, machine, process); } out: - free(prog_tags); - free(prog_lens); - free(prog_addrs); - free(func_infos); + free(info_linear); free(btf); return err ? -1 : 0; } -int perf_event__synthesize_bpf_events(struct perf_tool *tool, +int perf_event__synthesize_bpf_events(struct perf_session *session, perf_event__handler_t process, struct machine *machine, struct record_opts *opts) @@ -247,7 +325,7 @@ int perf_event__synthesize_bpf_events(struct perf_tool *tool, continue; } - err = perf_event__synthesize_one_bpf_prog(tool, process, + err = perf_event__synthesize_one_bpf_prog(session, process, machine, fd, event, opts); close(fd); @@ -261,3 +339,142 @@ int perf_event__synthesize_bpf_events(struct perf_tool *tool, free(event); return err; } + +static void perf_env__add_bpf_info(struct perf_env *env, u32 id) +{ + struct bpf_prog_info_linear *info_linear; + struct bpf_prog_info_node *info_node; + struct btf *btf = NULL; + u64 arrays; + u32 btf_id; + int fd; + + fd = bpf_prog_get_fd_by_id(id); + if (fd < 0) + return; + + arrays = 1UL << BPF_PROG_INFO_JITED_KSYMS; + arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS; + arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO; + arrays |= 1UL << BPF_PROG_INFO_PROG_TAGS; + arrays |= 1UL << BPF_PROG_INFO_JITED_INSNS; + arrays |= 1UL << BPF_PROG_INFO_LINE_INFO; + arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO; + + info_linear = bpf_program__get_prog_info_linear(fd, arrays); + if (IS_ERR_OR_NULL(info_linear)) { + pr_debug("%s: failed to get BPF program info. aborting\n", __func__); + goto out; + } + + btf_id = info_linear->info.btf_id; + + info_node = malloc(sizeof(struct bpf_prog_info_node)); + if (info_node) { + info_node->info_linear = info_linear; + perf_env__insert_bpf_prog_info(env, info_node); + } else + free(info_linear); + + if (btf_id == 0) + goto out; + + if (btf__get_from_id(btf_id, &btf)) { + pr_debug("%s: failed to get BTF of id %u, aborting\n", + __func__, btf_id); + goto out; + } + perf_env__fetch_btf(env, btf_id, btf); + +out: + free(btf); + close(fd); +} + +static int bpf_event__sb_cb(union perf_event *event, void *data) +{ + struct perf_env *env = data; + + if (event->header.type != PERF_RECORD_BPF_EVENT) + return -1; + + switch (event->bpf_event.type) { + case PERF_BPF_EVENT_PROG_LOAD: + perf_env__add_bpf_info(env, event->bpf_event.id); + + case PERF_BPF_EVENT_PROG_UNLOAD: + /* + * Do not free bpf_prog_info and btf of the program here, + * as annotation still need them. They will be freed at + * the end of the session. + */ + break; + default: + pr_debug("unexpected bpf_event type of %d\n", + event->bpf_event.type); + break; + } + + return 0; +} + +int bpf_event__add_sb_event(struct perf_evlist **evlist, + struct perf_env *env) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_DUMMY, + .sample_id_all = 1, + .watermark = 1, + .bpf_event = 1, + .size = sizeof(attr), /* to capture ABI version */ + }; + + /* + * Older gcc versions don't support designated initializers, like above, + * for unnamed union members, such as the following: + */ + attr.wakeup_watermark = 1; + + return perf_evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env); +} + +void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, + struct perf_env *env, + FILE *fp) +{ + __u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens); + __u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms); + char name[KSYM_NAME_LEN]; + struct btf *btf = NULL; + u32 sub_prog_cnt, i; + + sub_prog_cnt = info->nr_jited_ksyms; + if (sub_prog_cnt != info->nr_prog_tags || + sub_prog_cnt != info->nr_jited_func_lens) + return; + + if (info->btf_id) { + struct btf_node *node; + + node = perf_env__find_btf(env, info->btf_id); + if (node) + btf = btf__new((__u8 *)(node->data), + node->data_size); + } + + if (sub_prog_cnt == 1) { + synthesize_bpf_prog_name(name, KSYM_NAME_LEN, info, btf, 0); + fprintf(fp, "# bpf_prog_info %u: %s addr 0x%llx size %u\n", + info->id, name, prog_addrs[0], prog_lens[0]); + return; + } + + fprintf(fp, "# bpf_prog_info %u:\n", info->id); + for (i = 0; i < sub_prog_cnt; i++) { + synthesize_bpf_prog_name(name, KSYM_NAME_LEN, info, btf, i); + + fprintf(fp, "# \tsub_prog %u: %s addr 0x%llx size %u\n", + i, name, prog_addrs[i], prog_lens[i]); + } +} diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h index 7890067e1a37..04c33b3bfe28 100644 --- a/tools/perf/util/bpf-event.h +++ b/tools/perf/util/bpf-event.h @@ -3,22 +3,45 @@ #define __PERF_BPF_EVENT_H #include <linux/compiler.h> +#include <linux/rbtree.h> +#include <pthread.h> +#include <api/fd/array.h> #include "event.h" +#include <stdio.h> struct machine; union perf_event; +struct perf_env; struct perf_sample; -struct perf_tool; struct record_opts; +struct evlist; +struct target; + +struct bpf_prog_info_node { + struct bpf_prog_info_linear *info_linear; + struct rb_node rb_node; +}; + +struct btf_node { + struct rb_node rb_node; + u32 id; + u32 data_size; + char data[]; +}; #ifdef HAVE_LIBBPF_SUPPORT int machine__process_bpf_event(struct machine *machine, union perf_event *event, struct perf_sample *sample); -int perf_event__synthesize_bpf_events(struct perf_tool *tool, +int perf_event__synthesize_bpf_events(struct perf_session *session, perf_event__handler_t process, struct machine *machine, struct record_opts *opts); +int bpf_event__add_sb_event(struct perf_evlist **evlist, + struct perf_env *env); +void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, + struct perf_env *env, + FILE *fp); #else static inline int machine__process_bpf_event(struct machine *machine __maybe_unused, union perf_event *event __maybe_unused, @@ -27,12 +50,25 @@ static inline int machine__process_bpf_event(struct machine *machine __maybe_unu return 0; } -static inline int perf_event__synthesize_bpf_events(struct perf_tool *tool __maybe_unused, +static inline int perf_event__synthesize_bpf_events(struct perf_session *session __maybe_unused, perf_event__handler_t process __maybe_unused, struct machine *machine __maybe_unused, struct record_opts *opts __maybe_unused) { return 0; } + +static inline int bpf_event__add_sb_event(struct perf_evlist **evlist __maybe_unused, + struct perf_env *env __maybe_unused) +{ + return 0; +} + +static inline void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused, + struct perf_env *env __maybe_unused, + FILE *fp __maybe_unused) +{ + +} #endif // HAVE_LIBBPF_SUPPORT #endif diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index bff0d17920ed..0c5517a8d0b7 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -185,6 +185,7 @@ char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size) return bf; } +/* The caller is responsible to free the returned buffer. */ char *build_id_cache__origname(const char *sbuild_id) { char *linkname; diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c index ca0fff6272be..06f48312c5ed 100644 --- a/tools/perf/util/cloexec.c +++ b/tools/perf/util/cloexec.c @@ -7,7 +7,6 @@ #include "asm/bug.h" #include "debug.h" #include <unistd.h> -#include <asm/unistd.h> #include <sys/syscall.h> static unsigned long flag = PERF_FLAG_FD_CLOEXEC; diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index fa092511c52b..7e3c1b60120c 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -633,11 +633,10 @@ static int collect_config(const char *var, const char *value, } ret = set_value(item, value); - return ret; out_free: free(key); - return -1; + return ret; } int perf_config_set__collect(struct perf_config_set *set, const char *file_name, diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index ba4c623cd8de..39fe21e1cf93 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -387,6 +387,7 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder, break; case OCSD_INSTR_ISB: case OCSD_INSTR_DSB_DMB: + case OCSD_INSTR_WFI_WFE: case OCSD_INSTR_OTHER: default: packet->last_instr_taken_branch = false; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 110804936fc3..de488b43f440 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -422,11 +422,9 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm) if (!etmq->packet) goto out_free; - if (etm->synth_opts.last_branch || etm->sample_branches) { - etmq->prev_packet = zalloc(szp); - if (!etmq->prev_packet) - goto out_free; - } + etmq->prev_packet = zalloc(szp); + if (!etmq->prev_packet) + goto out_free; if (etm->synth_opts.last_branch) { size_t sz = sizeof(struct branch_stack); @@ -981,7 +979,6 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) * PREV_PACKET is a branch. */ if (etm->synth_opts.last_branch && - etmq->prev_packet && etmq->prev_packet->sample_type == CS_ETM_RANGE && etmq->prev_packet->last_instr_taken_branch) cs_etm__update_last_branch_rb(etmq); @@ -1014,7 +1011,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) etmq->period_instructions = instrs_over; } - if (etm->sample_branches && etmq->prev_packet) { + if (etm->sample_branches) { bool generate_sample = false; /* Generate sample for tracing on packet */ @@ -1071,9 +1068,6 @@ static int cs_etm__flush(struct cs_etm_queue *etmq) struct cs_etm_auxtrace *etm = etmq->etm; struct cs_etm_packet *tmp; - if (!etmq->prev_packet) - return 0; - /* Handle start tracing packet */ if (etmq->prev_packet->sample_type == CS_ETM_EMPTY) goto swap_packet; diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 26af43ad9ddd..e0311c9750ad 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -310,7 +310,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, if (flags & TEP_FIELD_IS_DYNAMIC) { unsigned long long tmp_val; - tmp_val = tep_read_number(fmtf->event->pevent, + tmp_val = tep_read_number(fmtf->event->tep, data + offset, len); offset = tmp_val; len = offset >> 16; @@ -354,7 +354,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, unsigned long long value_int; value_int = tep_read_number( - fmtf->event->pevent, + fmtf->event->tep, data + offset + i * len, len); if (!(flags & TEP_FIELD_IS_SIGNED)) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index e098e189f93e..6a64f713710d 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -14,6 +14,7 @@ #include "data.h" #include "util.h" #include "debug.h" +#include "header.h" static void close_dir(struct perf_data_file *files, int nr) { @@ -34,12 +35,16 @@ int perf_data__create_dir(struct perf_data *data, int nr) struct perf_data_file *files = NULL; int i, ret = -1; + if (WARN_ON(!data->is_dir)) + return -EINVAL; + files = zalloc(nr * sizeof(*files)); if (!files) return -ENOMEM; - data->dir.files = files; - data->dir.nr = nr; + data->dir.version = PERF_DIR_VERSION; + data->dir.files = files; + data->dir.nr = nr; for (i = 0; i < nr; i++) { struct perf_data_file *file = &files[i]; @@ -69,6 +74,13 @@ int perf_data__open_dir(struct perf_data *data) DIR *dir; int nr = 0; + if (WARN_ON(!data->is_dir)) + return -EINVAL; + + /* The version is provided by DIR_FORMAT feature. */ + if (WARN_ON(data->dir.version != PERF_DIR_VERSION)) + return -1; + dir = opendir(data->path); if (!dir) return -EINVAL; @@ -118,6 +130,26 @@ out_err: return ret; } +int perf_data__update_dir(struct perf_data *data) +{ + int i; + + if (WARN_ON(!data->is_dir)) + return -EINVAL; + + for (i = 0; i < data->dir.nr; i++) { + struct perf_data_file *file = &data->dir.files[i]; + struct stat st; + + if (fstat(file->fd, &st)) + return -1; + + file->size = st.st_size; + } + + return 0; +} + static bool check_pipe(struct perf_data *data) { struct stat st; @@ -173,6 +205,16 @@ static int check_backup(struct perf_data *data) return 0; } +static bool is_dir(struct perf_data *data) +{ + struct stat st; + + if (stat(data->path, &st)) + return false; + + return (st.st_mode & S_IFMT) == S_IFDIR; +} + static int open_file_read(struct perf_data *data) { struct stat st; @@ -254,6 +296,30 @@ static int open_file_dup(struct perf_data *data) return open_file(data); } +static int open_dir(struct perf_data *data) +{ + int ret; + + /* + * So far we open only the header, so we can read the data version and + * layout. + */ + if (asprintf(&data->file.path, "%s/header", data->path) < 0) + return -1; + + if (perf_data__is_write(data) && + mkdir(data->path, S_IRWXU) < 0) + return -1; + + ret = open_file(data); + + /* Cleanup whatever we managed to create so far. */ + if (ret && perf_data__is_write(data)) + rm_rf_perf_data(data->path); + + return ret; +} + int perf_data__open(struct perf_data *data) { if (check_pipe(data)) @@ -265,11 +331,18 @@ int perf_data__open(struct perf_data *data) if (check_backup(data)) return -1; - return open_file_dup(data); + if (perf_data__is_read(data)) + data->is_dir = is_dir(data); + + return perf_data__is_dir(data) ? + open_dir(data) : open_file_dup(data); } void perf_data__close(struct perf_data *data) { + if (perf_data__is_dir(data)) + perf_data__close_dir(data); + zfree(&data->file.path); close(data->file.fd); } @@ -288,9 +361,9 @@ ssize_t perf_data__write(struct perf_data *data, int perf_data__switch(struct perf_data *data, const char *postfix, - size_t pos, bool at_exit) + size_t pos, bool at_exit, + char **new_filepath) { - char *new_filepath; int ret; if (check_pipe(data)) @@ -298,15 +371,15 @@ int perf_data__switch(struct perf_data *data, if (perf_data__is_read(data)) return -EINVAL; - if (asprintf(&new_filepath, "%s.%s", data->path, postfix) < 0) + if (asprintf(new_filepath, "%s.%s", data->path, postfix) < 0) return -ENOMEM; /* * Only fire a warning, don't return error, continue fill * original file. */ - if (rename(data->path, new_filepath)) - pr_warning("Failed to rename %s to %s\n", data->path, new_filepath); + if (rename(data->path, *new_filepath)) + pr_warning("Failed to rename %s to %s\n", data->path, *new_filepath); if (!at_exit) { close(data->file.fd); @@ -323,6 +396,22 @@ int perf_data__switch(struct perf_data *data, } ret = data->file.fd; out: - free(new_filepath); return ret; } + +unsigned long perf_data__size(struct perf_data *data) +{ + u64 size = data->file.size; + int i; + + if (!data->is_dir) + return size; + + for (i = 0; i < data->dir.nr; i++) { + struct perf_data_file *file = &data->dir.files[i]; + + size += file->size; + } + + return size; +} diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 14b47be2bd69..259868a39019 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -19,10 +19,12 @@ struct perf_data { const char *path; struct perf_data_file file; bool is_pipe; + bool is_dir; bool force; enum perf_data_mode mode; struct { + u64 version; struct perf_data_file *files; int nr; } dir; @@ -43,14 +45,14 @@ static inline int perf_data__is_pipe(struct perf_data *data) return data->is_pipe; } -static inline int perf_data__fd(struct perf_data *data) +static inline bool perf_data__is_dir(struct perf_data *data) { - return data->file.fd; + return data->is_dir; } -static inline unsigned long perf_data__size(struct perf_data *data) +static inline int perf_data__fd(struct perf_data *data) { - return data->file.size; + return data->file.fd; } int perf_data__open(struct perf_data *data); @@ -68,9 +70,11 @@ ssize_t perf_data_file__write(struct perf_data_file *file, */ int perf_data__switch(struct perf_data *data, const char *postfix, - size_t pos, bool at_exit); + size_t pos, bool at_exit, char **new_filepath); int perf_data__create_dir(struct perf_data *data, int nr); int perf_data__open_dir(struct perf_data *data); void perf_data__close_dir(struct perf_data *data); +int perf_data__update_dir(struct perf_data *data); +unsigned long perf_data__size(struct perf_data *data); #endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index ba58ba603b69..e059976d9d93 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -184,6 +184,7 @@ int dso__read_binary_type_filename(const struct dso *dso, case DSO_BINARY_TYPE__KALLSYMS: case DSO_BINARY_TYPE__GUEST_KALLSYMS: case DSO_BINARY_TYPE__JAVA_JIT: + case DSO_BINARY_TYPE__BPF_PROG_INFO: case DSO_BINARY_TYPE__NOT_FOUND: ret = -1; break; @@ -1141,28 +1142,34 @@ void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated) static void dso__set_basename(struct dso *dso) { - /* - * basename() may modify path buffer, so we must pass - * a copy. - */ - char *base, *lname = strdup(dso->long_name); + char *base, *lname; + int tid; - if (!lname) - return; - - /* - * basename() may return a pointer to internal - * storage which is reused in subsequent calls - * so copy the result. - */ - base = strdup(basename(lname)); + if (sscanf(dso->long_name, "/tmp/perf-%d.map", &tid) == 1) { + if (asprintf(&base, "[JIT] tid %d", tid) < 0) + return; + } else { + /* + * basename() may modify path buffer, so we must pass + * a copy. + */ + lname = strdup(dso->long_name); + if (!lname) + return; - free(lname); + /* + * basename() may return a pointer to internal + * storage which is reused in subsequent calls + * so copy the result. + */ + base = strdup(basename(lname)); - if (!base) - return; + free(lname); - dso__set_short_name(dso, base, true); + if (!base) + return; + } + dso__set_short_name(dso, base, true); } int dso__name_len(const struct dso *dso) diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index bb417c54c25a..6e3f63781e51 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -14,6 +14,7 @@ struct machine; struct map; +struct perf_env; enum dso_binary_type { DSO_BINARY_TYPE__KALLSYMS = 0, @@ -35,6 +36,7 @@ enum dso_binary_type { DSO_BINARY_TYPE__KCORE, DSO_BINARY_TYPE__GUEST_KCORE, DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, + DSO_BINARY_TYPE__BPF_PROG_INFO, DSO_BINARY_TYPE__NOT_FOUND, }; @@ -189,6 +191,12 @@ struct dso { u64 debug_frame_offset; u64 eh_frame_hdr_offset; } data; + /* bpf prog information */ + struct { + u32 id; + u32 sub_id; + struct perf_env *env; + } bpf_prog; union { /* Tool specific area */ void *priv; diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 4c23779e271a..6a3eaf7d9353 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -3,15 +3,167 @@ #include "env.h" #include "sane_ctype.h" #include "util.h" +#include "bpf-event.h" #include <errno.h> #include <sys/utsname.h> +#include <bpf/libbpf.h> struct perf_env perf_env; +void perf_env__insert_bpf_prog_info(struct perf_env *env, + struct bpf_prog_info_node *info_node) +{ + __u32 prog_id = info_node->info_linear->info.id; + struct bpf_prog_info_node *node; + struct rb_node *parent = NULL; + struct rb_node **p; + + down_write(&env->bpf_progs.lock); + p = &env->bpf_progs.infos.rb_node; + + while (*p != NULL) { + parent = *p; + node = rb_entry(parent, struct bpf_prog_info_node, rb_node); + if (prog_id < node->info_linear->info.id) { + p = &(*p)->rb_left; + } else if (prog_id > node->info_linear->info.id) { + p = &(*p)->rb_right; + } else { + pr_debug("duplicated bpf prog info %u\n", prog_id); + goto out; + } + } + + rb_link_node(&info_node->rb_node, parent, p); + rb_insert_color(&info_node->rb_node, &env->bpf_progs.infos); + env->bpf_progs.infos_cnt++; +out: + up_write(&env->bpf_progs.lock); +} + +struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, + __u32 prog_id) +{ + struct bpf_prog_info_node *node = NULL; + struct rb_node *n; + + down_read(&env->bpf_progs.lock); + n = env->bpf_progs.infos.rb_node; + + while (n) { + node = rb_entry(n, struct bpf_prog_info_node, rb_node); + if (prog_id < node->info_linear->info.id) + n = n->rb_left; + else if (prog_id > node->info_linear->info.id) + n = n->rb_right; + else + goto out; + } + node = NULL; + +out: + up_read(&env->bpf_progs.lock); + return node; +} + +void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) +{ + struct rb_node *parent = NULL; + __u32 btf_id = btf_node->id; + struct btf_node *node; + struct rb_node **p; + + down_write(&env->bpf_progs.lock); + p = &env->bpf_progs.btfs.rb_node; + + while (*p != NULL) { + parent = *p; + node = rb_entry(parent, struct btf_node, rb_node); + if (btf_id < node->id) { + p = &(*p)->rb_left; + } else if (btf_id > node->id) { + p = &(*p)->rb_right; + } else { + pr_debug("duplicated btf %u\n", btf_id); + goto out; + } + } + + rb_link_node(&btf_node->rb_node, parent, p); + rb_insert_color(&btf_node->rb_node, &env->bpf_progs.btfs); + env->bpf_progs.btfs_cnt++; +out: + up_write(&env->bpf_progs.lock); +} + +struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id) +{ + struct btf_node *node = NULL; + struct rb_node *n; + + down_read(&env->bpf_progs.lock); + n = env->bpf_progs.btfs.rb_node; + + while (n) { + node = rb_entry(n, struct btf_node, rb_node); + if (btf_id < node->id) + n = n->rb_left; + else if (btf_id > node->id) + n = n->rb_right; + else + goto out; + } + node = NULL; + +out: + up_read(&env->bpf_progs.lock); + return node; +} + +/* purge data in bpf_progs.infos tree */ +static void perf_env__purge_bpf(struct perf_env *env) +{ + struct rb_root *root; + struct rb_node *next; + + down_write(&env->bpf_progs.lock); + + root = &env->bpf_progs.infos; + next = rb_first(root); + + while (next) { + struct bpf_prog_info_node *node; + + node = rb_entry(next, struct bpf_prog_info_node, rb_node); + next = rb_next(&node->rb_node); + rb_erase(&node->rb_node, root); + free(node); + } + + env->bpf_progs.infos_cnt = 0; + + root = &env->bpf_progs.btfs; + next = rb_first(root); + + while (next) { + struct btf_node *node; + + node = rb_entry(next, struct btf_node, rb_node); + next = rb_next(&node->rb_node); + rb_erase(&node->rb_node, root); + free(node); + } + + env->bpf_progs.btfs_cnt = 0; + + up_write(&env->bpf_progs.lock); +} + void perf_env__exit(struct perf_env *env) { int i; + perf_env__purge_bpf(env); zfree(&env->hostname); zfree(&env->os_release); zfree(&env->version); @@ -38,6 +190,13 @@ void perf_env__exit(struct perf_env *env) zfree(&env->memory_nodes); } +void perf_env__init(struct perf_env *env) +{ + env->bpf_progs.infos = RB_ROOT; + env->bpf_progs.btfs = RB_ROOT; + init_rwsem(&env->bpf_progs.lock); +} + int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]) { int i; diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index d01b8355f4ca..4f8e2b485c01 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -3,7 +3,9 @@ #define __PERF_ENV_H #include <linux/types.h> +#include <linux/rbtree.h> #include "cpumap.h" +#include "rwsem.h" struct cpu_topology_map { int socket_id; @@ -64,8 +66,23 @@ struct perf_env { struct memory_node *memory_nodes; unsigned long long memory_bsize; u64 clockid_res_ns; + + /* + * bpf_info_lock protects bpf rbtrees. This is needed because the + * trees are accessed by different threads in perf-top + */ + struct { + struct rw_semaphore lock; + struct rb_root infos; + u32 infos_cnt; + struct rb_root btfs; + u32 btfs_cnt; + } bpf_progs; }; +struct bpf_prog_info_node; +struct btf_node; + extern struct perf_env perf_env; void perf_env__exit(struct perf_env *env); @@ -80,4 +97,11 @@ const char *perf_env__arch(struct perf_env *env); const char *perf_env__raw_arch(struct perf_env *env); int perf_env__nr_cpus_avail(struct perf_env *env); +void perf_env__init(struct perf_env *env); +void perf_env__insert_bpf_prog_info(struct perf_env *env, + struct bpf_prog_info_node *info_node); +struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, + __u32 prog_id); +void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node); +struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id); #endif /* __PERF_ENV_H */ diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 36ae7e92dab1..4e908ec1ef64 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -6,6 +6,7 @@ #include <stdio.h> #include <linux/kernel.h> #include <linux/bpf.h> +#include <linux/perf_event.h> #include "../perf.h" #include "build-id.h" diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index ed20f4379956..4b6783ff5813 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -19,6 +19,7 @@ #include "debug.h" #include "units.h" #include "asm/bug.h" +#include "bpf-event.h" #include <signal.h> #include <unistd.h> @@ -230,35 +231,6 @@ void perf_evlist__set_leader(struct perf_evlist *evlist) } } -void perf_event_attr__set_max_precise_ip(struct perf_event_attr *pattr) -{ - struct perf_event_attr attr = { - .type = PERF_TYPE_HARDWARE, - .config = PERF_COUNT_HW_CPU_CYCLES, - .exclude_kernel = 1, - .precise_ip = 3, - }; - - event_attr_init(&attr); - - /* - * Unnamed union member, not supported as struct member named - * initializer in older compilers such as gcc 4.4.7 - */ - attr.sample_period = 1; - - while (attr.precise_ip != 0) { - int fd = sys_perf_event_open(&attr, 0, -1, -1, 0); - if (fd != -1) { - close(fd); - break; - } - --attr.precise_ip; - } - - pattr->precise_ip = attr.precise_ip; -} - int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise) { struct perf_evsel *evsel = perf_evsel__new_cycles(precise); @@ -1037,7 +1009,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, */ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, unsigned int auxtrace_pages, - bool auxtrace_overwrite, int nr_cblocks, int affinity) + bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush) { struct perf_evsel *evsel; const struct cpu_map *cpus = evlist->cpus; @@ -1047,7 +1019,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, * Its value is decided by evsel's write_backward. * So &mp should not be passed through const pointer. */ - struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity }; + struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity, .flush = flush }; if (!evlist->mmap) evlist->mmap = perf_evlist__alloc_mmap(evlist, false); @@ -1079,7 +1051,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages) { - return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS); + return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1); } int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) @@ -1856,3 +1828,125 @@ struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list, } return leader; } + +int perf_evlist__add_sb_event(struct perf_evlist **evlist, + struct perf_event_attr *attr, + perf_evsel__sb_cb_t cb, + void *data) +{ + struct perf_evsel *evsel; + bool new_evlist = (*evlist) == NULL; + + if (*evlist == NULL) + *evlist = perf_evlist__new(); + if (*evlist == NULL) + return -1; + + if (!attr->sample_id_all) { + pr_warning("enabling sample_id_all for all side band events\n"); + attr->sample_id_all = 1; + } + + evsel = perf_evsel__new_idx(attr, (*evlist)->nr_entries); + if (!evsel) + goto out_err; + + evsel->side_band.cb = cb; + evsel->side_band.data = data; + perf_evlist__add(*evlist, evsel); + return 0; + +out_err: + if (new_evlist) { + perf_evlist__delete(*evlist); + *evlist = NULL; + } + return -1; +} + +static void *perf_evlist__poll_thread(void *arg) +{ + struct perf_evlist *evlist = arg; + bool draining = false; + int i, done = 0; + + while (!done) { + bool got_data = false; + + if (evlist->thread.done) + draining = true; + + if (!draining) + perf_evlist__poll(evlist, 1000); + + for (i = 0; i < evlist->nr_mmaps; i++) { + struct perf_mmap *map = &evlist->mmap[i]; + union perf_event *event; + + if (perf_mmap__read_init(map)) + continue; + while ((event = perf_mmap__read_event(map)) != NULL) { + struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event); + + if (evsel && evsel->side_band.cb) + evsel->side_band.cb(event, evsel->side_band.data); + else + pr_warning("cannot locate proper evsel for the side band event\n"); + + perf_mmap__consume(map); + got_data = true; + } + perf_mmap__read_done(map); + } + + if (draining && !got_data) + break; + } + return NULL; +} + +int perf_evlist__start_sb_thread(struct perf_evlist *evlist, + struct target *target) +{ + struct perf_evsel *counter; + + if (!evlist) + return 0; + + if (perf_evlist__create_maps(evlist, target)) + goto out_delete_evlist; + + evlist__for_each_entry(evlist, counter) { + if (perf_evsel__open(counter, evlist->cpus, + evlist->threads) < 0) + goto out_delete_evlist; + } + + if (perf_evlist__mmap(evlist, UINT_MAX)) + goto out_delete_evlist; + + evlist__for_each_entry(evlist, counter) { + if (perf_evsel__enable(counter)) + goto out_delete_evlist; + } + + evlist->thread.done = 0; + if (pthread_create(&evlist->thread.th, NULL, perf_evlist__poll_thread, evlist)) + goto out_delete_evlist; + + return 0; + +out_delete_evlist: + perf_evlist__delete(evlist); + evlist = NULL; + return -1; +} + +void perf_evlist__stop_sb_thread(struct perf_evlist *evlist) +{ + if (!evlist) + return; + evlist->thread.done = 1; + pthread_join(evlist->thread.th, NULL); + perf_evlist__delete(evlist); +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 744906dd4887..c9a0f72677fd 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -54,6 +54,10 @@ struct perf_evlist { struct perf_sample *sample); u64 first_sample_time; u64 last_sample_time; + struct { + pthread_t th; + volatile int done; + } thread; }; struct perf_evsel_str_handler { @@ -87,6 +91,14 @@ int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, int perf_evlist__add_dummy(struct perf_evlist *evlist); +int perf_evlist__add_sb_event(struct perf_evlist **evlist, + struct perf_event_attr *attr, + perf_evsel__sb_cb_t cb, + void *data); +int perf_evlist__start_sb_thread(struct perf_evlist *evlist, + struct target *target); +void perf_evlist__stop_sb_thread(struct perf_evlist *evlist); + int perf_evlist__add_newtp(struct perf_evlist *evlist, const char *sys, const char *name, void *handler); @@ -165,7 +177,8 @@ unsigned long perf_event_mlock_kb_in_pages(void); int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, unsigned int auxtrace_pages, - bool auxtrace_overwrite, int nr_cblocks, int affinity); + bool auxtrace_overwrite, int nr_cblocks, + int affinity, int flush); int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages); void perf_evlist__munmap(struct perf_evlist *evlist); @@ -303,8 +316,6 @@ void perf_evlist__to_front(struct perf_evlist *evlist, void perf_evlist__set_tracking_event(struct perf_evlist *evlist, struct perf_evsel *tracking_evsel); -void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr); - struct perf_evsel * perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 3bbf73e979c0..a10cf4cde920 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -295,7 +295,6 @@ struct perf_evsel *perf_evsel__new_cycles(bool precise) if (!precise) goto new_event; - perf_event_attr__set_max_precise_ip(&attr); /* * Now let the usual logic to set up the perf_event_attr defaults * to kick in when we return and before perf_evsel__open() is called. @@ -305,6 +304,8 @@ new_event: if (evsel == NULL) goto out; + evsel->precise_max = true; + /* use asprintf() because free(evsel) assumes name is allocated */ if (asprintf(&evsel->name, "cycles%s%s%.*s", (attr.precise_ip || attr.exclude_kernel) ? ":" : "", @@ -579,6 +580,12 @@ static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size) return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); } +static int perf_evsel__tool_name(char *bf, size_t size) +{ + int ret = scnprintf(bf, size, "duration_time"); + return ret; +} + const char *perf_evsel__name(struct perf_evsel *evsel) { char bf[128]; @@ -600,7 +607,10 @@ const char *perf_evsel__name(struct perf_evsel *evsel) break; case PERF_TYPE_SOFTWARE: - perf_evsel__sw_name(evsel, bf, sizeof(bf)); + if (evsel->tool_event) + perf_evsel__tool_name(bf, sizeof(bf)); + else + perf_evsel__sw_name(evsel, bf, sizeof(bf)); break; case PERF_TYPE_TRACEPOINT: @@ -1036,7 +1046,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; attr->ksymbol = track && !perf_missing_features.ksymbol; - attr->bpf_event = track && opts->bpf_event && + attr->bpf_event = track && !opts->no_bpf_event && !perf_missing_features.bpf_event; if (opts->record_namespaces) @@ -1083,7 +1093,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, } if (evsel->precise_max) - perf_event_attr__set_max_precise_ip(attr); + attr->precise_ip = 3; if (opts->all_user) { attr->exclude_kernel = 1; @@ -1292,6 +1302,7 @@ void perf_evsel__exit(struct perf_evsel *evsel) { assert(list_empty(&evsel->node)); assert(evsel->evlist == NULL); + perf_evsel__free_counts(evsel); perf_evsel__free_fd(evsel); perf_evsel__free_id(evsel); perf_evsel__free_config_terms(evsel); @@ -1342,10 +1353,9 @@ void perf_counts_values__scale(struct perf_counts_values *count, count->val = 0; } else if (count->run < count->ena) { scaled = 1; - count->val = (u64)((double) count->val * count->ena / count->run + 0.5); + count->val = (u64)((double) count->val * count->ena / count->run); } - } else - count->ena = count->run = 0; + } if (pscaled) *pscaled = scaled; @@ -1749,6 +1759,59 @@ static bool ignore_missing_thread(struct perf_evsel *evsel, return true; } +static void display_attr(struct perf_event_attr *attr) +{ + if (verbose >= 2) { + fprintf(stderr, "%.60s\n", graph_dotted_line); + fprintf(stderr, "perf_event_attr:\n"); + perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL); + fprintf(stderr, "%.60s\n", graph_dotted_line); + } +} + +static int perf_event_open(struct perf_evsel *evsel, + pid_t pid, int cpu, int group_fd, + unsigned long flags) +{ + int precise_ip = evsel->attr.precise_ip; + int fd; + + while (1) { + pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", + pid, cpu, group_fd, flags); + + fd = sys_perf_event_open(&evsel->attr, pid, cpu, group_fd, flags); + if (fd >= 0) + break; + + /* + * Do quick precise_ip fallback if: + * - there is precise_ip set in perf_event_attr + * - maximum precise is requested + * - sys_perf_event_open failed with ENOTSUP error, + * which is associated with wrong precise_ip + */ + if (!precise_ip || !evsel->precise_max || (errno != ENOTSUP)) + break; + + /* + * We tried all the precise_ip values, and it's + * still failing, so leave it to standard fallback. + */ + if (!evsel->attr.precise_ip) { + evsel->attr.precise_ip = precise_ip; + break; + } + + pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP); + evsel->attr.precise_ip--; + pr_debug2("decreasing precise_ip by one (%d)\n", evsel->attr.precise_ip); + display_attr(&evsel->attr); + } + + return fd; +} + int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads) { @@ -1824,12 +1887,7 @@ retry_sample_id: if (perf_missing_features.sample_id_all) evsel->attr.sample_id_all = 0; - if (verbose >= 2) { - fprintf(stderr, "%.60s\n", graph_dotted_line); - fprintf(stderr, "perf_event_attr:\n"); - perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL); - fprintf(stderr, "%.60s\n", graph_dotted_line); - } + display_attr(&evsel->attr); for (cpu = 0; cpu < cpus->nr; cpu++) { @@ -1841,13 +1899,10 @@ retry_sample_id: group_fd = get_group_fd(evsel, cpu, thread); retry_open: - pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", - pid, cpus->map[cpu], group_fd, flags); - test_attr__ready(); - fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu], - group_fd, flags); + fd = perf_event_open(evsel, pid, cpus->map[cpu], + group_fd, flags); FD(evsel, cpu, thread) = fd; @@ -2322,7 +2377,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, if (data->user_regs.abi) { u64 mask = evsel->attr.sample_regs_user; - sz = hweight_long(mask) * sizeof(u64); + sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); data->user_regs.mask = mask; data->user_regs.regs = (u64 *)array; @@ -2378,7 +2433,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) { u64 mask = evsel->attr.sample_regs_intr; - sz = hweight_long(mask) * sizeof(u64); + sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); data->intr_regs.mask = mask; data->intr_regs.regs = (u64 *)array; @@ -2506,7 +2561,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_REGS_USER) { if (sample->user_regs.abi) { result += sizeof(u64); - sz = hweight_long(sample->user_regs.mask) * sizeof(u64); + sz = hweight64(sample->user_regs.mask) * sizeof(u64); result += sz; } else { result += sizeof(u64); @@ -2534,7 +2589,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_REGS_INTR) { if (sample->intr_regs.abi) { result += sizeof(u64); - sz = hweight_long(sample->intr_regs.mask) * sizeof(u64); + sz = hweight64(sample->intr_regs.mask) * sizeof(u64); result += sz; } else { result += sizeof(u64); @@ -2664,7 +2719,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, if (type & PERF_SAMPLE_REGS_USER) { if (sample->user_regs.abi) { *array++ = sample->user_regs.abi; - sz = hweight_long(sample->user_regs.mask) * sizeof(u64); + sz = hweight64(sample->user_regs.mask) * sizeof(u64); memcpy(array, sample->user_regs.regs, sz); array = (void *)array + sz; } else { @@ -2700,7 +2755,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, if (type & PERF_SAMPLE_REGS_INTR) { if (sample->intr_regs.abi) { *array++ = sample->intr_regs.abi; - sz = hweight_long(sample->intr_regs.mask) * sizeof(u64); + sz = hweight64(sample->intr_regs.mask) * sizeof(u64); memcpy(array, sample->intr_regs.regs, sz); array = (void *)array + sz; } else { diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index cc578e02e08f..6d190cbf1070 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -73,6 +73,13 @@ struct perf_evsel_config_term { struct perf_stat_evsel; +typedef int (perf_evsel__sb_cb_t)(union perf_event *event, void *data); + +enum perf_tool_event { + PERF_TOOL_NONE = 0, + PERF_TOOL_DURATION_TIME = 1, +}; + /** struct perf_evsel - event selector * * @evlist - evlist this evsel is in, if it is in one. @@ -119,6 +126,7 @@ struct perf_evsel { unsigned int sample_size; int id_pos; int is_pos; + enum perf_tool_event tool_event; bool uniquified_name; bool snapshot; bool supported; @@ -151,6 +159,10 @@ struct perf_evsel { bool collect_stat; bool weak_group; const char *pmu_name; + struct { + perf_evsel__sb_cb_t *cb; + void *data; + } side_band; }; union u64_swap { diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 01b324c275b9..2d2af2ac2b1e 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -18,6 +18,7 @@ #include <sys/utsname.h> #include <linux/time64.h> #include <dirent.h> +#include <bpf/libbpf.h> #include "evlist.h" #include "evsel.h" @@ -40,6 +41,7 @@ #include "time-utils.h" #include "units.h" #include "cputopo.h" +#include "bpf-event.h" #include "sane_ctype.h" @@ -861,6 +863,104 @@ static int write_clockid(struct feat_fd *ff, sizeof(ff->ph->env.clockid_res_ns)); } +static int write_dir_format(struct feat_fd *ff, + struct perf_evlist *evlist __maybe_unused) +{ + struct perf_session *session; + struct perf_data *data; + + session = container_of(ff->ph, struct perf_session, header); + data = session->data; + + if (WARN_ON(!perf_data__is_dir(data))) + return -1; + + return do_write(ff, &data->dir.version, sizeof(data->dir.version)); +} + +#ifdef HAVE_LIBBPF_SUPPORT +static int write_bpf_prog_info(struct feat_fd *ff, + struct perf_evlist *evlist __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + struct rb_root *root; + struct rb_node *next; + int ret; + + down_read(&env->bpf_progs.lock); + + ret = do_write(ff, &env->bpf_progs.infos_cnt, + sizeof(env->bpf_progs.infos_cnt)); + if (ret < 0) + goto out; + + root = &env->bpf_progs.infos; + next = rb_first(root); + while (next) { + struct bpf_prog_info_node *node; + size_t len; + + node = rb_entry(next, struct bpf_prog_info_node, rb_node); + next = rb_next(&node->rb_node); + len = sizeof(struct bpf_prog_info_linear) + + node->info_linear->data_len; + + /* before writing to file, translate address to offset */ + bpf_program__bpil_addr_to_offs(node->info_linear); + ret = do_write(ff, node->info_linear, len); + /* + * translate back to address even when do_write() fails, + * so that this function never changes the data. + */ + bpf_program__bpil_offs_to_addr(node->info_linear); + if (ret < 0) + goto out; + } +out: + up_read(&env->bpf_progs.lock); + return ret; +} +#else // HAVE_LIBBPF_SUPPORT +static int write_bpf_prog_info(struct feat_fd *ff __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + return 0; +} +#endif // HAVE_LIBBPF_SUPPORT + +static int write_bpf_btf(struct feat_fd *ff, + struct perf_evlist *evlist __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + struct rb_root *root; + struct rb_node *next; + int ret; + + down_read(&env->bpf_progs.lock); + + ret = do_write(ff, &env->bpf_progs.btfs_cnt, + sizeof(env->bpf_progs.btfs_cnt)); + + if (ret < 0) + goto out; + + root = &env->bpf_progs.btfs; + next = rb_first(root); + while (next) { + struct btf_node *node; + + node = rb_entry(next, struct btf_node, rb_node); + next = rb_next(&node->rb_node); + ret = do_write(ff, &node->id, + sizeof(u32) * 2 + node->data_size); + if (ret < 0) + goto out; + } +out: + up_read(&env->bpf_progs.lock); + return ret; +} + static int cpu_cache_level__sort(const void *a, const void *b) { struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a; @@ -1341,6 +1441,63 @@ static void print_clockid(struct feat_fd *ff, FILE *fp) ff->ph->env.clockid_res_ns * 1000); } +static void print_dir_format(struct feat_fd *ff, FILE *fp) +{ + struct perf_session *session; + struct perf_data *data; + + session = container_of(ff->ph, struct perf_session, header); + data = session->data; + + fprintf(fp, "# directory data version : %"PRIu64"\n", data->dir.version); +} + +static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp) +{ + struct perf_env *env = &ff->ph->env; + struct rb_root *root; + struct rb_node *next; + + down_read(&env->bpf_progs.lock); + + root = &env->bpf_progs.infos; + next = rb_first(root); + + while (next) { + struct bpf_prog_info_node *node; + + node = rb_entry(next, struct bpf_prog_info_node, rb_node); + next = rb_next(&node->rb_node); + + bpf_event__print_bpf_prog_info(&node->info_linear->info, + env, fp); + } + + up_read(&env->bpf_progs.lock); +} + +static void print_bpf_btf(struct feat_fd *ff, FILE *fp) +{ + struct perf_env *env = &ff->ph->env; + struct rb_root *root; + struct rb_node *next; + + down_read(&env->bpf_progs.lock); + + root = &env->bpf_progs.btfs; + next = rb_first(root); + + while (next) { + struct btf_node *node; + + node = rb_entry(next, struct btf_node, rb_node); + next = rb_next(&node->rb_node); + fprintf(fp, "# btf info of id %u\n", node->id); + } + + up_read(&env->bpf_progs.lock); +} + static void free_event_desc(struct perf_evsel *events) { struct perf_evsel *evsel; @@ -2373,6 +2530,143 @@ static int process_clockid(struct feat_fd *ff, return 0; } +static int process_dir_format(struct feat_fd *ff, + void *_data __maybe_unused) +{ + struct perf_session *session; + struct perf_data *data; + + session = container_of(ff->ph, struct perf_session, header); + data = session->data; + + if (WARN_ON(!perf_data__is_dir(data))) + return -1; + + return do_read_u64(ff, &data->dir.version); +} + +#ifdef HAVE_LIBBPF_SUPPORT +static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) +{ + struct bpf_prog_info_linear *info_linear; + struct bpf_prog_info_node *info_node; + struct perf_env *env = &ff->ph->env; + u32 count, i; + int err = -1; + + if (ff->ph->needs_swap) { + pr_warning("interpreting bpf_prog_info from systems with endianity is not yet supported\n"); + return 0; + } + + if (do_read_u32(ff, &count)) + return -1; + + down_write(&env->bpf_progs.lock); + + for (i = 0; i < count; ++i) { + u32 info_len, data_len; + + info_linear = NULL; + info_node = NULL; + if (do_read_u32(ff, &info_len)) + goto out; + if (do_read_u32(ff, &data_len)) + goto out; + + if (info_len > sizeof(struct bpf_prog_info)) { + pr_warning("detected invalid bpf_prog_info\n"); + goto out; + } + + info_linear = malloc(sizeof(struct bpf_prog_info_linear) + + data_len); + if (!info_linear) + goto out; + info_linear->info_len = sizeof(struct bpf_prog_info); + info_linear->data_len = data_len; + if (do_read_u64(ff, (u64 *)(&info_linear->arrays))) + goto out; + if (__do_read(ff, &info_linear->info, info_len)) + goto out; + if (info_len < sizeof(struct bpf_prog_info)) + memset(((void *)(&info_linear->info)) + info_len, 0, + sizeof(struct bpf_prog_info) - info_len); + + if (__do_read(ff, info_linear->data, data_len)) + goto out; + + info_node = malloc(sizeof(struct bpf_prog_info_node)); + if (!info_node) + goto out; + + /* after reading from file, translate offset to address */ + bpf_program__bpil_offs_to_addr(info_linear); + info_node->info_linear = info_linear; + perf_env__insert_bpf_prog_info(env, info_node); + } + + up_write(&env->bpf_progs.lock); + return 0; +out: + free(info_linear); + free(info_node); + up_write(&env->bpf_progs.lock); + return err; +} +#else // HAVE_LIBBPF_SUPPORT +static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data __maybe_unused) +{ + return 0; +} +#endif // HAVE_LIBBPF_SUPPORT + +static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + struct btf_node *node = NULL; + u32 count, i; + int err = -1; + + if (ff->ph->needs_swap) { + pr_warning("interpreting btf from systems with endianity is not yet supported\n"); + return 0; + } + + if (do_read_u32(ff, &count)) + return -1; + + down_write(&env->bpf_progs.lock); + + for (i = 0; i < count; ++i) { + u32 id, data_size; + + if (do_read_u32(ff, &id)) + goto out; + if (do_read_u32(ff, &data_size)) + goto out; + + node = malloc(sizeof(struct btf_node) + data_size); + if (!node) + goto out; + + node->id = id; + node->data_size = data_size; + + if (__do_read(ff, node->data, data_size)) + goto out; + + perf_env__insert_btf(env, node); + node = NULL; + } + + err = 0; +out: + up_write(&env->bpf_progs.lock); + free(node); + return err; +} + struct feature_ops { int (*write)(struct feat_fd *ff, struct perf_evlist *evlist); void (*print)(struct feat_fd *ff, FILE *fp); @@ -2432,7 +2726,10 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPN(CACHE, cache, true), FEAT_OPR(SAMPLE_TIME, sample_time, false), FEAT_OPR(MEM_TOPOLOGY, mem_topology, true), - FEAT_OPR(CLOCKID, clockid, false) + FEAT_OPR(CLOCKID, clockid, false), + FEAT_OPN(DIR_FORMAT, dir_format, false), + FEAT_OPR(BPF_PROG_INFO, bpf_prog_info, false), + FEAT_OPR(BPF_BTF, bpf_btf, false), }; struct header_print_data { diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 0d553ddca0a3..386da49e1bfa 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -39,6 +39,9 @@ enum { HEADER_SAMPLE_TIME, HEADER_MEM_TOPOLOGY, HEADER_CLOCKID, + HEADER_DIR_FORMAT, + HEADER_BPF_PROG_INFO, + HEADER_BPF_BTF, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; @@ -48,6 +51,10 @@ enum perf_header_version { PERF_HEADER_VERSION_2, }; +enum perf_dir_version { + PERF_DIR_VERSION = 1, +}; + struct perf_file_section { u64 offset; u64 size; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index f9eb95bf3938..7ace7a10054d 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -19,6 +19,7 @@ #include <math.h> #include <inttypes.h> #include <sys/param.h> +#include <linux/time64.h> static bool hists__filter_entry_by_dso(struct hists *hists, struct hist_entry *he); @@ -192,6 +193,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3); hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12); hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12); + hists__new_col_len(hists, HISTC_TIME, 12); if (h->srcline) { len = MAX(strlen(h->srcline), strlen(sort_srcline.se_header)); @@ -246,6 +248,14 @@ static void he_stat__add_cpumode_period(struct he_stat *he_stat, } } +static long hist_time(unsigned long htime) +{ + unsigned long time_quantum = symbol_conf.time_quantum; + if (time_quantum) + return (htime / time_quantum) * time_quantum; + return htime; +} + static void he_stat__add_period(struct he_stat *he_stat, u64 period, u64 weight) { @@ -426,6 +436,13 @@ static int hist_entry__init(struct hist_entry *he, goto err_rawdata; } + if (symbol_conf.res_sample) { + he->res_samples = calloc(sizeof(struct res_sample), + symbol_conf.res_sample); + if (!he->res_samples) + goto err_srcline; + } + INIT_LIST_HEAD(&he->pairs.node); thread__get(he->thread); he->hroot_in = RB_ROOT_CACHED; @@ -436,6 +453,9 @@ static int hist_entry__init(struct hist_entry *he, return 0; +err_srcline: + free(he->srcline); + err_rawdata: free(he->raw_data); @@ -593,6 +613,32 @@ out: return he; } +static unsigned random_max(unsigned high) +{ + unsigned thresh = -high % high; + for (;;) { + unsigned r = random(); + if (r >= thresh) + return r % high; + } +} + +static void hists__res_sample(struct hist_entry *he, struct perf_sample *sample) +{ + struct res_sample *r; + int j; + + if (he->num_res < symbol_conf.res_sample) { + j = he->num_res++; + } else { + j = random_max(symbol_conf.res_sample); + } + r = &he->res_samples[j]; + r->time = sample->time; + r->cpu = sample->cpu; + r->tid = sample->tid; +} + static struct hist_entry* __hists__add_entry(struct hists *hists, struct addr_location *al, @@ -635,10 +681,13 @@ __hists__add_entry(struct hists *hists, .raw_data = sample->raw_data, .raw_size = sample->raw_size, .ops = ops, + .time = hist_time(sample->time), }, *he = hists__findnew_entry(hists, &entry, al, sample_self); if (!hists->has_callchains && he && he->callchain_size != 0) hists->has_callchains = true; + if (he && symbol_conf.res_sample) + hists__res_sample(he, sample); return he; } @@ -1062,8 +1111,10 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent, iter->evsel, al, max_stack_depth); - if (err) + if (err) { + map__put(alm); return err; + } err = iter->ops->prepare_entry(iter, al); if (err) @@ -1162,6 +1213,7 @@ void hist_entry__delete(struct hist_entry *he) mem_info__zput(he->mem_info); } + zfree(&he->res_samples); zfree(&he->stat_acc); free_srcline(he->srcline); if (he->srcfile && he->srcfile[0]) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 4af27fbab24f..76ff6c6d03b8 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -31,6 +31,7 @@ enum hist_filter { enum hist_column { HISTC_SYMBOL, + HISTC_TIME, HISTC_DSO, HISTC_THREAD, HISTC_COMM, @@ -432,9 +433,18 @@ struct hist_browser_timer { }; struct annotation_options; +struct res_sample; + +enum rstype { + A_NORMAL, + A_ASM, + A_SOURCE +}; #ifdef HAVE_SLANG_SUPPORT #include "../ui/keysyms.h" +void attr_to_script(char *buf, struct perf_event_attr *attr); + int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel, struct hist_browser_timer *hbt, struct annotation_options *annotation_opts); @@ -449,7 +459,13 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct perf_env *env, bool warn_lost_event, struct annotation_options *annotation_options); -int script_browse(const char *script_opt); + +int script_browse(const char *script_opt, struct perf_evsel *evsel); + +void run_script(char *cmd); +int res_sample_browse(struct res_sample *res_samples, int num_res, + struct perf_evsel *evsel, enum rstype rstype); +void res_sample_init(void); #else static inline int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, @@ -478,11 +494,22 @@ static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused, return 0; } -static inline int script_browse(const char *script_opt __maybe_unused) +static inline int script_browse(const char *script_opt __maybe_unused, + struct perf_evsel *evsel __maybe_unused) { return 0; } +static inline int res_sample_browse(struct res_sample *res_samples __maybe_unused, + int num_res __maybe_unused, + struct perf_evsel *evsel __maybe_unused, + enum rstype rstype __maybe_unused) +{ + return 0; +} + +static inline void res_sample_init(void) {} + #define K_LEFT -1000 #define K_RIGHT -2000 #define K_SWITCH_INPUT_DATA -3000 diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 6e03db142091..872fab163585 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -251,19 +251,15 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d)) decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n / decoder->tsc_ctc_ratio_d; - - /* - * Allow for timestamps appearing to backwards because a TSC - * packet has slipped past a MTC packet, so allow 2 MTC ticks - * or ... - */ - decoder->tsc_slip = multdiv(2 << decoder->mtc_shift, - decoder->tsc_ctc_ratio_n, - decoder->tsc_ctc_ratio_d); } - /* ... or 0x100 paranoia */ - if (decoder->tsc_slip < 0x100) - decoder->tsc_slip = 0x100; + + /* + * A TSC packet can slip past MTC packets so that the timestamp appears + * to go backwards. One estimate is that can be up to about 40 CPU + * cycles, which is certainly less than 0x1000 TSC ticks, but accept + * slippage an order of magnitude more to be on the safe side. + */ + decoder->tsc_slip = 0x10000; intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift); intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 61959aba7e27..3c520baa198c 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1421,6 +1421,20 @@ static void machine__set_kernel_mmap(struct machine *machine, machine->vmlinux_map->end = ~0ULL; } +static void machine__update_kernel_mmap(struct machine *machine, + u64 start, u64 end) +{ + struct map *map = machine__kernel_map(machine); + + map__get(map); + map_groups__remove(&machine->kmaps, map); + + machine__set_kernel_mmap(machine, start, end); + + map_groups__insert(&machine->kmaps, map); + map__put(map); +} + int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); @@ -1453,17 +1467,11 @@ int machine__create_kernel_maps(struct machine *machine) goto out_put; } - /* we have a real start address now, so re-order the kmaps */ - map = machine__kernel_map(machine); - - map__get(map); - map_groups__remove(&machine->kmaps, map); - - /* assume it's the last in the kmaps */ - machine__set_kernel_mmap(machine, addr, ~0ULL); - - map_groups__insert(&machine->kmaps, map); - map__put(map); + /* + * we have a real start address now, so re-order the kmaps + * assume it's the last in the kmaps + */ + machine__update_kernel_mmap(machine, addr, ~0ULL); } if (machine__create_extra_kernel_maps(machine, kernel)) @@ -1599,7 +1607,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, if (strstr(kernel->long_name, "vmlinux")) dso__set_short_name(kernel, "[kernel.vmlinux]", false); - machine__set_kernel_mmap(machine, event->mmap.start, + machine__update_kernel_mmap(machine, event->mmap.start, event->mmap.start + event->mmap.len); /* diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index fbeb0c6efaa6..ee71efb9db62 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -261,6 +261,22 @@ bool __map__is_extra_kernel_map(const struct map *map) return kmap && kmap->name[0]; } +bool __map__is_bpf_prog(const struct map *map) +{ + const char *name; + + if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) + return true; + + /* + * If PERF_RECORD_BPF_EVENT is not included, the dso will not have + * type of DSO_BINARY_TYPE__BPF_PROG_INFO. In such cases, we can + * guess the type based on name. + */ + name = map->dso->short_name; + return name && (strstr(name, "bpf_prog_") == name); +} + bool map__has_symbols(const struct map *map) { return dso__has_symbols(map->dso); @@ -577,10 +593,25 @@ static void __maps__purge(struct maps *maps) } } +static void __maps__purge_names(struct maps *maps) +{ + struct rb_root *root = &maps->names; + struct rb_node *next = rb_first(root); + + while (next) { + struct map *pos = rb_entry(next, struct map, rb_node_name); + + next = rb_next(&pos->rb_node_name); + rb_erase_init(&pos->rb_node_name, root); + map__put(pos); + } +} + static void maps__exit(struct maps *maps) { down_write(&maps->lock); __maps__purge(maps); + __maps__purge_names(maps); up_write(&maps->lock); } @@ -895,10 +926,8 @@ static void __maps__insert_name(struct maps *maps, struct map *map) rc = strcmp(m->dso->short_name, map->dso->short_name); if (rc < 0) p = &(*p)->rb_left; - else if (rc > 0) - p = &(*p)->rb_right; else - return; + p = &(*p)->rb_right; } rb_link_node(&map->rb_node_name, parent, p); rb_insert_color(&map->rb_node_name, &maps->names); @@ -917,6 +946,9 @@ static void __maps__remove(struct maps *maps, struct map *map) { rb_erase_init(&map->rb_node, &maps->entries); map__put(map); + + rb_erase_init(&map->rb_node_name, &maps->names); + map__put(map); } void maps__remove(struct maps *maps, struct map *map) diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 0e20749f2c55..dc93787c74f0 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -159,10 +159,12 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, bool __map__is_kernel(const struct map *map); bool __map__is_extra_kernel_map(const struct map *map); +bool __map__is_bpf_prog(const struct map *map); static inline bool __map__is_kmodule(const struct map *map) { - return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map); + return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) && + !__map__is_bpf_prog(map); } bool map__has_symbols(const struct map *map); diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index cdc7740fc181..ef3d79b2c90b 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -440,6 +440,8 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c perf_mmap__setup_affinity_mask(map, mp); + map->flush = mp->flush; + if (auxtrace_mmap__mmap(&map->auxtrace_mmap, &mp->auxtrace_mp, map->base, fd)) return -1; @@ -492,7 +494,7 @@ static int __perf_mmap__read_init(struct perf_mmap *md) md->start = md->overwrite ? head : old; md->end = md->overwrite ? old : head; - if (md->start == md->end) + if ((md->end - md->start) < md->flush) return -EAGAIN; size = md->end - md->start; diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index e566c19b242b..b82f8c2d55c4 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -39,6 +39,7 @@ struct perf_mmap { } aio; #endif cpu_set_t affinity_mask; + u64 flush; }; /* @@ -70,7 +71,7 @@ enum bkw_mmap_state { }; struct mmap_params { - int prot, mask, nr_cblocks, affinity; + int prot, mask, nr_cblocks, affinity, flush; struct auxtrace_mmap_params auxtrace_mp; }; diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index ea523d3b248f..989fed6f43b5 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -270,6 +270,8 @@ static int __ordered_events__flush(struct ordered_events *oe, enum oe_flush how, "FINAL", "ROUND", "HALF ", + "TOP ", + "TIME ", }; int err; bool show_progress = false; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 4dcc01b2532c..4432bfe039fd 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -317,10 +317,12 @@ static struct perf_evsel * __add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, char *name, struct perf_pmu *pmu, - struct list_head *config_terms, bool auto_merge_stats) + struct list_head *config_terms, bool auto_merge_stats, + const char *cpu_list) { struct perf_evsel *evsel; - struct cpu_map *cpus = pmu ? pmu->cpus : NULL; + struct cpu_map *cpus = pmu ? pmu->cpus : + cpu_list ? cpu_map__new(cpu_list) : NULL; event_attr_init(attr); @@ -348,7 +350,25 @@ static int add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, char *name, struct list_head *config_terms) { - return __add_event(list, idx, attr, name, NULL, config_terms, false) ? 0 : -ENOMEM; + return __add_event(list, idx, attr, name, NULL, config_terms, false, NULL) ? 0 : -ENOMEM; +} + +static int add_event_tool(struct list_head *list, int *idx, + enum perf_tool_event tool_event) +{ + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_DUMMY, + }; + + evsel = __add_event(list, idx, &attr, NULL, NULL, NULL, false, "0"); + if (!evsel) + return -ENOMEM; + evsel->tool_event = tool_event; + if (tool_event == PERF_TOOL_DURATION_TIME) + evsel->unit = strdup("ns"); + return 0; } static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size) @@ -1233,6 +1253,13 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, get_config_name(head_config), &config_terms); } +int parse_events_add_tool(struct parse_events_state *parse_state, + struct list_head *list, + enum perf_tool_event tool_event) +{ + return add_event_tool(list, &parse_state->idx, tool_event); +} + int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, struct list_head *head_config, @@ -1267,7 +1294,8 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (!head_config) { attr.type = pmu->type; - evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats); + evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, + auto_merge_stats, NULL); if (evsel) { evsel->pmu_name = name; evsel->use_uncore_alias = use_uncore_alias; @@ -1295,7 +1323,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel = __add_event(list, &parse_state->idx, &attr, get_config_name(head_config), pmu, - &config_terms, auto_merge_stats); + &config_terms, auto_merge_stats, NULL); if (evsel) { evsel->unit = info.unit; evsel->scale = info.scale; @@ -2271,6 +2299,7 @@ static bool is_event_supported(u8 type, unsigned config) perf_evsel__delete(evsel); } + thread_map__put(tmap); return ret; } @@ -2341,6 +2370,7 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob, printf(" %-50s [%s]\n", buf, "SDT event"); free(buf); } + free(path); } else printf(" %-50s [%s]\n", nd->s, "SDT event"); if (nd2) { @@ -2427,6 +2457,25 @@ out_enomem: return evt_num; } +static void print_tool_event(const char *name, const char *event_glob, + bool name_only) +{ + if (event_glob && !strglobmatch(name, event_glob)) + return; + if (name_only) + printf("%s ", name); + else + printf(" %-50s [%s]\n", name, "Tool event"); + +} + +void print_tool_events(const char *event_glob, bool name_only) +{ + print_tool_event("duration_time", event_glob, name_only); + if (pager_in_use()) + printf("\n"); +} + void print_symbol_events(const char *event_glob, unsigned type, struct event_symbol *syms, unsigned max, bool name_only) @@ -2510,6 +2559,7 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag, print_symbol_events(event_glob, PERF_TYPE_SOFTWARE, event_symbols_sw, PERF_COUNT_SW_MAX, name_only); + print_tool_events(event_glob, name_only); print_hwcache_events(event_glob, name_only); diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 5ed035cbcbb7..a052cd6ac63e 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -160,6 +160,10 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, u32 type, u64 config, struct list_head *head_config); +enum perf_tool_event; +int parse_events_add_tool(struct parse_events_state *parse_state, + struct list_head *list, + enum perf_tool_event tool_event); int parse_events_add_cache(struct list_head *list, int *idx, char *type, char *op_result1, char *op_result2, struct parse_events_error *error, @@ -200,6 +204,7 @@ extern struct event_symbol event_symbols_sw[]; void print_symbol_events(const char *event_glob, unsigned type, struct event_symbol *syms, unsigned max, bool name_only); +void print_tool_events(const char *event_glob, bool name_only); void print_tracepoint_events(const char *subsys_glob, const char *event_glob, bool name_only); int print_hwcache_events(const char *event_glob, bool name_only); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 7805c71aaae2..c54bfe88626c 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -15,6 +15,7 @@ #include "../perf.h" #include "parse-events.h" #include "parse-events-bison.h" +#include "evsel.h" char *parse_events_get_text(yyscan_t yyscanner); YYSTYPE *parse_events_get_lval(yyscan_t yyscanner); @@ -154,6 +155,14 @@ static int sym(yyscan_t scanner, int type, int config) return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW; } +static int tool(yyscan_t scanner, enum perf_tool_event event) +{ + YYSTYPE *yylval = parse_events_get_lval(scanner); + + yylval->num = event; + return PE_VALUE_SYM_TOOL; +} + static int term(yyscan_t scanner, int type) { YYSTYPE *yylval = parse_events_get_lval(scanner); @@ -322,7 +331,7 @@ cpu-migrations|migrations { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); } emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } -duration_time { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } +duration_time { return tool(yyscanner, PERF_TOOL_DURATION_TIME); } bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); } /* diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 44819bdb037d..6ad8d4914969 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -14,6 +14,7 @@ #include <linux/types.h> #include "util.h" #include "pmu.h" +#include "evsel.h" #include "debug.h" #include "parse-events.h" #include "parse-events-bison.h" @@ -45,6 +46,7 @@ static void inc_group_count(struct list_head *list, %token PE_START_EVENTS PE_START_TERMS %token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM +%token PE_VALUE_SYM_TOOL %token PE_EVENT_NAME %token PE_NAME %token PE_BPF_OBJECT PE_BPF_SOURCE @@ -58,6 +60,7 @@ static void inc_group_count(struct list_head *list, %type <num> PE_VALUE %type <num> PE_VALUE_SYM_HW %type <num> PE_VALUE_SYM_SW +%type <num> PE_VALUE_SYM_TOOL %type <num> PE_RAW %type <num> PE_TERM %type <str> PE_NAME @@ -321,6 +324,15 @@ value_sym sep_slash_slash_dc ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, NULL)); $$ = list; } +| +PE_VALUE_SYM_TOOL sep_slash_slash_dc +{ + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_tool(_parse_state, list, $1)); + $$ = list; +} event_legacy_cache: PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 6199a3174ab9..e0429f4ef335 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -732,10 +732,20 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) if (!is_arm_pmu_core(name)) { pname = pe->pmu ? pe->pmu : "cpu"; + + /* + * uncore alias may be from different PMU + * with common prefix + */ + if (pmu_is_uncore(name) && + !strncmp(pname, name, strlen(pname))) + goto new_alias; + if (strcmp(pname, name)) continue; } +new_alias: /* need type casts to override 'const' */ __perf_pmu__new_alias(head, NULL, (char *)pe->name, (char *)pe->desc, (char *)pe->event, diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index a1b8d9649ca7..198e09ff611e 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -160,8 +160,10 @@ static struct map *kernel_get_module_map(const char *module) if (module && strchr(module, '/')) return dso__new_map(module); - if (!module) - module = "kernel"; + if (!module) { + pos = machine__kernel_map(host_machine); + return map__get(pos); + } for (pos = maps__first(maps); pos; pos = map__next(pos)) { /* short_name is "[module]" */ diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index dda0ac978b1e..6aa7e2352e16 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -342,7 +342,7 @@ static bool is_tracepoint(struct pyrf_event *pevent) static PyObject* tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field) { - struct tep_handle *pevent = field->event->pevent; + struct tep_handle *pevent = field->event->tep; void *data = pe->sample.raw_data; PyObject *ret = NULL; unsigned long long val; diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 5f06378a482b..61aa7f3df915 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -372,7 +372,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, ns = nsecs - s * NSEC_PER_SEC; scripting_context->event_data = data; - scripting_context->pevent = evsel->tp_format->pevent; + scripting_context->pevent = evsel->tp_format->tep; ENTER; SAVETMPS; diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 09604c6508f0..22f52b669871 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -837,7 +837,7 @@ static void python_process_tracepoint(struct perf_sample *sample, ns = nsecs - s * NSEC_PER_SEC; scripting_context->event_data = data; - scripting_context->pevent = evsel->tp_format->pevent; + scripting_context->pevent = evsel->tp_format->tep; context = _PyCapsule_New(scripting_context, NULL, NULL); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index db643f3c2b95..bad5f87ae001 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -132,6 +132,7 @@ struct perf_session *perf_session__new(struct perf_data *data, ordered_events__init(&session->ordered_events, ordered_events__deliver_event, NULL); + perf_env__init(&session->header.env); if (data) { if (perf_data__open(data)) goto out_delete; @@ -152,6 +153,10 @@ struct perf_session *perf_session__new(struct perf_data *data, } perf_evlist__init_trace_event_sample_raw(session->evlist); + + /* Open the directory data. */ + if (data->is_dir && perf_data__open_dir(data)) + goto out_delete; } } else { session->machines.host.env = &perf_env; @@ -1843,10 +1848,17 @@ fetch_mmaped_event(struct perf_session *session, #define NUM_MMAPS 128 #endif +struct reader; + +typedef s64 (*reader_cb_t)(struct perf_session *session, + union perf_event *event, + u64 file_offset); + struct reader { - int fd; - u64 data_size; - u64 data_offset; + int fd; + u64 data_size; + u64 data_offset; + reader_cb_t process; }; static int @@ -1916,12 +1928,14 @@ more: size = event->header.size; + skip = -EINVAL; + if (size < sizeof(struct perf_event_header) || - (skip = perf_session__process_event(session, event, file_pos)) < 0) { - pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", + (skip = rd->process(session, event, file_pos)) < 0) { + pr_err("%#" PRIx64 " [%#x]: failed to process type: %d [%s]\n", file_offset + head, event->header.size, - event->header.type); - err = -EINVAL; + event->header.type, strerror(-skip)); + err = skip; goto out; } @@ -1943,12 +1957,20 @@ out: return err; } +static s64 process_simple(struct perf_session *session, + union perf_event *event, + u64 file_offset) +{ + return perf_session__process_event(session, event, file_offset); +} + static int __perf_session__process_events(struct perf_session *session) { struct reader rd = { .fd = perf_data__fd(session->data), .data_size = session->header.data_size, .data_offset = session->header.data_offset, + .process = process_simple, }; struct ordered_events *oe = &session->ordered_events; struct perf_tool *tool = session->tool; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index d2299e912e59..5d2518e89fc4 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -3,6 +3,7 @@ #include <inttypes.h> #include <regex.h> #include <linux/mman.h> +#include <linux/time64.h> #include "sort.h" #include "hist.h" #include "comm.h" @@ -12,9 +13,11 @@ #include "evsel.h" #include "evlist.h" #include "strlist.h" +#include "strbuf.h" #include <traceevent/event-parse.h> #include "mem-events.h" #include "annotate.h" +#include "time-utils.h" #include <linux/kernel.h> regex_t parent_regex; @@ -654,6 +657,42 @@ struct sort_entry sort_socket = { .se_width_idx = HISTC_SOCKET, }; +/* --sort time */ + +static int64_t +sort__time_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->time - left->time; +} + +static int hist_entry__time_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + unsigned long secs; + unsigned long long nsecs; + char he_time[32]; + + nsecs = he->time; + secs = nsecs / NSEC_PER_SEC; + nsecs -= secs * NSEC_PER_SEC; + + if (symbol_conf.nanosecs) + snprintf(he_time, sizeof he_time, "%5lu.%09llu: ", + secs, nsecs); + else + timestamp__scnprintf_usec(he->time, he_time, + sizeof(he_time)); + + return repsep_snprintf(bf, size, "%-.*s", width, he_time); +} + +struct sort_entry sort_time = { + .se_header = "Time", + .se_cmp = sort__time_cmp, + .se_snprintf = hist_entry__time_snprintf, + .se_width_idx = HISTC_TIME, +}; + /* --sort trace */ static char *get_trace_output(struct hist_entry *he) @@ -1634,6 +1673,7 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_DSO_SIZE, "dso_size", sort_dso_size), DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id), DIM(SORT_SYM_IPC_NULL, "ipc_null", sort_sym_ipc_null), + DIM(SORT_TIME, "time", sort_time), }; #undef DIM @@ -3068,3 +3108,54 @@ void reset_output_field(void) reset_dimensions(); perf_hpp__reset_output_field(&perf_hpp_list); } + +#define INDENT (3*8 + 1) + +static void add_key(struct strbuf *sb, const char *str, int *llen) +{ + if (*llen >= 75) { + strbuf_addstr(sb, "\n\t\t\t "); + *llen = INDENT; + } + strbuf_addf(sb, " %s", str); + *llen += strlen(str) + 1; +} + +static void add_sort_string(struct strbuf *sb, struct sort_dimension *s, int n, + int *llen) +{ + int i; + + for (i = 0; i < n; i++) + add_key(sb, s[i].name, llen); +} + +static void add_hpp_sort_string(struct strbuf *sb, struct hpp_dimension *s, int n, + int *llen) +{ + int i; + + for (i = 0; i < n; i++) + add_key(sb, s[i].name, llen); +} + +const char *sort_help(const char *prefix) +{ + struct strbuf sb; + char *s; + int len = strlen(prefix) + INDENT; + + strbuf_init(&sb, 300); + strbuf_addstr(&sb, prefix); + add_hpp_sort_string(&sb, hpp_sort_dimensions, + ARRAY_SIZE(hpp_sort_dimensions), &len); + add_sort_string(&sb, common_sort_dimensions, + ARRAY_SIZE(common_sort_dimensions), &len); + add_sort_string(&sb, bstack_sort_dimensions, + ARRAY_SIZE(bstack_sort_dimensions), &len); + add_sort_string(&sb, memory_sort_dimensions, + ARRAY_SIZE(memory_sort_dimensions), &len); + s = strbuf_detach(&sb, NULL); + strbuf_release(&sb); + return s; +} diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 2fbee0b1011c..ce376a73f964 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -47,6 +47,12 @@ extern struct sort_entry sort_srcline; extern enum sort_type sort__first_dimension; extern const char default_mem_sort_order[]; +struct res_sample { + u64 time; + int cpu; + int tid; +}; + struct he_stat { u64 period; u64 period_sys; @@ -135,10 +141,13 @@ struct hist_entry { char *srcfile; struct symbol *parent; struct branch_info *branch_info; + long time; struct hists *hists; struct mem_info *mem_info; void *raw_data; u32 raw_size; + int num_res; + struct res_sample *res_samples; void *trace_output; struct perf_hpp_list *hpp_list; struct hist_entry *parent_he; @@ -231,6 +240,7 @@ enum sort_type { SORT_DSO_SIZE, SORT_CGROUP_ID, SORT_SYM_IPC_NULL, + SORT_TIME, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, @@ -286,6 +296,8 @@ void reset_output_field(void); void sort__setup_elide(FILE *fp); void perf_hpp__set_elide(int idx, bool elide); +const char *sort_help(const char *prefix); + int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset); bool is_strict_order(const char *order); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 6d043c78f3c2..3324f23c7efc 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -18,11 +18,6 @@ #define CNTR_NOT_SUPPORTED "<not supported>" #define CNTR_NOT_COUNTED "<not counted>" -static bool is_duration_time(struct perf_evsel *evsel) -{ - return !strcmp(evsel->name, "duration_time"); -} - static void print_running(struct perf_stat_config *config, u64 run, u64 ena) { @@ -628,9 +623,6 @@ static void print_aggr(struct perf_stat_config *config, ad.id = id = config->aggr_map->map[s]; first = true; evlist__for_each_entry(evlist, counter) { - if (is_duration_time(counter)) - continue; - ad.val = ad.ena = ad.run = 0; ad.nr = 0; if (!collect_data(config, counter, aggr_cb, &ad)) @@ -848,8 +840,6 @@ static void print_no_aggr_metric(struct perf_stat_config *config, if (prefix) fputs(prefix, config->output); evlist__for_each_entry(evlist, counter) { - if (is_duration_time(counter)) - continue; if (first) { aggr_printout(config, counter, cpu, 0); first = false; @@ -906,8 +896,6 @@ static void print_metric_headers(struct perf_stat_config *config, /* Print metrics headers only */ evlist__for_each_entry(evlist, counter) { - if (is_duration_time(counter)) - continue; os.evsel = counter; out.ctx = &os; out.print_metric = print_metric_header; @@ -1136,15 +1124,11 @@ perf_evlist__print_counters(struct perf_evlist *evlist, break; case AGGR_THREAD: evlist__for_each_entry(evlist, counter) { - if (is_duration_time(counter)) - continue; print_aggr_thread(config, _target, counter, prefix); } break; case AGGR_GLOBAL: evlist__for_each_entry(evlist, counter) { - if (is_duration_time(counter)) - continue; print_counter_aggr(config, counter, prefix); } if (metric_only) @@ -1155,8 +1139,6 @@ perf_evlist__print_counters(struct perf_evlist *evlist, print_no_aggr_metric(config, evlist, prefix); else { evlist__for_each_entry(evlist, counter) { - if (is_duration_time(counter)) - continue; print_counter(config, counter, prefix); } } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 4d40515307b8..2856cc9d5a31 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -291,10 +291,8 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel break; case AGGR_GLOBAL: aggr->val += count->val; - if (config->scale) { - aggr->ena += count->ena; - aggr->run += count->run; - } + aggr->ena += count->ena; + aggr->run += count->run; case AGGR_UNSET: default: break; @@ -442,10 +440,8 @@ int create_perf_stat_counter(struct perf_evsel *evsel, struct perf_event_attr *attr = &evsel->attr; struct perf_evsel *leader = evsel->leader; - if (config->scale) { - attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | - PERF_FORMAT_TOTAL_TIME_RUNNING; - } + attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING; /* * The event is part of non trivial group, let's enable diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 758bf5f74e6e..5cbad55cd99d 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -6,6 +6,7 @@ #include <string.h> #include <linux/kernel.h> #include <linux/mman.h> +#include <linux/time64.h> #include <sys/types.h> #include <sys/stat.h> #include <sys/param.h> @@ -39,15 +40,18 @@ int vmlinux_path__nr_entries; char **vmlinux_path; struct symbol_conf symbol_conf = { + .nanosecs = false, .use_modules = true, .try_vmlinux_path = true, .demangle = true, .demangle_kernel = false, .cumulate_callchain = true, + .time_quantum = 100 * NSEC_PER_MSEC, /* 100ms */ .show_hist_headers = true, .symfs = "", .event_group = true, .inline_name = true, + .res_sample = 0, }; static enum dso_binary_type binary_type_symtab[] = { @@ -1451,6 +1455,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO: return true; + case DSO_BINARY_TYPE__BPF_PROG_INFO: case DSO_BINARY_TYPE__NOT_FOUND: default: return false; diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index fffea68c1203..6c55fa6fccec 100644 --- a/tools/perf/util/symbol_conf.h +++ b/tools/perf/util/symbol_conf.h @@ -8,6 +8,7 @@ struct strlist; struct intlist; struct symbol_conf { + bool nanosecs; unsigned short priv_size; bool try_vmlinux_path, init_annotation, @@ -55,6 +56,7 @@ struct symbol_conf { *sym_list_str, *col_width_list_str, *bt_stop_list_str; + unsigned long time_quantum; struct strlist *dso_list, *comm_list, *sym_list, @@ -66,6 +68,7 @@ struct symbol_conf { struct intlist *pid_list, *tid_list; const char *symfs; + int res_sample; }; extern struct symbol_conf symbol_conf; diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c index 0f53baec660e..20663a460df3 100644 --- a/tools/perf/util/time-utils.c +++ b/tools/perf/util/time-utils.c @@ -453,6 +453,14 @@ int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz) return scnprintf(buf, sz, "%"PRIu64".%06"PRIu64, sec, usec); } +int timestamp__scnprintf_nsec(u64 timestamp, char *buf, size_t sz) +{ + u64 sec = timestamp / NSEC_PER_SEC, + nsec = timestamp % NSEC_PER_SEC; + + return scnprintf(buf, sz, "%" PRIu64 ".%09" PRIu64, sec, nsec); +} + int fetch_current_timestamp(char *buf, size_t sz) { struct timeval tv; diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h index b923de44e36f..72a42ea1d513 100644 --- a/tools/perf/util/time-utils.h +++ b/tools/perf/util/time-utils.h @@ -30,6 +30,7 @@ int perf_time__parse_for_ranges(const char *str, struct perf_session *session, int *range_size, int *range_num); int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz); +int timestamp__scnprintf_nsec(u64 timestamp, char *buf, size_t sz); int fetch_current_timestamp(char *buf, size_t sz); diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index ad74be1f0e42..863955e4094e 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -111,7 +111,7 @@ raw_field_value(struct tep_event *event, const char *name, void *data) unsigned long long read_size(struct tep_event *event, void *ptr, int size) { - return tep_read_number(event->pevent, ptr, size); + return tep_read_number(event->tep, ptr, size); } void event_format__fprintf(struct tep_event *event, diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index efe2f58cff4e..48d53d8e3e16 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -442,7 +442,7 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) tep_set_flag(pevent, TEP_NSEC_OUTPUT); tep_set_file_bigendian(pevent, file_bigendian); - tep_set_host_bigendian(pevent, host_bigendian); + tep_set_local_bigendian(pevent, host_bigendian); if (do_read(buf, 1) < 0) goto out; diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c index cbe0dd758e3a..01b9d89bf5bf 100644 --- a/tools/perf/util/trace-event.c +++ b/tools/perf/util/trace-event.c @@ -40,7 +40,7 @@ int trace_event__init(struct trace_event *t) static int trace_event__init2(void) { - int be = tep_host_bigendian(); + int be = tep_is_bigendian(); struct tep_handle *pevent; if (trace_event__init(&tevent)) @@ -49,7 +49,7 @@ static int trace_event__init2(void) pevent = tevent.pevent; tep_set_flag(pevent, TEP_NSEC_OUTPUT); tep_set_file_bigendian(pevent, be); - tep_set_host_bigendian(pevent, be); + tep_set_local_bigendian(pevent, be); tevent_initialized = true; return 0; } |