diff options
Diffstat (limited to 'tools/perf')
145 files changed, 12898 insertions, 7116 deletions
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 138fb6e94b3c..18ed1b0fceb3 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -199,6 +199,18 @@ also be supplied. For example: perf stat -C 0 -e 'hv_gpci/dtbp_ptitc,phys_processor_idx=0x2/' ... +EVENT QUALIFIERS: + +It is also possible to add extra qualifiers to an event: + +percore: + +Sums up the event counts for all hardware threads in a core, e.g.: + + + perf stat -e cpu/event=0,umask=0x3,percore=1/ + + EVENT GROUPS ------------ diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 8fe4dffcadd0..de269430720a 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -406,7 +406,8 @@ symbolic names, e.g. on x86, ax, si. To list the available registers use --intr-regs=ax,bx. The list of register is architecture dependent. --user-regs:: -Capture user registers at sample time. Same arguments as -I. +Similar to -I, but capture user registers at sample time. To list the available +user registers use --user-regs=\?. --running-time:: Record running and enabled time for read events (:S) @@ -459,6 +460,30 @@ 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. + +-z:: +--compression-level[=n]:: +Produce compressed trace using specified level n (default: 1 - fastest compression, +22 - smallest trace) + --all-kernel:: Configure all used events to run in kernel space. diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 39c05f89104e..1e312c2672e4 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -43,6 +43,10 @@ report:: param1 and param2 are defined as formats for the PMU in /sys/bus/event_source/devices/<pmu>/format/* + 'percore' is a event qualifier that sums up the event counts for both + hardware threads in a core. For example: + perf stat -A -a -e cpu/event,percore=1/,otherevent ... + - a symbolically formed event like 'pmu/config=M,config1=N,config2=K/' where M, N, K are numbers (in decimal, hex, octal format). Acceptable values for each of 'config', 'config1' and 'config2' diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index 593ef49b273c..6967e9b02be5 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -272,6 +272,19 @@ struct { Two uint64_t for the time of first sample and the time of last sample. + HEADER_COMPRESSED = 27, + +struct { + u32 version; + u32 type; + u32 level; + u32 ratio; + u32 mmap_len; +}; + +Indicates that trace contains records of PERF_RECORD_COMPRESSED type +that have perf_events records in compressed form. + other bits are reserved and should ignored for now HEADER_FEAT_BITS = 256, @@ -437,6 +450,17 @@ struct auxtrace_error_event { Describes a header feature. These are records used in pipe-mode that contain information that otherwise would be in perf.data file's header. + PERF_RECORD_COMPRESSED = 81, + +struct compressed_event { + struct perf_event_header header; + char data[]; +}; + +The header is followed by compressed data frame that can be decompressed +into array of perf trace records. The size of the entire compressed event +record including the header is limited by the max value of header.size. + Event types Define the event attributes with their IDs. diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index 864e37597252..401f0ed67439 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -22,6 +22,8 @@ OPTIONS verbose - general debug messages ordered-events - ordered events object debug messages data-convert - data convert command debug messages + stderr - write debug output (option -v) to stderr + in browser mode --buildid-dir:: Setup buildid cache directory. It has higher priority than diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index fe3f97e342fa..e1bb5288ab1f 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -59,6 +59,10 @@ ifeq ($(SRCARCH),arm64) LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 endif +ifeq ($(SRCARCH),csky) + NO_PERF_REGS := 0 +endif + ifeq ($(ARCH),s390) NO_PERF_REGS := 0 NO_SYSCALL_TABLE := 0 @@ -77,7 +81,7 @@ endif # Disable it on all other architectures in case libdw unwind # support is detected in system. Add supported architectures # to the check. -ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390)) +ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390 csky)) NO_LIBDW_DWARF_UNWIND := 1 endif @@ -152,6 +156,13 @@ 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 @@ -227,7 +238,7 @@ FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS) FEATURE_CHECK_LDFLAGS-libaio = -lrt -FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes +FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl CFLAGS += -fno-omit-frame-pointer CFLAGS += -ggdb3 @@ -787,6 +798,19 @@ ifndef NO_LZMA endif endif +ifndef NO_LIBZSTD + ifeq ($(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 diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index e8c9f77e9010..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 diff --git a/tools/perf/arch/csky/Build b/tools/perf/arch/csky/Build new file mode 100644 index 000000000000..e4e5f33c84d8 --- /dev/null +++ b/tools/perf/arch/csky/Build @@ -0,0 +1 @@ +perf-y += util/ diff --git a/tools/perf/arch/csky/Makefile b/tools/perf/arch/csky/Makefile new file mode 100644 index 000000000000..7fbca175099e --- /dev/null +++ b/tools/perf/arch/csky/Makefile @@ -0,0 +1,3 @@ +ifndef NO_DWARF +PERF_HAVE_DWARF_REGS := 1 +endif diff --git a/tools/perf/arch/csky/include/perf_regs.h b/tools/perf/arch/csky/include/perf_regs.h new file mode 100644 index 000000000000..8f336ea1161a --- /dev/null +++ b/tools/perf/arch/csky/include/perf_regs.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. + +#ifndef ARCH_PERF_REGS_H +#define ARCH_PERF_REGS_H + +#include <stdlib.h> +#include <linux/types.h> +#include <asm/perf_regs.h> + +#define PERF_REGS_MASK ((1ULL << PERF_REG_CSKY_MAX) - 1) +#define PERF_REGS_MAX PERF_REG_CSKY_MAX +#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32 + +#define PERF_REG_IP PERF_REG_CSKY_PC +#define PERF_REG_SP PERF_REG_CSKY_SP + +static inline const char *perf_reg_name(int id) +{ + switch (id) { + case PERF_REG_CSKY_A0: + return "a0"; + case PERF_REG_CSKY_A1: + return "a1"; + case PERF_REG_CSKY_A2: + return "a2"; + case PERF_REG_CSKY_A3: + return "a3"; + case PERF_REG_CSKY_REGS0: + return "regs0"; + case PERF_REG_CSKY_REGS1: + return "regs1"; + case PERF_REG_CSKY_REGS2: + return "regs2"; + case PERF_REG_CSKY_REGS3: + return "regs3"; + case PERF_REG_CSKY_REGS4: + return "regs4"; + case PERF_REG_CSKY_REGS5: + return "regs5"; + case PERF_REG_CSKY_REGS6: + return "regs6"; + case PERF_REG_CSKY_REGS7: + return "regs7"; + case PERF_REG_CSKY_REGS8: + return "regs8"; + case PERF_REG_CSKY_REGS9: + return "regs9"; + case PERF_REG_CSKY_SP: + return "sp"; + case PERF_REG_CSKY_LR: + return "lr"; + case PERF_REG_CSKY_PC: + return "pc"; +#if defined(__CSKYABIV2__) + case PERF_REG_CSKY_EXREGS0: + return "exregs0"; + case PERF_REG_CSKY_EXREGS1: + return "exregs1"; + case PERF_REG_CSKY_EXREGS2: + return "exregs2"; + case PERF_REG_CSKY_EXREGS3: + return "exregs3"; + case PERF_REG_CSKY_EXREGS4: + return "exregs4"; + case PERF_REG_CSKY_EXREGS5: + return "exregs5"; + case PERF_REG_CSKY_EXREGS6: + return "exregs6"; + case PERF_REG_CSKY_EXREGS7: + return "exregs7"; + case PERF_REG_CSKY_EXREGS8: + return "exregs8"; + case PERF_REG_CSKY_EXREGS9: + return "exregs9"; + case PERF_REG_CSKY_EXREGS10: + return "exregs10"; + case PERF_REG_CSKY_EXREGS11: + return "exregs11"; + case PERF_REG_CSKY_EXREGS12: + return "exregs12"; + case PERF_REG_CSKY_EXREGS13: + return "exregs13"; + case PERF_REG_CSKY_EXREGS14: + return "exregs14"; + case PERF_REG_CSKY_TLS: + return "tls"; + case PERF_REG_CSKY_HI: + return "hi"; + case PERF_REG_CSKY_LO: + return "lo"; +#endif + default: + return NULL; + } + + return NULL; +} + +#endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/csky/util/Build b/tools/perf/arch/csky/util/Build new file mode 100644 index 000000000000..1160bb2332ba --- /dev/null +++ b/tools/perf/arch/csky/util/Build @@ -0,0 +1,2 @@ +perf-$(CONFIG_DWARF) += dwarf-regs.o +perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o diff --git a/tools/perf/arch/csky/util/dwarf-regs.c b/tools/perf/arch/csky/util/dwarf-regs.c new file mode 100644 index 000000000000..ca86ecaeacbb --- /dev/null +++ b/tools/perf/arch/csky/util/dwarf-regs.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. +// Mapping of DWARF debug register numbers into register names. + +#include <stddef.h> +#include <dwarf-regs.h> + +#if defined(__CSKYABIV2__) +#define CSKY_MAX_REGS 73 +const char *csky_dwarf_regs_table[CSKY_MAX_REGS] = { + /* r0 ~ r8 */ + "%a0", "%a1", "%a2", "%a3", "%regs0", "%regs1", "%regs2", "%regs3", + /* r9 ~ r15 */ + "%regs4", "%regs5", "%regs6", "%regs7", "%regs8", "%regs9", "%sp", + "%lr", + /* r16 ~ r23 */ + "%exregs0", "%exregs1", "%exregs2", "%exregs3", "%exregs4", + "%exregs5", "%exregs6", "%exregs7", + /* r24 ~ r31 */ + "%exregs8", "%exregs9", "%exregs10", "%exregs11", "%exregs12", + "%exregs13", "%exregs14", "%tls", + "%pc", NULL, NULL, NULL, "%hi", "%lo", NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + "%epc", +}; +#else +#define CSKY_MAX_REGS 57 +const char *csky_dwarf_regs_table[CSKY_MAX_REGS] = { + /* r0 ~ r8 */ + "%sp", "%regs9", "%a0", "%a1", "%a2", "%a3", "%regs0", "%regs1", + /* r9 ~ r15 */ + "%regs2", "%regs3", "%regs4", "%regs5", "%regs6", "%regs7", "%regs8", + "%lr", + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + "%epc", +}; +#endif + +const char *get_arch_regstr(unsigned int n) +{ + return (n < CSKY_MAX_REGS) ? csky_dwarf_regs_table[n] : NULL; +} diff --git a/tools/perf/arch/csky/util/unwind-libdw.c b/tools/perf/arch/csky/util/unwind-libdw.c new file mode 100644 index 000000000000..4bb4a06776e4 --- /dev/null +++ b/tools/perf/arch/csky/util/unwind-libdw.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. + +#include <elfutils/libdwfl.h> +#include "../../util/unwind-libdw.h" +#include "../../util/perf_regs.h" +#include "../../util/event.h" + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) +{ + struct unwind_info *ui = arg; + struct regs_dump *user_regs = &ui->sample->user_regs; + Dwarf_Word dwarf_regs[PERF_REG_CSKY_MAX]; + +#define REG(r) ({ \ + Dwarf_Word val = 0; \ + perf_reg_value(&val, user_regs, PERF_REG_CSKY_##r); \ + val; \ +}) + +#if defined(__CSKYABIV2__) + dwarf_regs[0] = REG(A0); + dwarf_regs[1] = REG(A1); + dwarf_regs[2] = REG(A2); + dwarf_regs[3] = REG(A3); + dwarf_regs[4] = REG(REGS0); + dwarf_regs[5] = REG(REGS1); + dwarf_regs[6] = REG(REGS2); + dwarf_regs[7] = REG(REGS3); + dwarf_regs[8] = REG(REGS4); + dwarf_regs[9] = REG(REGS5); + dwarf_regs[10] = REG(REGS6); + dwarf_regs[11] = REG(REGS7); + dwarf_regs[12] = REG(REGS8); + dwarf_regs[13] = REG(REGS9); + dwarf_regs[14] = REG(SP); + dwarf_regs[15] = REG(LR); + dwarf_regs[16] = REG(EXREGS0); + dwarf_regs[17] = REG(EXREGS1); + dwarf_regs[18] = REG(EXREGS2); + dwarf_regs[19] = REG(EXREGS3); + dwarf_regs[20] = REG(EXREGS4); + dwarf_regs[21] = REG(EXREGS5); + dwarf_regs[22] = REG(EXREGS6); + dwarf_regs[23] = REG(EXREGS7); + dwarf_regs[24] = REG(EXREGS8); + dwarf_regs[25] = REG(EXREGS9); + dwarf_regs[26] = REG(EXREGS10); + dwarf_regs[27] = REG(EXREGS11); + dwarf_regs[28] = REG(EXREGS12); + dwarf_regs[29] = REG(EXREGS13); + dwarf_regs[30] = REG(EXREGS14); + dwarf_regs[31] = REG(TLS); + dwarf_regs[32] = REG(PC); +#else + dwarf_regs[0] = REG(SP); + dwarf_regs[1] = REG(REGS9); + dwarf_regs[2] = REG(A0); + dwarf_regs[3] = REG(A1); + dwarf_regs[4] = REG(A2); + dwarf_regs[5] = REG(A3); + dwarf_regs[6] = REG(REGS0); + dwarf_regs[7] = REG(REGS1); + dwarf_regs[8] = REG(REGS2); + dwarf_regs[9] = REG(REGS3); + dwarf_regs[10] = REG(REGS4); + dwarf_regs[11] = REG(REGS5); + dwarf_regs[12] = REG(REGS6); + dwarf_regs[13] = REG(REGS7); + dwarf_regs[14] = REG(REGS8); + dwarf_regs[15] = REG(LR); +#endif + dwfl_thread_state_register_pc(thread, REG(PC)); + + return dwfl_thread_state_registers(thread, 0, PERF_REG_CSKY_MAX, + dwarf_regs); +} diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h index 7f6d538f8a89..b7cd91a9014f 100644 --- a/tools/perf/arch/x86/include/perf_regs.h +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -8,9 +8,10 @@ void perf_regs_load(u64 *regs); +#define PERF_REGS_MAX PERF_REG_X86_XMM_MAX +#define PERF_XMM_REGS_MASK (~((1ULL << PERF_REG_X86_XMM0) - 1)) #ifndef HAVE_ARCH_X86_64_SUPPORT #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1) -#define PERF_REGS_MAX PERF_REG_X86_32_MAX #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32 #else #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \ @@ -18,7 +19,6 @@ void perf_regs_load(u64 *regs); (1ULL << PERF_REG_X86_FS) | \ (1ULL << PERF_REG_X86_GS)) #define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT) -#define PERF_REGS_MAX PERF_REG_X86_64_MAX #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64 #endif #define PERF_REG_IP PERF_REG_X86_IP @@ -77,6 +77,28 @@ static inline const char *perf_reg_name(int id) case PERF_REG_X86_R15: return "R15"; #endif /* HAVE_ARCH_X86_64_SUPPORT */ + +#define XMM(x) \ + case PERF_REG_X86_XMM ## x: \ + case PERF_REG_X86_XMM ## x + 1: \ + return "XMM" #x; + XMM(0) + XMM(1) + XMM(2) + XMM(3) + XMM(4) + XMM(5) + XMM(6) + XMM(7) + XMM(8) + XMM(9) + XMM(10) + XMM(11) + XMM(12) + XMM(13) + XMM(14) + XMM(15) +#undef XMM default: return NULL; } diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index fead6b3b4206..7886ca5263e3 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -31,6 +31,22 @@ const struct sample_reg sample_reg_masks[] = { SMPL_REG(R14, PERF_REG_X86_R14), SMPL_REG(R15, PERF_REG_X86_R15), #endif + SMPL_REG2(XMM0, PERF_REG_X86_XMM0), + SMPL_REG2(XMM1, PERF_REG_X86_XMM1), + SMPL_REG2(XMM2, PERF_REG_X86_XMM2), + SMPL_REG2(XMM3, PERF_REG_X86_XMM3), + SMPL_REG2(XMM4, PERF_REG_X86_XMM4), + SMPL_REG2(XMM5, PERF_REG_X86_XMM5), + SMPL_REG2(XMM6, PERF_REG_X86_XMM6), + SMPL_REG2(XMM7, PERF_REG_X86_XMM7), + SMPL_REG2(XMM8, PERF_REG_X86_XMM8), + SMPL_REG2(XMM9, PERF_REG_X86_XMM9), + SMPL_REG2(XMM10, PERF_REG_X86_XMM10), + SMPL_REG2(XMM11, PERF_REG_X86_XMM11), + SMPL_REG2(XMM12, PERF_REG_X86_XMM12), + SMPL_REG2(XMM13, PERF_REG_X86_XMM13), + SMPL_REG2(XMM14, PERF_REG_X86_XMM14), + SMPL_REG2(XMM15, PERF_REG_X86_XMM15), SMPL_REG_END }; @@ -254,3 +270,31 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op) return SDT_ARG_VALID; } + +uint64_t arch__intr_reg_mask(void) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .sample_type = PERF_SAMPLE_REGS_INTR, + .sample_regs_intr = PERF_XMM_REGS_MASK, + .precise_ip = 1, + .disabled = 1, + .exclude_kernel = 1, + }; + int fd; + /* + * In an unnamed union, init it here to build on older gcc versions + */ + attr.sample_period = 1; + + event_attr_init(&attr); + + fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + if (fd != -1) { + close(fd); + return (PERF_XMM_REGS_MASK | PERF_REGS_MASK); + } + + return PERF_REGS_MASK; +} 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-annotate.c b/tools/perf/builtin-annotate.c index 67f9d9ffacfb..77deb3a40596 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -159,8 +159,6 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter, struct perf_evsel *evsel = iter->evsel; int err; - hist__account_cycles(sample->branch_stack, al, sample, false); - bi = he->branch_info; err = addr_map_symbol__inc_samples(&bi->from, sample, evsel); @@ -199,6 +197,8 @@ static int process_branch_callback(struct perf_evsel *evsel, if (a.map != NULL) a.map->dso->hit = 1; + hist__account_cycles(sample->branch_stack, al, sample, false); + ret = hist_entry_iter__add(&iter, &a, PERF_MAX_STACK_DEPTH, ann); return ret; } diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 24086b7f1b14..8e0e06d3edfc 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -837,6 +837,9 @@ int cmd_inject(int argc, const char **argv) if (inject.session == NULL) return -1; + if (zstd_init(&(inject.session->zstd_data), 0) < 0) + pr_warning("Decompression initialization failed.\n"); + if (inject.build_ids) { /* * to make sure the mmap records are ordered correctly @@ -867,6 +870,7 @@ int cmd_inject(int argc, const char **argv) ret = __cmd_inject(&inject); out_delete: + zstd_fini(&(inject.session->zstd_data)); perf_session__delete(inject.session); return ret; } 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 a8394b4f1167..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) @@ -113,6 +114,7 @@ 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, diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 4e2d953d4bc5..e2c3a585a61e 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -133,6 +133,11 @@ static int record__write(struct record *rec, struct perf_mmap *map __maybe_unuse return 0; } +static int record__aio_enabled(struct record *rec); +static int record__comp_enabled(struct record *rec); +static size_t zstd_compress(struct perf_session *session, void *dst, size_t dst_size, + void *src, size_t src_size); + #ifdef HAVE_AIO_SUPPORT static int record__aio_write(struct aiocb *cblock, int trace_fd, void *buf, size_t size, off_t off) @@ -183,9 +188,9 @@ static int record__aio_complete(struct perf_mmap *md, struct aiocb *cblock) if (rem_size == 0) { cblock->aio_fildes = -1; /* - * md->refcount is incremented in perf_mmap__push() for - * every enqueued aio write request so decrement it because - * the request is now complete. + * md->refcount is incremented in record__aio_pushfn() for + * every aio write request started in record__aio_push() so + * decrement it because the request is now complete. */ perf_mmap__put(md); rc = 1; @@ -240,18 +245,89 @@ static int record__aio_sync(struct perf_mmap *md, bool sync_all) } while (1); } -static int record__aio_pushfn(void *to, struct aiocb *cblock, void *bf, size_t size, off_t off) +struct record_aio { + struct record *rec; + void *data; + size_t size; +}; + +static int record__aio_pushfn(struct perf_mmap *map, void *to, void *buf, size_t size) { - struct record *rec = to; - int ret, trace_fd = rec->session->data->file.fd; + struct record_aio *aio = to; - rec->samples++; + /* + * map->base data pointed by buf is copied into free map->aio.data[] buffer + * to release space in the kernel buffer as fast as possible, calling + * perf_mmap__consume() from perf_mmap__push() function. + * + * That lets the kernel to proceed with storing more profiling data into + * the kernel buffer earlier than other per-cpu kernel buffers are handled. + * + * Coping can be done in two steps in case the chunk of profiling data + * crosses the upper bound of the kernel buffer. In this case we first move + * part of data from map->start till the upper bound and then the reminder + * from the beginning of the kernel buffer till the end of the data chunk. + */ + + if (record__comp_enabled(aio->rec)) { + size = zstd_compress(aio->rec->session, aio->data + aio->size, + perf_mmap__mmap_len(map) - aio->size, + buf, size); + } else { + memcpy(aio->data + aio->size, buf, size); + } + + if (!aio->size) { + /* + * Increment map->refcount to guard map->aio.data[] buffer + * from premature deallocation because map object can be + * released earlier than aio write request started on + * map->aio.data[] buffer is complete. + * + * perf_mmap__put() is done at record__aio_complete() + * after started aio request completion or at record__aio_push() + * if the request failed to start. + */ + perf_mmap__get(map); + } + + aio->size += size; + + return size; +} + +static int record__aio_push(struct record *rec, struct perf_mmap *map, off_t *off) +{ + int ret, idx; + int trace_fd = rec->session->data->file.fd; + struct record_aio aio = { .rec = rec, .size = 0 }; + + /* + * Call record__aio_sync() to wait till map->aio.data[] buffer + * becomes available after previous aio write operation. + */ + + idx = record__aio_sync(map, false); + aio.data = map->aio.data[idx]; + ret = perf_mmap__push(map, &aio, record__aio_pushfn); + if (ret != 0) /* ret > 0 - no data, ret < 0 - error */ + return ret; - ret = record__aio_write(cblock, trace_fd, bf, size, off); + rec->samples++; + ret = record__aio_write(&(map->aio.cblocks[idx]), trace_fd, aio.data, aio.size, *off); if (!ret) { - rec->bytes_written += size; + *off += aio.size; + rec->bytes_written += aio.size; if (switch_output_size(rec)) trigger_hit(&switch_output_trigger); + } else { + /* + * Decrement map->refcount incremented in record__aio_pushfn() + * back if record__aio_write() operation failed to start, otherwise + * map->refcount is decremented in record__aio_complete() after + * aio write operation finishes successfully. + */ + perf_mmap__put(map); } return ret; @@ -273,7 +349,7 @@ static void record__aio_mmap_read_sync(struct record *rec) struct perf_evlist *evlist = rec->evlist; struct perf_mmap *maps = evlist->mmap; - if (!rec->opts.nr_cblocks) + if (!record__aio_enabled(rec)) return; for (i = 0; i < evlist->nr_mmaps; i++) { @@ -307,13 +383,8 @@ static int record__aio_parse(const struct option *opt, #else /* HAVE_AIO_SUPPORT */ static int nr_cblocks_max = 0; -static int record__aio_sync(struct perf_mmap *md __maybe_unused, bool sync_all __maybe_unused) -{ - return -1; -} - -static int record__aio_pushfn(void *to __maybe_unused, struct aiocb *cblock __maybe_unused, - void *bf __maybe_unused, size_t size __maybe_unused, off_t off __maybe_unused) +static int record__aio_push(struct record *rec __maybe_unused, struct perf_mmap *map __maybe_unused, + off_t *off __maybe_unused) { return -1; } @@ -337,6 +408,67 @@ 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; +} + +#ifdef HAVE_ZSTD_SUPPORT +static unsigned int comp_level_default = 1; + +static int record__parse_comp_level(const struct option *opt, const char *str, int unset) +{ + struct record_opts *opts = opt->value; + + if (unset) { + opts->comp_level = 0; + } else { + if (str) + opts->comp_level = strtol(str, NULL, 0); + if (!opts->comp_level) + opts->comp_level = comp_level_default; + } + + return 0; +} +#endif +static unsigned int comp_level_max = 22; + +static int record__comp_enabled(struct record *rec) +{ + return rec->opts.comp_level > 0; +} + static int process_synthesized_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample __maybe_unused, @@ -350,6 +482,11 @@ static int record__pushfn(struct perf_mmap *map, void *to, void *bf, size_t size { struct record *rec = to; + if (record__comp_enabled(rec)) { + size = zstd_compress(rec->session, map->data, perf_mmap__mmap_len(map), bf, size); + bf = map->data; + } + rec->samples++; return record__write(rec, map, bf, size); } @@ -546,7 +683,8 @@ 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, opts->comp_level) < 0) { if (errno == EPERM) { pr_err("Permission error mapping pages.\n" "Consider increasing " @@ -735,15 +873,46 @@ static void record__adjust_affinity(struct record *rec, struct perf_mmap *map) } } +static size_t process_comp_header(void *record, size_t increment) +{ + struct compressed_event *event = record; + size_t size = sizeof(*event); + + if (increment) { + event->header.size += increment; + return increment; + } + + event->header.type = PERF_RECORD_COMPRESSED; + event->header.size = size; + + return size; +} + +static size_t zstd_compress(struct perf_session *session, void *dst, size_t dst_size, + void *src, size_t src_size) +{ + size_t compressed; + size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct compressed_event) - 1; + + compressed = zstd_compress_stream_to_records(&session->zstd_data, dst, dst_size, src, src_size, + max_record_size, process_comp_header); + + session->bytes_transferred += src_size; + session->bytes_compressed += compressed; + + return compressed; +} + 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; int rc = 0; struct perf_mmap *maps; int trace_fd = rec->data.file.fd; - off_t off; + off_t off = 0; if (!evlist) return 0; @@ -759,28 +928,33 @@ 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 (perf_mmap__push(map, rec, record__pushfn) < 0) { + if (synch) + map->flush = flush; rc = -1; goto out; } } else { - int idx; - /* - * Call record__aio_sync() to wait till map->data buffer - * becomes available after previous aio write request. - */ - idx = record__aio_sync(map, false); - if (perf_mmap__aio_push(map, rec, idx, record__aio_pushfn, &off) != 0) { + if (record__aio_push(rec, map, &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 && @@ -806,15 +980,15 @@ 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) @@ -841,6 +1015,8 @@ static void record__init_features(struct record *rec) perf_header__clear_feat(&session->header, HEADER_CLOCKID); perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT); + if (!record__comp_enabled(rec)) + perf_header__clear_feat(&session->header, HEADER_COMPRESSED); perf_header__clear_feat(&session->header, HEADER_STAT); } @@ -1139,6 +1315,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) bool disabled = false, draining = false; struct perf_evlist *sb_evlist = NULL; int fd; + float ratio = 0; atexit(record__sig_exit); signal(SIGCHLD, sig_handler); @@ -1168,6 +1345,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) fd = perf_data__fd(data); rec->session = session; + if (zstd_init(&session->zstd_data, rec->opts.comp_level) < 0) { + pr_err("Compression initialization failed.\n"); + return -1; + } + + session->header.env.comp_type = PERF_COMP_ZSTD; + session->header.env.comp_level = rec->opts.comp_level; + record__init_features(rec); if (rec->opts.use_clockid && rec->opts.clockid_res_ns) @@ -1197,6 +1382,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) err = -1; goto out_child; } + session->header.env.comp_mmap_len = session->evlist->mmap_len; err = bpf__apply_obj_config(); if (err) { @@ -1340,7 +1526,7 @@ 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; @@ -1441,8 +1627,14 @@ 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 (rec->session->bytes_transferred && rec->session->bytes_compressed) { + ratio = (float)rec->session->bytes_transferred/(float)rec->session->bytes_compressed; + session->header.env.comp_ratio = ratio + 0.5; + } + if (forks) { int exit_status; @@ -1489,12 +1681,19 @@ out_child: else samples[0] = '\0'; - fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s%s ]\n", + fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s%s", perf_data__size(data) / 1024.0 / 1024.0, data->path, postfix, samples); + if (ratio) { + fprintf(stderr, ", compressed (original %.3f MB, ratio is %.3f)", + rec->session->bytes_transferred / 1024.0 / 1024.0, + ratio); + } + fprintf(stderr, " ]\n"); } out_delete_session: + zstd_fini(&session->zstd_data); perf_session__delete(session); if (!opts->no_bpf_event) @@ -1846,6 +2045,7 @@ static struct record record = { .uses_mmap = true, .default_per_cpu = true, }, + .mmap_flush = MMAP_FLUSH_DEFAULT, }, .tool = { .sample = process_sample_event, @@ -1912,6 +2112,9 @@ 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, @@ -1965,10 +2168,10 @@ static struct option __record_options[] = { "use per-thread mmaps"), OPT_CALLBACK_OPTARG('I', "intr-regs", &record.opts.sample_intr_regs, NULL, "any register", "sample selected machine registers on interrupt," - " use -I ? to list register names", parse_regs), + " use '-I?' to list register names", parse_intr_regs), OPT_CALLBACK_OPTARG(0, "user-regs", &record.opts.sample_user_regs, NULL, "any register", "sample selected machine registers on interrupt," - " use -I ? to list register names", parse_regs), + " use '--user-regs=?' to list register names", parse_user_regs), OPT_BOOLEAN(0, "running-time", &record.opts.running_time, "Record running/enabled time of read (:S) events"), OPT_CALLBACK('k', "clockid", &record.opts, @@ -2016,6 +2219,11 @@ static struct option __record_options[] = { OPT_CALLBACK(0, "affinity", &record.opts, "node|cpu", "Set affinity mask of trace reading thread to NUMA node cpu mask or cpu of processed mmap buffer", record__parse_affinity), +#ifdef HAVE_ZSTD_SUPPORT + OPT_CALLBACK_OPTARG('z', "compression-level", &record.opts, &comp_level_default, + "n", "Compressed records using specified level (default: 1 - fastest compression, 22 - greatest compression)", + record__parse_comp_level), +#endif OPT_END() }; @@ -2075,6 +2283,12 @@ int cmd_record(int argc, const char **argv) "cgroup monitoring only available in system-wide mode"); } + + if (rec->opts.comp_level != 0) { + pr_debug("Compression enabled, disabling build id collection at the end of the session.\n"); + rec->no_buildid = true; + } + if (rec->opts.record_switch_events && !perf_can_record_switch_events()) { ui__error("kernel does not support recording context switch events\n"); @@ -2220,10 +2434,14 @@ int cmd_record(int argc, const char **argv) if (rec->opts.nr_cblocks > nr_cblocks_max) rec->opts.nr_cblocks = nr_cblocks_max; - if (verbose > 0) - pr_info("nr_cblocks: %d\n", rec->opts.nr_cblocks); + pr_debug("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); + + if (rec->opts.comp_level > comp_level_max) + rec->opts.comp_level = comp_level_max; + pr_debug("comp level: %d\n", rec->opts.comp_level); err = __cmd_record(&record, argc, argv); out: diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 4054eb1f98ac..1ca533f06a4c 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -136,9 +136,6 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter, if (!ui__has_annotation() && !rep->symbol_ipc) return 0; - hist__account_cycles(sample->branch_stack, al, sample, - rep->nonany_branch_mode); - if (sort__mode == SORT_MODE__BRANCH) { bi = he->branch_info; err = addr_map_symbol__inc_samples(&bi->from, sample, evsel); @@ -181,9 +178,6 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter, if (!ui__has_annotation() && !rep->symbol_ipc) return 0; - hist__account_cycles(sample->branch_stack, al, sample, - rep->nonany_branch_mode); - bi = he->branch_info; err = addr_map_symbol__inc_samples(&bi->from, sample, evsel); if (err) @@ -282,6 +276,11 @@ static int process_sample_event(struct perf_tool *tool, if (al.map != NULL) al.map->dso->hit = 1; + if (ui__has_annotation() || rep->symbol_ipc) { + hist__account_cycles(sample->branch_stack, &al, sample, + rep->nonany_branch_mode); + } + ret = hist_entry_iter__add(&iter, &al, rep->max_stack, rep); if (ret < 0) pr_debug("problem adding hist entry, skipping event\n"); @@ -1259,6 +1258,9 @@ repeat: if (session == NULL) return -1; + if (zstd_init(&(session->zstd_data), 0) < 0) + pr_warning("Decompression initialization failed. Reported data may be incomplete.\n"); + if (report.queue_size) { ordered_events__set_alloc_size(&session->ordered_events, report.queue_size); @@ -1449,7 +1451,7 @@ repeat: error: if (report.ptime_range) zfree(&report.ptime_range); - + zstd_fini(&(session->zstd_data)); perf_session__delete(session); return ret; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index c3625ec374e0..24b8e690fb69 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); @@ -833,6 +847,18 @@ static int perf_stat__get_core_cached(struct perf_stat_config *config, return perf_stat__get_aggr(config, perf_stat__get_core, map, idx); } +static bool term_percore_set(void) +{ + struct perf_evsel *counter; + + evlist__for_each_entry(evsel_list, counter) { + if (counter->percore) + return true; + } + + return false; +} + static int perf_stat_init_aggr_mode(void) { int nr; @@ -853,6 +879,15 @@ static int perf_stat_init_aggr_mode(void) stat_config.aggr_get_id = perf_stat__get_core_cached; break; case AGGR_NONE: + if (term_percore_set()) { + if (cpu_map__build_core_map(evsel_list->cpus, + &stat_config.aggr_map)) { + perror("cannot build core map"); + return -1; + } + stat_config.aggr_get_id = perf_stat__get_core_cached; + } + break; case AGGR_GLOBAL: case AGGR_THREAD: case AGGR_UNSET: 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/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.h b/tools/perf/perf.h index c59743def8d3..d59dee61b64d 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -85,6 +85,8 @@ struct record_opts { u64 clockid_res_ns; int nr_cblocks; int affinity; + int mmap_flush; + unsigned int comp_level; }; enum perf_affinity { diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a57-a72/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a57-a72/core-imp-def.json new file mode 100644 index 000000000000..0ac9b7927450 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a57-a72/core-imp-def.json @@ -0,0 +1,179 @@ +[ + { + "ArchStdEvent": "L1D_CACHE_RD", + }, + { + "ArchStdEvent": "L1D_CACHE_WR", + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD", + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_WR", + }, + { + "ArchStdEvent": "L1D_CACHE_WB_VICTIM", + }, + { + "ArchStdEvent": "L1D_CACHE_WB_CLEAN", + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL", + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_RD", + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_WR", + }, + { + "ArchStdEvent": "L2D_CACHE_RD", + }, + { + "ArchStdEvent": "L2D_CACHE_WR", + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD", + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR", + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM", + }, + { + "ArchStdEvent": "L2D_CACHE_WB_CLEAN", + }, + { + "ArchStdEvent": "L2D_CACHE_INVAL", + }, + { + "ArchStdEvent": "BUS_ACCESS_RD", + }, + { + "ArchStdEvent": "BUS_ACCESS_WR", + }, + { + "ArchStdEvent": "BUS_ACCESS_SHARED", + }, + { + "ArchStdEvent": "BUS_ACCESS_NOT_SHARED", + }, + { + "ArchStdEvent": "BUS_ACCESS_NORMAL", + }, + { + "ArchStdEvent": "BUS_ACCESS_PERIPH", + }, + { + "ArchStdEvent": "MEM_ACCESS_RD", + }, + { + "ArchStdEvent": "MEM_ACCESS_WR", + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC", + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC", + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC", + }, + { + "ArchStdEvent": "LDREX_SPEC", + }, + { + "ArchStdEvent": "STREX_PASS_SPEC", + }, + { + "ArchStdEvent": "STREX_FAIL_SPEC", + }, + { + "ArchStdEvent": "LD_SPEC", + }, + { + "ArchStdEvent": "ST_SPEC", + }, + { + "ArchStdEvent": "LDST_SPEC", + }, + { + "ArchStdEvent": "DP_SPEC", + }, + { + "ArchStdEvent": "ASE_SPEC", + }, + { + "ArchStdEvent": "VFP_SPEC", + }, + { + "ArchStdEvent": "PC_WRITE_SPEC", + }, + { + "ArchStdEvent": "CRYPTO_SPEC", + }, + { + "ArchStdEvent": "BR_IMMED_SPEC", + }, + { + "ArchStdEvent": "BR_RETURN_SPEC", + }, + { + "ArchStdEvent": "BR_INDIRECT_SPEC", + }, + { + "ArchStdEvent": "ISB_SPEC", + }, + { + "ArchStdEvent": "DSB_SPEC", + }, + { + "ArchStdEvent": "DMB_SPEC", + }, + { + "ArchStdEvent": "EXC_UNDEF", + }, + { + "ArchStdEvent": "EXC_SVC", + }, + { + "ArchStdEvent": "EXC_PABORT", + }, + { + "ArchStdEvent": "EXC_DABORT", + }, + { + "ArchStdEvent": "EXC_IRQ", + }, + { + "ArchStdEvent": "EXC_FIQ", + }, + { + "ArchStdEvent": "EXC_SMC", + }, + { + "ArchStdEvent": "EXC_HVC", + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT", + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT", + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER", + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ", + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ", + }, + { + "ArchStdEvent": "RC_LD_SPEC", + }, + { + "ArchStdEvent": "RC_ST_SPEC", + }, +] diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index 59cd8604b0bd..927fcddcb4aa 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -12,7 +12,10 @@ # # #Family-model,Version,Filename,EventType -0x00000000410fd03[[:xdigit:]],v1,arm/cortex-a53,core +0x00000000410fd030,v1,arm/cortex-a53,core +0x00000000420f1000,v1,arm/cortex-a53,core +0x00000000410fd070,v1,arm/cortex-a57-a72,core +0x00000000410fd080,v1,arm/cortex-a57-a72,core 0x00000000420f5160,v1,cavium/thunderx2,core 0x00000000430f0af0,v1,cavium/thunderx2,core 0x00000000480fd010,v1,hisilicon/hip08,core 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/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/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/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 68c92bb599ee..58f77fd0f59f 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -235,6 +235,7 @@ static struct map { { "iMPH-U", "uncore_arb" }, { "CPU-M-CF", "cpum_cf" }, { "CPU-M-SF", "cpum_sf" }, + { "UPI LL", "uncore_upi" }, {} }; @@ -414,7 +415,6 @@ static int save_arch_std_events(void *data, char *name, char *event, char *metric_name, char *metric_group) { struct event_struct *es; - struct stat *sb = data; es = malloc(sizeof(*es)); if (!es) diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 74ef92f1d19a..affed7d149be 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -456,6 +456,10 @@ class CallGraphLevelItemBase(object): self.query_done = False; self.child_count = 0 self.child_items = [] + if parent_item: + self.level = parent_item.level + 1 + else: + self.level = 0 def getChildItem(self, row): return self.child_items[row] @@ -877,9 +881,14 @@ class TreeWindowBase(QMdiSubWindow): super(TreeWindowBase, self).__init__(parent) self.model = None - self.view = None self.find_bar = None + self.view = QTreeView() + self.view.setSelectionMode(QAbstractItemView.ContiguousSelection) + self.view.CopyCellsToClipboard = CopyTreeCellsToClipboard + + self.context_menu = TreeContextMenu(self.view) + def DisplayFound(self, ids): if not len(ids): return False @@ -921,7 +930,6 @@ class CallGraphWindow(TreeWindowBase): self.model = LookupCreateModel("Context-Sensitive Call Graph", lambda x=glb: CallGraphModel(x)) - self.view = QTreeView() self.view.setModel(self.model) for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)): @@ -944,7 +952,6 @@ class CallTreeWindow(TreeWindowBase): self.model = LookupCreateModel("Call Tree", lambda x=glb: CallTreeModel(x)) - self.view = QTreeView() self.view.setModel(self.model) for c, w in ((0, 230), (1, 100), (2, 100), (3, 70), (4, 70), (5, 100)): @@ -1649,10 +1656,14 @@ class BranchWindow(QMdiSubWindow): self.view = QTreeView() self.view.setUniformRowHeights(True) + self.view.setSelectionMode(QAbstractItemView.ContiguousSelection) + self.view.CopyCellsToClipboard = CopyTreeCellsToClipboard self.view.setModel(self.model) self.ResizeColumnsToContents() + self.context_menu = TreeContextMenu(self.view) + self.find_bar = FindBar(self, self, True) self.finder = ChildDataItemFinder(self.model.root) @@ -2261,6 +2272,240 @@ class ResizeColumnsToContentsBase(QObject): self.data_model.rowsInserted.disconnect(self.UpdateColumnWidths) self.ResizeColumnsToContents() +# Convert value to CSV + +def ToCSValue(val): + if '"' in val: + val = val.replace('"', '""') + if "," in val or '"' in val: + val = '"' + val + '"' + return val + +# Key to sort table model indexes by row / column, assuming fewer than 1000 columns + +glb_max_cols = 1000 + +def RowColumnKey(a): + return a.row() * glb_max_cols + a.column() + +# Copy selected table cells to clipboard + +def CopyTableCellsToClipboard(view, as_csv=False, with_hdr=False): + indexes = sorted(view.selectedIndexes(), key=RowColumnKey) + idx_cnt = len(indexes) + if not idx_cnt: + return + if idx_cnt == 1: + with_hdr=False + min_row = indexes[0].row() + max_row = indexes[0].row() + min_col = indexes[0].column() + max_col = indexes[0].column() + for i in indexes: + min_row = min(min_row, i.row()) + max_row = max(max_row, i.row()) + min_col = min(min_col, i.column()) + max_col = max(max_col, i.column()) + if max_col > glb_max_cols: + raise RuntimeError("glb_max_cols is too low") + max_width = [0] * (1 + max_col - min_col) + for i in indexes: + c = i.column() - min_col + max_width[c] = max(max_width[c], len(str(i.data()))) + text = "" + pad = "" + sep = "" + if with_hdr: + model = indexes[0].model() + for col in range(min_col, max_col + 1): + val = model.headerData(col, Qt.Horizontal) + if as_csv: + text += sep + ToCSValue(val) + sep = "," + else: + c = col - min_col + max_width[c] = max(max_width[c], len(val)) + width = max_width[c] + align = model.headerData(col, Qt.Horizontal, Qt.TextAlignmentRole) + if align & Qt.AlignRight: + val = val.rjust(width) + text += pad + sep + val + pad = " " * (width - len(val)) + sep = " " + text += "\n" + pad = "" + sep = "" + last_row = min_row + for i in indexes: + if i.row() > last_row: + last_row = i.row() + text += "\n" + pad = "" + sep = "" + if as_csv: + text += sep + ToCSValue(str(i.data())) + sep = "," + else: + width = max_width[i.column() - min_col] + if i.data(Qt.TextAlignmentRole) & Qt.AlignRight: + val = str(i.data()).rjust(width) + else: + val = str(i.data()) + text += pad + sep + val + pad = " " * (width - len(val)) + sep = " " + QApplication.clipboard().setText(text) + +def CopyTreeCellsToClipboard(view, as_csv=False, with_hdr=False): + indexes = view.selectedIndexes() + if not len(indexes): + return + + selection = view.selectionModel() + + first = None + for i in indexes: + above = view.indexAbove(i) + if not selection.isSelected(above): + first = i + break + + if first is None: + raise RuntimeError("CopyTreeCellsToClipboard internal error") + + model = first.model() + row_cnt = 0 + col_cnt = model.columnCount(first) + max_width = [0] * col_cnt + + indent_sz = 2 + indent_str = " " * indent_sz + + expanded_mark_sz = 2 + if sys.version_info[0] == 3: + expanded_mark = "\u25BC " + not_expanded_mark = "\u25B6 " + else: + expanded_mark = unicode(chr(0xE2) + chr(0x96) + chr(0xBC) + " ", "utf-8") + not_expanded_mark = unicode(chr(0xE2) + chr(0x96) + chr(0xB6) + " ", "utf-8") + leaf_mark = " " + + if not as_csv: + pos = first + while True: + row_cnt += 1 + row = pos.row() + for c in range(col_cnt): + i = pos.sibling(row, c) + if c: + n = len(str(i.data())) + else: + n = len(str(i.data()).strip()) + n += (i.internalPointer().level - 1) * indent_sz + n += expanded_mark_sz + max_width[c] = max(max_width[c], n) + pos = view.indexBelow(pos) + if not selection.isSelected(pos): + break + + text = "" + pad = "" + sep = "" + if with_hdr: + for c in range(col_cnt): + val = model.headerData(c, Qt.Horizontal, Qt.DisplayRole).strip() + if as_csv: + text += sep + ToCSValue(val) + sep = "," + else: + max_width[c] = max(max_width[c], len(val)) + width = max_width[c] + align = model.headerData(c, Qt.Horizontal, Qt.TextAlignmentRole) + if align & Qt.AlignRight: + val = val.rjust(width) + text += pad + sep + val + pad = " " * (width - len(val)) + sep = " " + text += "\n" + pad = "" + sep = "" + + pos = first + while True: + row = pos.row() + for c in range(col_cnt): + i = pos.sibling(row, c) + val = str(i.data()) + if not c: + if model.hasChildren(i): + if view.isExpanded(i): + mark = expanded_mark + else: + mark = not_expanded_mark + else: + mark = leaf_mark + val = indent_str * (i.internalPointer().level - 1) + mark + val.strip() + if as_csv: + text += sep + ToCSValue(val) + sep = "," + else: + width = max_width[c] + if c and i.data(Qt.TextAlignmentRole) & Qt.AlignRight: + val = val.rjust(width) + text += pad + sep + val + pad = " " * (width - len(val)) + sep = " " + pos = view.indexBelow(pos) + if not selection.isSelected(pos): + break + text = text.rstrip() + "\n" + pad = "" + sep = "" + + QApplication.clipboard().setText(text) + +def CopyCellsToClipboard(view, as_csv=False, with_hdr=False): + view.CopyCellsToClipboard(view, as_csv, with_hdr) + +def CopyCellsToClipboardHdr(view): + CopyCellsToClipboard(view, False, True) + +def CopyCellsToClipboardCSV(view): + CopyCellsToClipboard(view, True, True) + +# Context menu + +class ContextMenu(object): + + def __init__(self, view): + self.view = view + self.view.setContextMenuPolicy(Qt.CustomContextMenu) + self.view.customContextMenuRequested.connect(self.ShowContextMenu) + + def ShowContextMenu(self, pos): + menu = QMenu(self.view) + self.AddActions(menu) + menu.exec_(self.view.mapToGlobal(pos)) + + def AddCopy(self, menu): + menu.addAction(CreateAction("&Copy selection", "Copy to clipboard", lambda: CopyCellsToClipboardHdr(self.view), self.view)) + menu.addAction(CreateAction("Copy selection as CS&V", "Copy to clipboard as CSV", lambda: CopyCellsToClipboardCSV(self.view), self.view)) + + def AddActions(self, menu): + self.AddCopy(menu) + +class TreeContextMenu(ContextMenu): + + def __init__(self, view): + super(TreeContextMenu, self).__init__(view) + + def AddActions(self, menu): + i = self.view.currentIndex() + text = str(i.data()).strip() + if len(text): + menu.addAction(CreateAction('Copy "' + text + '"', "Copy to clipboard", lambda: QApplication.clipboard().setText(text), self.view)) + self.AddCopy(menu) + # Table window class TableWindow(QMdiSubWindow, ResizeColumnsToContentsBase): @@ -2279,9 +2524,13 @@ class TableWindow(QMdiSubWindow, ResizeColumnsToContentsBase): self.view.verticalHeader().setVisible(False) self.view.sortByColumn(-1, Qt.AscendingOrder) self.view.setSortingEnabled(True) + self.view.setSelectionMode(QAbstractItemView.ContiguousSelection) + self.view.CopyCellsToClipboard = CopyTableCellsToClipboard self.ResizeColumnsToContents() + self.context_menu = ContextMenu(self.view) + self.find_bar = FindBar(self, self, True) self.finder = ChildDataItemFinder(self.data_model) @@ -2395,6 +2644,10 @@ class TopCallsWindow(QMdiSubWindow, ResizeColumnsToContentsBase): self.view.setModel(self.model) self.view.setEditTriggers(QAbstractItemView.NoEditTriggers) self.view.verticalHeader().setVisible(False) + self.view.setSelectionMode(QAbstractItemView.ContiguousSelection) + self.view.CopyCellsToClipboard = CopyTableCellsToClipboard + + self.context_menu = ContextMenu(self.view) self.ResizeColumnsToContents() @@ -2660,6 +2913,60 @@ class HelpOnlyWindow(QMainWindow): self.setCentralWidget(self.text) +# PostqreSQL server version + +def PostqreSQLServerVersion(db): + query = QSqlQuery(db) + QueryExec(query, "SELECT VERSION()") + if query.next(): + v_str = query.value(0) + v_list = v_str.strip().split(" ") + if v_list[0] == "PostgreSQL" and v_list[2] == "on": + return v_list[1] + return v_str + return "Unknown" + +# SQLite version + +def SQLiteVersion(db): + query = QSqlQuery(db) + QueryExec(query, "SELECT sqlite_version()") + if query.next(): + return query.value(0) + return "Unknown" + +# About dialog + +class AboutDialog(QDialog): + + def __init__(self, glb, parent=None): + super(AboutDialog, self).__init__(parent) + + self.setWindowTitle("About Exported SQL Viewer") + self.setMinimumWidth(300) + + pyside_version = "1" if pyside_version_1 else "2" + + text = "<pre>" + text += "Python version: " + sys.version.split(" ")[0] + "\n" + text += "PySide version: " + pyside_version + "\n" + text += "Qt version: " + qVersion() + "\n" + if glb.dbref.is_sqlite3: + text += "SQLite version: " + SQLiteVersion(glb.db) + "\n" + else: + text += "PostqreSQL version: " + PostqreSQLServerVersion(glb.db) + "\n" + text += "</pre>" + + self.text = QTextBrowser() + self.text.setHtml(text) + self.text.setReadOnly(True) + self.text.setOpenExternalLinks(True) + + self.vbox = QVBoxLayout() + self.vbox.addWidget(self.text) + + self.setLayout(self.vbox); + # Font resize def ResizeFont(widget, diff): @@ -2732,6 +3039,8 @@ class MainWindow(QMainWindow): file_menu.addAction(CreateExitAction(glb.app, self)) edit_menu = menu.addMenu("&Edit") + edit_menu.addAction(CreateAction("&Copy", "Copy to clipboard", self.CopyToClipboard, self, QKeySequence.Copy)) + edit_menu.addAction(CreateAction("Copy as CS&V", "Copy to clipboard as CSV", self.CopyToClipboardCSV, self)) edit_menu.addAction(CreateAction("&Find...", "Find items", self.Find, self, QKeySequence.Find)) edit_menu.addAction(CreateAction("Fetch &more records...", "Fetch more records", self.FetchMoreRecords, self, [QKeySequence(Qt.Key_F8)])) edit_menu.addAction(CreateAction("&Shrink Font", "Make text smaller", self.ShrinkFont, self, [QKeySequence("Ctrl+-")])) @@ -2755,6 +3064,21 @@ class MainWindow(QMainWindow): help_menu = menu.addMenu("&Help") help_menu.addAction(CreateAction("&Exported SQL Viewer Help", "Helpful information", self.Help, self, QKeySequence.HelpContents)) + help_menu.addAction(CreateAction("&About Exported SQL Viewer", "About this application", self.About, self)) + + def Try(self, fn): + win = self.mdi_area.activeSubWindow() + if win: + try: + fn(win.view) + except: + pass + + def CopyToClipboard(self): + self.Try(CopyCellsToClipboardHdr) + + def CopyToClipboardCSV(self): + self.Try(CopyCellsToClipboardCSV) def Find(self): win = self.mdi_area.activeSubWindow() @@ -2773,12 +3097,10 @@ class MainWindow(QMainWindow): pass def ShrinkFont(self): - win = self.mdi_area.activeSubWindow() - ShrinkFont(win.view) + self.Try(ShrinkFont) def EnlargeFont(self): - win = self.mdi_area.activeSubWindow() - EnlargeFont(win.view) + self.Try(EnlargeFont) def EventMenu(self, events, reports_menu): branches_events = 0 @@ -2828,6 +3150,10 @@ class MainWindow(QMainWindow): def Help(self): HelpWindow(self.glb, self) + def About(self): + dialog = AboutDialog(self.glb, self) + dialog.exec_() + # XED Disassembler class xed_state_t(Structure): diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index 7f6c52021e41..946ab4b63acd 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -304,7 +304,7 @@ int test__dso_data_cache(struct test *test __maybe_unused, int subtest __maybe_u /* Make sure we did not leak any file descriptor. */ nr_end = open_files_cnt(); pr_debug("nr start %ld, nr stop %ld\n", nr, nr_end); - TEST_ASSERT_VAL("failed leadking files", nr == nr_end); + TEST_ASSERT_VAL("failed leaking files", nr == nr_end); return 0; } @@ -380,6 +380,6 @@ int test__dso_data_reopen(struct test *test __maybe_unused, int subtest __maybe_ /* Make sure we did not leak any file descriptor. */ nr_end = open_files_cnt(); pr_debug("nr start %ld, nr stop %ld\n", nr, nr_end); - TEST_ASSERT_VAL("failed leadking files", nr == nr_end); + TEST_ASSERT_VAL("failed leaking files", nr == nr_end); return 0; } diff --git a/tools/perf/tests/make b/tools/perf/tests/make index e46723568516..5363a12a8b9b 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -107,7 +107,7 @@ make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 make_minimal += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 make_minimal += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 make_minimal += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 -make_minimal += NO_LIBCRYPTO=1 NO_SDT=1 NO_JVMTI=1 +make_minimal += NO_LIBCRYPTO=1 NO_SDT=1 NO_JVMTI=1 NO_LIBZSTD=1 # $(run) contains all available tests run := make_pure diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh new file mode 100755 index 000000000000..5dcba800109f --- /dev/null +++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh @@ -0,0 +1,34 @@ +#!/bin/sh +# Zstd perf.data compression/decompression + +trace_file=$(mktemp /tmp/perf.data.XXX) +perf_tool=perf + +skip_if_no_z_record() { + $perf_tool record -h 2>&1 | grep -q '\-z, \-\-compression\-level' +} + +collect_z_record() { + echo "Collecting compressed record file:" + $perf_tool record -o $trace_file -g -z -F 5000 -- \ + dd count=500 if=/dev/random of=/dev/null +} + +check_compressed_stats() { + echo "Checking compressed events stats:" + $perf_tool report -i $trace_file --header --stats | \ + grep -E "(# compressed : Zstd,)|(COMPRESSED events:)" +} + +check_compressed_output() { + $perf_tool inject -i $trace_file -o $trace_file.decomp && + $perf_tool report -i $trace_file --stdio | head -n -3 > $trace_file.comp.output && + $perf_tool report -i $trace_file.decomp --stdio | head -n -3 > $trace_file.decomp.output && + diff $trace_file.comp.output $trace_file.decomp.output +} + +skip_if_no_z_record || exit 2 +collect_z_record && check_compressed_stats && check_compressed_output +err=$? +rm -f $trace_file* +exit $err diff --git a/tools/perf/trace/beauty/renameat.c b/tools/perf/trace/beauty/renameat.c index 6dab340cc506..852d2e271833 100644 --- a/tools/perf/trace/beauty/renameat.c +++ b/tools/perf/trace/beauty/renameat.c @@ -2,7 +2,6 @@ // Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> #include "trace/beauty/beauty.h" -#include <uapi/linux/fs.h> static size_t renameat2__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix) { diff --git a/tools/perf/trace/strace/groups/string b/tools/perf/trace/strace/groups/string new file mode 100644 index 000000000000..c87129a3e3c4 --- /dev/null +++ b/tools/perf/trace/strace/groups/string @@ -0,0 +1,65 @@ +access +acct +add_key +chdir +chmod +chown +chroot +creat +delete_module +execve +execveat +faccessat +fchmodat +fchownat +fgetxattr +finit_module +fremovexattr +fsetxattr +futimesat +getxattr +inotify_add_watch +lchown +lgetxattr +link +linkat +listxattr +llistxattr +lremovexattr +lsetxattr +lstat +memfd_create +mkdir +mkdirat +mknod +mknodat +mq_open +mq_timedsend +mq_unlink +name_to_handle_at +newfstatat +open +openat +pivot_root +pwrite64 +quotactl +readlink +readlinkat +removexattr +rename +renameat +renameat2 +request_key +rmdir +setxattr +stat +statfs +statx +swapoff +swapon +symlink +symlinkat +truncate +unlink +unlinkat +utimensat diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 8dd3102301ea..6d5bbc8b589b 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -145,6 +145,8 @@ perf-y += scripting-engines/ perf-$(CONFIG_ZLIB) += zlib.o perf-$(CONFIG_LZMA) += lzma.o +perf-$(CONFIG_ZSTD) += zstd.o + perf-y += demangle-java.o perf-y += demangle-rust.o diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index c8b01176c9e1..0b8573fd9b05 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1021,7 +1021,7 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64 float ipc = n_insn / ((double)ch->cycles / (double)ch->num); /* Hide data when there are too many overlaps. */ - if (ch->reset >= 0x7fff || ch->reset >= ch->num / 2) + if (ch->reset >= 0x7fff) return; for (offset = start; offset <= end; offset++) { @@ -1714,8 +1714,8 @@ static int symbol__disassemble_bpf(struct symbol *sym, if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO) return -1; - pr_debug("%s: handling sym %s addr %lx len %lx\n", __func__, - sym->name, sym->start, sym->end - sym->start); + 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)); @@ -1740,7 +1740,7 @@ static int symbol__disassemble_bpf(struct symbol *sym, info_linear = info_node->info_linear; sub_id = dso->bpf_prog.sub_id; - info.buffer = (void *)(info_linear->info.jited_prog_insns); + 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) @@ -1776,7 +1776,7 @@ static int symbol__disassemble_bpf(struct symbol *sym, const char *srcline; u64 addr; - addr = pc + ((u64 *)(info_linear->info.jited_ksyms))[sub_id]; + addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id]; count = disassemble(pc, &info); if (prog_linfo) 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/compress.h b/tools/perf/util/compress.h index 892e92e7e7fc..0cd3369af2a4 100644 --- a/tools/perf/util/compress.h +++ b/tools/perf/util/compress.h @@ -2,6 +2,11 @@ #ifndef PERF_COMPRESS_H #define PERF_COMPRESS_H +#include <stdbool.h> +#ifdef HAVE_ZSTD_SUPPORT +#include <zstd.h> +#endif + #ifdef HAVE_ZLIB_SUPPORT int gzip_decompress_to_file(const char *input, int output_fd); bool gzip_is_compressed(const char *input); @@ -12,4 +17,52 @@ int lzma_decompress_to_file(const char *input, int output_fd); bool lzma_is_compressed(const char *input); #endif +struct zstd_data { +#ifdef HAVE_ZSTD_SUPPORT + ZSTD_CStream *cstream; + ZSTD_DStream *dstream; +#endif +}; + +#ifdef HAVE_ZSTD_SUPPORT + +int zstd_init(struct zstd_data *data, int level); +int zstd_fini(struct zstd_data *data); + +size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size, + void *src, size_t src_size, size_t max_record_size, + size_t process_header(void *record, size_t increment)); + +size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size, + void *dst, size_t dst_size); +#else /* !HAVE_ZSTD_SUPPORT */ + +static inline int zstd_init(struct zstd_data *data __maybe_unused, int level __maybe_unused) +{ + return 0; +} + +static inline int zstd_fini(struct zstd_data *data __maybe_unused) +{ + return 0; +} + +static inline +size_t zstd_compress_stream_to_records(struct zstd_data *data __maybe_unused, + void *dst __maybe_unused, size_t dst_size __maybe_unused, + void *src __maybe_unused, size_t src_size __maybe_unused, + size_t max_record_size __maybe_unused, + size_t process_header(void *record, size_t increment) __maybe_unused) +{ + return 0; +} + +static inline size_t zstd_decompress_stream(struct zstd_data *data __maybe_unused, void *src __maybe_unused, + size_t src_size __maybe_unused, void *dst __maybe_unused, + size_t dst_size __maybe_unused) +{ + return 0; +} +#endif + #endif /* PERF_COMPRESS_H */ 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/env.c b/tools/perf/util/env.c index 9494f9dc61ec..6a3eaf7d9353 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -115,8 +115,8 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id) } node = NULL; - up_read(&env->bpf_progs.lock); out: + up_read(&env->bpf_progs.lock); return node; } diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index 4f8e2b485c01..271a90b326c4 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -62,6 +62,11 @@ struct perf_env { struct cpu_topology_map *cpu; struct cpu_cache_level *caches; int caches_cnt; + u32 comp_ratio; + u32 comp_ver; + u32 comp_type; + u32 comp_level; + u32 comp_mmap_len; struct numa_node *numa_nodes; struct memory_node *memory_nodes; unsigned long long memory_bsize; @@ -80,6 +85,12 @@ struct perf_env { } bpf_progs; }; +enum perf_compress_type { + PERF_COMP_NONE = 0, + PERF_COMP_ZSTD, + PERF_COMP_MAX +}; + struct bpf_prog_info_node; struct btf_node; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index ba7be74fad6e..d1ad6c419724 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -68,6 +68,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_EVENT_UPDATE] = "EVENT_UPDATE", [PERF_RECORD_TIME_CONV] = "TIME_CONV", [PERF_RECORD_HEADER_FEATURE] = "FEATURE", + [PERF_RECORD_COMPRESSED] = "COMPRESSED", }; static const char *perf_ns__names[] = { diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 36ae7e92dab1..9e999550f247 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" @@ -254,6 +255,7 @@ enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_EVENT_UPDATE = 78, PERF_RECORD_TIME_CONV = 79, PERF_RECORD_HEADER_FEATURE = 80, + PERF_RECORD_COMPRESSED = 81, PERF_RECORD_HEADER_MAX }; @@ -626,6 +628,11 @@ struct feature_event { char data[]; }; +struct compressed_event { + struct perf_event_header header; + char data[]; +}; + union perf_event { struct perf_event_header header; struct mmap_event mmap; @@ -659,6 +666,7 @@ union perf_event { struct feature_event feat; struct ksymbol_event ksymbol_event; struct bpf_event bpf_event; + struct compressed_event pack; }; void perf_event__print_totals(void); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 51ead577533f..69d0fa8ab16f 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1009,7 +1009,8 @@ 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, + int comp_level) { struct perf_evsel *evsel; const struct cpu_map *cpus = evlist->cpus; @@ -1019,7 +1020,8 @@ 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, + .comp_level = comp_level }; if (!evlist->mmap) evlist->mmap = perf_evlist__alloc_mmap(evlist, false); @@ -1051,7 +1053,7 @@ 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, 0); } int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 6a94785b9100..49354fe24d5f 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -177,7 +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 comp_level); int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages); void perf_evlist__munmap(struct perf_evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 966360844fff..a6f572a40deb 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -580,6 +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]; @@ -601,7 +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: @@ -804,6 +813,8 @@ static void apply_config_terms(struct perf_evsel *evsel, break; case PERF_EVSEL__CONFIG_TERM_DRV_CFG: break; + case PERF_EVSEL__CONFIG_TERM_PERCORE: + break; default: break; } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 0f2c6c93d721..cad54e8ba522 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -50,6 +50,7 @@ enum term_type { PERF_EVSEL__CONFIG_TERM_OVERWRITE, PERF_EVSEL__CONFIG_TERM_DRV_CFG, PERF_EVSEL__CONFIG_TERM_BRANCH, + PERF_EVSEL__CONFIG_TERM_PERCORE, }; struct perf_evsel_config_term { @@ -67,6 +68,7 @@ struct perf_evsel_config_term { bool overwrite; char *branch; unsigned long max_events; + bool percore; } val; bool weak; }; @@ -75,6 +77,11 @@ 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. @@ -121,6 +128,7 @@ 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; @@ -152,6 +160,7 @@ struct perf_evsel { struct perf_evsel **metric_events; bool collect_stat; bool weak_group; + bool percore; const char *pmu_name; struct { perf_evsel__sb_cb_t *cb; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 2d2af2ac2b1e..847ae51a524b 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1344,6 +1344,30 @@ out: return ret; } +static int write_compressed(struct feat_fd *ff __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + int ret; + + ret = do_write(ff, &(ff->ph->env.comp_ver), sizeof(ff->ph->env.comp_ver)); + if (ret) + return ret; + + ret = do_write(ff, &(ff->ph->env.comp_type), sizeof(ff->ph->env.comp_type)); + if (ret) + return ret; + + ret = do_write(ff, &(ff->ph->env.comp_level), sizeof(ff->ph->env.comp_level)); + if (ret) + return ret; + + ret = do_write(ff, &(ff->ph->env.comp_ratio), sizeof(ff->ph->env.comp_ratio)); + if (ret) + return ret; + + return do_write(ff, &(ff->ph->env.comp_mmap_len), sizeof(ff->ph->env.comp_mmap_len)); +} + static void print_hostname(struct feat_fd *ff, FILE *fp) { fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname); @@ -1688,6 +1712,13 @@ static void print_cache(struct feat_fd *ff, FILE *fp __maybe_unused) } } +static void print_compressed(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# compressed : %s, level = %d, ratio = %d\n", + ff->ph->env.comp_type == PERF_COMP_ZSTD ? "Zstd" : "Unknown", + ff->ph->env.comp_level, ff->ph->env.comp_ratio); +} + static void print_pmu_mappings(struct feat_fd *ff, FILE *fp) { const char *delimiter = "# pmu mappings: "; @@ -2667,6 +2698,27 @@ out: return err; } +static int process_compressed(struct feat_fd *ff, + void *data __maybe_unused) +{ + if (do_read_u32(ff, &(ff->ph->env.comp_ver))) + return -1; + + if (do_read_u32(ff, &(ff->ph->env.comp_type))) + return -1; + + if (do_read_u32(ff, &(ff->ph->env.comp_level))) + return -1; + + if (do_read_u32(ff, &(ff->ph->env.comp_ratio))) + return -1; + + if (do_read_u32(ff, &(ff->ph->env.comp_mmap_len))) + return -1; + + return 0; +} + struct feature_ops { int (*write)(struct feat_fd *ff, struct perf_evlist *evlist); void (*print)(struct feat_fd *ff, FILE *fp); @@ -2730,6 +2782,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPN(DIR_FORMAT, dir_format, false), FEAT_OPR(BPF_PROG_INFO, bpf_prog_info, false), FEAT_OPR(BPF_BTF, bpf_btf, false), + FEAT_OPR(COMPRESSED, compressed, false), }; struct header_print_data { diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 386da49e1bfa..5b3abe4172e2 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -42,6 +42,7 @@ enum { HEADER_DIR_FORMAT, HEADER_BPF_PROG_INFO, HEADER_BPF_BTF, + HEADER_COMPRESSED, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; 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 872fab163585..f4c3c84b090f 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -58,6 +58,7 @@ enum intel_pt_pkt_state { INTEL_PT_STATE_NO_IP, INTEL_PT_STATE_ERR_RESYNC, INTEL_PT_STATE_IN_SYNC, + INTEL_PT_STATE_TNT_CONT, INTEL_PT_STATE_TNT, INTEL_PT_STATE_TIP, INTEL_PT_STATE_TIP_PGD, @@ -72,8 +73,9 @@ static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state) case INTEL_PT_STATE_NO_IP: case INTEL_PT_STATE_ERR_RESYNC: case INTEL_PT_STATE_IN_SYNC: - case INTEL_PT_STATE_TNT: + case INTEL_PT_STATE_TNT_CONT: return true; + case INTEL_PT_STATE_TNT: case INTEL_PT_STATE_TIP: case INTEL_PT_STATE_TIP_PGD: case INTEL_PT_STATE_FUP: @@ -888,16 +890,20 @@ static uint64_t intel_pt_next_period(struct intel_pt_decoder *decoder) timestamp = decoder->timestamp + decoder->timestamp_insn_cnt; masked_timestamp = timestamp & decoder->period_mask; if (decoder->continuous_period) { - if (masked_timestamp != decoder->last_masked_timestamp) + if (masked_timestamp > decoder->last_masked_timestamp) return 1; } else { timestamp += 1; masked_timestamp = timestamp & decoder->period_mask; - if (masked_timestamp != decoder->last_masked_timestamp) { + if (masked_timestamp > decoder->last_masked_timestamp) { decoder->last_masked_timestamp = masked_timestamp; decoder->continuous_period = true; } } + + if (masked_timestamp < decoder->last_masked_timestamp) + return decoder->period_ticks; + return decoder->period_ticks - (timestamp - masked_timestamp); } @@ -926,7 +932,10 @@ static void intel_pt_sample_insn(struct intel_pt_decoder *decoder) case INTEL_PT_PERIOD_TICKS: timestamp = decoder->timestamp + decoder->timestamp_insn_cnt; masked_timestamp = timestamp & decoder->period_mask; - decoder->last_masked_timestamp = masked_timestamp; + if (masked_timestamp > decoder->last_masked_timestamp) + decoder->last_masked_timestamp = masked_timestamp; + else + decoder->last_masked_timestamp += decoder->period_ticks; break; case INTEL_PT_PERIOD_NONE: case INTEL_PT_PERIOD_MTC: @@ -1254,7 +1263,9 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder) return -ENOENT; } decoder->tnt.count -= 1; - if (!decoder->tnt.count) + if (decoder->tnt.count) + decoder->pkt_state = INTEL_PT_STATE_TNT_CONT; + else decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; decoder->tnt.payload <<= 1; decoder->state.from_ip = decoder->ip; @@ -1285,7 +1296,9 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder) if (intel_pt_insn.branch == INTEL_PT_BR_CONDITIONAL) { decoder->tnt.count -= 1; - if (!decoder->tnt.count) + if (decoder->tnt.count) + decoder->pkt_state = INTEL_PT_STATE_TNT_CONT; + else decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; if (decoder->tnt.payload & BIT63) { decoder->tnt.payload <<= 1; @@ -1305,8 +1318,11 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder) return 0; } decoder->ip += intel_pt_insn.length; - if (!decoder->tnt.count) + if (!decoder->tnt.count) { + decoder->sample_timestamp = decoder->timestamp; + decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; return -EAGAIN; + } decoder->tnt.payload <<= 1; continue; } @@ -2365,6 +2381,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) err = intel_pt_walk_trace(decoder); break; case INTEL_PT_STATE_TNT: + case INTEL_PT_STATE_TNT_CONT: err = intel_pt_walk_tnt(decoder); if (err == -EAGAIN) err = intel_pt_walk_trace(decoder); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 3c520baa198c..28a9541c4835 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1234,8 +1234,9 @@ static char *get_kernel_version(const char *root_dir) if (!file) return NULL; - version[0] = '\0'; tmp = fgets(version, sizeof(version), file); + if (!tmp) + *version = '\0'; fclose(file); name = strstr(version, prefix); diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index cdc7740fc181..868c0b0e909c 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -157,6 +157,10 @@ void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __mayb } #ifdef HAVE_AIO_SUPPORT +static int perf_mmap__aio_enabled(struct perf_mmap *map) +{ + return map->aio.nr_cblocks > 0; +} #ifdef HAVE_LIBNUMA_SUPPORT static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx) @@ -198,7 +202,7 @@ static int perf_mmap__aio_bind(struct perf_mmap *map, int idx, int cpu, int affi return 0; } -#else +#else /* !HAVE_LIBNUMA_SUPPORT */ static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx) { map->aio.data[idx] = malloc(perf_mmap__mmap_len(map)); @@ -285,81 +289,12 @@ static void perf_mmap__aio_munmap(struct perf_mmap *map) zfree(&map->aio.cblocks); zfree(&map->aio.aiocb); } - -int perf_mmap__aio_push(struct perf_mmap *md, void *to, int idx, - int push(void *to, struct aiocb *cblock, void *buf, size_t size, off_t off), - off_t *off) +#else /* !HAVE_AIO_SUPPORT */ +static int perf_mmap__aio_enabled(struct perf_mmap *map __maybe_unused) { - u64 head = perf_mmap__read_head(md); - unsigned char *data = md->base + page_size; - unsigned long size, size0 = 0; - void *buf; - int rc = 0; - - rc = perf_mmap__read_init(md); - if (rc < 0) - return (rc == -EAGAIN) ? 0 : -1; - - /* - * md->base data is copied into md->data[idx] buffer to - * release space in the kernel buffer as fast as possible, - * thru perf_mmap__consume() below. - * - * That lets the kernel to proceed with storing more - * profiling data into the kernel buffer earlier than other - * per-cpu kernel buffers are handled. - * - * Coping can be done in two steps in case the chunk of - * profiling data crosses the upper bound of the kernel buffer. - * In this case we first move part of data from md->start - * till the upper bound and then the reminder from the - * beginning of the kernel buffer till the end of - * the data chunk. - */ - - size = md->end - md->start; - - if ((md->start & md->mask) + size != (md->end & md->mask)) { - buf = &data[md->start & md->mask]; - size = md->mask + 1 - (md->start & md->mask); - md->start += size; - memcpy(md->aio.data[idx], buf, size); - size0 = size; - } - - buf = &data[md->start & md->mask]; - size = md->end - md->start; - md->start += size; - memcpy(md->aio.data[idx] + size0, buf, size); - - /* - * Increment md->refcount to guard md->data[idx] buffer - * from premature deallocation because md object can be - * released earlier than aio write request started - * on mmap->data[idx] is complete. - * - * perf_mmap__put() is done at record__aio_complete() - * after started request completion. - */ - perf_mmap__get(md); - - md->prev = head; - perf_mmap__consume(md); - - rc = push(to, &md->aio.cblocks[idx], md->aio.data[idx], size0 + size, *off); - if (!rc) { - *off += size0 + size; - } else { - /* - * Decrement md->refcount back if aio write - * operation failed to start. - */ - perf_mmap__put(md); - } - - return rc; + return 0; } -#else + static int perf_mmap__aio_mmap(struct perf_mmap *map __maybe_unused, struct mmap_params *mp __maybe_unused) { @@ -374,6 +309,10 @@ static void perf_mmap__aio_munmap(struct perf_mmap *map __maybe_unused) void perf_mmap__munmap(struct perf_mmap *map) { perf_mmap__aio_munmap(map); + if (map->data != NULL) { + munmap(map->data, perf_mmap__mmap_len(map)); + map->data = NULL; + } if (map->base != NULL) { munmap(map->base, perf_mmap__mmap_len(map)); map->base = NULL; @@ -440,6 +379,21 @@ 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; + + map->comp_level = mp->comp_level; + + if (map->comp_level && !perf_mmap__aio_enabled(map)) { + map->data = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE, + MAP_PRIVATE|MAP_ANONYMOUS, 0, 0); + if (map->data == MAP_FAILED) { + pr_debug2("failed to mmap data buffer, error %d\n", + errno); + map->data = NULL; + return -1; + } + } + if (auxtrace_mmap__mmap(&map->auxtrace_mmap, &mp->auxtrace_mp, map->base, fd)) return -1; @@ -492,7 +446,7 @@ 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; @@ -538,7 +492,7 @@ int perf_mmap__push(struct perf_mmap *md, void *to, rc = perf_mmap__read_init(md); if (rc < 0) - return (rc == -EAGAIN) ? 0 : -1; + return (rc == -EAGAIN) ? 1 : -1; size = md->end - md->start; diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index e566c19b242b..274ce389cd84 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -39,6 +39,9 @@ struct perf_mmap { } aio; #endif cpu_set_t affinity_mask; + u64 flush; + void *data; + int comp_level; }; /* @@ -70,7 +73,7 @@ enum bkw_mmap_state { }; struct mmap_params { - int prot, mask, nr_cblocks, affinity; + int prot, mask, nr_cblocks, affinity, flush, comp_level; struct auxtrace_mmap_params auxtrace_mp; }; @@ -98,18 +101,6 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map); int perf_mmap__push(struct perf_mmap *md, void *to, int push(struct perf_mmap *map, void *to, void *buf, size_t size)); -#ifdef HAVE_AIO_SUPPORT -int perf_mmap__aio_push(struct perf_mmap *md, void *to, int idx, - int push(void *to, struct aiocb *cblock, void *buf, size_t size, off_t off), - off_t *off); -#else -static inline int perf_mmap__aio_push(struct perf_mmap *md __maybe_unused, void *to __maybe_unused, int idx __maybe_unused, - int push(void *to, struct aiocb *cblock, void *buf, size_t size, off_t off) __maybe_unused, - off_t *off __maybe_unused) -{ - return 0; -} -#endif size_t perf_mmap__mmap_len(struct perf_mmap *map); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 5ef4939408f2..cf0b9b81c5aa 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) @@ -930,6 +950,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = { [PARSE_EVENTS__TERM_TYPE_OVERWRITE] = "overwrite", [PARSE_EVENTS__TERM_TYPE_NOOVERWRITE] = "no-overwrite", [PARSE_EVENTS__TERM_TYPE_DRV_CFG] = "driver-config", + [PARSE_EVENTS__TERM_TYPE_PERCORE] = "percore", }; static bool config_term_shrinked; @@ -950,6 +971,7 @@ config_term_avail(int term_type, struct parse_events_error *err) case PARSE_EVENTS__TERM_TYPE_CONFIG2: case PARSE_EVENTS__TERM_TYPE_NAME: case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: + case PARSE_EVENTS__TERM_TYPE_PERCORE: return true; default: if (!err) @@ -1041,6 +1063,14 @@ do { \ case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS: CHECK_TYPE_VAL(NUM); break; + case PARSE_EVENTS__TERM_TYPE_PERCORE: + CHECK_TYPE_VAL(NUM); + if ((unsigned int)term->val.num > 1) { + err->str = strdup("expected 0 or 1"); + err->idx = term->err_val; + return -EINVAL; + } + break; default: err->str = strdup("unknown term"); err->idx = term->err_term; @@ -1179,6 +1209,10 @@ do { \ case PARSE_EVENTS__TERM_TYPE_DRV_CFG: ADD_CONFIG_TERM(DRV_CFG, drv_cfg, term->val.str); break; + case PARSE_EVENTS__TERM_TYPE_PERCORE: + ADD_CONFIG_TERM(PERCORE, percore, + term->val.num ? true : false); + break; default: break; } @@ -1233,6 +1267,25 @@ 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); +} + +static bool config_term_percore(struct list_head *config_terms) +{ + struct perf_evsel_config_term *term; + + list_for_each_entry(term, config_terms, list) { + if (term->type == PERF_EVSEL__CONFIG_TERM_PERCORE) + return term->val.percore; + } + + return false; +} + int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, struct list_head *head_config, @@ -1267,7 +1320,8 @@ 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 +1349,7 @@ 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; @@ -1305,6 +1359,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel->metric_name = info.metric_name; evsel->pmu_name = name; evsel->use_uncore_alias = use_uncore_alias; + evsel->percore = config_term_percore(&evsel->config_terms); } return evsel ? 0 : -ENOMEM; @@ -2429,6 +2484,25 @@ 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) @@ -2512,6 +2586,7 @@ 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..f7139e1a2fd3 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -75,6 +75,7 @@ enum { PARSE_EVENTS__TERM_TYPE_NOOVERWRITE, PARSE_EVENTS__TERM_TYPE_OVERWRITE, PARSE_EVENTS__TERM_TYPE_DRV_CFG, + PARSE_EVENTS__TERM_TYPE_PERCORE, __PARSE_EVENTS__TERM_TYPE_NR, }; @@ -160,6 +161,10 @@ 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 +205,7 @@ 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..ca6098874fe2 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); @@ -274,6 +283,7 @@ inherit { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); } no-inherit { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); } overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); } no-overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); } +percore { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); } , { return ','; } "/" { BEGIN(INITIAL); return '/'; } {name_minus} { return str(yyscanner, PE_NAME); } @@ -322,7 +332,7 @@ 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/parse-regs-options.c b/tools/perf/util/parse-regs-options.c index e6599e290f46..08581e276225 100644 --- a/tools/perf/util/parse-regs-options.c +++ b/tools/perf/util/parse-regs-options.c @@ -5,13 +5,14 @@ #include <subcmd/parse-options.h> #include "util/parse-regs-options.h" -int -parse_regs(const struct option *opt, const char *str, int unset) +static int +__parse_regs(const struct option *opt, const char *str, int unset, bool intr) { uint64_t *mode = (uint64_t *)opt->value; const struct sample_reg *r; char *s, *os = NULL, *p; int ret = -1; + uint64_t mask; if (unset) return 0; @@ -22,6 +23,11 @@ parse_regs(const struct option *opt, const char *str, int unset) if (*mode) return -1; + if (intr) + mask = arch__intr_reg_mask(); + else + mask = arch__user_reg_mask(); + /* str may be NULL in case no arg is passed to -I */ if (str) { /* because str is read-only */ @@ -37,19 +43,20 @@ parse_regs(const struct option *opt, const char *str, int unset) if (!strcmp(s, "?")) { fprintf(stderr, "available registers: "); for (r = sample_reg_masks; r->name; r++) { - fprintf(stderr, "%s ", r->name); + if (r->mask & mask) + fprintf(stderr, "%s ", r->name); } fputc('\n', stderr); /* just printing available regs */ return -1; } for (r = sample_reg_masks; r->name; r++) { - if (!strcasecmp(s, r->name)) + if ((r->mask & mask) && !strcasecmp(s, r->name)) break; } if (!r->name) { - ui__warning("unknown register %s," - " check man page\n", s); + ui__warning("Unknown register \"%s\", check man page or run \"perf record %s?\"\n", + s, intr ? "-I" : "--user-regs="); goto error; } @@ -65,8 +72,20 @@ parse_regs(const struct option *opt, const char *str, int unset) /* default to all possible regs */ if (*mode == 0) - *mode = PERF_REGS_MASK; + *mode = mask; error: free(os); return ret; } + +int +parse_user_regs(const struct option *opt, const char *str, int unset) +{ + return __parse_regs(opt, str, unset, false); +} + +int +parse_intr_regs(const struct option *opt, const char *str, int unset) +{ + return __parse_regs(opt, str, unset, true); +} diff --git a/tools/perf/util/parse-regs-options.h b/tools/perf/util/parse-regs-options.h index cdefb1acf6be..2b23d25c6394 100644 --- a/tools/perf/util/parse-regs-options.h +++ b/tools/perf/util/parse-regs-options.h @@ -2,5 +2,6 @@ #ifndef _PERF_PARSE_REGS_OPTIONS_H #define _PERF_PARSE_REGS_OPTIONS_H 1 struct option; -int parse_regs(const struct option *opt, const char *str, int unset); +int parse_user_regs(const struct option *opt, const char *str, int unset); +int parse_intr_regs(const struct option *opt, const char *str, int unset); #endif /* _PERF_PARSE_REGS_OPTIONS_H */ diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index 2acfcc527cac..2774cec1f15f 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -13,6 +13,16 @@ int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused, return SDT_ARG_SKIP; } +uint64_t __weak arch__intr_reg_mask(void) +{ + return PERF_REGS_MASK; +} + +uint64_t __weak arch__user_reg_mask(void) +{ + return PERF_REGS_MASK; +} + #ifdef HAVE_PERF_REGS_SUPPORT int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) { diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index c9319f8d17a6..cb9c246c8962 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -12,6 +12,7 @@ struct sample_reg { uint64_t mask; }; #define SMPL_REG(n, b) { .name = #n, .mask = 1ULL << (b) } +#define SMPL_REG2(n, b) { .name = #n, .mask = 3ULL << (b) } #define SMPL_REG_END { .name = NULL } extern const struct sample_reg sample_reg_masks[]; @@ -22,6 +23,8 @@ enum { }; int arch_sdt_arg_parse_op(char *old_op, char **new_op); +uint64_t arch__intr_reg_mask(void); +uint64_t arch__user_reg_mask(void); #ifdef HAVE_PERF_REGS_SUPPORT #include <perf_regs.h> 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 b17f1c9bc965..2310a1752983 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -29,6 +29,61 @@ #include "stat.h" #include "arch/common.h" +#ifdef HAVE_ZSTD_SUPPORT +static int perf_session__process_compressed_event(struct perf_session *session, + union perf_event *event, u64 file_offset) +{ + void *src; + size_t decomp_size, src_size; + u64 decomp_last_rem = 0; + size_t decomp_len = session->header.env.comp_mmap_len; + struct decomp *decomp, *decomp_last = session->decomp_last; + + decomp = mmap(NULL, sizeof(struct decomp) + decomp_len, PROT_READ|PROT_WRITE, + MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); + if (decomp == MAP_FAILED) { + pr_err("Couldn't allocate memory for decompression\n"); + return -1; + } + + decomp->file_pos = file_offset; + decomp->head = 0; + + if (decomp_last) { + decomp_last_rem = decomp_last->size - decomp_last->head; + memcpy(decomp->data, &(decomp_last->data[decomp_last->head]), decomp_last_rem); + decomp->size = decomp_last_rem; + } + + src = (void *)event + sizeof(struct compressed_event); + src_size = event->pack.header.size - sizeof(struct compressed_event); + + decomp_size = zstd_decompress_stream(&(session->zstd_data), src, src_size, + &(decomp->data[decomp_last_rem]), decomp_len - decomp_last_rem); + if (!decomp_size) { + munmap(decomp, sizeof(struct decomp) + decomp_len); + pr_err("Couldn't decompress data\n"); + return -1; + } + + decomp->size += decomp_size; + + if (session->decomp == NULL) { + session->decomp = decomp; + session->decomp_last = decomp; + } else { + session->decomp_last->next = decomp; + session->decomp_last = decomp; + } + + pr_debug("decomp (B): %ld to %ld\n", src_size, decomp_size); + + return 0; +} +#else /* !HAVE_ZSTD_SUPPORT */ +#define perf_session__process_compressed_event perf_session__process_compressed_event_stub +#endif + static int perf_session__deliver_event(struct perf_session *session, union perf_event *event, struct perf_tool *tool, @@ -197,6 +252,21 @@ static void perf_session__delete_threads(struct perf_session *session) machine__delete_threads(&session->machines.host); } +static void perf_session__release_decomp_events(struct perf_session *session) +{ + struct decomp *next, *decomp; + size_t decomp_len; + next = session->decomp; + decomp_len = session->header.env.comp_mmap_len; + do { + decomp = next; + if (decomp == NULL) + break; + next = decomp->next; + munmap(decomp, decomp_len + sizeof(struct decomp)); + } while (1); +} + void perf_session__delete(struct perf_session *session) { if (session == NULL) @@ -205,6 +275,7 @@ void perf_session__delete(struct perf_session *session) auxtrace_index__free(&session->auxtrace_index); perf_session__destroy_kernel_maps(session); perf_session__delete_threads(session); + perf_session__release_decomp_events(session); perf_env__exit(&session->header.env); machines__exit(&session->machines); if (session->data) @@ -358,6 +429,14 @@ static int process_stat_round_stub(struct perf_session *perf_session __maybe_unu return 0; } +static int perf_session__process_compressed_event_stub(struct perf_session *session __maybe_unused, + union perf_event *event __maybe_unused, + u64 file_offset __maybe_unused) +{ + dump_printf(": unhandled!\n"); + return 0; +} + void perf_tool__fill_defaults(struct perf_tool *tool) { if (tool->sample == NULL) @@ -430,6 +509,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->time_conv = process_event_op2_stub; if (tool->feature == NULL) tool->feature = process_event_op2_stub; + if (tool->compressed == NULL) + tool->compressed = perf_session__process_compressed_event; } static void swap_sample_id_all(union perf_event *event, void *data) @@ -1373,7 +1454,9 @@ static s64 perf_session__process_user_event(struct perf_session *session, int fd = perf_data__fd(session->data); int err; - dump_event(session->evlist, event, file_offset, &sample); + if (event->header.type != PERF_RECORD_COMPRESSED || + tool->compressed == perf_session__process_compressed_event_stub) + dump_event(session->evlist, event, file_offset, &sample); /* These events are processed right away */ switch (event->header.type) { @@ -1426,6 +1509,11 @@ static s64 perf_session__process_user_event(struct perf_session *session, return tool->time_conv(session, event); case PERF_RECORD_HEADER_FEATURE: return tool->feature(session, event); + case PERF_RECORD_COMPRESSED: + err = tool->compressed(session, event, file_offset); + if (err) + dump_event(session->evlist, event, file_offset, &sample); + return err; default: return -EINVAL; } @@ -1708,6 +1796,8 @@ static int perf_session__flush_thread_stacks(struct perf_session *session) volatile int session_done; +static int __perf_session__process_decomp_events(struct perf_session *session); + static int __perf_session__process_pipe_events(struct perf_session *session) { struct ordered_events *oe = &session->ordered_events; @@ -1788,6 +1878,10 @@ more: if (skip > 0) head += skip; + err = __perf_session__process_decomp_events(session); + if (err) + goto out_err; + if (!session_done()) goto more; done: @@ -1836,6 +1930,39 @@ fetch_mmaped_event(struct perf_session *session, return event; } +static int __perf_session__process_decomp_events(struct perf_session *session) +{ + s64 skip; + u64 size, file_pos = 0; + struct decomp *decomp = session->decomp_last; + + if (!decomp) + return 0; + + while (decomp->head < decomp->size && !session_done()) { + union perf_event *event = fetch_mmaped_event(session, decomp->head, decomp->size, decomp->data); + + if (!event) + break; + + size = event->header.size; + + 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", + decomp->file_pos + decomp->head, event->header.size, event->header.type); + return -EINVAL; + } + + if (skip) + size += skip; + + decomp->head += size; + } + + return 0; +} + /* * On 64bit we can mmap the data file in one go. No need for tiny mmap * slices. On 32bit we use 32MB. @@ -1928,12 +2055,14 @@ more: size = event->header.size; + skip = -EINVAL; + if (size < sizeof(struct perf_event_header) || (skip = rd->process(session, event, file_pos)) < 0) { - pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", + 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; } @@ -1943,6 +2072,10 @@ more: head += size; file_pos += size; + err = __perf_session__process_decomp_events(session); + if (err) + goto out; + ui_progress__update(prog, size); if (session_done()) diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index d96eccd7d27f..dd8920b745bc 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -8,6 +8,7 @@ #include "machine.h" #include "data.h" #include "ordered-events.h" +#include "util/compress.h" #include <linux/kernel.h> #include <linux/rbtree.h> #include <linux/perf_event.h> @@ -35,6 +36,19 @@ struct perf_session { struct ordered_events ordered_events; struct perf_data *data; struct perf_tool *tool; + u64 bytes_transferred; + u64 bytes_compressed; + struct zstd_data zstd_data; + struct decomp *decomp; + struct decomp *decomp_last; +}; + +struct decomp { + struct decomp *next; + u64 file_pos; + u64 head; + size_t size; + char data[]; }; struct perf_tool; diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 6d043c78f3c2..4c53bae5644b 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) { @@ -93,9 +88,17 @@ static void aggr_printout(struct perf_stat_config *config, config->csv_sep); break; case AGGR_NONE: - fprintf(config->output, "CPU%*d%s", - config->csv_output ? 0 : -4, - perf_evsel__cpus(evsel)->map[id], config->csv_sep); + if (evsel->percore) { + fprintf(config->output, "S%d-C%*d%s", + cpu_map__id_to_socket(id), + config->csv_output ? 0 : -5, + cpu_map__id_to_cpu(id), config->csv_sep); + } else { + fprintf(config->output, "CPU%*d%s ", + config->csv_output ? 0 : -5, + perf_evsel__cpus(evsel)->map[id], + config->csv_sep); + } break; case AGGR_THREAD: fprintf(config->output, "%*s-%*d%s", @@ -599,6 +602,41 @@ static void aggr_cb(struct perf_stat_config *config, } } +static void print_counter_aggrdata(struct perf_stat_config *config, + struct perf_evsel *counter, int s, + char *prefix, bool metric_only, + bool *first) +{ + struct aggr_data ad; + FILE *output = config->output; + u64 ena, run, val; + int id, nr; + double uval; + + ad.id = id = config->aggr_map->map[s]; + ad.val = ad.ena = ad.run = 0; + ad.nr = 0; + if (!collect_data(config, counter, aggr_cb, &ad)) + return; + + nr = ad.nr; + ena = ad.ena; + run = ad.run; + val = ad.val; + if (*first && metric_only) { + *first = false; + aggr_printout(config, counter, id, nr); + } + if (prefix && !metric_only) + fprintf(output, "%s", prefix); + + uval = val * counter->scale; + printout(config, id, nr, counter, uval, prefix, + run, ena, 1.0, &rt_stat); + if (!metric_only) + fputc('\n', output); +} + static void print_aggr(struct perf_stat_config *config, struct perf_evlist *evlist, char *prefix) @@ -606,9 +644,7 @@ static void print_aggr(struct perf_stat_config *config, bool metric_only = config->metric_only; FILE *output = config->output; struct perf_evsel *counter; - int s, id, nr; - double uval; - u64 ena, run, val; + int s; bool first; if (!(config->aggr_map || config->aggr_get_id)) @@ -621,36 +657,14 @@ static void print_aggr(struct perf_stat_config *config, * Without each counter has its own line. */ for (s = 0; s < config->aggr_map->nr; s++) { - struct aggr_data ad; if (prefix && metric_only) fprintf(output, "%s", prefix); - 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)) - continue; - nr = ad.nr; - ena = ad.ena; - run = ad.run; - val = ad.val; - if (first && metric_only) { - first = false; - aggr_printout(config, counter, id, nr); - } - if (prefix && !metric_only) - fprintf(output, "%s", prefix); - - uval = val * counter->scale; - printout(config, id, nr, counter, uval, prefix, - run, ena, 1.0, &rt_stat); - if (!metric_only) - fputc('\n', output); + print_counter_aggrdata(config, counter, s, + prefix, metric_only, + &first); } if (metric_only) fputc('\n', output); @@ -848,8 +862,6 @@ 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 +918,6 @@ 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; @@ -1101,6 +1111,30 @@ static void print_footer(struct perf_stat_config *config) "the same PMU. Try reorganizing the group.\n"); } +static void print_percore(struct perf_stat_config *config, + struct perf_evsel *counter, char *prefix) +{ + bool metric_only = config->metric_only; + FILE *output = config->output; + int s; + bool first = true; + + if (!(config->aggr_map || config->aggr_get_id)) + return; + + for (s = 0; s < config->aggr_map->nr; s++) { + if (prefix && metric_only) + fprintf(output, "%s", prefix); + + print_counter_aggrdata(config, counter, s, + prefix, metric_only, + &first); + } + + if (metric_only) + fputc('\n', output); +} + void perf_evlist__print_counters(struct perf_evlist *evlist, struct perf_stat_config *config, @@ -1136,15 +1170,11 @@ 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) @@ -1155,9 +1185,10 @@ 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); + if (counter->percore) + print_percore(config, counter, prefix); + else + print_counter(config, counter, prefix); } } break; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 2856cc9d5a31..c3115d939b0b 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -277,9 +277,11 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel if (!evsel->snapshot) perf_evsel__compute_deltas(evsel, cpu, thread, count); perf_counts_values__scale(count, config->scale, NULL); - if (config->aggr_mode == AGGR_NONE) - perf_stat__update_shadow_stats(evsel, count->val, cpu, - &rt_stat); + if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) { + perf_stat__update_shadow_stats(evsel, count->val, + cpu, &rt_stat); + } + if (config->aggr_mode == AGGR_THREAD) { if (config->stats) perf_stat__update_shadow_stats(evsel, diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 50678d318185..403045a2bbea 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -15,6 +15,7 @@ #include "map.h" #include "symbol.h" #include "unwind.h" +#include "callchain.h" #include <api/fs/fs.h> @@ -327,7 +328,7 @@ static int thread__prepare_access(struct thread *thread) { int err = 0; - if (symbol_conf.use_callchain) + if (dwarf_callchain_users) err = __thread__prepare_access(thread); return err; diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 250391672f9f..9096a6e3de59 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -28,6 +28,7 @@ typedef int (*event_attr_op)(struct perf_tool *tool, typedef int (*event_op2)(struct perf_session *session, union perf_event *event); typedef s64 (*event_op3)(struct perf_session *session, union perf_event *event); +typedef int (*event_op4)(struct perf_session *session, union perf_event *event, u64 data); typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event, struct ordered_events *oe); @@ -72,6 +73,7 @@ struct perf_tool { stat, stat_round, feature; + event_op4 compressed; event_op3 auxtrace; bool ordered_events; bool ordering_requires_timestamps; 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; } diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index f3c666a84e4d..25e1406b1f8b 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -617,8 +617,6 @@ static unw_accessors_t accessors = { static int _unwind__prepare_access(struct thread *thread) { - if (!dwarf_callchain_users) - return 0; thread->addr_space = unw_create_addr_space(&accessors, 0); if (!thread->addr_space) { pr_err("unwind: Can't create unwind address space.\n"); @@ -631,15 +629,11 @@ static int _unwind__prepare_access(struct thread *thread) static void _unwind__flush_access(struct thread *thread) { - if (!dwarf_callchain_users) - return; unw_flush_cache(thread->addr_space, 0, 0); } static void _unwind__finish_access(struct thread *thread) { - if (!dwarf_callchain_users) - return; unw_destroy_addr_space(thread->addr_space); } diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 9778b3133b77..c0811977d7d5 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -5,6 +5,7 @@ #include "session.h" #include "debug.h" #include "env.h" +#include "callchain.h" struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops; struct unwind_libunwind_ops __weak *x86_32_unwind_libunwind_ops; @@ -24,6 +25,9 @@ int unwind__prepare_access(struct thread *thread, struct map *map, struct unwind_libunwind_ops *ops = local_unwind_libunwind_ops; int err; + if (!dwarf_callchain_users) + return 0; + if (thread->addr_space) { pr_debug("unwind: thread map already set, dso=%s\n", map->dso->name); @@ -65,12 +69,18 @@ out_register: void unwind__flush_access(struct thread *thread) { + if (!dwarf_callchain_users) + return; + if (thread->unwind_libunwind_ops) thread->unwind_libunwind_ops->flush_access(thread); } void unwind__finish_access(struct thread *thread) { + if (!dwarf_callchain_users) + return; + if (thread->unwind_libunwind_ops) thread->unwind_libunwind_ops->finish_access(thread); } diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c new file mode 100644 index 000000000000..23bdb9884576 --- /dev/null +++ b/tools/perf/util/zstd.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <string.h> + +#include "util/compress.h" +#include "util/debug.h" + +int zstd_init(struct zstd_data *data, int level) +{ + size_t ret; + + data->dstream = ZSTD_createDStream(); + if (data->dstream == NULL) { + pr_err("Couldn't create decompression stream.\n"); + return -1; + } + + ret = ZSTD_initDStream(data->dstream); + if (ZSTD_isError(ret)) { + pr_err("Failed to initialize decompression stream: %s\n", ZSTD_getErrorName(ret)); + return -1; + } + + if (!level) + return 0; + + data->cstream = ZSTD_createCStream(); + if (data->cstream == NULL) { + pr_err("Couldn't create compression stream.\n"); + return -1; + } + + ret = ZSTD_initCStream(data->cstream, level); + if (ZSTD_isError(ret)) { + pr_err("Failed to initialize compression stream: %s\n", ZSTD_getErrorName(ret)); + return -1; + } + + return 0; +} + +int zstd_fini(struct zstd_data *data) +{ + if (data->dstream) { + ZSTD_freeDStream(data->dstream); + data->dstream = NULL; + } + + if (data->cstream) { + ZSTD_freeCStream(data->cstream); + data->cstream = NULL; + } + + return 0; +} + +size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size, + void *src, size_t src_size, size_t max_record_size, + size_t process_header(void *record, size_t increment)) +{ + size_t ret, size, compressed = 0; + ZSTD_inBuffer input = { src, src_size, 0 }; + ZSTD_outBuffer output; + void *record; + + while (input.pos < input.size) { + record = dst; + size = process_header(record, 0); + compressed += size; + dst += size; + dst_size -= size; + output = (ZSTD_outBuffer){ dst, (dst_size > max_record_size) ? + max_record_size : dst_size, 0 }; + ret = ZSTD_compressStream(data->cstream, &output, &input); + ZSTD_flushStream(data->cstream, &output); + if (ZSTD_isError(ret)) { + pr_err("failed to compress %ld bytes: %s\n", + (long)src_size, ZSTD_getErrorName(ret)); + memcpy(dst, src, src_size); + return src_size; + } + size = output.pos; + size = process_header(record, size); + compressed += size; + dst += size; + dst_size -= size; + } + + return compressed; +} + +size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size, + void *dst, size_t dst_size) +{ + size_t ret; + ZSTD_inBuffer input = { src, src_size, 0 }; + ZSTD_outBuffer output = { dst, dst_size, 0 }; + + while (input.pos < input.size) { + ret = ZSTD_decompressStream(data->dstream, &output, &input); + if (ZSTD_isError(ret)) { + pr_err("failed to decompress (B): %ld -> %ld : %s\n", + src_size, output.size, ZSTD_getErrorName(ret)); + break; + } + output.dst = dst + output.pos; + output.size = dst_size - output.pos; + } + + return output.pos; +} |