diff options
Diffstat (limited to 'tools/perf/pmu-events/arch')
20 files changed, 10901 insertions, 6 deletions
diff --git a/tools/perf/pmu-events/arch/powerpc/mapfile.csv b/tools/perf/pmu-events/arch/powerpc/mapfile.csv index e925baa0c30b..a0f3a11ca19f 100644 --- a/tools/perf/pmu-events/arch/powerpc/mapfile.csv +++ b/tools/perf/pmu-events/arch/powerpc/mapfile.csv @@ -13,9 +13,13 @@ # # Power8 entries -004b0000,1,power8.json,core -004b0201,1,power8.json,core -004c0000,1,power8.json,core -004d0000,1,power8.json,core -004d0100,1,power8.json,core -004d0200,1,power8.json,core +004b0000,1,power8,core +004b0201,1,power8,core +004c0000,1,power8,core +004d0000,1,power8,core +004d0100,1,power8,core +004d0200,1,power8,core +004c0100,1,power8,core +004e0100,1,power9,core +004e0200,1,power9,core +004e1200,1,power9,core diff --git a/tools/perf/pmu-events/arch/powerpc/power9/cache.json b/tools/perf/pmu-events/arch/powerpc/power9/cache.json new file mode 100644 index 000000000000..18f6645f2897 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/cache.json @@ -0,0 +1,137 @@ +[ + {, + "EventCode": "0x300F4", + "EventName": "PM_THRD_CONC_RUN_INST", + "BriefDescription": "PPC Instructions Finished by this thread when all threads in the core had the run-latch set" + }, + {, + "EventCode": "0x1E056", + "EventName": "PM_CMPLU_STALL_FLUSH_ANY_THREAD", + "BriefDescription": "Cycles in which the NTC instruction is not allowed to complete because any of the 4 threads in the same core suffered a flush, which blocks completion" + }, + {, + "EventCode": "0x4D016", + "EventName": "PM_CMPLU_STALL_FXLONG", + "BriefDescription": "Completion stall due to a long latency scalar fixed point instruction (division, square root)" + }, + {, + "EventCode": "0x2D016", + "EventName": "PM_CMPLU_STALL_FXU", + "BriefDescription": "Finish stall due to a scalar fixed point or CR instruction in the execution pipeline. These instructions get routed to the ALU, ALU2, and DIV pipes" + }, + {, + "EventCode": "0x1D15C", + "EventName": "PM_MRK_DTLB_MISS_1G", + "BriefDescription": "Marked Data TLB reload (after a miss) page size 2M. Implies radix translation was used" + }, + {, + "EventCode": "0x4D12A", + "EventName": "PM_MRK_DATA_FROM_RL4_CYC", + "BriefDescription": "Duration in cycles to reload from another chip's L4 on the same Node or Group ( Remote) due to a marked load" + }, + {, + "EventCode": "0x1003C", + "EventName": "PM_CMPLU_STALL_DMISS_L2L3", + "BriefDescription": "Completion stall by Dcache miss which resolved in L2/L3" + }, + {, + "EventCode": "0x4C014", + "EventName": "PM_CMPLU_STALL_LMQ_FULL", + "BriefDescription": "Finish stall because the NTF instruction was a load that missed in the L1 and the LMQ was unable to accept this load miss request because it was full" + }, + {, + "EventCode": "0x14048", + "EventName": "PM_INST_FROM_ON_CHIP_CACHE", + "BriefDescription": "The processor's Instruction cache was reloaded either shared or modified data from another core's L2/L3 on the same chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x4D014", + "EventName": "PM_CMPLU_STALL_LOAD_FINISH", + "BriefDescription": "Finish stall because the NTF instruction was a load instruction with all its dependencies satisfied just going through the LSU pipe to finish" + }, + {, + "EventCode": "0x2404A", + "EventName": "PM_INST_FROM_RL4", + "BriefDescription": "The processor's Instruction cache was reloaded from another chip's L4 on the same Node or Group ( Remote) due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x1404A", + "EventName": "PM_INST_FROM_RL2L3_SHR", + "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x401EA", + "EventName": "PM_THRESH_EXC_128", + "BriefDescription": "Threshold counter exceeded a value of 128" + }, + {, + "EventCode": "0x400F6", + "EventName": "PM_BR_MPRED_CMPL", + "BriefDescription": "Number of Branch Mispredicts" + }, + {, + "EventCode": "0x2F140", + "EventName": "PM_MRK_DPTEG_FROM_L2_MEPF", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 hit without dispatch conflicts on Mepf state. due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x101E6", + "EventName": "PM_THRESH_EXC_4096", + "BriefDescription": "Threshold counter exceed a count of 4096" + }, + {, + "EventCode": "0x3D156", + "EventName": "PM_MRK_DTLB_MISS_64K", + "BriefDescription": "Marked Data TLB Miss page size 64K" + }, + {, + "EventCode": "0x4C15E", + "EventName": "PM_MRK_DTLB_MISS_16M", + "BriefDescription": "Marked Data TLB Miss page size 16M" + }, + {, + "EventCode": "0x2D15E", + "EventName": "PM_MRK_DTLB_MISS_16G", + "BriefDescription": "Marked Data TLB Miss page size 16G" + }, + {, + "EventCode": "0x3F14A", + "EventName": "PM_MRK_DPTEG_FROM_RMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4C016", + "EventName": "PM_CMPLU_STALL_DMISS_L2L3_CONFLICT", + "BriefDescription": "Completion stall due to cache miss that resolves in the L2 or L3 with a conflict" + }, + {, + "EventCode": "0x2C01A", + "EventName": "PM_CMPLU_STALL_LHS", + "BriefDescription": "Finish stall because the NTF instruction was a load that hit on an older store and it was waiting for store data" + }, + {, + "EventCode": "0x401E4", + "EventName": "PM_MRK_DTLB_MISS", + "BriefDescription": "Marked dtlb miss" + }, + {, + "EventCode": "0x24046", + "EventName": "PM_INST_FROM_RL2L3_MOD", + "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x1002A", + "EventName": "PM_CMPLU_STALL_LARX", + "BriefDescription": "Finish stall because the NTF instruction was a larx waiting to be satisfied" + }, + {, + "EventCode": "0x3006C", + "EventName": "PM_RUN_CYC_SMT2_MODE", + "BriefDescription": "Cycles in which this thread's run latch is set and the core is in SMT2 mode" + }, + {, + "EventCode": "0x1C058", + "EventName": "PM_DTLB_MISS_16G", + "BriefDescription": "Data TLB Miss page size 16G" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/powerpc/power9/floating-point.json b/tools/perf/pmu-events/arch/powerpc/power9/floating-point.json new file mode 100644 index 000000000000..8a83bca26552 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/floating-point.json @@ -0,0 +1,32 @@ +[ + {, + "EventCode": "0x1415A", + "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_LDHITST_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L2 with load hit store conflict due to a marked load" + }, + {, + "EventCode": "0x10058", + "EventName": "PM_MEM_LOC_THRESH_IFU", + "BriefDescription": "Local Memory above threshold for IFU speculation control" + }, + {, + "EventCode": "0x2D028", + "EventName": "PM_RADIX_PWC_L2_PDE_FROM_L2", + "BriefDescription": "A Page Directory Entry was reloaded to a level 2 page walk cache from the core's L2 data cache" + }, + {, + "EventCode": "0x30012", + "EventName": "PM_FLUSH_COMPLETION", + "BriefDescription": "The instruction that was next to complete did not complete because it suffered a flush" + }, + {, + "EventCode": "0x2D154", + "EventName": "PM_MRK_DERAT_MISS_64K", + "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 64K" + }, + {, + "EventCode": "0x4016E", + "EventName": "PM_THRESH_NOT_MET", + "BriefDescription": "Threshold counter did not meet threshold" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json new file mode 100644 index 000000000000..c63a919eda98 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json @@ -0,0 +1,372 @@ +[ + {, + "EventCode": "0x3E15C", + "EventName": "PM_MRK_L2_TM_ST_ABORT_SISTER", + "BriefDescription": "TM marked store abort for this thread" + }, + {, + "EventCode": "0x25044", + "EventName": "PM_IPTEG_FROM_L31_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a instruction side request" + }, + {, + "EventCode": "0x101E8", + "EventName": "PM_THRESH_EXC_256", + "BriefDescription": "Threshold counter exceed a count of 256" + }, + {, + "EventCode": "0x4504E", + "EventName": "PM_IPTEG_FROM_L3MISS", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a instruction side request" + }, + {, + "EventCode": "0x1006A", + "EventName": "PM_NTC_ISSUE_HELD_DARQ_FULL", + "BriefDescription": "The NTC instruction is being held at dispatch because there are no slots in the DARQ for it" + }, + {, + "EventCode": "0x4E016", + "EventName": "PM_CMPLU_STALL_LSAQ_ARB", + "BriefDescription": "Finish stall because the NTF instruction was a load or store that was held in LSAQ because an older instruction from SRQ or LRQ won arbitration to the LSU pipe when this instruction tried to launch" + }, + {, + "EventCode": "0x1001A", + "EventName": "PM_LSU_SRQ_FULL_CYC", + "BriefDescription": "Cycles in which the Store Queue is full on all 4 slices. This is event is not per thread. All the threads will see the same count for this core resource" + }, + {, + "EventCode": "0x1E15E", + "EventName": "PM_MRK_L2_TM_REQ_ABORT", + "BriefDescription": "TM abort" + }, + {, + "EventCode": "0x34052", + "EventName": "PM_INST_SYS_PUMP_MPRED", + "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for an instruction fetch" + }, + {, + "EventCode": "0x20114", + "EventName": "PM_MRK_L2_RC_DISP", + "BriefDescription": "Marked Instruction RC dispatched in L2" + }, + {, + "EventCode": "0x4C044", + "EventName": "PM_DATA_FROM_L31_ECO_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's ECO L3 on the same chip due to a demand load" + }, + {, + "EventCode": "0x1C044", + "EventName": "PM_DATA_FROM_L3_NO_CONFLICT", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 without conflict due to a demand load" + }, + {, + "EventCode": "0x44050", + "EventName": "PM_INST_SYS_PUMP_MPRED_RTY", + "BriefDescription": "Final Pump Scope (system) ended up larger than Initial Pump Scope (Chip/Group) for an instruction fetch" + }, + {, + "EventCode": "0x30154", + "EventName": "PM_MRK_FAB_RSP_DCLAIM", + "BriefDescription": "Marked store had to do a dclaim" + }, + {, + "EventCode": "0x30014", + "EventName": "PM_CMPLU_STALL_STORE_FIN_ARB", + "BriefDescription": "Finish stall because the NTF instruction was a store waiting for a slot in the store finish pipe. This means the instruction is ready to finish but there are instructions ahead of it, using the finish pipe" + }, + {, + "EventCode": "0x3E054", + "EventName": "PM_LD_MISS_L1", + "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load." + }, + {, + "EventCode": "0x2E01A", + "EventName": "PM_CMPLU_STALL_LSU_FLUSH_NEXT", + "BriefDescription": "Completion stall of one cycle because the LSU requested to flush the next iop in the sequence. It takes 1 cycle for the ISU to process this request before the LSU instruction is allowed to complete" + }, + {, + "EventCode": "0x2D01C", + "EventName": "PM_CMPLU_STALL_STCX", + "BriefDescription": "Finish stall because the NTF instruction was a stcx waiting for response from L2" + }, + {, + "EventCode": "0x2C010", + "EventName": "PM_CMPLU_STALL_LSU", + "BriefDescription": "Completion stall by LSU instruction" + }, + {, + "EventCode": "0x2C042", + "EventName": "PM_DATA_FROM_L3_MEPF", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 without dispatch conflicts hit on Mepf state due to a demand load" + }, + {, + "EventCode": "0x4E012", + "EventName": "PM_CMPLU_STALL_MTFPSCR", + "BriefDescription": "Completion stall because the ISU is updating the register and notifying the Effective Address Table (EAT)" + }, + {, + "EventCode": "0x100F2", + "EventName": "PM_1PLUS_PPC_CMPL", + "BriefDescription": "1 or more ppc insts finished" + }, + {, + "EventCode": "0x3001C", + "EventName": "PM_LSU_REJECT_LMQ_FULL", + "BriefDescription": "LSU Reject due to LMQ full (up to 4 per cycles)" + }, + {, + "EventCode": "0x15046", + "EventName": "PM_IPTEG_FROM_L31_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L3 on the same chip due to a instruction side request" + }, + {, + "EventCode": "0x1015E", + "EventName": "PM_MRK_FAB_RSP_RD_T_INTV", + "BriefDescription": "Sampled Read got a T intervention" + }, + {, + "EventCode": "0x101EC", + "EventName": "PM_THRESH_MET", + "BriefDescription": "threshold exceeded" + }, + {, + "EventCode": "0x10020", + "EventName": "PM_PMC4_REWIND", + "BriefDescription": "PMC4 Rewind Event" + }, + {, + "EventCode": "0x301EA", + "EventName": "PM_THRESH_EXC_1024", + "BriefDescription": "Threshold counter exceeded a value of 1024" + }, + {, + "EventCode": "0x34056", + "EventName": "PM_CMPLU_STALL_LSU_MFSPR", + "BriefDescription": "Finish stall because the NTF instruction was a mfspr instruction targeting an LSU SPR and it was waiting for the register data to be returned" + }, + {, + "EventCode": "0x44056", + "EventName": "PM_VECTOR_ST_CMPL", + "BriefDescription": "Number of vector store instructions completed" + }, + {, + "EventCode": "0x2C124", + "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_OTHER", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 with dispatch conflict due to a marked load" + }, + {, + "EventCode": "0x4C12A", + "EventName": "PM_MRK_DATA_FROM_RL2L3_SHR_CYC", + "BriefDescription": "Duration in cycles to reload with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load" + }, + {, + "EventCode": "0x3C056", + "EventName": "PM_DTLB_MISS_64K", + "BriefDescription": "Data TLB Miss page size 64K" + }, + {, + "EventCode": "0x30060", + "EventName": "PM_TM_TRANS_RUN_INST", + "BriefDescription": "Run instructions completed in transactional state (gated by the run latch)" + }, + {, + "EventCode": "0x2C014", + "EventName": "PM_CMPLU_STALL_STORE_FINISH", + "BriefDescription": "Finish stall because the NTF instruction was a store with all its dependencies met, just waiting to go through the LSU pipe to finish" + }, + {, + "EventCode": "0x3515A", + "EventName": "PM_MRK_DATA_FROM_ON_CHIP_CACHE_CYC", + "BriefDescription": "Duration in cycles to reload either shared or modified data from another core's L2/L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x34050", + "EventName": "PM_INST_SYS_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was system pump (prediction=correct) for an instruction fetch" + }, + {, + "EventCode": "0x3015E", + "EventName": "PM_MRK_FAB_RSP_CLAIM_RTY", + "BriefDescription": "Sampled store did a rwitm and got a rty" + }, + {, + "EventCode": "0x0", + "EventName": "PM_SUSPENDED", + "BriefDescription": "Counter OFF" + }, + {, + "EventCode": "0x10010", + "EventName": "PM_PMC4_OVERFLOW", + "BriefDescription": "Overflow from counter 4" + }, + {, + "EventCode": "0x3E04A", + "EventName": "PM_DPTEG_FROM_RMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2F152", + "EventName": "PM_MRK_FAB_RSP_DCLAIM_CYC", + "BriefDescription": "cycles L2 RC took for a dclaim" + }, + {, + "EventCode": "0x10004", + "EventName": "PM_CMPLU_STALL_LRQ_OTHER", + "BriefDescription": "Finish stall due to LRQ miscellaneous reasons, lost arbitration to LMQ slot, bank collisions, set prediction cleanup, set prediction multihit and others" + }, + {, + "EventCode": "0x4F150", + "EventName": "PM_MRK_FAB_RSP_RWITM_CYC", + "BriefDescription": "cycles L2 RC took for a rwitm" + }, + {, + "EventCode": "0x4E042", + "EventName": "PM_DPTEG_FROM_L3", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x1F054", + "EventName": "PM_TLB_HIT", + "BriefDescription": "Number of times the TLB had the data required by the instruction. Applies to both HPT and RPT" + }, + {, + "EventCode": "0x2C01E", + "EventName": "PM_CMPLU_STALL_SYNC_PMU_INT", + "BriefDescription": "Cycles in which the NTC instruction is waiting for a synchronous PMU interrupt" + }, + {, + "EventCode": "0x24050", + "EventName": "PM_IOPS_CMPL", + "BriefDescription": "Internal Operations completed" + }, + {, + "EventCode": "0x1515C", + "EventName": "PM_SYNC_MRK_BR_MPRED", + "BriefDescription": "Marked Branch mispredict that can cause a synchronous interrupt" + }, + {, + "EventCode": "0x300FA", + "EventName": "PM_INST_FROM_L3MISS", + "BriefDescription": "Marked instruction was reloaded from a location beyond the local chiplet" + }, + {, + "EventCode": "0x15044", + "EventName": "PM_IPTEG_FROM_L3_NO_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without conflict due to a instruction side request" + }, + {, + "EventCode": "0x15152", + "EventName": "PM_SYNC_MRK_BR_LINK", + "BriefDescription": "Marked Branch and link branch that can cause a synchronous interrupt" + }, + {, + "EventCode": "0x1E050", + "EventName": "PM_CMPLU_STALL_TEND", + "BriefDescription": "Finish stall because the NTF instruction was a tend instruction awaiting response from L2" + }, + {, + "EventCode": "0x1013E", + "EventName": "PM_MRK_LD_MISS_EXPOSED_CYC", + "BriefDescription": "Marked Load exposed Miss (use edge detect to count #)" + }, + {, + "EventCode": "0x25042", + "EventName": "PM_IPTEG_FROM_L3_MEPF", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without dispatch conflicts hit on Mepf state. due to a instruction side request" + }, + {, + "EventCode": "0x14054", + "EventName": "PM_INST_PUMP_CPRED", + "BriefDescription": "Pump prediction correct. Counts across all types of pumps for an instruction fetch" + }, + {, + "EventCode": "0x4015E", + "EventName": "PM_MRK_FAB_RSP_RD_RTY", + "BriefDescription": "Sampled L2 reads retry count" + }, + {, + "EventCode": "0x45048", + "EventName": "PM_IPTEG_FROM_DL2L3_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a instruction side request" + }, + {, + "EventCode": "0x44052", + "EventName": "PM_INST_PUMP_MPRED", + "BriefDescription": "Pump misprediction. Counts across all types of pumps for an instruction fetch" + }, + {, + "EventCode": "0x30026", + "EventName": "PM_CMPLU_STALL_STORE_DATA", + "BriefDescription": "Finish stall because the next to finish instruction was a store waiting on data" + }, + {, + "EventCode": "0x301E6", + "EventName": "PM_MRK_DERAT_MISS", + "BriefDescription": "Erat Miss (TLB Access) All page sizes" + }, + {, + "EventCode": "0x24154", + "EventName": "PM_THRESH_ACC", + "BriefDescription": "This event increments every time the threshold event counter ticks. Thresholding must be enabled (via MMCRA) and the thresholding start event must occur for this counter to increment. It will stop incrementing when the thresholding stop event occurs or when thresholding is disabled, until the next time a configured thresholding start event occurs." + }, + {, + "EventCode": "0x2015E", + "EventName": "PM_MRK_FAB_RSP_RWITM_RTY", + "BriefDescription": "Sampled store did a rwitm and got a rty" + }, + {, + "EventCode": "0x200FA", + "EventName": "PM_BR_TAKEN_CMPL", + "BriefDescription": "New event for Branch Taken" + }, + {, + "EventCode": "0x35044", + "EventName": "PM_IPTEG_FROM_L31_ECO_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's ECO L3 on the same chip due to a instruction side request" + }, + {, + "EventCode": "0x4C010", + "EventName": "PM_CMPLU_STALL_STORE_PIPE_ARB", + "BriefDescription": "Finish stall because the NTF instruction was a store waiting for the next relaunch opportunity after an internal reject. This means the instruction is ready to relaunch and tried once but lost arbitration" + }, + {, + "EventCode": "0x4C01C", + "EventName": "PM_CMPLU_STALL_ST_FWD", + "BriefDescription": "Completion stall due to store forward" + }, + {, + "EventCode": "0x3515C", + "EventName": "PM_MRK_DATA_FROM_RL4", + "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on the same Node or Group ( Remote) due to a marked load" + }, + {, + "EventCode": "0x2D14C", + "EventName": "PM_MRK_DATA_FROM_L31_ECO_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's ECO L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x40116", + "EventName": "PM_MRK_LARX_FIN", + "BriefDescription": "Larx finished" + }, + {, + "EventCode": "0x4C056", + "EventName": "PM_DTLB_MISS_16M", + "BriefDescription": "Data TLB Miss page size 16M" + }, + {, + "EventCode": "0x1003A", + "EventName": "PM_CMPLU_STALL_LSU_FIN", + "BriefDescription": "Finish stall because the NTF instruction was an LSU op (other than a load or a store) with all its dependencies met and just going through the LSU pipe to finish" + }, + {, + "EventCode": "0x3012A", + "EventName": "PM_MRK_L2_RC_DONE", + "BriefDescription": "Marked RC done" + }, + {, + "EventCode": "0x45044", + "EventName": "PM_IPTEG_FROM_L31_ECO_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a instruction side request" + } +] diff --git a/tools/perf/pmu-events/arch/powerpc/power9/marked.json b/tools/perf/pmu-events/arch/powerpc/power9/marked.json new file mode 100644 index 000000000000..b9df54fb37e3 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/marked.json @@ -0,0 +1,647 @@ +[ + {, + "EventCode": "0x3C052", + "EventName": "PM_DATA_SYS_PUMP_MPRED", + "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for a demand load" + }, + {, + "EventCode": "0x3013E", + "EventName": "PM_MRK_STALL_CMPLU_CYC", + "BriefDescription": "Number of cycles the marked instruction is experiencing a stall while it is next to complete (NTC)" + }, + {, + "EventCode": "0x4F056", + "EventName": "PM_RADIX_PWC_L1_PDE_FROM_L3MISS", + "BriefDescription": "A Page Directory Entry was reloaded to a level 1 page walk cache from beyond the core's L3 data cache. The source could be local/remote/distant memory or another core's cache" + }, + {, + "EventCode": "0x24158", + "EventName": "PM_MRK_INST", + "BriefDescription": "An instruction was marked. Includes both Random Instruction Sampling (RIS) at decode time and Random Event Sampling (RES) at the time the configured event happens" + }, + {, + "EventCode": "0x1E046", + "EventName": "PM_DPTEG_FROM_L31_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x3C04A", + "EventName": "PM_DATA_FROM_RMEM", + "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to a demand load" + }, + {, + "EventCode": "0x2C01C", + "EventName": "PM_CMPLU_STALL_DMISS_REMOTE", + "BriefDescription": "Completion stall by Dcache miss which resolved from remote chip (cache or memory)" + }, + {, + "EventCode": "0x44040", + "EventName": "PM_INST_FROM_L2_DISP_CONFLICT_OTHER", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 with dispatch conflict due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x2E050", + "EventName": "PM_DARQ0_7_9_ENTRIES", + "BriefDescription": "Cycles in which 7,8, or 9 DARQ entries (out of 12) are in use" + }, + {, + "EventCode": "0x2D02E", + "EventName": "PM_RADIX_PWC_L3_PTE_FROM_L2", + "BriefDescription": "A Page Table Entry was reloaded to a level 3 page walk cache from the core's L2 data cache. This implies that a level 4 PWC access was not necessary for this translation" + }, + {, + "EventCode": "0x3F05E", + "EventName": "PM_RADIX_PWC_L3_PTE_FROM_L3", + "BriefDescription": "A Page Table Entry was reloaded to a level 3 page walk cache from the core's L3 data cache. This implies that a level 4 PWC access was not necessary for this translation" + }, + {, + "EventCode": "0x2E01E", + "EventName": "PM_CMPLU_STALL_NTC_FLUSH", + "BriefDescription": "Completion stall due to ntc flush" + }, + {, + "EventCode": "0x1F14C", + "EventName": "PM_MRK_DPTEG_FROM_LL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x20130", + "EventName": "PM_MRK_INST_DECODED", + "BriefDescription": "An instruction was marked at decode time. Random Instruction Sampling (RIS) only" + }, + {, + "EventCode": "0x3F144", + "EventName": "PM_MRK_DPTEG_FROM_L31_ECO_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's ECO L3 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4D058", + "EventName": "PM_VECTOR_FLOP_CMPL", + "BriefDescription": "Vector FP instruction completed" + }, + {, + "EventCode": "0x14040", + "EventName": "PM_INST_FROM_L2_NO_CONFLICT", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 without conflict due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x4404E", + "EventName": "PM_INST_FROM_L3MISS_MOD", + "BriefDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L3 due to a instruction fetch" + }, + {, + "EventCode": "0x3003A", + "EventName": "PM_CMPLU_STALL_EXCEPTION", + "BriefDescription": "Cycles in which the NTC instruction is not allowed to complete because it was interrupted by ANY exception, which has to be serviced before the instruction can complete" + }, + {, + "EventCode": "0x4F144", + "EventName": "PM_MRK_DPTEG_FROM_L31_ECO_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x3E044", + "EventName": "PM_DPTEG_FROM_L31_ECO_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's ECO L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x300F6", + "EventName": "PM_L1_DCACHE_RELOAD_VALID", + "BriefDescription": "DL1 reloaded due to Demand Load" + }, + {, + "EventCode": "0x1415E", + "EventName": "PM_MRK_DATA_FROM_L3MISS_CYC", + "BriefDescription": "Duration in cycles to reload from a location other than the local core's L3 due to a marked load" + }, + {, + "EventCode": "0x1E052", + "EventName": "PM_CMPLU_STALL_SLB", + "BriefDescription": "Finish stall because the NTF instruction was awaiting L2 response for an SLB" + }, + {, + "EventCode": "0x4404C", + "EventName": "PM_INST_FROM_DMEM", + "BriefDescription": "The processor's Instruction cache was reloaded from another chip's memory on the same Node or Group (Distant) due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x3000E", + "EventName": "PM_FXU_1PLUS_BUSY", + "BriefDescription": "At least one of the 4 FXU units is busy" + }, + {, + "EventCode": "0x2C048", + "EventName": "PM_DATA_FROM_LMEM", + "BriefDescription": "The processor's data cache was reloaded from the local chip's Memory due to a demand load" + }, + {, + "EventCode": "0x3000A", + "EventName": "PM_CMPLU_STALL_PM", + "BriefDescription": "Finish stall because the NTF instruction was issued to the Permute execution pipe and waiting to finish. Includes permute and decimal fixed point instructions (128 bit BCD arithmetic) + a few 128 bit fixpoint add/subtract instructions with carry. Not qualified by vector or multicycle" + }, + {, + "EventCode": "0x1504E", + "EventName": "PM_IPTEG_FROM_L2MISS", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a instruction side request" + }, + {, + "EventCode": "0x1C052", + "EventName": "PM_DATA_GRP_PUMP_MPRED_RTY", + "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for a demand load" + }, + {, + "EventCode": "0x30008", + "EventName": "PM_DISP_STARVED", + "BriefDescription": "Dispatched Starved" + }, + {, + "EventCode": "0x14042", + "EventName": "PM_INST_FROM_L2", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x4000C", + "EventName": "PM_FREQ_UP", + "BriefDescription": "Power Management: Above Threshold A" + }, + {, + "EventCode": "0x3C050", + "EventName": "PM_DATA_SYS_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was system pump (prediction=correct) for a demand load" + }, + {, + "EventCode": "0x25040", + "EventName": "PM_IPTEG_FROM_L2_MEPF", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 hit without dispatch conflicts on Mepf state. due to a instruction side request" + }, + {, + "EventCode": "0x10132", + "EventName": "PM_MRK_INST_ISSUED", + "BriefDescription": "Marked instruction issued" + }, + {, + "EventCode": "0x1C046", + "EventName": "PM_DATA_FROM_L31_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L3 on the same chip due to a demand load" + }, + {, + "EventCode": "0x2C044", + "EventName": "PM_DATA_FROM_L31_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L3 on the same chip due to a demand load" + }, + {, + "EventCode": "0x2C04A", + "EventName": "PM_DATA_FROM_RL4", + "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on the same Node or Group ( Remote) due to a demand load" + }, + {, + "EventCode": "0x24044", + "EventName": "PM_INST_FROM_L31_MOD", + "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another core's L3 on the same chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x4C050", + "EventName": "PM_DATA_SYS_PUMP_MPRED_RTY", + "BriefDescription": "Final Pump Scope (system) ended up larger than Initial Pump Scope (Chip/Group) for a demand load" + }, + {, + "EventCode": "0x2C052", + "EventName": "PM_DATA_GRP_PUMP_MPRED", + "BriefDescription": "Final Pump Scope (Group) ended up either larger or smaller than Initial Pump Scope for a demand load" + }, + {, + "EventCode": "0x2F148", + "EventName": "PM_MRK_DPTEG_FROM_LMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's Memory due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4D01A", + "EventName": "PM_CMPLU_STALL_EIEIO", + "BriefDescription": "Finish stall because the NTF instruction is an EIEIO waiting for response from L2" + }, + {, + "EventCode": "0x4F14E", + "EventName": "PM_MRK_DPTEG_FROM_L3MISS", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4F05A", + "EventName": "PM_RADIX_PWC_L4_PTE_FROM_L3", + "BriefDescription": "A Page Table Entry was reloaded to a level 4 page walk cache from the core's L3 data cache. This is the deepest level of PWC possible for a translation" + }, + {, + "EventCode": "0x1F05A", + "EventName": "PM_RADIX_PWC_L4_PTE_FROM_L2", + "BriefDescription": "A Page Table Entry was reloaded to a level 4 page walk cache from the core's L2 data cache. This is the deepest level of PWC possible for a translation" + }, + {, + "EventCode": "0x30068", + "EventName": "PM_L1_ICACHE_RELOADED_PREF", + "BriefDescription": "Counts all Icache prefetch reloads ( includes demand turned into prefetch)" + }, + {, + "EventCode": "0x4C04A", + "EventName": "PM_DATA_FROM_OFF_CHIP_CACHE", + "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a demand load" + }, + {, + "EventCode": "0x400FE", + "EventName": "PM_DATA_FROM_MEMORY", + "BriefDescription": "The processor's data cache was reloaded from a memory location including L4 from local remote or distant due to a demand load" + }, + {, + "EventCode": "0x3F058", + "EventName": "PM_RADIX_PWC_L1_PDE_FROM_L3", + "BriefDescription": "A Page Directory Entry was reloaded to a level 1 page walk cache from the core's L3 data cache" + }, + {, + "EventCode": "0x4D142", + "EventName": "PM_MRK_DATA_FROM_L3", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 due to a marked load" + }, + {, + "EventCode": "0x30050", + "EventName": "PM_SYS_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was system pump for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x30028", + "EventName": "PM_CMPLU_STALL_SPEC_FINISH", + "BriefDescription": "Finish stall while waiting for the non-speculative finish of either a stcx waiting for its result or a load waiting for non-critical sectors of data and ECC" + }, + {, + "EventCode": "0x400F4", + "EventName": "PM_RUN_PURR", + "BriefDescription": "Run_PURR" + }, + {, + "EventCode": "0x3404C", + "EventName": "PM_INST_FROM_DL4", + "BriefDescription": "The processor's Instruction cache was reloaded from another chip's L4 on a different Node or Group (Distant) due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x3D05A", + "EventName": "PM_NTC_ISSUE_HELD_OTHER", + "BriefDescription": "The NTC instruction is being held at dispatch during regular pipeline cycles, or because the VSU is busy with multi-cycle instructions, or because of a write-back collision with VSU" + }, + {, + "EventCode": "0x2E048", + "EventName": "PM_DPTEG_FROM_LMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's Memory due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2D02A", + "EventName": "PM_RADIX_PWC_L3_PDE_FROM_L2", + "BriefDescription": "A Page Directory Entry was reloaded to a level 3 page walk cache from the core's L2 data cache" + }, + {, + "EventCode": "0x1F05C", + "EventName": "PM_RADIX_PWC_L3_PDE_FROM_L3", + "BriefDescription": "A Page Directory Entry was reloaded to a level 3 page walk cache from the core's L3 data cache" + }, + {, + "EventCode": "0x4D04A", + "EventName": "PM_DARQ0_0_3_ENTRIES", + "BriefDescription": "Cycles in which 3 or less DARQ entries (out of 12) are in use" + }, + {, + "EventCode": "0x1404C", + "EventName": "PM_INST_FROM_LL4", + "BriefDescription": "The processor's Instruction cache was reloaded from the local chip's L4 cache due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x200FD", + "EventName": "PM_L1_ICACHE_MISS", + "BriefDescription": "Demand iCache Miss" + }, + {, + "EventCode": "0x34040", + "EventName": "PM_INST_FROM_L2_DISP_CONFLICT_LDHITST", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 with load hit store conflict due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x20138", + "EventName": "PM_MRK_ST_NEST", + "BriefDescription": "Marked store sent to nest" + }, + {, + "EventCode": "0x44048", + "EventName": "PM_INST_FROM_DL2L3_MOD", + "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x35046", + "EventName": "PM_IPTEG_FROM_L21_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L2 on the same chip due to a instruction side request" + }, + {, + "EventCode": "0x4C04E", + "EventName": "PM_DATA_FROM_L3MISS_MOD", + "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L3 due to a demand load" + }, + {, + "EventCode": "0x401E0", + "EventName": "PM_MRK_INST_CMPL", + "BriefDescription": "marked instruction completed" + }, + {, + "EventCode": "0x2C128", + "EventName": "PM_MRK_DATA_FROM_DL2L3_SHR_CYC", + "BriefDescription": "Duration in cycles to reload with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load" + }, + {, + "EventCode": "0x34044", + "EventName": "PM_INST_FROM_L31_ECO_SHR", + "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another core's ECO L3 on the same chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x4E018", + "EventName": "PM_CMPLU_STALL_NTC_DISP_FIN", + "BriefDescription": "Finish stall because the NTF instruction was one that must finish at dispatch." + }, + {, + "EventCode": "0x2E05E", + "EventName": "PM_LMQ_EMPTY_CYC", + "BriefDescription": "Cycles in which the LMQ has no pending load misses for this thread" + }, + {, + "EventCode": "0x4C122", + "EventName": "PM_DARQ1_0_3_ENTRIES", + "BriefDescription": "Cycles in which 3 or fewer DARQ1 entries (out of 12) are in use" + }, + {, + "EventCode": "0x4F058", + "EventName": "PM_RADIX_PWC_L2_PTE_FROM_L3", + "BriefDescription": "A Page Table Entry was reloaded to a level 2 page walk cache from the core's L3 data cache. This implies that level 3 and level 4 PWC accesses were not necessary for this translation" + }, + {, + "EventCode": "0x14046", + "EventName": "PM_INST_FROM_L31_SHR", + "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another core's L3 on the same chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x3012C", + "EventName": "PM_MRK_ST_FWD", + "BriefDescription": "Marked st forwards" + }, + {, + "EventCode": "0x101E0", + "EventName": "PM_MRK_INST_DISP", + "BriefDescription": "The thread has dispatched a randomly sampled marked instruction" + }, + {, + "EventCode": "0x1D058", + "EventName": "PM_DARQ0_10_12_ENTRIES", + "BriefDescription": "Cycles in which 10 or more DARQ entries (out of 12) are in use" + }, + {, + "EventCode": "0x300FE", + "EventName": "PM_DATA_FROM_L3MISS", + "BriefDescription": "Demand LD - L3 Miss (not L2 hit and not L3 hit)" + }, + {, + "EventCode": "0x30006", + "EventName": "PM_CMPLU_STALL_OTHER_CMPL", + "BriefDescription": "Instructions the core completed while this tread was stalled" + }, + {, + "EventCode": "0x1005C", + "EventName": "PM_CMPLU_STALL_DP", + "BriefDescription": "Finish stall because the NTF instruction was a scalar instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Not qualified multicycle. Qualified by NOT vector" + }, + {, + "EventCode": "0x1E042", + "EventName": "PM_DPTEG_FROM_L2", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x1016E", + "EventName": "PM_MRK_BR_CMPL", + "BriefDescription": "Branch Instruction completed" + }, + {, + "EventCode": "0x2013A", + "EventName": "PM_MRK_BRU_FIN", + "BriefDescription": "bru marked instr finish" + }, + {, + "EventCode": "0x4F05E", + "EventName": "PM_RADIX_PWC_L3_PTE_FROM_L3MISS", + "BriefDescription": "A Page Table Entry was reloaded to a level 3 page walk cache from beyond the core's L3 data cache. This implies that a level 4 PWC access was not necessary for this translation. The source could be local/remote/distant memory or another core's cache" + }, + {, + "EventCode": "0x400FC", + "EventName": "PM_ITLB_MISS", + "BriefDescription": "ITLB Reloaded. Counts 1 per ITLB miss for HPT but multiple for radix depending on number of levels traveresed" + }, + {, + "EventCode": "0x2D024", + "EventName": "PM_RADIX_PWC_L2_HIT", + "BriefDescription": "A radix translation attempt missed in the TLB but hit on both the first and second levels of page walk cache." + }, + {, + "EventCode": "0x3F056", + "EventName": "PM_RADIX_PWC_L3_HIT", + "BriefDescription": "A radix translation attempt missed in the TLB but hit on the first, second, and third levels of page walk cache." + }, + {, + "EventCode": "0x4E014", + "EventName": "PM_TM_TX_PASS_RUN_INST", + "BriefDescription": "Run instructions spent in successful transactions" + }, + {, + "EventCode": "0x1E044", + "EventName": "PM_DPTEG_FROM_L3_NO_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without conflict due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4D05A", + "EventName": "PM_NON_MATH_FLOP_CMPL", + "BriefDescription": "Non FLOP operation completed" + }, + {, + "EventCode": "0x101E2", + "EventName": "PM_MRK_BR_TAKEN_CMPL", + "BriefDescription": "Marked Branch Taken completed" + }, + {, + "EventCode": "0x3E158", + "EventName": "PM_MRK_STCX_FAIL", + "BriefDescription": "marked stcx failed" + }, + {, + "EventCode": "0x1C048", + "EventName": "PM_DATA_FROM_ON_CHIP_CACHE", + "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on the same chip due to a demand load" + }, + {, + "EventCode": "0x1C054", + "EventName": "PM_DATA_PUMP_CPRED", + "BriefDescription": "Pump prediction correct. Counts across all types of pumps for a demand load" + }, + {, + "EventCode": "0x4405E", + "EventName": "PM_DARQ_STORE_REJECT", + "BriefDescription": "The DARQ attempted to transmit a store into an LSAQ or SRQ entry but It was rejected. Divide by PM_DARQ_STORE_XMIT to get reject ratio" + }, + {, + "EventCode": "0x1C042", + "EventName": "PM_DATA_FROM_L2", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 due to a demand load" + }, + {, + "EventCode": "0x1D14C", + "EventName": "PM_MRK_DATA_FROM_LL4", + "BriefDescription": "The processor's data cache was reloaded from the local chip's L4 cache due to a marked load" + }, + {, + "EventCode": "0x1006C", + "EventName": "PM_RUN_CYC_ST_MODE", + "BriefDescription": "Cycles run latch is set and core is in ST mode" + }, + {, + "EventCode": "0x3C044", + "EventName": "PM_DATA_FROM_L31_ECO_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's ECO L3 on the same chip due to a demand load" + }, + {, + "EventCode": "0x4C052", + "EventName": "PM_DATA_PUMP_MPRED", + "BriefDescription": "Pump misprediction. Counts across all types of pumps for a demand load" + }, + {, + "EventCode": "0x20050", + "EventName": "PM_GRP_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope and data sourced across this scope was group pump for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x1F150", + "EventName": "PM_MRK_ST_L2DISP_TO_CMPL_CYC", + "BriefDescription": "cycles from L2 rc disp to l2 rc completion" + }, + {, + "EventCode": "0x4505A", + "EventName": "PM_SP_FLOP_CMPL", + "BriefDescription": "SP instruction completed" + }, + {, + "EventCode": "0x4000A", + "EventName": "PM_ISQ_36_44_ENTRIES", + "BriefDescription": "Cycles in which 36 or more Issue Queue entries are in use. This is a shared event, not per thread. There are 44 issue queue entries across 4 slices in the whole core" + }, + {, + "EventCode": "0x2C12E", + "EventName": "PM_MRK_DATA_FROM_LL4_CYC", + "BriefDescription": "Duration in cycles to reload from the local chip's L4 cache due to a marked load" + }, + {, + "EventCode": "0x2C058", + "EventName": "PM_MEM_PREF", + "BriefDescription": "Memory prefetch for this thread. Includes L4" + }, + {, + "EventCode": "0x40012", + "EventName": "PM_L1_ICACHE_RELOADED_ALL", + "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch" + }, + {, + "EventCode": "0x4003C", + "EventName": "PM_DISP_HELD_SYNC_HOLD", + "BriefDescription": "Cycles in which dispatch is held because of a synchronizing instruction in the pipeline" + }, + {, + "EventCode": "0x3003C", + "EventName": "PM_CMPLU_STALL_NESTED_TEND", + "BriefDescription": "Completion stall because the ISU is updating the TEXASR to keep track of the nested tend and decrement the TEXASR nested level. This is a short delay" + }, + {, + "EventCode": "0x3D05C", + "EventName": "PM_DISP_HELD_HB_FULL", + "BriefDescription": "Dispatch held due to History Buffer full. Could be GPR/VSR/VMR/FPR/CR/XVF; CR; XVF (XER/VSCR/FPSCR)" + }, + {, + "EventCode": "0x30052", + "EventName": "PM_SYS_PUMP_MPRED", + "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x2E044", + "EventName": "PM_DPTEG_FROM_L31_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x34048", + "EventName": "PM_INST_FROM_DL2L3_SHR", + "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x45042", + "EventName": "PM_IPTEG_FROM_L3", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 due to a instruction side request" + }, + {, + "EventCode": "0x15042", + "EventName": "PM_IPTEG_FROM_L2", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 due to a instruction side request" + }, + {, + "EventCode": "0x1C05E", + "EventName": "PM_MEM_LOC_THRESH_LSU_MED", + "BriefDescription": "Local memory above threshold for data prefetch" + }, + {, + "EventCode": "0x40134", + "EventName": "PM_MRK_INST_TIMEO", + "BriefDescription": "marked Instruction finish timeout (instruction lost)" + }, + {, + "EventCode": "0x1002C", + "EventName": "PM_L1_DCACHE_RELOADED_ALL", + "BriefDescription": "L1 data cache reloaded for demand. If MMCR1[16] is 1, prefetches will be included as well" + }, + {, + "EventCode": "0x30130", + "EventName": "PM_MRK_INST_FIN", + "BriefDescription": "marked instruction finished" + }, + {, + "EventCode": "0x1F14A", + "EventName": "PM_MRK_DPTEG_FROM_RL2L3_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x3504E", + "EventName": "PM_DARQ0_4_6_ENTRIES", + "BriefDescription": "Cycles in which 4, 5, or 6 DARQ entries (out of 12) are in use" + }, + {, + "EventCode": "0x30064", + "EventName": "PM_DARQ_STORE_XMIT", + "BriefDescription": "The DARQ attempted to transmit a store into an LSAQ or SRQ entry. Includes rejects. Not qualified by thread, so it includes counts for the whole core" + }, + {, + "EventCode": "0x45046", + "EventName": "PM_IPTEG_FROM_L21_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L2 on the same chip due to a instruction side request" + }, + {, + "EventCode": "0x2C016", + "EventName": "PM_CMPLU_STALL_PASTE", + "BriefDescription": "Finish stall because the NTF instruction was a paste waiting for response from L2" + }, + {, + "EventCode": "0x24156", + "EventName": "PM_MRK_STCX_FIN", + "BriefDescription": "Number of marked stcx instructions finished. This includes instructions in the speculative path of a branch that may be flushed" + }, + {, + "EventCode": "0x15150", + "EventName": "PM_SYNC_MRK_PROBE_NOP", + "BriefDescription": "Marked probeNops which can cause synchronous interrupts" + }, + {, + "EventCode": "0x301E4", + "EventName": "PM_MRK_BR_MPRED_CMPL", + "BriefDescription": "Marked Branch Mispredicted" + } +] diff --git a/tools/perf/pmu-events/arch/powerpc/power9/memory.json b/tools/perf/pmu-events/arch/powerpc/power9/memory.json new file mode 100644 index 000000000000..9960d1c0dd44 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/memory.json @@ -0,0 +1,132 @@ +[ + {, + "EventCode": "0x3006E", + "EventName": "PM_NEST_REF_CLK", + "BriefDescription": "Multiply by 4 to obtain the number of PB cycles" + }, + {, + "EventCode": "0x20010", + "EventName": "PM_PMC1_OVERFLOW", + "BriefDescription": "Overflow from counter 1" + }, + {, + "EventCode": "0x2005A", + "EventName": "PM_DARQ1_7_9_ENTRIES", + "BriefDescription": "Cycles in which 7 to 9 DARQ1 entries (out of 12) are in use" + }, + {, + "EventCode": "0x3C048", + "EventName": "PM_DATA_FROM_DL2L3_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a demand load" + }, + {, + "EventCode": "0x10008", + "EventName": "PM_RUN_SPURR", + "BriefDescription": "Run SPURR" + }, + {, + "EventCode": "0x200F6", + "EventName": "PM_LSU_DERAT_MISS", + "BriefDescription": "DERAT Reloaded due to a DERAT miss" + }, + {, + "EventCode": "0x4C048", + "EventName": "PM_DATA_FROM_DL2L3_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a demand load" + }, + {, + "EventCode": "0x1D15E", + "EventName": "PM_MRK_RUN_CYC", + "BriefDescription": "Run cycles in which a marked instruction is in the pipeline" + }, + {, + "EventCode": "0x4003E", + "EventName": "PM_LD_CMPL", + "BriefDescription": "count of Loads completed" + }, + {, + "EventCode": "0x2D156", + "EventName": "PM_MRK_DTLB_MISS_4K", + "BriefDescription": "Marked Data TLB Miss page size 4k" + }, + {, + "EventCode": "0x4C042", + "EventName": "PM_DATA_FROM_L3", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 due to a demand load" + }, + {, + "EventCode": "0x4D02C", + "EventName": "PM_PMC1_REWIND", + "BriefDescription": "" + }, + {, + "EventCode": "0x15158", + "EventName": "PM_SYNC_MRK_L2HIT", + "BriefDescription": "Marked L2 Hits that can throw a synchronous interrupt" + }, + {, + "EventCode": "0x3404A", + "EventName": "PM_INST_FROM_RMEM", + "BriefDescription": "The processor's Instruction cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x301E2", + "EventName": "PM_MRK_ST_CMPL", + "BriefDescription": "Marked store completed and sent to nest" + }, + {, + "EventCode": "0x1C050", + "EventName": "PM_DATA_CHIP_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for a demand load" + }, + {, + "EventCode": "0x4C040", + "EventName": "PM_DATA_FROM_L2_DISP_CONFLICT_OTHER", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 with dispatch conflict due to a demand load" + }, + {, + "EventCode": "0x2E05C", + "EventName": "PM_LSU_REJECT_ERAT_MISS", + "BriefDescription": "LSU Reject due to ERAT (up to 4 per cycles)" + }, + {, + "EventCode": "0x1000A", + "EventName": "PM_PMC3_REWIND", + "BriefDescription": "PMC3 rewind event. A rewind happens when a speculative event (such as latency or CPI stack) is selected on PMC3 and the stall reason or reload source did not match the one programmed in PMC3. When this occurs, the count in PMC3 will not change." + }, + {, + "EventCode": "0x3C058", + "EventName": "PM_LARX_FIN", + "BriefDescription": "Larx finished" + }, + {, + "EventCode": "0x1C040", + "EventName": "PM_DATA_FROM_L2_NO_CONFLICT", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 without conflict due to a demand load" + }, + {, + "EventCode": "0x2C040", + "EventName": "PM_DATA_FROM_L2_MEPF", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state due to a demand load" + }, + {, + "EventCode": "0x2E05A", + "EventName": "PM_LRQ_REJECT", + "BriefDescription": "Internal LSU reject from LRQ. Rejects cause the load to go back to LRQ, but it stays contained within the LSU once it gets issued. This event counts the number of times the LRQ attempts to relaunch an instruction after a reject. Any load can suffer multiple rejects" + }, + {, + "EventCode": "0x2C05C", + "EventName": "PM_INST_GRP_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was group pump (prediction=correct) for an instruction fetch (demand only)" + }, + {, + "EventCode": "0x4D056", + "EventName": "PM_NON_FMA_FLOP_CMPL", + "BriefDescription": "Non FMA instruction completed" + }, + {, + "EventCode": "0x3E050", + "EventName": "PM_DARQ1_4_6_ENTRIES", + "BriefDescription": "Cycles in which 4, 5, or 6 DARQ1 entries (out of 12) are in use" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/powerpc/power9/other.json b/tools/perf/pmu-events/arch/powerpc/power9/other.json new file mode 100644 index 000000000000..54cc3be00fc2 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json @@ -0,0 +1,2392 @@ +[ + {, + "EventCode": "0x3084", + "EventName": "PM_ISU1_ISS_HOLD_ALL", + "BriefDescription": "All ISU rejects" + }, + {, + "EventCode": "0xF880", + "EventName": "PM_SNOOP_TLBIE", + "BriefDescription": "TLBIE snoop" + }, + {, + "EventCode": "0x4088", + "EventName": "PM_IC_DEMAND_REQ", + "BriefDescription": "Demand Instruction fetch request" + }, + {, + "EventCode": "0x20A4", + "EventName": "PM_TM_TRESUME", + "BriefDescription": "TM resume instruction completed" + }, + {, + "EventCode": "0x40008", + "EventName": "PM_SRQ_EMPTY_CYC", + "BriefDescription": "Cycles in which the SRQ has at least one (out of four) empty slice" + }, + {, + "EventCode": "0x20064", + "EventName": "PM_IERAT_RELOAD_4K", + "BriefDescription": "IERAT reloaded (after a miss) for 4K pages" + }, + {, + "EventCode": "0x260B4", + "EventName": "PM_L3_P2_LCO_RTY", + "BriefDescription": "L3 initiated LCO received retry on port 2 (can try 4 times)" + }, + {, + "EventCode": "0x20006", + "EventName": "PM_DISP_HELD_ISSQ_FULL", + "BriefDescription": "Dispatch held due to Issue q full. Includes issue queue and branch queue" + }, + {, + "EventCode": "0x201E4", + "EventName": "PM_MRK_DATA_FROM_L3MISS", + "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L3 due to a marked load" + }, + {, + "EventCode": "0x4E044", + "EventName": "PM_DPTEG_FROM_L31_ECO_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x40B8", + "EventName": "PM_BR_MPRED_TAKEN_CR", + "BriefDescription": "A Conditional Branch that resolved to taken was mispredicted as not taken (due to the BHT Direction Prediction)." + }, + {, + "EventCode": "0xF8AC", + "EventName": "PM_DC_DEALLOC_NO_CONF", + "BriefDescription": "A demand load referenced a line in an active fuzzy prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software.Fuzzy stream confirm (out of order effects, or pf cant keep up)" + }, + {, + "EventCode": "0xD090", + "EventName": "PM_LS0_DC_COLLISIONS", + "BriefDescription": "Read-write data cache collisions" + }, + {, + "EventCode": "0x40BC", + "EventName": "PM_THRD_PRIO_0_1_CYC", + "BriefDescription": "Cycles thread running at priority level 0 or 1" + }, + {, + "EventCode": "0x2084", + "EventName": "PM_FLUSH_HB_RESTORE_CYC", + "BriefDescription": "Cycles in which no new instructions can be dispatched to the ICT after a flush. History buffer recovery" + }, + {, + "EventCode": "0x4F054", + "EventName": "PM_RADIX_PWC_MISS", + "BriefDescription": "A radix translation attempt missed in the TLB and all levels of page walk cache." + }, + {, + "EventCode": "0x24048", + "EventName": "PM_INST_FROM_LMEM", + "BriefDescription": "The processor's Instruction cache was reloaded from the local chip's Memory due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0xD8B4", + "EventName": "PM_LSU0_LRQ_S0_VALID_CYC", + "BriefDescription": "Slot 0 of LRQ valid" + }, + {, + "EventCode": "0x2E052", + "EventName": "PM_TM_PASSED", + "BriefDescription": "Number of TM transactions that passed" + }, + {, + "EventCode": "0xD1A0", + "EventName": "PM_MRK_LSU_FLUSH_LHS", + "BriefDescription": "Effective Address alias flush : no EA match but Real Address match. If the data has not yet been returned for this load, the instruction will just be rejected, but if it has returned data, it will be flushed" + }, + {, + "EventCode": "0xF088", + "EventName": "PM_LSU0_STORE_REJECT", + "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met" + }, + {, + "EventCode": "0x360B2", + "EventName": "PM_L3_GRP_GUESS_WRONG_LOW", + "BriefDescription": "Initial scope=group (GS or NNS) but data from outside group (far or rem). Prediction too Low" + }, + {, + "EventCode": "0x168A6", + "EventName": "PM_TM_CAM_OVERFLOW", + "BriefDescription": "L3 TM cam overflow during L2 co of SC" + }, + {, + "EventCode": "0xE8B0", + "EventName": "PM_TEND_PEND_CYC", + "BriefDescription": "TEND latency per thread" + }, + {, + "EventCode": "0x4884", + "EventName": "PM_IBUF_FULL_CYC", + "BriefDescription": "Cycles No room in ibuff" + }, + {, + "EventCode": "0xD08C", + "EventName": "PM_LSU2_LDMX_FIN", + "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491): The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region. This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])" + }, + {, + "EventCode": "0x300F8", + "EventName": "PM_TB_BIT_TRANS", + "BriefDescription": "timebase event" + }, + {, + "EventCode": "0x3C040", + "EventName": "PM_DATA_FROM_L2_DISP_CONFLICT_LDHITST", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 with load hit store conflict due to a demand load" + }, + {, + "EventCode": "0xE0BC", + "EventName": "PM_LS0_PTE_TABLEWALK_CYC", + "BriefDescription": "Cycles when a tablewalk is pending on this thread on table 0" + }, + {, + "EventCode": "0x3884", + "EventName": "PM_ISU3_ISS_HOLD_ALL", + "BriefDescription": "All ISU rejects" + }, + {, + "EventCode": "0x460A6", + "EventName": "PM_RD_FORMING_SC", + "BriefDescription": "Read forming SC" + }, + {, + "EventCode": "0x468A0", + "EventName": "PM_L3_PF_OFF_CHIP_MEM", + "BriefDescription": "L3 PF from Off chip memory" + }, + {, + "EventCode": "0x268AA", + "EventName": "PM_L3_P1_LCO_DATA", + "BriefDescription": "LCO sent with data port 1" + }, + {, + "EventCode": "0xE894", + "EventName": "PM_LSU1_TM_L1_HIT", + "BriefDescription": "Load tm hit in L1" + }, + {, + "EventCode": "0x5888", + "EventName": "PM_IC_INVALIDATE", + "BriefDescription": "Ic line invalidated" + }, + {, + "EventCode": "0x2890", + "EventName": "PM_DISP_CLB_HELD_TLBIE", + "BriefDescription": "Dispatch Hold: Due to TLBIE" + }, + {, + "EventCode": "0x1001C", + "EventName": "PM_CMPLU_STALL_THRD", + "BriefDescription": "Completion Stalled because the thread was blocked" + }, + {, + "EventCode": "0x368A6", + "EventName": "PM_SNP_TM_HIT_T", + "BriefDescription": "Snp TM sthit T/Tn/Te" + }, + {, + "EventCode": "0x3001A", + "EventName": "PM_DATA_TABLEWALK_CYC", + "BriefDescription": "Data Tablewalk Cycles. Could be 1 or 2 active tablewalks. Includes data prefetches." + }, + {, + "EventCode": "0xD894", + "EventName": "PM_LS3_DC_COLLISIONS", + "BriefDescription": "Read-write data cache collisions" + }, + {, + "EventCode": "0x35158", + "EventName": "PM_MRK_DATA_FROM_L31_ECO_MOD_CYC", + "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's ECO L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0xF0B4", + "EventName": "PM_DC_PREF_CONS_ALLOC", + "BriefDescription": "Prefetch stream allocated in the conservative phase by either the hardware prefetch mechanism or software prefetch" + }, + {, + "EventCode": "0xF894", + "EventName": "PM_LSU3_L1_CAM_CANCEL", + "BriefDescription": "ls3 l1 tm cam cancel" + }, + {, + "EventCode": "0x2888", + "EventName": "PM_FLUSH_DISP_TLBIE", + "BriefDescription": "Dispatch Flush: TLBIE" + }, + {, + "EventCode": "0xD1A4", + "EventName": "PM_MRK_LSU_FLUSH_SAO", + "BriefDescription": "A load-hit-load condition with Strong Address Ordering will have address compare disabled and flush" + }, + {, + "EventCode": "0x4E11E", + "EventName": "PM_MRK_DATA_FROM_DMEM_CYC", + "BriefDescription": "Duration in cycles to reload from another chip's memory on the same Node or Group (Distant) due to a marked load" + }, + {, + "EventCode": "0x5894", + "EventName": "PM_LWSYNC", + "BriefDescription": "Lwsync instruction decoded and transferred" + }, + {, + "EventCode": "0x14156", + "EventName": "PM_MRK_DATA_FROM_L2_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L2 due to a marked load" + }, + {, + "EventCode": "0x468A6", + "EventName": "PM_RD_CLEARING_SC", + "BriefDescription": "Read clearing SC" + }, + {, + "EventCode": "0x50A0", + "EventName": "PM_HWSYNC", + "BriefDescription": "Hwsync instruction decoded and transferred" + }, + {, + "EventCode": "0x168B0", + "EventName": "PM_L3_P1_NODE_PUMP", + "BriefDescription": "L3 PF sent with nodal scope port 1, counts even retried requests" + }, + {, + "EventCode": "0xD0BC", + "EventName": "PM_LSU0_1_LRQF_FULL_CYC", + "BriefDescription": "Counts the number of cycles the LRQF is full. LRQF is the queue that holds loads between finish and completion. If it fills up, instructions stay in LRQ until completion, potentially backing up the LRQ" + }, + {, + "EventCode": "0x2D148", + "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_LDHITST", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 with load hit store conflict due to a marked load" + }, + {, + "EventCode": "0x460A8", + "EventName": "PM_SN_HIT", + "BriefDescription": "Any port snooper hit L3. Up to 4 can happen in a cycle but we only count 1" + }, + {, + "EventCode": "0x360AA", + "EventName": "PM_L3_P0_CO_MEM", + "BriefDescription": "L3 CO to memory port 0 with or without data" + }, + {, + "EventCode": "0xF0A4", + "EventName": "PM_DC_PREF_HW_ALLOC", + "BriefDescription": "Prefetch stream allocated by the hardware prefetch mechanism" + }, + {, + "EventCode": "0xF0BC", + "EventName": "PM_LS2_UNALIGNED_ST", + "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size. If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0xD0AC", + "EventName": "PM_SRQ_SYNC_CYC", + "BriefDescription": "A sync is in the S2Q (edge detect to count)" + }, + {, + "EventCode": "0x401E6", + "EventName": "PM_MRK_INST_FROM_L3MISS", + "BriefDescription": "Marked instruction was reloaded from a location beyond the local chiplet" + }, + {, + "EventCode": "0x26082", + "EventName": "PM_L2_IC_INV", + "BriefDescription": "I-cache Invalidates sent over the realod bus to the core" + }, + {, + "EventCode": "0xC8AC", + "EventName": "PM_LSU_FLUSH_RELAUNCH_MISS", + "BriefDescription": "If a load that has already returned data and has to relaunch for any reason then gets a miss (erat, setp, data cache), it will often be flushed at relaunch time because the data might be inconsistent" + }, + {, + "EventCode": "0x260A4", + "EventName": "PM_L3_LD_HIT", + "BriefDescription": "L3 Hits for demand LDs" + }, + {, + "EventCode": "0xF0A0", + "EventName": "PM_DATA_STORE", + "BriefDescription": "All ops that drain from s2q to L2 containing data" + }, + {, + "EventCode": "0x1D148", + "EventName": "PM_MRK_DATA_FROM_RMEM", + "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to a marked load" + }, + {, + "EventCode": "0x16088", + "EventName": "PM_L2_LOC_GUESS_CORRECT", + "BriefDescription": "L2 guess local (LNS) and guess was correct (ie data local)" + }, + {, + "EventCode": "0x160A4", + "EventName": "PM_L3_HIT", + "BriefDescription": "L3 Hits (L2 miss hitting L3, including data/instrn/xlate)" + }, + {, + "EventCode": "0xE09C", + "EventName": "PM_LSU0_TM_L1_MISS", + "BriefDescription": "Load tm L1 miss" + }, + {, + "EventCode": "0x168B4", + "EventName": "PM_L3_P1_LCO_RTY", + "BriefDescription": "L3 initiated LCO received retry on port 1 (can try 4 times)" + }, + {, + "EventCode": "0x268AC", + "EventName": "PM_L3_RD_USAGE", + "BriefDescription": "Rotating sample of 16 RD actives" + }, + {, + "EventCode": "0x1415C", + "EventName": "PM_MRK_DATA_FROM_L3_MEPF_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L3 without dispatch conflicts hit on Mepf state due to a marked load" + }, + {, + "EventCode": "0xE880", + "EventName": "PM_L1_SW_PREF", + "BriefDescription": "Software L1 Prefetches, including SW Transient Prefetches" + }, + {, + "EventCode": "0x288C", + "EventName": "PM_DISP_CLB_HELD_BAL", + "BriefDescription": "Dispatch/CLB Hold: Balance Flush" + }, + {, + "EventCode": "0x101EA", + "EventName": "PM_MRK_L1_RELOAD_VALID", + "BriefDescription": "Marked demand reload" + }, + {, + "EventCode": "0x1D156", + "EventName": "PM_MRK_LD_MISS_L1_CYC", + "BriefDescription": "Marked ld latency" + }, + {, + "EventCode": "0x4C01A", + "EventName": "PM_CMPLU_STALL_DMISS_L3MISS", + "BriefDescription": "Completion stall due to cache miss resolving missed the L3" + }, + {, + "EventCode": "0x2006C", + "EventName": "PM_RUN_CYC_SMT4_MODE", + "BriefDescription": "Cycles in which this thread's run latch is set and the core is in SMT4 mode" + }, + {, + "EventCode": "0x5088", + "EventName": "PM_DECODE_FUSION_OP_PRESERV", + "BriefDescription": "Destructive op operand preservation" + }, + {, + "EventCode": "0x1D14E", + "EventName": "PM_MRK_DATA_FROM_OFF_CHIP_CACHE_CYC", + "BriefDescription": "Duration in cycles to reload either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked load" + }, + {, + "EventCode": "0x509C", + "EventName": "PM_FORCED_NOP", + "BriefDescription": "Instruction was forced to execute as a nop because it was found to behave like a nop (have no effect) at decode time" + }, + {, + "EventCode": "0xC098", + "EventName": "PM_LS2_UNALIGNED_LD", + "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size. If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0x20058", + "EventName": "PM_DARQ1_10_12_ENTRIES", + "BriefDescription": "Cycles in which 10 or more DARQ1 entries (out of 12) are in use" + }, + {, + "EventCode": "0x360A6", + "EventName": "PM_SNP_TM_HIT_M", + "BriefDescription": "Snp TM st hit M/Mu" + }, + {, + "EventCode": "0x5898", + "EventName": "PM_LINK_STACK_INVALID_PTR", + "BriefDescription": "It is most often caused by certain types of flush where the pointer is not available. Can result in the data in the link stack becoming unusable." + }, + {, + "EventCode": "0x46088", + "EventName": "PM_L2_CHIP_PUMP", + "BriefDescription": "RC requests that were local (aka chip) pump attempts" + }, + {, + "EventCode": "0x28A0", + "EventName": "PM_TM_TSUSPEND", + "BriefDescription": "TM suspend instruction completed" + }, + {, + "EventCode": "0x20054", + "EventName": "PM_L1_PREF", + "BriefDescription": "A data line was written to the L1 due to a hardware or software prefetch" + }, + {, + "EventCode": "0xF888", + "EventName": "PM_LSU1_STORE_REJECT", + "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met" + }, + {, + "EventCode": "0x4505E", + "EventName": "PM_FLOP_CMPL", + "BriefDescription": "Floating Point Operation Finished" + }, + {, + "EventCode": "0x1D144", + "EventName": "PM_MRK_DATA_FROM_L3_DISP_CONFLICT", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 with dispatch conflict due to a marked load" + }, + {, + "EventCode": "0x400FA", + "EventName": "PM_RUN_INST_CMPL", + "BriefDescription": "Run_Instructions" + }, + {, + "EventCode": "0x15154", + "EventName": "PM_SYNC_MRK_L3MISS", + "BriefDescription": "Marked L3 misses that can throw a synchronous interrupt" + }, + {, + "EventCode": "0xE0B4", + "EventName": "PM_LS0_TM_DISALLOW", + "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it" + }, + {, + "EventCode": "0x26884", + "EventName": "PM_DSIDE_MRU_TOUCH", + "BriefDescription": "D-side L2 MRU touch sent to L2" + }, + {, + "EventCode": "0x30134", + "EventName": "PM_MRK_ST_CMPL_INT", + "BriefDescription": "marked store finished with intervention" + }, + {, + "EventCode": "0xC0B8", + "EventName": "PM_LSU_FLUSH_SAO", + "BriefDescription": "A load-hit-load condition with Strong Address Ordering will have address compare disabled and flush" + }, + {, + "EventCode": "0x50A8", + "EventName": "PM_EAT_FORCE_MISPRED", + "BriefDescription": "XL-form branch was mispredicted due to the predicted target address missing from EAT. The EAT forces a mispredict in this case since there is no predicated target to validate. This is a rare case that may occur when the EAT is full and a branch is issued" + }, + {, + "EventCode": "0xC094", + "EventName": "PM_LS0_UNALIGNED_LD", + "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size. If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0xF8BC", + "EventName": "PM_LS3_UNALIGNED_ST", + "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size. If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0x58B0", + "EventName": "PM_BTAC_GOOD_RESULT", + "BriefDescription": "BTAC predicts a taken branch and the BHT agrees, and the target address is correct" + }, + {, + "EventCode": "0x1C04C", + "EventName": "PM_DATA_FROM_LL4", + "BriefDescription": "The processor's data cache was reloaded from the local chip's L4 cache due to a demand load" + }, + {, + "EventCode": "0x3608E", + "EventName": "PM_TM_ST_CONF", + "BriefDescription": "TM Store (fav or non-fav) ran into conflict (failed)" + }, + {, + "EventCode": "0xD998", + "EventName": "PM_MRK_LSU_FLUSH_EMSH", + "BriefDescription": "An ERAT miss was detected after a set-p hit. Erat tracker indicates fail due to tlbmiss and the instruction gets flushed because the instruction was working on the wrong address" + }, + {, + "EventCode": "0xF8A0", + "EventName": "PM_NON_DATA_STORE", + "BriefDescription": "All ops that drain from s2q to L2 and contain no data" + }, + {, + "EventCode": "0x3F146", + "EventName": "PM_MRK_DPTEG_FROM_L21_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L2 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x40A0", + "EventName": "PM_BR_UNCOND", + "BriefDescription": "Unconditional Branch Completed. HW branch prediction was not used for this branch. This can be an I-form branch, a B-form branch with BO-field set to branch always, or a B-form branch which was covenrted to a Resolve." + }, + {, + "EventCode": "0x1F056", + "EventName": "PM_RADIX_PWC_L1_HIT", + "BriefDescription": "A radix translation attempt missed in the TLB and only the first level page walk cache was a hit." + }, + {, + "EventCode": "0xF8A8", + "EventName": "PM_DC_PREF_FUZZY_CONF", + "BriefDescription": "A demand load referenced a line in an active fuzzy prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software.Fuzzy stream confirm (out of order effects, or pf cant keep up)" + }, + {, + "EventCode": "0xF8A4", + "EventName": "PM_DC_PREF_SW_ALLOC", + "BriefDescription": "Prefetch stream allocated by software prefetching" + }, + {, + "EventCode": "0xE0A0", + "EventName": "PM_LSU2_TM_L1_MISS", + "BriefDescription": "Load tm L1 miss" + }, + {, + "EventCode": "0x2894", + "EventName": "PM_TM_OUTER_TEND", + "BriefDescription": "Completion time outer tend" + }, + {, + "EventCode": "0xF098", + "EventName": "PM_XLATE_HPT_MODE", + "BriefDescription": "LSU reports every cycle the thread is in HPT translation mode (as opposed to radix mode)" + }, + {, + "EventCode": "0x2C04E", + "EventName": "PM_LD_MISS_L1_FIN", + "BriefDescription": "Number of load instructions that finished with an L1 miss. Note that even if a load spans multiple slices this event will increment only once per load op." + }, + {, + "EventCode": "0x30162", + "EventName": "PM_MRK_LSU_DERAT_MISS", + "BriefDescription": "Marked derat reload (miss) for any page size" + }, + {, + "EventCode": "0x160A0", + "EventName": "PM_L3_PF_MISS_L3", + "BriefDescription": "L3 PF missed in L3" + }, + {, + "EventCode": "0x1C04A", + "EventName": "PM_DATA_FROM_RL2L3_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a demand load" + }, + {, + "EventCode": "0xD99C", + "EventName": "PM_MRK_LSU_FLUSH_UE", + "BriefDescription": "Correctable ECC error on reload data, reported at critical data forward time" + }, + {, + "EventCode": "0x268B0", + "EventName": "PM_L3_P1_GRP_PUMP", + "BriefDescription": "L3 PF sent with grp scope port 1, counts even retried requests" + }, + {, + "EventCode": "0x30016", + "EventName": "PM_CMPLU_STALL_SRQ_FULL", + "BriefDescription": "Finish stall because the NTF instruction was a store that was held in LSAQ because the SRQ was full" + }, + {, + "EventCode": "0x40B4", + "EventName": "PM_BR_PRED_TA", + "BriefDescription": "Conditional Branch Completed that had its target address predicted. Only XL-form branches set this event. This equal the sum of CCACHE, LSTACK, and PCACHE" + }, + {, + "EventCode": "0x40AC", + "EventName": "PM_BR_MPRED_CCACHE", + "BriefDescription": "Conditional Branch Completed that was Mispredicted due to the Count Cache Target Prediction" + }, + {, + "EventCode": "0x3688A", + "EventName": "PM_L2_RTY_LD", + "BriefDescription": "RC retries on PB for any load from core (excludes DCBFs)" + }, + {, + "EventCode": "0xE08C", + "EventName": "PM_LSU0_ERAT_HIT", + "BriefDescription": "Primary ERAT hit. There is no secondary ERAT" + }, + {, + "EventCode": "0xE088", + "EventName": "PM_LS2_ERAT_MISS_PREF", + "BriefDescription": "LS0 Erat miss due to prefetch" + }, + {, + "EventCode": "0xF0A8", + "EventName": "PM_DC_PREF_CONF", + "BriefDescription": "A demand load referenced a line in an active prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software. Includes forwards and backwards streams" + }, + {, + "EventCode": "0x16888", + "EventName": "PM_L2_LOC_GUESS_WRONG", + "BriefDescription": "L2 guess local (LNS) and guess was not correct (ie data not on chip)" + }, + {, + "EventCode": "0xE0A4", + "EventName": "PM_TMA_REQ_L2", + "BriefDescription": "addrs only req to L2 only on the first one,Indication that Load footprint is not expanding" + }, + {, + "EventCode": "0x5884", + "EventName": "PM_DECODE_LANES_NOT_AVAIL", + "BriefDescription": "Decode has something to transmit but dispatch lanes are not available" + }, + {, + "EventCode": "0x3C042", + "EventName": "PM_DATA_FROM_L3_DISP_CONFLICT", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 with dispatch conflict due to a demand load" + }, + {, + "EventCode": "0x168AA", + "EventName": "PM_L3_P1_LCO_NO_DATA", + "BriefDescription": "Dataless L3 LCO sent port 1" + }, + {, + "EventCode": "0x3D140", + "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_OTHER_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L2 with dispatch conflict due to a marked load" + }, + {, + "EventCode": "0xC89C", + "EventName": "PM_LS1_LAUNCH_HELD_PREF", + "BriefDescription": "Number of times a load or store instruction was unable to launch/relaunch because a high priority prefetch used that relaunch cycle" + }, + {, + "EventCode": "0x4894", + "EventName": "PM_IC_RELOAD_PRIVATE", + "BriefDescription": "Reloading line was brought in private for a specific thread. Most lines are brought in shared for all eight threads. If RA does not match then invalidates and then brings it shared to other thread. In P7 line brought in private , then line was invalidat" + }, + {, + "EventCode": "0x1688E", + "EventName": "PM_TM_LD_CAUSED_FAIL", + "BriefDescription": "Non-TM Load caused any thread to fail" + }, + {, + "EventCode": "0x26084", + "EventName": "PM_L2_RCLD_DISP_FAIL_OTHER", + "BriefDescription": "All I-or-D side load dispatch attempts for this thread that failed due to reason other than address collision (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0x101E4", + "EventName": "PM_MRK_L1_ICACHE_MISS", + "BriefDescription": "sampled Instruction suffered an icache Miss" + }, + {, + "EventCode": "0x20A0", + "EventName": "PM_TM_NESTED_TBEGIN", + "BriefDescription": "Completion Tm nested tbegin" + }, + {, + "EventCode": "0x368AA", + "EventName": "PM_L3_P1_CO_MEM", + "BriefDescription": "L3 CO to memory port 1 with or without data" + }, + {, + "EventCode": "0xC8A4", + "EventName": "PM_LSU3_FALSE_LHS", + "BriefDescription": "False LHS match detected" + }, + {, + "EventCode": "0xD9A4", + "EventName": "PM_MRK_LSU_FLUSH_LARX_STCX", + "BriefDescription": "A larx is flushed because an older larx has an LMQ reservation for the same thread. A stcx is flushed because an older stcx is in the LMQ. The flush happens when the older larx/stcx relaunches" + }, + {, + "EventCode": "0x4D012", + "EventName": "PM_PMC3_SAVED", + "BriefDescription": "PMC3 Rewind Value saved" + }, + {, + "EventCode": "0xE888", + "EventName": "PM_LS3_ERAT_MISS_PREF", + "BriefDescription": "LS1 Erat miss due to prefetch" + }, + {, + "EventCode": "0x368B4", + "EventName": "PM_L3_RD0_BUSY", + "BriefDescription": "Lifetime, sample of RD machine 0 valid" + }, + {, + "EventCode": "0x46080", + "EventName": "PM_L2_DISP_ALL_L2MISS", + "BriefDescription": "All successful Ld/St dispatches for this thread that were an L2 miss (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0xF8B8", + "EventName": "PM_LS1_UNALIGNED_ST", + "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size. If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0x408C", + "EventName": "PM_L1_DEMAND_WRITE", + "BriefDescription": "Instruction Demand sectors written into IL1" + }, + {, + "EventCode": "0x368A8", + "EventName": "PM_SN_INVL", + "BriefDescription": "Any port snooper detects a store to a line in the Sx state and invalidates the line. Up to 4 can happen in a cycle but we only count 1" + }, + {, + "EventCode": "0x160B2", + "EventName": "PM_L3_LOC_GUESS_CORRECT", + "BriefDescription": "initial scope=node/chip (LNS) and data from local node (local) (pred successful) - always PFs only" + }, + {, + "EventCode": "0x48B4", + "EventName": "PM_DECODE_FUSION_CONST_GEN", + "BriefDescription": "32-bit constant generation" + }, + {, + "EventCode": "0x4D146", + "EventName": "PM_MRK_DATA_FROM_L21_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L2 on the same chip due to a marked load" + }, + {, + "EventCode": "0xE080", + "EventName": "PM_S2Q_FULL", + "BriefDescription": "Cycles during which the S2Q is full" + }, + {, + "EventCode": "0x268B4", + "EventName": "PM_L3_P3_LCO_RTY", + "BriefDescription": "L3 initiated LCO received retry on port 3 (can try 4 times)" + }, + {, + "EventCode": "0xD8B8", + "EventName": "PM_LSU0_LMQ_S0_VALID", + "BriefDescription": "Slot 0 of LMQ valid" + }, + {, + "EventCode": "0x2098", + "EventName": "PM_TM_NESTED_TEND", + "BriefDescription": "Completion time nested tend" + }, + {, + "EventCode": "0x36084", + "EventName": "PM_L2_RCST_DISP", + "BriefDescription": "All D-side store dispatch attempts for this thread" + }, + {, + "EventCode": "0x368A0", + "EventName": "PM_L3_PF_OFF_CHIP_CACHE", + "BriefDescription": "L3 PF from Off chip cache" + }, + {, + "EventCode": "0x20056", + "EventName": "PM_TAKEN_BR_MPRED_CMPL", + "BriefDescription": "Total number of taken branches that were incorrectly predicted as not-taken. This event counts branches completed and does not include speculative instructions" + }, + {, + "EventCode": "0x4688A", + "EventName": "PM_L2_SYS_PUMP", + "BriefDescription": "RC requests that were system pump attempts" + }, + {, + "EventCode": "0xE090", + "EventName": "PM_LSU2_ERAT_HIT", + "BriefDescription": "Primary ERAT hit. There is no secondary ERAT" + }, + {, + "EventCode": "0x4001C", + "EventName": "PM_INST_IMC_MATCH_CMPL", + "BriefDescription": "IMC Match Count" + }, + {, + "EventCode": "0x40A8", + "EventName": "PM_BR_PRED_LSTACK", + "BriefDescription": "Conditional Branch Completed that used the Link Stack for Target Prediction" + }, + {, + "EventCode": "0x268A2", + "EventName": "PM_L3_CI_MISS", + "BriefDescription": "L3 castins miss (total count)" + }, + {, + "EventCode": "0x289C", + "EventName": "PM_TM_NON_FAV_TBEGIN", + "BriefDescription": "Dispatch time non favored tbegin" + }, + {, + "EventCode": "0xF08C", + "EventName": "PM_LSU2_STORE_REJECT", + "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met" + }, + {, + "EventCode": "0x360A0", + "EventName": "PM_L3_PF_ON_CHIP_CACHE", + "BriefDescription": "L3 PF from On chip cache" + }, + {, + "EventCode": "0x35152", + "EventName": "PM_MRK_DATA_FROM_L2MISS_CYC", + "BriefDescription": "Duration in cycles to reload from a location other than the local core's L2 due to a marked load" + }, + {, + "EventCode": "0x160AC", + "EventName": "PM_L3_SN_USAGE", + "BriefDescription": "Rotating sample of 16 snoop valids" + }, + {, + "EventCode": "0x16084", + "EventName": "PM_L2_RCLD_DISP", + "BriefDescription": "All I-or-D side load dispatch attempts for this thread (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0x1608C", + "EventName": "PM_RC0_BUSY", + "BriefDescription": "RC mach 0 Busy. Used by PMU to sample ave RC lifetime (mach0 used as sample point)" + }, + {, + "EventCode": "0x36082", + "EventName": "PM_L2_LD_DISP", + "BriefDescription": "All successful I-or-D side load dispatches for this thread (excludes i_l2mru_tch_reqs)." + }, + {, + "EventCode": "0xF8B0", + "EventName": "PM_L3_SW_PREF", + "BriefDescription": "L3 load prefetch, sourced from a software prefetch stream, was sent to the nest" + }, + {, + "EventCode": "0xF884", + "EventName": "PM_TABLEWALK_CYC_PREF", + "BriefDescription": "tablewalk qualified for pte prefetches" + }, + {, + "EventCode": "0x4D144", + "EventName": "PM_MRK_DATA_FROM_L31_ECO_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's ECO L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x16884", + "EventName": "PM_L2_RCLD_DISP_FAIL_ADDR", + "BriefDescription": "All I-od-D side load dispatch attempts for this thread that failed due to address collision with RC/CO/SN/SQ machine (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0x460A0", + "EventName": "PM_L3_PF_ON_CHIP_MEM", + "BriefDescription": "L3 PF from On chip memory" + }, + {, + "EventCode": "0xF084", + "EventName": "PM_PTE_PREFETCH", + "BriefDescription": "PTE prefetches" + }, + {, + "EventCode": "0x2D026", + "EventName": "PM_RADIX_PWC_L1_PDE_FROM_L2", + "BriefDescription": "A Page Directory Entry was reloaded to a level 1 page walk cache from the core's L2 data cache" + }, + {, + "EventCode": "0x48B0", + "EventName": "PM_BR_MPRED_PCACHE", + "BriefDescription": "Conditional Branch Completed that was Mispredicted due to pattern cache prediction" + }, + {, + "EventCode": "0x2C126", + "EventName": "PM_MRK_DATA_FROM_L2", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 due to a marked load" + }, + {, + "EventCode": "0xE0AC", + "EventName": "PM_TM_FAIL_TLBIE", + "BriefDescription": "Transaction failed because there was a TLBIE hit in the bloom filter" + }, + {, + "EventCode": "0x260AA", + "EventName": "PM_L3_P0_LCO_DATA", + "BriefDescription": "LCO sent with data port 0" + }, + {, + "EventCode": "0x4888", + "EventName": "PM_IC_PREF_REQ", + "BriefDescription": "Instruction prefetch requests" + }, + {, + "EventCode": "0xC898", + "EventName": "PM_LS3_UNALIGNED_LD", + "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size. If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0x488C", + "EventName": "PM_IC_PREF_WRITE", + "BriefDescription": "Instruction prefetch written into IL1" + }, + {, + "EventCode": "0xF89C", + "EventName": "PM_XLATE_MISS", + "BriefDescription": "The LSU requested a line from L2 for translation. It may be satisfied from any source beyond L2. Includes speculative instructions" + }, + {, + "EventCode": "0x14158", + "EventName": "PM_MRK_DATA_FROM_L2_NO_CONFLICT_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L2 without conflict due to a marked load" + }, + {, + "EventCode": "0x35156", + "EventName": "PM_MRK_DATA_FROM_L31_SHR_CYC", + "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x268A6", + "EventName": "PM_TM_RST_SC", + "BriefDescription": "TM-snp rst RM SC" + }, + {, + "EventCode": "0x468A4", + "EventName": "PM_L3_TRANS_PF", + "BriefDescription": "L3 Transient prefetch received from L2" + }, + {, + "EventCode": "0x4094", + "EventName": "PM_IC_PREF_CANCEL_L2", + "BriefDescription": "L2 Squashed a demand or prefetch request" + }, + {, + "EventCode": "0x48AC", + "EventName": "PM_BR_MPRED_LSTACK", + "BriefDescription": "Conditional Branch Completed that was Mispredicted due to the Link Stack Target Prediction" + }, + {, + "EventCode": "0xE88C", + "EventName": "PM_LSU1_ERAT_HIT", + "BriefDescription": "Primary ERAT hit. There is no secondary ERAT" + }, + {, + "EventCode": "0xC0B4", + "EventName": "PM_LSU_FLUSH_WRK_ARND", + "BriefDescription": "LSU workaround flush. These flushes are setup with programmable scan only latches to perform various actions when the flush macro receives a trigger from the dbg macros. These actions include things like flushing the next op encountered for a particular thread or flushing the next op that is NTC op that is encountered on a particular slice. The kind of flush that the workaround is setup to perform is highly variable." + }, + {, + "EventCode": "0x34054", + "EventName": "PM_PARTIAL_ST_FIN", + "BriefDescription": "Any store finished by an LSU slice" + }, + {, + "EventCode": "0x5880", + "EventName": "PM_THRD_PRIO_6_7_CYC", + "BriefDescription": "Cycles thread running at priority level 6 or 7" + }, + {, + "EventCode": "0x4898", + "EventName": "PM_IC_DEMAND_L2_BR_REDIRECT", + "BriefDescription": "L2 I cache demand request due to branch Mispredict ( 15 cycle path)" + }, + {, + "EventCode": "0x4880", + "EventName": "PM_BANK_CONFLICT", + "BriefDescription": "Read blocked due to interleave conflict. The ifar logic will detect an interleave conflict and kill the data that was read that cycle." + }, + {, + "EventCode": "0x360B0", + "EventName": "PM_L3_P0_SYS_PUMP", + "BriefDescription": "L3 PF sent with sys scope port 0, counts even retried requests" + }, + {, + "EventCode": "0x3006A", + "EventName": "PM_IERAT_RELOAD_64K", + "BriefDescription": "IERAT Reloaded (Miss) for a 64k page" + }, + {, + "EventCode": "0xD8BC", + "EventName": "PM_LSU2_3_LRQF_FULL_CYC", + "BriefDescription": "Counts the number of cycles the LRQF is full. LRQF is the queue that holds loads between finish and completion. If it fills up, instructions stay in LRQ until completion, potentially backing up the LRQ" + }, + {, + "EventCode": "0x46086", + "EventName": "PM_L2_SN_M_RD_DONE", + "BriefDescription": "SNP dispatched for a read and was M (true M)" + }, + {, + "EventCode": "0x40154", + "EventName": "PM_MRK_FAB_RSP_BKILL", + "BriefDescription": "Marked store had to do a bkill" + }, + {, + "EventCode": "0xF094", + "EventName": "PM_LSU2_L1_CAM_CANCEL", + "BriefDescription": "ls2 l1 tm cam cancel" + }, + {, + "EventCode": "0x2D014", + "EventName": "PM_CMPLU_STALL_LRQ_FULL", + "BriefDescription": "Finish stall because the NTF instruction was a load that was held in LSAQ (load-store address queue) because the LRQ (load-reorder queue) was full" + }, + {, + "EventCode": "0x3E05E", + "EventName": "PM_L3_CO_MEPF", + "BriefDescription": "L3 castouts in Mepf state for this thread" + }, + {, + "EventCode": "0x460A2", + "EventName": "PM_L3_LAT_CI_HIT", + "BriefDescription": "L3 Lateral Castins Hit" + }, + {, + "EventCode": "0x3D14E", + "EventName": "PM_MRK_DATA_FROM_DL2L3_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load" + }, + {, + "EventCode": "0x3D15E", + "EventName": "PM_MULT_MRK", + "BriefDescription": "mult marked instr" + }, + {, + "EventCode": "0x4084", + "EventName": "PM_EAT_FULL_CYC", + "BriefDescription": "Cycles No room in EAT" + }, + {, + "EventCode": "0x5098", + "EventName": "PM_LINK_STACK_WRONG_ADD_PRED", + "BriefDescription": "Link stack predicts wrong address, because of link stack design limitation or software violating the coding conventions" + }, + {, + "EventCode": "0x2C050", + "EventName": "PM_DATA_GRP_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was group pump (prediction=correct) for a demand load" + }, + {, + "EventCode": "0xC0A4", + "EventName": "PM_LSU2_FALSE_LHS", + "BriefDescription": "False LHS match detected" + }, + {, + "EventCode": "0x58A0", + "EventName": "PM_LINK_STACK_CORRECT", + "BriefDescription": "Link stack predicts right address" + }, + {, + "EventCode": "0x4C05A", + "EventName": "PM_DTLB_MISS_1G", + "BriefDescription": "Data TLB reload (after a miss) page size 1G. Implies radix translation was used" + }, + {, + "EventCode": "0x36886", + "EventName": "PM_L2_SN_SX_I_DONE", + "BriefDescription": "SNP dispatched and went from Sx to Ix" + }, + {, + "EventCode": "0x4E04A", + "EventName": "PM_DPTEG_FROM_OFF_CHIP_CACHE", + "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2C12C", + "EventName": "PM_MRK_DATA_FROM_DL4_CYC", + "BriefDescription": "Duration in cycles to reload from another chip's L4 on a different Node or Group (Distant) due to a marked load" + }, + {, + "EventCode": "0x2608E", + "EventName": "PM_TM_LD_CONF", + "BriefDescription": "TM Load (fav or non-fav) ran into conflict (failed)" + }, + {, + "EventCode": "0x4080", + "EventName": "PM_INST_FROM_L1", + "BriefDescription": "Instruction fetches from L1. L1 instruction hit" + }, + {, + "EventCode": "0xE898", + "EventName": "PM_LSU3_TM_L1_HIT", + "BriefDescription": "Load tm hit in L1" + }, + {, + "EventCode": "0x260A0", + "EventName": "PM_L3_CO_MEM", + "BriefDescription": "L3 CO to memory OR of port 0 and 1 (lossy = may undercount if two cresp come in the same cyc)" + }, + {, + "EventCode": "0x16082", + "EventName": "PM_L2_CASTOUT_MOD", + "BriefDescription": "L2 Castouts - Modified (M,Mu,Me)" + }, + {, + "EventCode": "0xC09C", + "EventName": "PM_LS0_LAUNCH_HELD_PREF", + "BriefDescription": "Number of times a load or store instruction was unable to launch/relaunch because a high priority prefetch used that relaunch cycle" + }, + {, + "EventCode": "0xC8B8", + "EventName": "PM_LSU_FLUSH_LARX_STCX", + "BriefDescription": "A larx is flushed because an older larx has an LMQ reservation for the same thread. A stcx is flushed because an older stcx is in the LMQ. The flush happens when the older larx/stcx relaunches" + }, + {, + "EventCode": "0x260A6", + "EventName": "PM_NON_TM_RST_SC", + "BriefDescription": "Non-TM snp rst TM SC" + }, + {, + "EventCode": "0x3608A", + "EventName": "PM_L2_RTY_ST", + "BriefDescription": "RC retries on PB for any store from core (excludes DCBFs)" + }, + {, + "EventCode": "0x24040", + "EventName": "PM_INST_FROM_L2_MEPF", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state. due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x209C", + "EventName": "PM_TM_FAV_TBEGIN", + "BriefDescription": "Dispatch time Favored tbegin" + }, + {, + "EventCode": "0x2D01E", + "EventName": "PM_ICT_NOSLOT_DISP_HELD_ISSQ", + "BriefDescription": "Ict empty for this thread due to dispatch hold on this thread due to Issue q full, BRQ full, XVCF Full, Count cache, Link, Tar full" + }, + {, + "EventCode": "0x50A4", + "EventName": "PM_FLUSH_MPRED", + "BriefDescription": "Branch mispredict flushes. Includes target and address misprecition" + }, + {, + "EventCode": "0x508C", + "EventName": "PM_SHL_CREATED", + "BriefDescription": "Store-Hit-Load Table Entry Created" + }, + {, + "EventCode": "0x1504C", + "EventName": "PM_IPTEG_FROM_LL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a instruction side request" + }, + {, + "EventCode": "0x268A4", + "EventName": "PM_L3_LD_MISS", + "BriefDescription": "L3 Misses for demand LDs" + }, + {, + "EventCode": "0x26088", + "EventName": "PM_L2_GRP_GUESS_CORRECT", + "BriefDescription": "L2 guess grp (GS or NNS) and guess was correct (data intra-group AND ^on-chip)" + }, + {, + "EventCode": "0xD088", + "EventName": "PM_LSU0_LDMX_FIN", + "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491): The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region. This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])." + }, + {, + "EventCode": "0xE8B4", + "EventName": "PM_LS1_TM_DISALLOW", + "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it" + }, + {, + "EventCode": "0x1688C", + "EventName": "PM_RC_USAGE", + "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each RC machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running" + }, + {, + "EventCode": "0x3F054", + "EventName": "PM_RADIX_PWC_L4_PTE_FROM_L3MISS", + "BriefDescription": "A Page Table Entry was reloaded to a level 4 page walk cache from beyond the core's L3 data cache. This is the deepest level of PWC possible for a translation. The source could be local/remote/distant memory or another core's cache" + }, + {, + "EventCode": "0x2608A", + "EventName": "PM_ISIDE_DISP_FAIL_ADDR", + "BriefDescription": "All I-side dispatch attempts for this thread that failed due to a addr collision with another machine (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0x50B4", + "EventName": "PM_TAGE_CORRECT_TAKEN_CMPL", + "BriefDescription": "The TAGE overrode BHT direction prediction and it was correct. Counted at completion for taken branches only" + }, + {, + "EventCode": "0x2090", + "EventName": "PM_DISP_CLB_HELD_SB", + "BriefDescription": "Dispatch/CLB Hold: Scoreboard" + }, + {, + "EventCode": "0xE0B0", + "EventName": "PM_TM_FAIL_NON_TX_CONFLICT", + "BriefDescription": "Non transactional conflict from LSU, gets reported to TEXASR" + }, + {, + "EventCode": "0xD198", + "EventName": "PM_MRK_LSU_FLUSH_ATOMIC", + "BriefDescription": "Quad-word loads (lq) are considered atomic because they always span at least 2 slices. If a snoop or store from another thread changes the data the load is accessing between the 2 or 3 pieces of the lq instruction, the lq will be flushed" + }, + {, + "EventCode": "0x201E0", + "EventName": "PM_MRK_DATA_FROM_MEMORY", + "BriefDescription": "The processor's data cache was reloaded from a memory location including L4 from local remote or distant due to a marked load" + }, + {, + "EventCode": "0x368A2", + "EventName": "PM_L3_L2_CO_MISS", + "BriefDescription": "L2 CO miss" + }, + {, + "EventCode": "0x3608C", + "EventName": "PM_CO0_BUSY", + "BriefDescription": "CO mach 0 Busy. Used by PMU to sample ave CO lifetime (mach0 used as sample point)" + }, + {, + "EventCode": "0x2C122", + "EventName": "PM_MRK_DATA_FROM_L3_DISP_CONFLICT_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L3 with dispatch conflict due to a marked load" + }, + {, + "EventCode": "0x35154", + "EventName": "PM_MRK_DATA_FROM_L3_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L3 due to a marked load" + }, + {, + "EventCode": "0x1D140", + "EventName": "PM_MRK_DATA_FROM_L31_MOD_CYC", + "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x4404A", + "EventName": "PM_INST_FROM_OFF_CHIP_CACHE", + "BriefDescription": "The processor's Instruction cache was reloaded either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x28AC", + "EventName": "PM_TM_FAIL_SELF", + "BriefDescription": "TM aborted because a self-induced conflict occurred in Suspended state, due to one of the following: a store to a storage location that was previously accessed transactionally; a dcbf, dcbi, or icbi specify- ing a block that was previously accessed transactionally; a dcbst specifying a block that was previously written transactionally; or a tlbie that specifies a translation that was pre- viously used transactionally" + }, + {, + "EventCode": "0x45056", + "EventName": "PM_SCALAR_FLOP_CMPL", + "BriefDescription": "Scalar flop operation completed" + }, + {, + "EventCode": "0x16092", + "EventName": "PM_L2_LD_MISS_128B", + "BriefDescription": "All successful D-side load dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 128B (i.e., M=0)" + }, + {, + "EventCode": "0x2E014", + "EventName": "PM_STCX_FIN", + "BriefDescription": "Number of stcx instructions finished. This includes instructions in the speculative path of a branch that may be flushed" + }, + {, + "EventCode": "0xE0B8", + "EventName": "PM_LS2_TM_DISALLOW", + "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it" + }, + {, + "EventCode": "0x2094", + "EventName": "PM_TM_OUTER_TBEGIN", + "BriefDescription": "Completion time outer tbegin" + }, + {, + "EventCode": "0x160B4", + "EventName": "PM_L3_P0_LCO_RTY", + "BriefDescription": "L3 initiated LCO received retry on port 0 (can try 4 times)" + }, + {, + "EventCode": "0x36892", + "EventName": "PM_DSIDE_OTHER_64B_L2MEMACC", + "BriefDescription": "Valid when first beat of data comes in for an D-side fetch where data came EXCLUSIVELY from memory that was for hpc_read64, (RC had to fetch other 64B of a line from MC) i.e., number of times RC had to go to memory to get 'missing' 64B" + }, + {, + "EventCode": "0x20A8", + "EventName": "PM_TM_FAIL_FOOTPRINT_OVERFLOW", + "BriefDescription": "TM aborted because the tracking limit for transactional storage accesses was exceeded.. Asynchronous" + }, + {, + "EventCode": "0x30018", + "EventName": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL", + "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF; CR; XVF (XER/VSCR/FPSCR)" + }, + {, + "EventCode": "0xC894", + "EventName": "PM_LS1_UNALIGNED_LD", + "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size. If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0x360A2", + "EventName": "PM_L3_L2_CO_HIT", + "BriefDescription": "L2 CO hits" + }, + {, + "EventCode": "0x36092", + "EventName": "PM_DSIDE_L2MEMACC", + "BriefDescription": "Valid when first beat of data comes in for an D-side fetch where data came EXCLUSIVELY from memory (excluding hpcread64 accesses), i.e., total memory accesses by RCs" + }, + {, + "EventCode": "0x10138", + "EventName": "PM_MRK_BR_2PATH", + "BriefDescription": "marked branches which are not strongly biased" + }, + {, + "EventCode": "0x2884", + "EventName": "PM_ISYNC", + "BriefDescription": "Isync completion count per thread" + }, + {, + "EventCode": "0x16882", + "EventName": "PM_L2_CASTOUT_SHR", + "BriefDescription": "L2 Castouts - Shared (Tx,Sx)" + }, + {, + "EventCode": "0xD884", + "EventName": "PM_LSU3_SET_MPRED", + "BriefDescription": "Set prediction(set-p) miss. The entry was not found in the Set prediction table" + }, + {, + "EventCode": "0x26092", + "EventName": "PM_L2_LD_MISS_64B", + "BriefDescription": "All successful D-side load dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 64B(i.e., M=1)" + }, + {, + "EventCode": "0x26080", + "EventName": "PM_L2_LD_MISS", + "BriefDescription": "All successful D-Side Load dispatches that were an L2 miss for this thread" + }, + {, + "EventCode": "0x3D14C", + "EventName": "PM_MRK_DATA_FROM_DMEM", + "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group (Distant) due to a marked load" + }, + {, + "EventCode": "0x100FA", + "EventName": "PM_ANY_THRD_RUN_CYC", + "BriefDescription": "Cycles in which at least one thread has the run latch set" + }, + {, + "EventCode": "0x2C12A", + "EventName": "PM_MRK_DATA_FROM_RMEM_CYC", + "BriefDescription": "Duration in cycles to reload from another chip's memory on the same Node or Group ( Remote) due to a marked load" + }, + {, + "EventCode": "0x25048", + "EventName": "PM_IPTEG_FROM_LMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's Memory due to a instruction side request" + }, + {, + "EventCode": "0xD8A8", + "EventName": "PM_ISLB_MISS", + "BriefDescription": "Instruction SLB miss - Total of all segment sizes" + }, + {, + "EventCode": "0xD19C", + "EventName": "PM_MRK_LSU_FLUSH_RELAUNCH_MISS", + "BriefDescription": "If a load that has already returned data and has to relaunch for any reason then gets a miss (erat, setp, data cache), it will often be flushed at relaunch time because the data might be inconsistent" + }, + {, + "EventCode": "0x260A2", + "EventName": "PM_L3_CI_HIT", + "BriefDescription": "L3 Castins Hit (total count)" + }, + {, + "EventCode": "0x44054", + "EventName": "PM_VECTOR_LD_CMPL", + "BriefDescription": "Number of vector load instructions completed" + }, + {, + "EventCode": "0x1E05C", + "EventName": "PM_CMPLU_STALL_NESTED_TBEGIN", + "BriefDescription": "Completion stall because the ISU is updating the TEXASR to keep track of the nested tbegin. This is a short delay, and it includes ROT" + }, + {, + "EventCode": "0x1608E", + "EventName": "PM_ST_CAUSED_FAIL", + "BriefDescription": "Non-TM Store caused any thread to fail" + }, + {, + "EventCode": "0x3080", + "EventName": "PM_ISU0_ISS_HOLD_ALL", + "BriefDescription": "All ISU rejects" + }, + {, + "EventCode": "0x1515A", + "EventName": "PM_SYNC_MRK_L2MISS", + "BriefDescription": "Marked L2 Miss that can throw a synchronous interrupt" + }, + {, + "EventCode": "0x26892", + "EventName": "PM_L2_ST_MISS_64B", + "BriefDescription": "All successful D-side store dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 64B (i.e., M=1)" + }, + {, + "EventCode": "0x2688C", + "EventName": "PM_CO_USAGE", + "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each CO machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running" + }, + {, + "EventCode": "0xD084", + "EventName": "PM_LSU2_SET_MPRED", + "BriefDescription": "Set prediction(set-p) miss. The entry was not found in the Set prediction table" + }, + {, + "EventCode": "0x48B8", + "EventName": "PM_BR_MPRED_TAKEN_TA", + "BriefDescription": "Conditional Branch Completed that was Mispredicted due to the Target Address Prediction from the Count Cache or Link Stack. Only XL-form branches that resolved Taken set this event." + }, + {, + "EventCode": "0x50B0", + "EventName": "PM_BTAC_BAD_RESULT", + "BriefDescription": "BTAC thinks branch will be taken but it is either predicted not-taken by the BHT, or the target address is wrong (less common). In both cases, a redirect will happen" + }, + {, + "EventCode": "0xD888", + "EventName": "PM_LSU1_LDMX_FIN", + "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491): The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region. This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])." + }, + {, + "EventCode": "0x58B4", + "EventName": "PM_TAGE_CORRECT", + "BriefDescription": "The TAGE overrode BHT direction prediction and it was correct. Includes taken and not taken and is counted at execution time" + }, + {, + "EventCode": "0x3688C", + "EventName": "PM_SN_USAGE", + "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each SN machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running" + }, + {, + "EventCode": "0x46084", + "EventName": "PM_L2_RCST_DISP_FAIL_OTHER", + "BriefDescription": "All D-side store dispatch attempts for this thread that failed due to reason other than address collision" + }, + {, + "EventCode": "0xF0AC", + "EventName": "PM_DC_PREF_STRIDED_CONF", + "BriefDescription": "A demand load referenced a line in an active strided prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software." + }, + {, + "EventCode": "0x45054", + "EventName": "PM_FMA_CMPL", + "BriefDescription": "two flops operation completed (fmadd, fnmadd, fmsub, fnmsub) Scalar instructions only. " + }, + {, + "EventCode": "0x5090", + "EventName": "PM_SHL_ST_DISABLE", + "BriefDescription": "Store-Hit-Load Table Read Hit with entry Disabled (entry was disabled due to the entry shown to not prevent the flush)" + }, + {, + "EventCode": "0x201E8", + "EventName": "PM_THRESH_EXC_512", + "BriefDescription": "Threshold counter exceeded a value of 512" + }, + {, + "EventCode": "0x5084", + "EventName": "PM_DECODE_FUSION_EXT_ADD", + "BriefDescription": "32-bit extended addition" + }, + {, + "EventCode": "0x36080", + "EventName": "PM_L2_INST", + "BriefDescription": "All successful I-side dispatches for this thread (excludes i_l2mru_tch reqs)." + }, + {, + "EventCode": "0x3504C", + "EventName": "PM_IPTEG_FROM_DL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on a different Node or Group (Distant) due to a instruction side request" + }, + {, + "EventCode": "0xD890", + "EventName": "PM_LS1_DC_COLLISIONS", + "BriefDescription": "Read-write data cache collisions" + }, + {, + "EventCode": "0x1688A", + "EventName": "PM_ISIDE_DISP", + "BriefDescription": "All I-side dispatch attempts for this thread (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0x468AA", + "EventName": "PM_L3_P1_CO_L31", + "BriefDescription": "L3 CO to L3.1 (LCO) port 1 with or without data" + }, + {, + "EventCode": "0x28B0", + "EventName": "PM_DISP_HELD_TBEGIN", + "BriefDescription": "This outer tbegin transaction cannot be dispatched until the previous tend instruction completes" + }, + {, + "EventCode": "0xE8A0", + "EventName": "PM_LSU3_TM_L1_MISS", + "BriefDescription": "Load tm L1 miss" + }, + {, + "EventCode": "0x2C05E", + "EventName": "PM_INST_GRP_PUMP_MPRED", + "BriefDescription": "Final Pump Scope (Group) ended up either larger or smaller than Initial Pump Scope for an instruction fetch (demand only)" + }, + {, + "EventCode": "0xC8BC", + "EventName": "PM_STCX_SUCCESS_CMPL", + "BriefDescription": "Number of stcx instructions that completed successfully" + }, + {, + "EventCode": "0xE098", + "EventName": "PM_LSU2_TM_L1_HIT", + "BriefDescription": "Load tm hit in L1" + }, + {, + "EventCode": "0x44044", + "EventName": "PM_INST_FROM_L31_ECO_MOD", + "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another core's ECO L3 on the same chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x16886", + "EventName": "PM_CO_DISP_FAIL", + "BriefDescription": "CO dispatch failed due to all CO machines being busy" + }, + {, + "EventCode": "0x3D146", + "EventName": "PM_MRK_DATA_FROM_L3_NO_CONFLICT", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 without conflict due to a marked load" + }, + {, + "EventCode": "0x16892", + "EventName": "PM_L2_ST_MISS_128B", + "BriefDescription": "All successful D-side store dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 128B (i.e., M=0)" + }, + {, + "EventCode": "0x26890", + "EventName": "PM_ISIDE_L2MEMACC", + "BriefDescription": "Valid when first beat of data comes in for an I-side fetch where data came from memory" + }, + {, + "EventCode": "0xD094", + "EventName": "PM_LS2_DC_COLLISIONS", + "BriefDescription": "Read-write data cache collisions" + }, + {, + "EventCode": "0x3C05E", + "EventName": "PM_MEM_RWITM", + "BriefDescription": "Memory Read With Intent to Modify for this thread" + }, + {, + "EventCode": "0x26882", + "EventName": "PM_L2_DC_INV", + "BriefDescription": "D-cache invalidates sent over the reload bus to the core" + }, + {, + "EventCode": "0xC090", + "EventName": "PM_LSU_STCX", + "BriefDescription": "STCX sent to nest, i.e. total" + }, + {, + "EventCode": "0xD080", + "EventName": "PM_LSU0_SET_MPRED", + "BriefDescription": "Set prediction(set-p) miss. The entry was not found in the Set prediction table" + }, + {, + "EventCode": "0x2C120", + "EventName": "PM_MRK_DATA_FROM_L2_NO_CONFLICT", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 without conflict due to a marked load" + }, + {, + "EventCode": "0x36086", + "EventName": "PM_L2_RC_ST_DONE", + "BriefDescription": "RC did store to line that was Tx or Sx" + }, + {, + "EventCode": "0xE8AC", + "EventName": "PM_TM_FAIL_TX_CONFLICT", + "BriefDescription": "Transactional conflict from LSU, gets reported to TEXASR" + }, + {, + "EventCode": "0x48A8", + "EventName": "PM_DECODE_FUSION_LD_ST_DISP", + "BriefDescription": "32-bit displacement D-form and 16-bit displacement X-form" + }, + {, + "EventCode": "0x3D144", + "EventName": "PM_MRK_DATA_FROM_L2_MEPF_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L2 hit without dispatch conflicts on Mepf state. due to a marked load" + }, + {, + "EventCode": "0x44046", + "EventName": "PM_INST_FROM_L21_MOD", + "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another core's L2 on the same chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x40B0", + "EventName": "PM_BR_PRED_TAKEN_CR", + "BriefDescription": "Conditional Branch that had its direction predicted. I-form branches do not set this event. In addition, B-form branches which do not use the BHT do not set this event - these are branches with BO-field set to 'always taken' and branches" + }, + {, + "EventCode": "0x15040", + "EventName": "PM_IPTEG_FROM_L2_NO_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a instruction side request" + }, + {, + "EventCode": "0xD9A0", + "EventName": "PM_MRK_LSU_FLUSH_LHL_SHL", + "BriefDescription": "The instruction was flushed because of a sequential load/store consistency. If a load or store hits on an older load that has either been snooped (for loads) or has stale data (for stores)." + }, + {, + "EventCode": "0x35042", + "EventName": "PM_IPTEG_FROM_L3_DISP_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a instruction side request" + }, + {, + "EventCode": "0xF898", + "EventName": "PM_XLATE_RADIX_MODE", + "BriefDescription": "LSU reports every cycle the thread is in radix translation mode (as opposed to HPT mode)" + }, + {, + "EventCode": "0x2D142", + "EventName": "PM_MRK_DATA_FROM_L3_MEPF", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 without dispatch conflicts hit on Mepf state. due to a marked load" + }, + {, + "EventCode": "0x160B0", + "EventName": "PM_L3_P0_NODE_PUMP", + "BriefDescription": "L3 PF sent with nodal scope port 0, counts even retried requests" + }, + {, + "EventCode": "0xD88C", + "EventName": "PM_LSU3_LDMX_FIN", + "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491): The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region. This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])." + }, + {, + "EventCode": "0x36882", + "EventName": "PM_L2_LD_HIT", + "BriefDescription": "All successful I-or-D side load dispatches for this thread that were L2 hits (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0x168AC", + "EventName": "PM_L3_CI_USAGE", + "BriefDescription": "Rotating sample of 16 CI or CO actives" + }, + {, + "EventCode": "0x20134", + "EventName": "PM_MRK_FXU_FIN", + "BriefDescription": "fxu marked instr finish" + }, + {, + "EventCode": "0x4608E", + "EventName": "PM_TM_CAP_OVERFLOW", + "BriefDescription": "TM Footprint Capacity Overflow" + }, + {, + "EventCode": "0x4F05C", + "EventName": "PM_RADIX_PWC_L2_PTE_FROM_L3MISS", + "BriefDescription": "A Page Table Entry was reloaded to a level 2 page walk cache from beyond the core's L3 data cache. This implies that level 3 and level 4 PWC accesses were not necessary for this translation. The source could be local/remote/distant memory or another core's cache" + }, + {, + "EventCode": "0x40014", + "EventName": "PM_PROBE_NOP_DISP", + "BriefDescription": "ProbeNops dispatched" + }, + {, + "EventCode": "0x58A8", + "EventName": "PM_DECODE_HOLD_ICT_FULL", + "BriefDescription": "Counts the number of cycles in which the IFU was not able to decode and transmit one or more instructions because all itags were in use. This means the ICT is full for this thread" + }, + {, + "EventCode": "0x10052", + "EventName": "PM_GRP_PUMP_MPRED_RTY", + "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x2505E", + "EventName": "PM_BACK_BR_CMPL", + "BriefDescription": "Branch instruction completed with a target address less than current instruction address" + }, + {, + "EventCode": "0x2688A", + "EventName": "PM_ISIDE_DISP_FAIL_OTHER", + "BriefDescription": "All I-side dispatch attempts for this thread that failed due to a reason other than addrs collision (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0x2001A", + "EventName": "PM_NTC_ALL_FIN", + "BriefDescription": "Cycles after all instructions have finished to group completed" + }, + {, + "EventCode": "0x3005A", + "EventName": "PM_ISQ_0_8_ENTRIES", + "BriefDescription": "Cycles in which 8 or less Issue Queue entries are in use. This is a shared event, not per thread" + }, + {, + "EventCode": "0x3515E", + "EventName": "PM_MRK_BACK_BR_CMPL", + "BriefDescription": "Marked branch instruction completed with a target address less than current instruction address" + }, + {, + "EventCode": "0xF890", + "EventName": "PM_LSU1_L1_CAM_CANCEL", + "BriefDescription": "ls1 l1 tm cam cancel" + }, + {, + "EventCode": "0xE884", + "EventName": "PM_LS1_ERAT_MISS_PREF", + "BriefDescription": "LS1 Erat miss due to prefetch" + }, + {, + "EventCode": "0xE89C", + "EventName": "PM_LSU1_TM_L1_MISS", + "BriefDescription": "Load tm L1 miss" + }, + {, + "EventCode": "0x28A8", + "EventName": "PM_TM_FAIL_CONF_NON_TM", + "BriefDescription": "TM aborted because a conflict occurred with a non-transactional access by another processor" + }, + {, + "EventCode": "0x16890", + "EventName": "PM_L1PF_L2MEMACC", + "BriefDescription": "Valid when first beat of data comes in for an L1PF where data came from memory" + }, + {, + "EventCode": "0x4504C", + "EventName": "PM_IPTEG_FROM_DMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group (Distant) due to a instruction side request" + }, + {, + "EventCode": "0x1002E", + "EventName": "PM_LMQ_MERGE", + "BriefDescription": "A demand miss collides with a prefetch for the same line" + }, + {, + "EventCode": "0x160B6", + "EventName": "PM_L3_WI0_BUSY", + "BriefDescription": "Rotating sample of 8 WI valid" + }, + {, + "EventCode": "0x368AC", + "EventName": "PM_L3_CO0_BUSY", + "BriefDescription": "Lifetime, sample of CO machine 0 valid" + }, + {, + "EventCode": "0x2E040", + "EventName": "PM_DPTEG_FROM_L2_MEPF", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 hit without dispatch conflicts on Mepf state. due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x1D152", + "EventName": "PM_MRK_DATA_FROM_DL4", + "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on a different Node or Group (Distant) due to a marked load" + }, + {, + "EventCode": "0x46880", + "EventName": "PM_ISIDE_MRU_TOUCH", + "BriefDescription": "I-side L2 MRU touch sent to L2 for this thread" + }, + {, + "EventCode": "0x1C05C", + "EventName": "PM_DTLB_MISS_2M", + "BriefDescription": "Data TLB reload (after a miss) page size 2M. Implies radix translation was used" + }, + {, + "EventCode": "0x50B8", + "EventName": "PM_TAGE_OVERRIDE_WRONG", + "BriefDescription": "The TAGE overrode BHT direction prediction but it was incorrect. Counted at completion for taken branches only" + }, + {, + "EventCode": "0x160AE", + "EventName": "PM_L3_P0_PF_RTY", + "BriefDescription": "L3 PF received retry port 0, every retry counted" + }, + {, + "EventCode": "0x268B2", + "EventName": "PM_L3_LOC_GUESS_WRONG", + "BriefDescription": "Initial scope=node (LNS) but data from out side local node (near or far or rem). Prediction too Low" + }, + {, + "EventCode": "0x36088", + "EventName": "PM_L2_SYS_GUESS_CORRECT", + "BriefDescription": "L2 guess system (VGS or RNS) and guess was correct (ie data beyond-group)" + }, + {, + "EventCode": "0x589C", + "EventName": "PM_PTESYNC", + "BriefDescription": "ptesync instruction counted when the instruction is decoded and transmitted" + }, + {, + "EventCode": "0x26086", + "EventName": "PM_CO_TM_SC_FOOTPRINT", + "BriefDescription": "L2 did a cleanifdirty CO to the L3 (ie created an SC line in the L3) OR L2 TM_store hit dirty HPC line and L3 indicated SC line formed in L3 on RDR bus" + }, + {, + "EventCode": "0x1E05A", + "EventName": "PM_CMPLU_STALL_ANY_SYNC", + "BriefDescription": "Cycles in which the NTC sync instruction (isync, lwsync or hwsync) is not allowed to complete" + }, + {, + "EventCode": "0xF090", + "EventName": "PM_LSU0_L1_CAM_CANCEL", + "BriefDescription": "ls0 l1 tm cam cancel" + }, + {, + "EventCode": "0xC0A8", + "EventName": "PM_LSU_FLUSH_CI", + "BriefDescription": "Load was not issued to LSU as a cache inhibited (non-cacheable) load but it was later determined to be cache inhibited" + }, + {, + "EventCode": "0x20AC", + "EventName": "PM_TM_FAIL_CONF_TM", + "BriefDescription": "TM aborted because a conflict occurred with another transaction." + }, + {, + "EventCode": "0x588C", + "EventName": "PM_SHL_ST_DEP_CREATED", + "BriefDescription": "Store-Hit-Load Table Read Hit with entry Enabled" + }, + {, + "EventCode": "0x360AC", + "EventName": "PM_L3_SN0_BUSY", + "BriefDescription": "Lifetime, sample of snooper machine 0 valid" + }, + {, + "EventCode": "0x3005C", + "EventName": "PM_BFU_BUSY", + "BriefDescription": "Cycles in which all 4 Binary Floating Point units are busy. The BFU is running at capacity" + }, + {, + "EventCode": "0x48A0", + "EventName": "PM_BR_PRED_PCACHE", + "BriefDescription": "Conditional branch completed that used pattern cache prediction" + }, + {, + "EventCode": "0x26880", + "EventName": "PM_L2_ST_MISS", + "BriefDescription": "All successful D-Side Store dispatches that were an L2 miss for this thread" + }, + {, + "EventCode": "0xF8B4", + "EventName": "PM_DC_PREF_XCONS_ALLOC", + "BriefDescription": "Prefetch stream allocated in the Ultra conservative phase by either the hardware prefetch mechanism or software prefetch" + }, + {, + "EventCode": "0x35048", + "EventName": "PM_IPTEG_FROM_DL2L3_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a instruction side request" + }, + {, + "EventCode": "0x260A8", + "EventName": "PM_L3_PF_HIT_L3", + "BriefDescription": "L3 PF hit in L3 (abandoned)" + }, + {, + "EventCode": "0x360B4", + "EventName": "PM_L3_PF0_BUSY", + "BriefDescription": "Lifetime, sample of PF machine 0 valid" + }, + {, + "EventCode": "0xC0B0", + "EventName": "PM_LSU_FLUSH_UE", + "BriefDescription": "Correctable ECC error on reload data, reported at critical data forward time" + }, + {, + "EventCode": "0x4013A", + "EventName": "PM_MRK_IC_MISS", + "BriefDescription": "Marked instruction experienced I cache miss" + }, + {, + "EventCode": "0x2088", + "EventName": "PM_FLUSH_DISP_SB", + "BriefDescription": "Dispatch Flush: Scoreboard" + }, + {, + "EventCode": "0x401E8", + "EventName": "PM_MRK_DATA_FROM_L2MISS", + "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L2 due to a marked load" + }, + {, + "EventCode": "0x3688E", + "EventName": "PM_TM_ST_CAUSED_FAIL", + "BriefDescription": "TM Store (fav or non-fav) caused another thread to fail" + }, + {, + "EventCode": "0x460B2", + "EventName": "PM_L3_SYS_GUESS_WRONG", + "BriefDescription": "Initial scope=system (VGS or RNS) but data from local or near. Prediction too high" + }, + {, + "EventCode": "0x58B8", + "EventName": "PM_TAGE_OVERRIDE_WRONG_SPEC", + "BriefDescription": "The TAGE overrode BHT direction prediction and it was correct. Includes taken and not taken and is counted at execution time" + }, + {, + "EventCode": "0xE890", + "EventName": "PM_LSU3_ERAT_HIT", + "BriefDescription": "Primary ERAT hit. There is no secondary ERAT" + }, + {, + "EventCode": "0x2898", + "EventName": "PM_TM_TABORT_TRECLAIM", + "BriefDescription": "Completion time tabortnoncd, tabortcd, treclaim" + }, + {, + "EventCode": "0x4C054", + "EventName": "PM_DERAT_MISS_16G", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16G" + }, + {, + "EventCode": "0x268A0", + "EventName": "PM_L3_CO_L31", + "BriefDescription": "L3 CO to L3.1 OR of port 0 and 1 (lossy = may undercount if two cresps come in the same cyc)" + }, + {, + "EventCode": "0x5080", + "EventName": "PM_THRD_PRIO_4_5_CYC", + "BriefDescription": "Cycles thread running at priority level 4 or 5" + }, + {, + "EventCode": "0x2505C", + "EventName": "PM_VSU_FIN", + "BriefDescription": "VSU instruction finished. Up to 4 per cycle" + }, + {, + "EventCode": "0x40A4", + "EventName": "PM_BR_PRED_CCACHE", + "BriefDescription": "Conditional Branch Completed that used the Count Cache for Target Prediction" + }, + {, + "EventCode": "0x2E04A", + "EventName": "PM_DPTEG_FROM_RL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on the same Node or Group ( Remote) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4D12E", + "EventName": "PM_MRK_DATA_FROM_DL2L3_MOD_CYC", + "BriefDescription": "Duration in cycles to reload with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load" + }, + {, + "EventCode": "0xC8B4", + "EventName": "PM_LSU_FLUSH_LHL_SHL", + "BriefDescription": "The instruction was flushed because of a sequential load/store consistency. If a load or store hits on an older load that has either been snooped (for loads) or has stale data (for stores)." + }, + {, + "EventCode": "0x58A4", + "EventName": "PM_FLUSH_LSU", + "BriefDescription": "LSU flushes. Includes all lsu flushes" + }, + {, + "EventCode": "0x1D150", + "EventName": "PM_MRK_DATA_FROM_DL2L3_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load" + }, + {, + "EventCode": "0xC8A0", + "EventName": "PM_LSU1_FALSE_LHS", + "BriefDescription": "False LHS match detected" + }, + {, + "EventCode": "0x48BC", + "EventName": "PM_THRD_PRIO_2_3_CYC", + "BriefDescription": "Cycles thread running at priority level 2 or 3" + }, + {, + "EventCode": "0x10134", + "EventName": "PM_MRK_ST_DONE_L2", + "BriefDescription": "marked store completed in L2 ( RC machine done)" + }, + {, + "EventCode": "0x368B2", + "EventName": "PM_L3_GRP_GUESS_WRONG_HIGH", + "BriefDescription": "Initial scope=group (GS or NNS) but data from local node. Prediction too high" + }, + {, + "EventCode": "0xE8BC", + "EventName": "PM_LS1_PTE_TABLEWALK_CYC", + "BriefDescription": "Cycles when a tablewalk is pending on this thread on table 1" + }, + {, + "EventCode": "0x1F152", + "EventName": "PM_MRK_FAB_RSP_BKILL_CYC", + "BriefDescription": "cycles L2 RC took for a bkill" + }, + {, + "EventCode": "0x4C124", + "EventName": "PM_MRK_DATA_FROM_L3_NO_CONFLICT_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L3 without conflict due to a marked load" + }, + {, + "EventCode": "0x2F14A", + "EventName": "PM_MRK_DPTEG_FROM_RL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on the same Node or Group ( Remote) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x26888", + "EventName": "PM_L2_GRP_GUESS_WRONG", + "BriefDescription": "L2 guess grp (GS or NNS) and guess was not correct (ie data on-chip OR beyond-group)" + }, + {, + "EventCode": "0x368AE", + "EventName": "PM_L3_P1_CO_RTY", + "BriefDescription": "L3 CO received retry port 1 (memory only), every retry counted" + }, + {, + "EventCode": "0xC0AC", + "EventName": "PM_LSU_FLUSH_EMSH", + "BriefDescription": "An ERAT miss was detected after a set-p hit. Erat tracker indicates fail due to tlbmiss and the instruction gets flushed because the instruction was working on the wrong address" + }, + {, + "EventCode": "0x260B2", + "EventName": "PM_L3_SYS_GUESS_CORRECT", + "BriefDescription": "Initial scope=system (VGS or RNS) and data from outside group (far or rem)(pred successful)" + }, + {, + "EventCode": "0x1D146", + "EventName": "PM_MRK_DATA_FROM_MEMORY_CYC", + "BriefDescription": "Duration in cycles to reload from a memory location including L4 from local remote or distant due to a marked load" + }, + {, + "EventCode": "0xE094", + "EventName": "PM_LSU0_TM_L1_HIT", + "BriefDescription": "Load tm hit in L1" + }, + {, + "EventCode": "0x46888", + "EventName": "PM_L2_GROUP_PUMP", + "BriefDescription": "RC requests that were on group (aka nodel) pump attempts" + }, + {, + "EventCode": "0xF0B0", + "EventName": "PM_L3_LD_PREF", + "BriefDescription": "L3 load prefetch, sourced from a hardware or software stream, was sent to the nest" + }, + {, + "EventCode": "0x16080", + "EventName": "PM_L2_LD", + "BriefDescription": "All successful D-side Load dispatches for this thread (L2 miss + L2 hits)" + }, + {, + "EventCode": "0x4505C", + "EventName": "PM_MATH_FLOP_CMPL", + "BriefDescription": "Math flop instruction completed" + }, + {, + "EventCode": "0x368B0", + "EventName": "PM_L3_P1_SYS_PUMP", + "BriefDescription": "L3 PF sent with sys scope port 1, counts even retried requests" + }, + {, + "EventCode": "0x1F146", + "EventName": "PM_MRK_DPTEG_FROM_L31_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L3 on the same chip due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2000C", + "EventName": "PM_THRD_ALL_RUN_CYC", + "BriefDescription": "Cycles in which all the threads have the run latch set" + }, + {, + "EventCode": "0xC0BC", + "EventName": "PM_LSU_FLUSH_OTHER", + "BriefDescription": "Other LSU flushes including: Sync (sync ack from L2 caused search of LRQ for oldest snooped load, This will either signal a Precise Flush of the oldest snooped loa or a Flush Next PPC); Data Valid Flush Next (several cases of this, one example is store and reload are lined up such that a store-hit-reload scenario exists and the CDF has already launched and has gotten bad/stale data); Bad Data Valid Flush Next (might be a few cases of this, one example is a larxa (D$ hit) return data and dval but can't allocate to LMQ (LMQ full or other reason). Already gave dval but can't watch it for snoop_hit_larx. Need to take the “bad dval” back and flush all younger ops)" + }, + {, + "EventCode": "0x5094", + "EventName": "PM_IC_MISS_ICBI", + "BriefDescription": "threaded version, IC Misses where we got EA dir hit but no sector valids were on. ICBI took line out" + }, + {, + "EventCode": "0xC8A8", + "EventName": "PM_LSU_FLUSH_ATOMIC", + "BriefDescription": "Quad-word loads (lq) are considered atomic because they always span at least 2 slices. If a snoop or store from another thread changes the data the load is accessing between the 2 or 3 pieces of the lq instruction, the lq will be flushed" + }, + {, + "EventCode": "0x1E04E", + "EventName": "PM_DPTEG_FROM_L2MISS", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4D05E", + "EventName": "PM_BR_CMPL", + "BriefDescription": "Any Branch instruction completed" + }, + {, + "EventCode": "0x260B0", + "EventName": "PM_L3_P0_GRP_PUMP", + "BriefDescription": "L3 PF sent with grp scope port 0, counts even retried requests" + }, + {, + "EventCode": "0x30132", + "EventName": "PM_MRK_VSU_FIN", + "BriefDescription": "VSU marked instr finish" + }, + {, + "EventCode": "0x2D120", + "EventName": "PM_MRK_DATA_FROM_OFF_CHIP_CACHE", + "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked load" + }, + {, + "EventCode": "0x1E048", + "EventName": "PM_DPTEG_FROM_ON_CHIP_CACHE", + "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x16086", + "EventName": "PM_L2_SN_M_WR_DONE", + "BriefDescription": "SNP dispatched for a write and was M (true M); for DMA cacheinj this will pulse if rty/push is required (won't pulse if cacheinj is accepted)" + }, + {, + "EventCode": "0x489C", + "EventName": "PM_BR_CORECT_PRED_TAKEN_CMPL", + "BriefDescription": "Conditional Branch Completed in which the HW correctly predicted the direction as taken. Counted at completion time" + }, + {, + "EventCode": "0xF0B8", + "EventName": "PM_LS0_UNALIGNED_ST", + "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size. If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0x20132", + "EventName": "PM_MRK_DFU_FIN", + "BriefDescription": "Decimal Unit marked Instruction Finish" + }, + {, + "EventCode": "0x160A6", + "EventName": "PM_TM_SC_CO", + "BriefDescription": "L3 castout TM SC line" + }, + {, + "EventCode": "0xC8B0", + "EventName": "PM_LSU_FLUSH_LHS", + "BriefDescription": "Effective Address alias flush : no EA match but Real Address match. If the data has not yet been returned for this load, the instruction will just be rejected, but if it has returned data, it will be flushed" + }, + {, + "EventCode": "0x3F150", + "EventName": "PM_MRK_ST_DRAIN_TO_L2DISP_CYC", + "BriefDescription": "cycles to drain st from core to L2" + }, + {, + "EventCode": "0x168A4", + "EventName": "PM_L3_MISS", + "BriefDescription": "L3 Misses (L2 miss also missing L3, including data/instrn/xlate)" + }, + {, + "EventCode": "0xF080", + "EventName": "PM_LSU_STCX_FAIL", + "BriefDescription": "" + }, + {, + "EventCode": "0x30038", + "EventName": "PM_CMPLU_STALL_DMISS_LMEM", + "BriefDescription": "Completion stall due to cache miss that resolves in local memory" + }, + {, + "EventCode": "0x28A4", + "EventName": "PM_MRK_TEND_FAIL", + "BriefDescription": "Nested or not nested tend failed for a marked tend instruction" + }, + {, + "EventCode": "0x100FC", + "EventName": "PM_LD_REF_L1", + "BriefDescription": "All L1 D cache load references counted at finish, gated by reject" + }, + {, + "EventCode": "0xC0A0", + "EventName": "PM_LSU0_FALSE_LHS", + "BriefDescription": "False LHS match detected" + }, + {, + "EventCode": "0x468A8", + "EventName": "PM_SN_MISS", + "BriefDescription": "Any port snooper L3 miss or collision. Up to 4 can happen in a cycle but we only count 1" + }, + {, + "EventCode": "0x36888", + "EventName": "PM_L2_SYS_GUESS_WRONG", + "BriefDescription": "L2 guess system (VGS or RNS) and guess was not correct (ie data ^beyond-group)" + }, + {, + "EventCode": "0x2080", + "EventName": "PM_EE_OFF_EXT_INT", + "BriefDescription": "CyclesMSR[EE] is off and external interrupts are active" + }, + {, + "EventCode": "0xE8B8", + "EventName": "PM_LS3_TM_DISALLOW", + "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it" + }, + {, + "EventCode": "0x2688E", + "EventName": "PM_TM_FAV_CAUSED_FAIL", + "BriefDescription": "TM Load (fav) caused another thread to fail" + }, + {, + "EventCode": "0x16090", + "EventName": "PM_SN0_BUSY", + "BriefDescription": "SN mach 0 Busy. Used by PMU to sample ave SN lifetime (mach0 used as sample point)" + }, + {, + "EventCode": "0x360AE", + "EventName": "PM_L3_P0_CO_RTY", + "BriefDescription": "L3 CO received retry port 0 (memory only), every retry counted" + }, + {, + "EventCode": "0x168A8", + "EventName": "PM_L3_WI_USAGE", + "BriefDescription": "Lifetime, sample of Write Inject machine 0 valid" + }, + {, + "EventCode": "0x468A2", + "EventName": "PM_L3_LAT_CI_MISS", + "BriefDescription": "L3 Lateral Castins Miss" + }, + {, + "EventCode": "0x4090", + "EventName": "PM_IC_PREF_CANCEL_PAGE", + "BriefDescription": "Prefetch Canceled due to page boundary" + }, + {, + "EventCode": "0xF09C", + "EventName": "PM_SLB_TABLEWALK_CYC", + "BriefDescription": "Cycles when a tablewalk is pending on this thread on the SLB table" + }, + {, + "EventCode": "0x460AA", + "EventName": "PM_L3_P0_CO_L31", + "BriefDescription": "L3 CO to L3.1 (LCO) port 0 with or without data" + }, + {, + "EventCode": "0x2880", + "EventName": "PM_FLUSH_DISP", + "BriefDescription": "Dispatch flush" + }, + {, + "EventCode": "0x168AE", + "EventName": "PM_L3_P1_PF_RTY", + "BriefDescription": "L3 PF received retry port 1, every retry counted" + }, + {, + "EventCode": "0x46082", + "EventName": "PM_L2_ST_DISP", + "BriefDescription": "All successful D-side store dispatches for this thread " + }, + {, + "EventCode": "0x4609E", + "EventName": "PM_L2_INST_MISS", + "BriefDescription": "All successful I-side dispatches that were an L2 miss for this thread (excludes i_l2mru_tch reqs)" + }, + {, + "EventCode": "0xE084", + "EventName": "PM_LS0_ERAT_MISS_PREF", + "BriefDescription": "LS0 Erat miss due to prefetch" + }, + {, + "EventCode": "0x409C", + "EventName": "PM_BR_PRED", + "BriefDescription": "Conditional Branch Executed in which the HW predicted the Direction or Target. Includes taken and not taken and is counted at execution time" + }, + {, + "EventCode": "0x2D144", + "EventName": "PM_MRK_DATA_FROM_L31_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x360A4", + "EventName": "PM_L3_CO_LCO", + "BriefDescription": "Total L3 COs occurred on LCO L3.1 (good cresp, may end up in mem on a retry)" + }, + {, + "EventCode": "0x4890", + "EventName": "PM_IC_PREF_CANCEL_HIT", + "BriefDescription": "Prefetch Canceled due to icache hit" + }, + {, + "EventCode": "0x268A8", + "EventName": "PM_RD_HIT_PF", + "BriefDescription": "RD machine hit L3 PF machine" + }, + {, + "EventCode": "0x16880", + "EventName": "PM_L2_ST", + "BriefDescription": "All successful D-side store dispatches for this thread (L2 miss + L2 hits)" + }, + {, + "EventCode": "0x4098", + "EventName": "PM_IC_DEMAND_L2_BHT_REDIRECT", + "BriefDescription": "L2 I cache demand request due to BHT redirect, branch redirect ( 2 bubbles 3 cycles)" + }, + {, + "EventCode": "0xD0B4", + "EventName": "PM_LSU0_SRQ_S0_VALID_CYC", + "BriefDescription": "Slot 0 of SRQ valid" + }, + {, + "EventCode": "0x160AA", + "EventName": "PM_L3_P0_LCO_NO_DATA", + "BriefDescription": "Dataless L3 LCO sent port 0" + }, + {, + "EventCode": "0x208C", + "EventName": "PM_CLB_HELD", + "BriefDescription": "CLB (control logic block - indicates quadword fetch block) Hold: Any Reason" + }, + {, + "EventCode": "0xF88C", + "EventName": "PM_LSU3_STORE_REJECT", + "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met" + }, + {, + "EventCode": "0x200F2", + "EventName": "PM_INST_DISP", + "BriefDescription": "# PPC Dispatched" + }, + {, + "EventCode": "0x4E05E", + "EventName": "PM_TM_OUTER_TBEGIN_DISP", + "BriefDescription": "Number of outer tbegin instructions dispatched. The dispatch unit determines whether the tbegin instruction is outer or nested. This is a speculative count, which includes flushed instructions" + }, + {, + "EventCode": "0x2D018", + "EventName": "PM_CMPLU_STALL_EXEC_UNIT", + "BriefDescription": "Completion stall due to execution units (FXU/VSU/CRU)" + }, + {, + "EventCode": "0x20B0", + "EventName": "PM_LSU_FLUSH_NEXT", + "BriefDescription": "LSU flush next reported at flush time. Sometimes these also come with an exception" + }, + {, + "EventCode": "0x3880", + "EventName": "PM_ISU2_ISS_HOLD_ALL", + "BriefDescription": "All ISU rejects" + }, + {, + "EventCode": "0x46882", + "EventName": "PM_L2_ST_HIT", + "BriefDescription": "All successful D-side store dispatches for this thread that were L2 hits" + }, + {, + "EventCode": "0x360A8", + "EventName": "PM_L3_CO", + "BriefDescription": "L3 castout occurring (does not include casthrough or log writes (cinj/dmaw))" + }, + {, + "EventCode": "0x368A4", + "EventName": "PM_L3_CINJ", + "BriefDescription": "L3 castin of cache inject" + }, + {, + "EventCode": "0xC890", + "EventName": "PM_LSU_NCST", + "BriefDescription": "Asserts when a i=1 store op is sent to the nest. No record of issue pipe (LS0/LS1) is maintained so this is for both pipes. Probably don't need separate LS0 and LS1" + }, + {, + "EventCode": "0xD880", + "EventName": "PM_LSU1_SET_MPRED", + "BriefDescription": "Set prediction(set-p) miss. The entry was not found in the Set prediction table" + }, + {, + "EventCode": "0xD0B8", + "EventName": "PM_LSU_LMQ_FULL_CYC", + "BriefDescription": "Counts the number of cycles the LMQ is full" + }, + {, + "EventCode": "0x168B2", + "EventName": "PM_L3_GRP_GUESS_CORRECT", + "BriefDescription": "Initial scope=group (GS or NNS) and data from same group (near) (pred successful)" + }, + {, + "EventCode": "0x48A4", + "EventName": "PM_STOP_FETCH_PENDING_CYC", + "BriefDescription": "Fetching is stopped due to an incoming instruction that will result in a flush" + }, + {, + "EventCode": "0x36884", + "EventName": "PM_L2_RCST_DISP_FAIL_ADDR", + "BriefDescription": "All D-side store dispatch attempts for this thread that failed due to address collision with RC/CO/SN/SQ" + }, + {, + "EventCode": "0x260AC", + "EventName": "PM_L3_PF_USAGE", + "BriefDescription": "Rotating sample of 32 PF actives" + } +] diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json new file mode 100644 index 000000000000..bc2db636dabf --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json @@ -0,0 +1,552 @@ +[ + {, + "EventCode": "0x4D04C", + "EventName": "PM_DFU_BUSY", + "BriefDescription": "Cycles in which all 4 Decimal Floating Point units are busy. The DFU is running at capacity" + }, + {, + "EventCode": "0x100F6", + "EventName": "PM_IERAT_RELOAD", + "BriefDescription": "Number of I-ERAT reloads" + }, + {, + "EventCode": "0x201E2", + "EventName": "PM_MRK_LD_MISS_L1", + "BriefDescription": "Marked DL1 Demand Miss counted at exec time. Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load." + }, + {, + "EventCode": "0x40010", + "EventName": "PM_PMC3_OVERFLOW", + "BriefDescription": "Overflow from counter 3" + }, + {, + "EventCode": "0x1005A", + "EventName": "PM_CMPLU_STALL_DFLONG", + "BriefDescription": "Finish stall because the NTF instruction was a multi-cycle instruction issued to the Decimal Floating Point execution pipe and waiting to finish. Includes decimal floating point instructions + 128 bit binary floating point instructions. Qualified by multicycle" + }, + {, + "EventCode": "0x4D140", + "EventName": "PM_MRK_DATA_FROM_ON_CHIP_CACHE", + "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x3F14C", + "EventName": "PM_MRK_DPTEG_FROM_DL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on a different Node or Group (Distant) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x1E040", + "EventName": "PM_DPTEG_FROM_L2_NO_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x24052", + "EventName": "PM_FXU_IDLE", + "BriefDescription": "Cycles in which FXU0, FXU1, FXU2, and FXU3 are all idle" + }, + {, + "EventCode": "0x1E054", + "EventName": "PM_CMPLU_STALL", + "BriefDescription": "Nothing completed and ICT not empty" + }, + {, + "EventCode": "0x2", + "EventName": "PM_INST_CMPL", + "BriefDescription": "Number of PowerPC Instructions that completed." + }, + {, + "EventCode": "0x3D058", + "EventName": "PM_VSU_DP_FSQRT_FDIV", + "BriefDescription": "vector versions of fdiv,fsqrt" + }, + {, + "EventCode": "0x10006", + "EventName": "PM_DISP_HELD", + "BriefDescription": "Dispatch Held" + }, + {, + "EventCode": "0x3D154", + "EventName": "PM_MRK_DERAT_MISS_16M", + "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16M" + }, + {, + "EventCode": "0x200F8", + "EventName": "PM_EXT_INT", + "BriefDescription": "external interrupt" + }, + {, + "EventCode": "0x20008", + "EventName": "PM_ICT_EMPTY_CYC", + "BriefDescription": "Cycles in which the ICT is completely empty. No itags are assigned to any thread" + }, + {, + "EventCode": "0x4F146", + "EventName": "PM_MRK_DPTEG_FROM_L21_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L2 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x10056", + "EventName": "PM_MEM_READ", + "BriefDescription": "Reads from Memory from this thread (includes data/inst/xlate/l1prefetch/inst prefetch). Includes L4" + }, + {, + "EventCode": "0x3C04C", + "EventName": "PM_DATA_FROM_DL4", + "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on a different Node or Group (Distant) due to a demand load" + }, + {, + "EventCode": "0x4E046", + "EventName": "PM_DPTEG_FROM_L21_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L2 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2E016", + "EventName": "PM_NTC_ISSUE_HELD_ARB", + "BriefDescription": "The NTC instruction is being held at dispatch because it lost arbitration onto the issue pipe to another instruction (from the same thread or a different thread)" + }, + {, + "EventCode": "0x15156", + "EventName": "PM_SYNC_MRK_FX_DIVIDE", + "BriefDescription": "Marked fixed point divide that can cause a synchronous interrupt" + }, + {, + "EventCode": "0x1C056", + "EventName": "PM_DERAT_MISS_4K", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 4K" + }, + {, + "EventCode": "0x2F142", + "EventName": "PM_MRK_DPTEG_FROM_L3_MEPF", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without dispatch conflicts hit on Mepf state. due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x10024", + "EventName": "PM_PMC5_OVERFLOW", + "BriefDescription": "Overflow from counter 5" + }, + {, + "EventCode": "0x2C018", + "EventName": "PM_CMPLU_STALL_DMISS_L21_L31", + "BriefDescription": "Completion stall by Dcache miss which resolved on chip ( excluding local L2/L3)" + }, + {, + "EventCode": "0x4006A", + "EventName": "PM_IERAT_RELOAD_16M", + "BriefDescription": "IERAT Reloaded (Miss) for a 16M page" + }, + {, + "EventCode": "0x4E010", + "EventName": "PM_ICT_NOSLOT_IC_L3MISS", + "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from beyond the local L3. The source could be local/remote/distant memory or another core's cache" + }, + {, + "EventCode": "0x4D01C", + "EventName": "PM_ICT_NOSLOT_DISP_HELD_SYNC", + "BriefDescription": "Dispatch held due to a synchronizing instruction at dispatch" + }, + {, + "EventCode": "0x2D01A", + "EventName": "PM_ICT_NOSLOT_IC_MISS", + "BriefDescription": "Ict empty for this thread due to Icache Miss" + }, + {, + "EventCode": "0x3D152", + "EventName": "PM_MRK_DERAT_MISS_1G", + "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 1G. Implies radix translation" + }, + {, + "EventCode": "0x4F14A", + "EventName": "PM_MRK_DPTEG_FROM_OFF_CHIP_CACHE", + "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x30058", + "EventName": "PM_TLBIE_FIN", + "BriefDescription": "tlbie finished" + }, + {, + "EventCode": "0x100F8", + "EventName": "PM_ICT_NOSLOT_CYC", + "BriefDescription": "Number of cycles the ICT has no itags assigned to this thread" + }, + {, + "EventCode": "0x3E042", + "EventName": "PM_DPTEG_FROM_L3_DISP_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x1F140", + "EventName": "PM_MRK_DPTEG_FROM_L2_NO_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2C05A", + "EventName": "PM_DERAT_MISS_1G", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 1G. Implies radix translation" + }, + {, + "EventCode": "0x1F058", + "EventName": "PM_RADIX_PWC_L2_PTE_FROM_L2", + "BriefDescription": "A Page Table Entry was reloaded to a level 2 page walk cache from the core's L2 data cache. This implies that level 3 and level 4 PWC accesses were not necessary for this translation" + }, + {, + "EventCode": "0x1D14A", + "EventName": "PM_MRK_DATA_FROM_RL2L3_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load" + }, + {, + "EventCode": "0x10050", + "EventName": "PM_CHIP_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x45058", + "EventName": "PM_IC_MISS_CMPL", + "BriefDescription": "Non-speculative icache miss, counted at completion" + }, + {, + "EventCode": "0x2D150", + "EventName": "PM_MRK_DERAT_MISS_4K", + "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 4K" + }, + {, + "EventCode": "0x34058", + "EventName": "PM_ICT_NOSLOT_BR_MPRED_ICMISS", + "BriefDescription": "Ict empty for this thread due to Icache Miss and branch mispred" + }, + {, + "EventCode": "0x10022", + "EventName": "PM_PMC2_SAVED", + "BriefDescription": "PMC2 Rewind Value saved" + }, + {, + "EventCode": "0x2000A", + "EventName": "PM_HV_CYC", + "BriefDescription": "Cycles in which msr_hv is high. Note that this event does not take msr_pr into consideration" + }, + {, + "EventCode": "0x1F144", + "EventName": "PM_MRK_DPTEG_FROM_L3_NO_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x300FC", + "EventName": "PM_DTLB_MISS", + "BriefDescription": "Data PTEG reload" + }, + {, + "EventCode": "0x2D152", + "EventName": "PM_MRK_DERAT_MISS_2M", + "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation" + }, + {, + "EventCode": "0x2C046", + "EventName": "PM_DATA_FROM_RL2L3_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a demand load" + }, + {, + "EventCode": "0x20052", + "EventName": "PM_GRP_PUMP_MPRED", + "BriefDescription": "Final Pump Scope (Group) ended up either larger or smaller than Initial Pump Scope for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x3F05A", + "EventName": "PM_RADIX_PWC_L2_PDE_FROM_L3", + "BriefDescription": "A Page Directory Entry was reloaded to a level 2 page walk cache from the core's L3 data cache" + }, + {, + "EventCode": "0x1E04A", + "EventName": "PM_DPTEG_FROM_RL2L3_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x10064", + "EventName": "PM_ICT_NOSLOT_DISP_HELD_TBEGIN", + "BriefDescription": "the NTC instruction is being held at dispatch because it is a tbegin instruction and there is an older tbegin in the pipeline that must complete before the younger tbegin can dispatch" + }, + {, + "EventCode": "0x2E046", + "EventName": "PM_DPTEG_FROM_RL2L3_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4F14C", + "EventName": "PM_MRK_DPTEG_FROM_DMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group (Distant) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2E042", + "EventName": "PM_DPTEG_FROM_L3_MEPF", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without dispatch conflicts hit on Mepf state. due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2D012", + "EventName": "PM_CMPLU_STALL_DFU", + "BriefDescription": "Finish stall because the NTF instruction was issued to the Decimal Floating Point execution pipe and waiting to finish. Includes decimal floating point instructions + 128 bit binary floating point instructions. Not qualified by multicycle" + }, + {, + "EventCode": "0x4C04C", + "EventName": "PM_DATA_FROM_DMEM", + "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group (Distant) due to a demand load" + }, + {, + "EventCode": "0x30022", + "EventName": "PM_PMC4_SAVED", + "BriefDescription": "PMC4 Rewind Value saved (matched condition)" + }, + {, + "EventCode": "0x200F4", + "EventName": "PM_RUN_CYC", + "BriefDescription": "Run_cycles" + }, + {, + "EventCode": "0x400F2", + "EventName": "PM_1PLUS_PPC_DISP", + "BriefDescription": "Cycles at least one Instr Dispatched" + }, + {, + "EventCode": "0x3D148", + "EventName": "PM_MRK_DATA_FROM_L21_MOD_CYC", + "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's L2 on the same chip due to a marked load" + }, + {, + "EventCode": "0x2F146", + "EventName": "PM_MRK_DPTEG_FROM_RL2L3_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4E01A", + "EventName": "PM_ICT_NOSLOT_DISP_HELD", + "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any reason" + }, + {, + "EventCode": "0x401EC", + "EventName": "PM_THRESH_EXC_2048", + "BriefDescription": "Threshold counter exceeded a value of 2048" + }, + {, + "EventCode": "0x35150", + "EventName": "PM_MRK_DATA_FROM_RL2L3_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load" + }, + {, + "EventCode": "0x3E052", + "EventName": "PM_ICT_NOSLOT_IC_L3", + "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from the local L3" + }, + {, + "EventCode": "0x2405A", + "EventName": "PM_NTC_FIN", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline (NTC) finishes. This event is used to account for cycles in which work is being completed in the CPI stack" + }, + {, + "EventCode": "0x40052", + "EventName": "PM_PUMP_MPRED", + "BriefDescription": "Pump misprediction. Counts across all types of pumps for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x30056", + "EventName": "PM_TM_ABORTS", + "BriefDescription": "Number of TM transactions aborted" + }, + {, + "EventCode": "0x2404C", + "EventName": "PM_INST_FROM_MEMORY", + "BriefDescription": "The processor's Instruction cache was reloaded from a memory location including L4 from local remote or distant due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x1C05A", + "EventName": "PM_DERAT_MISS_2M", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation" + }, + {, + "EventCode": "0x30024", + "EventName": "PM_PMC6_OVERFLOW", + "BriefDescription": "Overflow from counter 6" + }, + {, + "EventCode": "0x10068", + "EventName": "PM_BRU_FIN", + "BriefDescription": "Branch Instruction Finished" + }, + {, + "EventCode": "0x30020", + "EventName": "PM_PMC2_REWIND", + "BriefDescription": "PMC2 Rewind Event (did not match condition)" + }, + {, + "EventCode": "0x40064", + "EventName": "PM_DUMMY2_REMOVE_ME", + "BriefDescription": "Space holder for LS_PC_RELOAD_RA" + }, + {, + "EventCode": "0x3F148", + "EventName": "PM_MRK_DPTEG_FROM_DL2L3_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4D01E", + "EventName": "PM_ICT_NOSLOT_BR_MPRED", + "BriefDescription": "Ict empty for this thread due to branch mispred" + }, + {, + "EventCode": "0x3405E", + "EventName": "PM_IFETCH_THROTTLE", + "BriefDescription": "Cycles in which Instruction fetch throttle was active." + }, + {, + "EventCode": "0x1F148", + "EventName": "PM_MRK_DPTEG_FROM_ON_CHIP_CACHE", + "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on the same chip due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x3E046", + "EventName": "PM_DPTEG_FROM_L21_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L2 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2F144", + "EventName": "PM_MRK_DPTEG_FROM_L31_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4C15C", + "EventName": "PM_MRK_DERAT_MISS_16G", + "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16G" + }, + {, + "EventCode": "0x14052", + "EventName": "PM_INST_GRP_PUMP_MPRED_RTY", + "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for an instruction fetch" + }, + {, + "EventCode": "0xD0A8", + "EventName": "PM_DSLB_MISS", + "BriefDescription": "Data SLB Miss - Total of all segment sizes" + }, + {, + "EventCode": "0x4C058", + "EventName": "PM_MEM_CO", + "BriefDescription": "Memory castouts from this thread" + }, + {, + "EventCode": "0x40004", + "EventName": "PM_FXU_FIN", + "BriefDescription": "The fixed point unit Unit finished an instruction. Instructions that finish may not necessary complete." + }, + {, + "EventCode": "0x2C054", + "EventName": "PM_DERAT_MISS_64K", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K" + }, + {, + "EventCode": "0x10018", + "EventName": "PM_IC_DEMAND_CYC", + "BriefDescription": "Icache miss demand cycles" + }, + {, + "EventCode": "0x3C054", + "EventName": "PM_DERAT_MISS_16M", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16M" + }, + {, + "EventCode": "0x2D14E", + "EventName": "PM_MRK_DATA_FROM_L21_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L2 on the same chip due to a marked load" + }, + {, + "EventCode": "0x3405C", + "EventName": "PM_CMPLU_STALL_DPLONG", + "BriefDescription": "Finish stall because the NTF instruction was a scalar multi-cycle instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Qualified by NOT vector AND multicycle" + }, + {, + "EventCode": "0x4D052", + "EventName": "PM_2FLOP_CMPL", + "BriefDescription": "DP vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres ,fsqrte, fneg " + }, + {, + "EventCode": "0x1F142", + "EventName": "PM_MRK_DPTEG_FROM_L2", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x40062", + "EventName": "PM_DUMMY1_REMOVE_ME", + "BriefDescription": "Space holder for L2_PC_PM_MK_LDST_SCOPE_PRED_STATUS" + }, + {, + "EventCode": "0x4C012", + "EventName": "PM_CMPLU_STALL_ERAT_MISS", + "BriefDescription": "Finish stall because the NTF instruction was a load or store that suffered a translation miss" + }, + {, + "EventCode": "0x4D050", + "EventName": "PM_VSU_NON_FLOP_CMPL", + "BriefDescription": "Non FLOP operation completed" + }, + {, + "EventCode": "0x2E012", + "EventName": "PM_TM_TX_PASS_RUN_CYC", + "BriefDescription": "cycles spent in successful transactions" + }, + {, + "EventCode": "0x4D04E", + "EventName": "PM_VSU_FSQRT_FDIV", + "BriefDescription": "four flops operation (fdiv,fsqrt) Scalar Instructions only" + }, + {, + "EventCode": "0x4C120", + "EventName": "PM_MRK_DATA_FROM_L2_MEPF", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state. due to a marked load" + }, + {, + "EventCode": "0x10062", + "EventName": "PM_LD_L3MISS_PEND_CYC", + "BriefDescription": "Cycles L3 miss was pending for this thread" + }, + {, + "EventCode": "0x2F14C", + "EventName": "PM_MRK_DPTEG_FROM_MEMORY", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a memory location including L4 from local remote or distant due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x14050", + "EventName": "PM_INST_CHIP_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for an instruction fetch" + }, + {, + "EventCode": "0x2000E", + "EventName": "PM_FXU_BUSY", + "BriefDescription": "Cycles in which all 4 FXUs are busy. The FXU is running at capacity" + }, + {, + "EventCode": "0x20066", + "EventName": "PM_TLB_MISS", + "BriefDescription": "TLB Miss (I + D)" + }, + {, + "EventCode": "0x10054", + "EventName": "PM_PUMP_CPRED", + "BriefDescription": "Pump prediction correct. Counts across all types of pumps for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x4D124", + "EventName": "PM_MRK_DATA_FROM_L31_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x400F8", + "EventName": "PM_FLUSH", + "BriefDescription": "Flush (any type)" + }, + {, + "EventCode": "0x30004", + "EventName": "PM_CMPLU_STALL_EMQ_FULL", + "BriefDescription": "Finish stall because the next to finish instruction suffered an ERAT miss and the EMQ was full" + }, + {, + "EventCode": "0x1D154", + "EventName": "PM_MRK_DATA_FROM_L21_SHR_CYC", + "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's L2 on the same chip due to a marked load" + } +] diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json new file mode 100644 index 000000000000..3ef8a10aac86 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json @@ -0,0 +1,122 @@ +[ + {, + "EventCode": "0x20036", + "EventName": "PM_BR_2PATH", + "BriefDescription": "Branches that are not strongly biased" + }, + {, + "EventCode": "0x40056", + "EventName": "PM_MEM_LOC_THRESH_LSU_HIGH", + "BriefDescription": "Local memory above threshold for LSU medium" + }, + {, + "EventCode": "0x2C056", + "EventName": "PM_DTLB_MISS_4K", + "BriefDescription": "Data TLB Miss page size 4k" + }, + {, + "EventCode": "0x40118", + "EventName": "PM_MRK_DCACHE_RELOAD_INTV", + "BriefDescription": "Combined Intervention event" + }, + {, + "EventCode": "0x4F148", + "EventName": "PM_MRK_DPTEG_FROM_DL2L3_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x301E8", + "EventName": "PM_THRESH_EXC_64", + "BriefDescription": "Threshold counter exceeded a value of 64" + }, + {, + "EventCode": "0x4E04E", + "EventName": "PM_DPTEG_FROM_L3MISS", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x40050", + "EventName": "PM_SYS_PUMP_MPRED_RTY", + "BriefDescription": "Final Pump Scope (system) ended up larger than Initial Pump Scope (Chip/Group) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x1F14E", + "EventName": "PM_MRK_DPTEG_FROM_L2MISS", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4D018", + "EventName": "PM_CMPLU_STALL_BRU", + "BriefDescription": "Completion stall due to a Branch Unit" + }, + {, + "EventCode": "0x45052", + "EventName": "PM_4FLOP_CMPL", + "BriefDescription": "4 FLOP instruction completed" + }, + {, + "EventCode": "0x3D142", + "EventName": "PM_MRK_DATA_FROM_LMEM", + "BriefDescription": "The processor's data cache was reloaded from the local chip's Memory due to a marked load" + }, + {, + "EventCode": "0x4C01E", + "EventName": "PM_CMPLU_STALL_CRYPTO", + "BriefDescription": "Finish stall because the NTF instruction was routed to the crypto execution pipe and was waiting to finish" + }, + {, + "EventCode": "0x3000C", + "EventName": "PM_FREQ_DOWN", + "BriefDescription": "Power Management: Below Threshold B" + }, + {, + "EventCode": "0x4D128", + "EventName": "PM_MRK_DATA_FROM_LMEM_CYC", + "BriefDescription": "Duration in cycles to reload from the local chip's Memory due to a marked load" + }, + {, + "EventCode": "0x4D054", + "EventName": "PM_8FLOP_CMPL", + "BriefDescription": "8 FLOP instruction completed" + }, + {, + "EventCode": "0x10026", + "EventName": "PM_TABLEWALK_CYC", + "BriefDescription": "Cycles when an instruction tablewalk is active" + }, + {, + "EventCode": "0x2C012", + "EventName": "PM_CMPLU_STALL_DCACHE_MISS", + "BriefDescription": "Finish stall because the NTF instruction was a load that missed the L1 and was waiting for the data to return from the nest" + }, + {, + "EventCode": "0x2E04C", + "EventName": "PM_DPTEG_FROM_MEMORY", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a memory location including L4 from local remote or distant due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x3F142", + "EventName": "PM_MRK_DPTEG_FROM_L3_DISP_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4F142", + "EventName": "PM_MRK_DPTEG_FROM_L3", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x10060", + "EventName": "PM_TM_TRANS_RUN_CYC", + "BriefDescription": "run cycles in transactional state" + }, + {, + "EventCode": "0x1E04C", + "EventName": "PM_DPTEG_FROM_LL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x45050", + "EventName": "PM_1FLOP_CMPL", + "BriefDescription": "one flop (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg) operation completed" + } +] diff --git a/tools/perf/pmu-events/arch/powerpc/power9/translation.json b/tools/perf/pmu-events/arch/powerpc/power9/translation.json new file mode 100644 index 000000000000..8c0f12024afa --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/translation.json @@ -0,0 +1,232 @@ +[ + {, + "EventCode": "0x1E", + "EventName": "PM_CYC", + "BriefDescription": "Processor cycles" + }, + {, + "EventCode": "0x30010", + "EventName": "PM_PMC2_OVERFLOW", + "BriefDescription": "Overflow from counter 2" + }, + {, + "EventCode": "0x3C046", + "EventName": "PM_DATA_FROM_L21_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L2 on the same chip due to a demand load" + }, + {, + "EventCode": "0x4D05C", + "EventName": "PM_DP_QP_FLOP_CMPL", + "BriefDescription": "Double-Precion or Quad-Precision instruction completed" + }, + {, + "EventCode": "0x4E04C", + "EventName": "PM_DPTEG_FROM_DMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group (Distant) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x20016", + "EventName": "PM_ST_FIN", + "BriefDescription": "Store finish count. Includes speculative activity" + }, + {, + "EventCode": "0x44042", + "EventName": "PM_INST_FROM_L3", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x1504A", + "EventName": "PM_IPTEG_FROM_RL2L3_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a instruction side request" + }, + {, + "EventCode": "0x40132", + "EventName": "PM_MRK_LSU_FIN", + "BriefDescription": "lsu marked instr PPC finish" + }, + {, + "EventCode": "0x3C05C", + "EventName": "PM_CMPLU_STALL_VFXU", + "BriefDescription": "Finish stall due to a vector fixed point instruction in the execution pipeline. These instructions get routed to the ALU, ALU2, and DIV pipes" + }, + {, + "EventCode": "0x30066", + "EventName": "PM_LSU_FIN", + "BriefDescription": "LSU Finished a PPC instruction (up to 4 per cycle)" + }, + {, + "EventCode": "0x2011C", + "EventName": "PM_MRK_NTC_CYC", + "BriefDescription": "Cycles during which the marked instruction is next to complete (completion is held up because the marked instruction hasn't completed yet)" + }, + {, + "EventCode": "0x3E048", + "EventName": "PM_DPTEG_FROM_DL2L3_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2E018", + "EventName": "PM_CMPLU_STALL_VFXLONG", + "BriefDescription": "Completion stall due to a long latency vector fixed point instruction (division, square root)" + }, + {, + "EventCode": "0x1C04E", + "EventName": "PM_DATA_FROM_L2MISS_MOD", + "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L2 due to a demand load" + }, + {, + "EventCode": "0x15048", + "EventName": "PM_IPTEG_FROM_ON_CHIP_CACHE", + "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on the same chip due to a instruction side request" + }, + {, + "EventCode": "0x34046", + "EventName": "PM_INST_FROM_L21_SHR", + "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another core's L2 on the same chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x1E058", + "EventName": "PM_STCX_FAIL", + "BriefDescription": "stcx failed" + }, + {, + "EventCode": "0x20112", + "EventName": "PM_MRK_NTF_FIN", + "BriefDescription": "Marked next to finish instruction finished" + }, + {, + "EventCode": "0x300F0", + "EventName": "PM_ST_MISS_L1", + "BriefDescription": "Store Missed L1" + }, + {, + "EventCode": "0x4C046", + "EventName": "PM_DATA_FROM_L21_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L2 on the same chip due to a demand load" + }, + {, + "EventCode": "0x2504A", + "EventName": "PM_IPTEG_FROM_RL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on the same Node or Group ( Remote) due to a instruction side request" + }, + {, + "EventCode": "0x2003E", + "EventName": "PM_LSU_LMQ_SRQ_EMPTY_CYC", + "BriefDescription": "Cycles in which the LSU is empty for all threads (lmq and srq are completely empty)" + }, + {, + "EventCode": "0x201E6", + "EventName": "PM_THRESH_EXC_32", + "BriefDescription": "Threshold counter exceeded a value of 32" + }, + {, + "EventCode": "0x4405C", + "EventName": "PM_CMPLU_STALL_VDP", + "BriefDescription": "Finish stall because the NTF instruction was a vector instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Not qualified multicycle. Qualified by vector" + }, + {, + "EventCode": "0x4D010", + "EventName": "PM_PMC1_SAVED", + "BriefDescription": "PMC1 Rewind Value saved" + }, + {, + "EventCode": "0x200FE", + "EventName": "PM_DATA_FROM_L2MISS", + "BriefDescription": "Demand LD - L2 Miss (not L2 hit)" + }, + {, + "EventCode": "0x2D14A", + "EventName": "PM_MRK_DATA_FROM_RL2L3_MOD_CYC", + "BriefDescription": "Duration in cycles to reload with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load" + }, + {, + "EventCode": "0x10028", + "EventName": "PM_STALL_END_ICT_EMPTY", + "BriefDescription": "The number a times the core transitioned from a stall to ICT-empty for this thread" + }, + {, + "EventCode": "0x2504C", + "EventName": "PM_IPTEG_FROM_MEMORY", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a memory location including L4 from local remote or distant due to a instruction side request" + }, + {, + "EventCode": "0x4504A", + "EventName": "PM_IPTEG_FROM_OFF_CHIP_CACHE", + "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a instruction side request" + }, + {, + "EventCode": "0x1404E", + "EventName": "PM_INST_FROM_L2MISS", + "BriefDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L2 due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x34042", + "EventName": "PM_INST_FROM_L3_DISP_CONFLICT", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 with dispatch conflict due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x4E048", + "EventName": "PM_DPTEG_FROM_DL2L3_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x200F0", + "EventName": "PM_ST_CMPL", + "BriefDescription": "Stores completed from S2Q (2nd-level store queue)." + }, + {, + "EventCode": "0x4E05C", + "EventName": "PM_LSU_REJECT_LHS", + "BriefDescription": "LSU Reject due to LHS (up to 4 per cycle)" + }, + {, + "EventCode": "0x14044", + "EventName": "PM_INST_FROM_L3_NO_CONFLICT", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 without conflict due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x3E04C", + "EventName": "PM_DPTEG_FROM_DL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on a different Node or Group (Distant) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x1F15E", + "EventName": "PM_MRK_PROBE_NOP_CMPL", + "BriefDescription": "Marked probeNops completed" + }, + {, + "EventCode": "0x20018", + "EventName": "PM_ST_FWD", + "BriefDescription": "Store forwards that finished" + }, + {, + "EventCode": "0x1D142", + "EventName": "PM_MRK_DATA_FROM_L31_ECO_SHR_CYC", + "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's ECO L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x24042", + "EventName": "PM_INST_FROM_L3_MEPF", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 without dispatch conflicts hit on Mepf state. due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x25046", + "EventName": "PM_IPTEG_FROM_RL2L3_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a instruction side request" + }, + {, + "EventCode": "0x3504A", + "EventName": "PM_IPTEG_FROM_RMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a instruction side request" + }, + {, + "EventCode": "0x3C05A", + "EventName": "PM_CMPLU_STALL_VDPLONG", + "BriefDescription": "Finish stall because the NTF instruction was a scalar multi-cycle instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Qualified by NOT vector AND multicycle" + }, + {, + "EventCode": "0x2E01C", + "EventName": "PM_CMPLU_STALL_TLBIE", + "BriefDescription": "Finish stall because the NTF instruction was a tlbie waiting for response from L2" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index d1a12e584c1b..4ea068366c3e 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -34,3 +34,4 @@ GenuineIntel-6-2C,v2,westmereep-dp,core GenuineIntel-6-2C,v2,westmereep-dp,core GenuineIntel-6-25,v2,westmereep-sp,core GenuineIntel-6-2F,v2,westmereex,core +GenuineIntel-6-55,v1,skylakex,core diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json new file mode 100644 index 000000000000..b5bc742b6fbc --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json @@ -0,0 +1,1672 @@ +[ + { + "EventCode": "0x24", + "UMask": "0x21", + "BriefDescription": "Demand Data Read miss L2, no rejects", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x22", + "BriefDescription": "RFO requests that miss L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x24", + "BriefDescription": "L2 cache misses when fetching instructions", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x27", + "BriefDescription": "Demand requests that miss L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_MISS", + "PublicDescription": "Demand requests that miss L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x38", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.PF_MISS", + "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x3f", + "BriefDescription": "All requests that miss L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.MISS", + "PublicDescription": "All requests that miss L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x41", + "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.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x42", + "BriefDescription": "RFO requests that hit L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x44", + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0xd8", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.PF_HIT", + "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0xe1", + "BriefDescription": "Demand Data Read requests", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0xe2", + "BriefDescription": "RFO requests to L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_RFO", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0xe4", + "BriefDescription": "L2 code requests", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts the total number of L2 code requests.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0xe7", + "BriefDescription": "Demand requests to L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "PublicDescription": "Demand requests to L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0xf8", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_PF", + "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0xff", + "BriefDescription": "All L2 requests", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.REFERENCES", + "PublicDescription": "All L2 requests.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x2E", + "UMask": "0x41", + "BriefDescription": "Core-originated cacheable demand requests missed L3", + "Counter": "0,1,2,3", + "EventName": "LONGEST_LAT_CACHE.MISS", + "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" + }, + { + "EventCode": "0x2E", + "UMask": "0x4f", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x48", + "UMask": "0x1", + "BriefDescription": "L1D miss outstandings duration in cycles", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x48", + "UMask": "0x1", + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "0,1,2,3", + "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 from any thread on physical core.", + "Counter": "0,1,2,3", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", + "AnyThread": "1", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x48", + "UMask": "0x2", + "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.", + "Counter": "0,1,2,3", + "EventName": "L1D_PEND_MISS.FB_FULL", + "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x51", + "UMask": "0x1", + "BriefDescription": "L1D data line replacements", + "Counter": "0,1,2,3", + "EventName": "L1D.REPLACEMENT", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x1", + "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", + "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.", + "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", + "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).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x1", + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", + "CounterMask": "6", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x2", + "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle. ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x2", + "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", + "CounterMask": "1", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x4", + "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding RFO (store) 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 (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x4", + "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "CounterMask": "1", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x8", + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions 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.", + "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.", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "UMask": "0x1", + "BriefDescription": "Demand Data Read requests sent to uncore", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "UMask": "0x2", + "BriefDescription": "Cacheable and noncachaeble code read requests", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "UMask": "0x4", + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "UMask": "0x8", + "BriefDescription": "Demand and prefetch data reads", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "UMask": "0x80", + "BriefDescription": "Any memory transaction that reached the SQ.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB2", + "UMask": "0x1", + "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", + "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select 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" + }, + { + "EventCode": "0xD0", + "UMask": "0x11", + "BriefDescription": "Retired load instructions that miss the STLB.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD0", + "UMask": "0x12", + "BriefDescription": "Retired store instructions that miss the STLB.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "SampleAfterValue": "100003", + "L1_Hit_Indication": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD0", + "UMask": "0x21", + "BriefDescription": "Retired load instructions with locked access.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD0", + "UMask": "0x41", + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD0", + "UMask": "0x42", + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "L1_Hit_Indication": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD0", + "UMask": "0x81", + "BriefDescription": "All retired load instructions.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD0", + "UMask": "0x82", + "BriefDescription": "All retired store instructions.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "SampleAfterValue": "2000003", + "L1_Hit_Indication": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "UMask": "0x1", + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "Data_LA": "1", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "UMask": "0x2", + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "PublicDescription": "Retired load instructions with L2 cache hits as data sources.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "UMask": "0x4", + "BriefDescription": "Retired load instructions with L3 cache hits as data sources", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L3_HIT", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. ", + "SampleAfterValue": "50021", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "UMask": "0x8", + "BriefDescription": "Retired load instructions missed L1 cache as data sources", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L1_MISS", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "UMask": "0x10", + "BriefDescription": "Retired load instructions missed L2 cache as data sources", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "PublicDescription": "Retired load instructions missed L2 cache as data sources.", + "SampleAfterValue": "50021", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "UMask": "0x20", + "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L3_MISS", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. ", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "UMask": "0x40", + "BriefDescription": "Retired load instructions which data sources were load 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_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. ", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD2", + "UMask": "0x1", + "BriefDescription": "Retired load instructions 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_L3_HIT_RETIRED.XSNP_MISS", + "SampleAfterValue": "20011", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD2", + "UMask": "0x2", + "BriefDescription": "Retired load instructions 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_L3_HIT_RETIRED.XSNP_HIT", + "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "SampleAfterValue": "20011", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD2", + "UMask": "0x4", + "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", + "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.", + "SampleAfterValue": "20011", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD2", + "UMask": "0x8", + "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", + "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD3", + "UMask": "0x1", + "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", + "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD3", + "UMask": "0x2", + "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from remote dram", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD3", + "UMask": "0x4", + "BriefDescription": "Retired load instructions whose data sources was remote HITM", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", + "PublicDescription": "Retired load instructions whose data sources was remote HITM.", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD3", + "UMask": "0x8", + "BriefDescription": "Retired load instructions whose data sources was forwarded from a remote cache", + "Data_LA": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", + "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD4", + "UMask": "0x4", + "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xF0", + "UMask": "0x40", + "BriefDescription": "L2 writebacks that access L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_TRANS.L2_WB", + "PublicDescription": "Counts L2 writebacks that access L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF1", + "UMask": "0x1f", + "BriefDescription": "L2 cache lines filling L2", + "Counter": "0,1,2,3", + "EventName": "L2_LINES_IN.ALL", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF2", + "UMask": "0x1", + "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", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF2", + "UMask": "0x2", + "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.", + "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", + "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.", + "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", + "Counter": "0,1,2,3", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF4", + "UMask": "0x10", + "BriefDescription": "Number of cache line split locks sent to uncore.", + "Counter": "0,1,2,3", + "EventName": "SQ_MISC.SPLIT_LOCK", + "PublicDescription": "Counts the number of cache line split locks sent to the uncore.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts demand data reads that 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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts demand data reads that hit in the L3.", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand data writes (RFOs) that 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.", + "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 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 ", + "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.", + "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": "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "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.", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand code reads 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.", + "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 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 ", + "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.", + "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": "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "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.", + "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.", + "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 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.", + "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 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 ", + "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.", + "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": "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "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.", + "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.", + "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 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.", + "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 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 ", + "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.", + "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": "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "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.", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0100 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "PF_L1D_AND_SW & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0400 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch data reads that have any response type.", + "MSRValue": "0x0000010490 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0490 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch data reads that hit in the L3.", + "MSRValue": "0x3f803c0490 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch RFOs that have any response type.", + "MSRValue": "0x0000010120 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0120 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch RFOs that hit in the L3.", + "MSRValue": "0x3f803c0120 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch data reads that have any response type.", + "MSRValue": "0x0000010491 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0491 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.", + "MSRValue": "0x3f803c0491 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.", + "MSRValue": "0x0000010122 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0122 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.", + "MSRValue": "0x3f803c0122 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json new file mode 100644 index 000000000000..1c09a328df36 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json @@ -0,0 +1,88 @@ +[ + { + "EventCode": "0xC7", + "UMask": "0x1", + "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired. Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC7", + "UMask": "0x2", + "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired. Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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. ", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "PublicDescription": "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC7", + "UMask": "0x40", + "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" + }, + { + "EventCode": "0xC7", + "UMask": "0x80", + "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" + }, + { + "EventCode": "0xCA", + "UMask": "0x1e", + "BriefDescription": "Cycles with any input/output SSE or FP assist", + "Counter": "0,1,2,3", + "EventName": "FP_ASSIST.ANY", + "CounterMask": "1", + "PublicDescription": "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json new file mode 100644 index 000000000000..40abc0852cd6 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json @@ -0,0 +1,482 @@ +[ + { + "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", + "CounterMask": "1", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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": "0x8", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", + "EventName": "IDQ.DSB_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts cycles during which uops are being 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", + "EventName": "IDQ.MS_DSB_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting 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 4 Uops", + "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.", + "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", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x20", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_MITE_UOPS", + "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x24", + "BriefDescription": "Cycles MITE is delivering 4 Uops", + "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).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x24", + "BriefDescription": "Cycles MITE is delivering any Uop", + "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).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x30", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "SampleAfterValue": "2000003", + "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", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x30", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x80", + "UMask": "0x4", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", + "Counter": "0,1,2,3", + "EventName": "ICACHE_16B.IFDATA_STALL", + "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x83", + "UMask": "0x1", + "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "Counter": "0,1,2,3", + "EventName": "ICACHE_64B.IFTAG_HIT", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x83", + "UMask": "0x2", + "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "Counter": "0,1,2,3", + "EventName": "ICACHE_64B.IFTAG_MISS", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x83", + "UMask": "0x4", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "Counter": "0,1,2,3", + "EventName": "ICACHE_64B.IFTAG_STALL", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x9C", + "UMask": "0x1", + "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.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" + }, + { + "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", + "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.", + "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", + "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.", + "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.", + "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.", + "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.", + "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.", + "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.", + "Counter": "0,1,2,3", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xAB", + "UMask": "0x2", + "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 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.", + "PEBS": "1", + "MSRValue": "0x11", + "Counter": "0,1,2,3", + "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" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "PEBS": "1", + "MSRValue": "0x12", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.L1I_MISS", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", + "PEBS": "1", + "MSRValue": "0x13", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired Instructions who experienced iTLB true miss.", + "PEBS": "1", + "MSRValue": "0x14", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", + "PEBS": "1", + "MSRValue": "0x15", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.STLB_MISS", + "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. ", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "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.", + "PEBS": "1", + "MSRValue": "0x400206", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "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.", + "PEBS": "1", + "MSRValue": "0x200206", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "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.", + "PEBS": "1", + "MSRValue": "0x400406", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "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.", + "PEBS": "1", + "MSRValue": "0x400806", + "Counter": "0,1,2,3", + "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" + }, + { + "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.", + "PEBS": "1", + "MSRValue": "0x401006", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "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.", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "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.", + "PEBS": "1", + "MSRValue": "0x402006", + "Counter": "0,1,2,3", + "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" + }, + { + "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.", + "PEBS": "1", + "MSRValue": "0x404006", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "PEBS": "1", + "MSRValue": "0x408006", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "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.", + "PEBS": "1", + "MSRValue": "0x410006", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "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.", + "PEBS": "1", + "MSRValue": "0x420006", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "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.", + "PEBS": "1", + "MSRValue": "0x100206", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", + "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.", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "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.", + "PEBS": "1", + "MSRValue": "0x300206", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/memory.json b/tools/perf/pmu-events/arch/x86/skylakex/memory.json new file mode 100644 index 000000000000..ca22a22c1abd --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/memory.json @@ -0,0 +1,1396 @@ +[ + { + "EventCode": "0x54", + "UMask": "0x1", + "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", + "Counter": "0,1,2,3", + "EventName": "TX_MEM.ABORT_CONFLICT", + "PublicDescription": "Number of times a TSX line had a cache conflict.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x54", + "UMask": "0x2", + "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.", + "Counter": "0,1,2,3", + "EventName": "TX_MEM.ABORT_CAPACITY", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x54", + "UMask": "0x4", + "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer", + "Counter": "0,1,2,3", + "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK", + "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x54", + "UMask": "0x8", + "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.", + "Counter": "0,1,2,3", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY", + "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x54", + "UMask": "0x10", + "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer", + "Counter": "0,1,2,3", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH", + "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x54", + "UMask": "0x20", + "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.", + "Counter": "0,1,2,3", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT", + "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x54", + "UMask": "0x40", + "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.", + "Counter": "0,1,2,3", + "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL", + "PublicDescription": "Number of times we could not allocate Lock Buffer.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5d", + "UMask": "0x1", + "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.", + "Counter": "0,1,2,3", + "EventName": "TX_EXEC.MISC1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5d", + "UMask": "0x2", + "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region", + "Counter": "0,1,2,3", + "EventName": "TX_EXEC.MISC2", + "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5d", + "UMask": "0x4", + "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded", + "Counter": "0,1,2,3", + "EventName": "TX_EXEC.MISC3", + "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5d", + "UMask": "0x8", + "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.", + "Counter": "0,1,2,3", + "EventName": "TX_EXEC.MISC4", + "PublicDescription": "RTM region detected inside HLE.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5d", + "UMask": "0x10", + "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region", + "Counter": "0,1,2,3", + "EventName": "TX_EXEC.MISC5", + "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x10", + "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x10", + "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.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", + "CounterMask": "1", + "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.", + "Counter": "0,1,2,3", + "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": "0xA3", + "UMask": "0x2", + "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", + "CounterMask": "2", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x6", + "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "CounterMask": "6", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "UMask": "0x10", + "BriefDescription": "Demand Data Read requests who miss L3 cache", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Demand Data Read requests who miss L3 cache.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC3", + "UMask": "0x2", + "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", + "Counter": "0,1,2,3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "Errata": "SKL089", + "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x1", + "BriefDescription": "Number of times an HLE execution started.", + "Counter": "0,1,2,3", + "EventName": "HLE_RETIRED.START", + "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x2", + "BriefDescription": "Number of times an HLE execution successfully committed", + "Counter": "0,1,2,3", + "EventName": "HLE_RETIRED.COMMIT", + "PublicDescription": "Number of times HLE commit succeeded.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x4", + "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", + "PublicDescription": "Number of times HLE abort was triggered.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x8", + "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).", + "Counter": "0,1,2,3", + "EventName": "HLE_RETIRED.ABORTED_MEM", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x10", + "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.", + "Counter": "0,1,2,3", + "EventName": "HLE_RETIRED.ABORTED_TIMER", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x20", + "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" + }, + { + "EventCode": "0xC8", + "UMask": "0x40", + "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type", + "Counter": "0,1,2,3", + "EventName": "HLE_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x80", + "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).", + "Counter": "0,1,2,3", + "EventName": "HLE_RETIRED.ABORTED_EVENTS", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x1", + "BriefDescription": "Number of times an RTM execution started.", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.START", + "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x2", + "BriefDescription": "Number of times an RTM execution successfully committed", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.COMMIT", + "PublicDescription": "Number of times RTM commit succeeded.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x4", + "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", + "PublicDescription": "Number of times RTM abort was triggered.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x8", + "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.ABORTED_MEM", + "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x10", + "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.ABORTED_TIMER", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x20", + "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", + "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x40", + "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x80", + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.ABORTED_EVENTS", + "PublicDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCD", + "UMask": "0x1", + "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.", + "PEBS": "2", + "MSRValue": "0x4", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "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.", + "TakenAlone": "1", + "SampleAfterValue": "100003", + "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.", + "PEBS": "2", + "MSRValue": "0x8", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "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.", + "TakenAlone": "1", + "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 16 cycles.", + "PEBS": "2", + "MSRValue": "0x10", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "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.", + "TakenAlone": "1", + "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 32 cycles.", + "PEBS": "2", + "MSRValue": "0x20", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "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.", + "TakenAlone": "1", + "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 64 cycles.", + "PEBS": "2", + "MSRValue": "0x40", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "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.", + "TakenAlone": "1", + "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 128 cycles.", + "PEBS": "2", + "MSRValue": "0x80", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "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.", + "TakenAlone": "1", + "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 256 cycles.", + "PEBS": "2", + "MSRValue": "0x100", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "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.", + "TakenAlone": "1", + "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 512 cycles.", + "PEBS": "2", + "MSRValue": "0x200", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "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.", + "TakenAlone": "1", + "SampleAfterValue": "101", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts demand data reads that miss in the L3.", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3.", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand code reads that miss in the L3.", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "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 miss in the L3.", + "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. ", + "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 miss the L3 and clean or shared data is transferred from remote cache.", + "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. ", + "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 miss the L3 and the modified data is transferred from remote cache.", + "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. ", + "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 miss the L3 and the data is returned from local or remote dram.", + "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. ", + "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 miss the L3 and the data is returned from remote dram.", + "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. ", + "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 miss the L3 and the data is returned from local dram.", + "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. ", + "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 miss in the L3.", + "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. ", + "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 miss the L3 and clean or shared data is transferred from remote cache.", + "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. ", + "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 miss the L3 and the modified data is transferred from remote cache.", + "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. ", + "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 miss the L3 and the data is returned from local or remote dram.", + "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. ", + "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 miss the L3 and the data is returned from remote dram.", + "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. ", + "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 miss the L3 and the data is returned from local dram.", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch data reads that miss in the L3.", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch RFOs that miss in the L3.", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3.", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3.", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "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 ", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/other.json b/tools/perf/pmu-events/arch/x86/skylakex/other.json new file mode 100644 index 000000000000..70243b0b0586 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/other.json @@ -0,0 +1,72 @@ +[ + { + "EventCode": "0x28", + "UMask": "0x7", + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the Non-AVX turbo schedule.", + "Counter": "0,1,2,3", + "EventName": "CORE_POWER.LVL0_TURBO_LICENSE", + "PublicDescription": "Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x28", + "UMask": "0x18", + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX2 turbo schedule.", + "Counter": "0,1,2,3", + "EventName": "CORE_POWER.LVL1_TURBO_LICENSE", + "PublicDescription": "Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x28", + "UMask": "0x20", + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.", + "Counter": "0,1,2,3", + "EventName": "CORE_POWER.LVL2_TURBO_LICENSE", + "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server michroarchtecture). This includes high current AVX 512-bit instructions.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x28", + "UMask": "0x40", + "BriefDescription": "Core cycles the core was throttled due to a pending power level request.", + "Counter": "0,1,2,3", + "EventName": "CORE_POWER.THROTTLE", + "PublicDescription": "Core cycles the out-of-order engine was throttled due to a pending power level request.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCB", + "UMask": "0x1", + "BriefDescription": "Number of hardware interrupts received by the processor.", + "Counter": "0,1,2,3", + "EventName": "HW_INTERRUPTS.RECEIVED", + "PublicDescription": "Counts the number of hardware interruptions received by the processor.", + "SampleAfterValue": "203", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xFE", + "UMask": "0x2", + "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly", + "Counter": "0,1,2,3", + "EventName": "IDI_MISC.WB_UPGRADE", + "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xFE", + "UMask": "0x4", + "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly", + "Counter": "0,1,2,3", + "EventName": "IDI_MISC.WB_DOWNGRADE", + "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json new file mode 100644 index 000000000000..0895d1e52a4a --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json @@ -0,0 +1,950 @@ +[ + { + "EventCode": "0x00", + "UMask": "0x1", + "BriefDescription": "Instructions retired from execution.", + "Counter": "Fixed counter 1", + "EventName": "INST_RETIRED.ANY", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "Fixed counter 1" + }, + { + "EventCode": "0x00", + "UMask": "0x2", + "BriefDescription": "Core cycles when the thread is not in halt state", + "Counter": "Fixed counter 2", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "Fixed counter 2" + }, + { + "EventCode": "0x00", + "UMask": "0x2", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "Counter": "Fixed counter 2", + "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "Fixed counter 2" + }, + { + "EventCode": "0x00", + "UMask": "0x3", + "BriefDescription": "Reference cycles when the core is not in halt state.", + "Counter": "Fixed counter 3", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "Fixed counter 3" + }, + { + "EventCode": "0x03", + "UMask": "0x2", + "BriefDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded .", + "Counter": "0,1,2,3", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:a. preceding store conflicts with the load (incomplete overlap),b. store forwarding is impossible due to u-arch limitations,c. preceding lock RMW operations are not forwarded,d. store has the no-forward bit set (uncacheable/page-split/masked stores),e. all-blocking stores are used (mostly, fences and port I/O), and others.The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x03", + "UMask": "0x8", + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use", + "Counter": "0,1,2,3", + "EventName": "LD_BLOCKS.NO_SR", + "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x07", + "UMask": "0x1", + "BriefDescription": "False dependencies in MOB due to partial compare on address.", + "Counter": "0,1,2,3", + "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", + "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0D", + "UMask": "0x1", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)", + "Counter": "0,1,2,3", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0D", + "UMask": "0x1", + "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).", + "Counter": "0,1,2,3", + "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0D", + "UMask": "0x80", + "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.", + "Counter": "0,1,2,3", + "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0E", + "UMask": "0x1", + "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", + "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).", + "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", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0E", + "UMask": "0x2", + "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 \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0E", + "UMask": "0x20", + "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.", + "Counter": "0,1,2,3", + "EventName": "UOPS_ISSUED.SLOW_LEA", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x14", + "UMask": "0x1", + "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "Counter": "0,1,2,3", + "EventName": "ARITH.DIVIDER_ACTIVE", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x0", + "BriefDescription": "Thread cycles when thread is not in halt state", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "PublicDescription": "This is an architectural event that 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. For this reason, this event may have a changing ratio with regards to wall clock time.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x0", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EdgeDetect": "1", + "EventCode": "0x3C", + "UMask": "0x0", + "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.RING0_TRANS", + "CounterMask": "1", + "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x1", + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", + "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.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_THREAD_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 the thread is unhalted.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "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.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", + "AnyThread": "1", + "SampleAfterValue": "2503", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x2", + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x2", + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "2503", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x4C", + "UMask": "0x1", + "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", + "Counter": "0,1,2,3", + "EventName": "LOAD_HIT_PRE.SW_PF", + "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", + "SampleAfterValue": "100003", + "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" + }, + { + "EdgeDetect": "1", + "Invert": "1", + "EventCode": "0x5E", + "UMask": "0x1", + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", + "Counter": "0,1,2,3", + "EventName": "RS_EVENTS.EMPTY_END", + "CounterMask": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound 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.", + "Counter": "0,1,2,3", + "EventName": "ILD_STALL.LCP", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x1", + "BriefDescription": "Cycles per thread when uops are executed in port 0", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_0", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x2", + "BriefDescription": "Cycles per thread when uops are executed in port 1", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_1", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x4", + "BriefDescription": "Cycles per thread when uops are executed in port 2", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x8", + "BriefDescription": "Cycles per thread when uops are executed in port 3", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x10", + "BriefDescription": "Cycles per thread when uops are executed in port 4", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x20", + "BriefDescription": "Cycles per thread when uops are executed in port 5", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x40", + "BriefDescription": "Cycles per thread when uops are executed in port 6", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_6", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x80", + "BriefDescription": "Cycles per thread when uops are executed in port 7", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_7", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA2", + "UMask": "0x8", + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "Counter": "0,1,2,3", + "EventName": "RESOURCE_STALLS.SB", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x1", + "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x4", + "BriefDescription": "Total execution stalls.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "CounterMask": "4", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x5", + "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", + "CounterMask": "5", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x8", + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "CounterMask": "8", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0xc", + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "CounterMask": "12", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x10", + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "CounterMask": "16", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x14", + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", + "CounterMask": "20", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xA6", + "UMask": "0x1", + "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.", + "Counter": "0,1,2,3", + "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA6", + "UMask": "0x2", + "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3", + "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA6", + "UMask": "0x4", + "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3", + "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA6", + "UMask": "0x8", + "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3", + "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA6", + "UMask": "0x10", + "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3", + "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA6", + "UMask": "0x40", + "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.", + "Counter": "0,1,2,3", + "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA8", + "UMask": "0x1", + "BriefDescription": "Number of Uops delivered by the LSD.", + "Counter": "0,1,2,3", + "EventName": "LSD.UOPS", + "PublicDescription": "Number of uops delivered to the back-end 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", + "CounterMask": "1", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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": "0xB1", + "UMask": "0x1", + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "Counter": "0,1,2,3", + "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" + }, + { + "Invert": "1", + "EventCode": "0xB1", + "UMask": "0x1", + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this 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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x1", + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "CounterMask": "1", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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", + "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.", + "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", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x2", + "BriefDescription": "Number of uops executed on the core.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE", + "PublicDescription": "Number of uops executed from any thread.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x2", + "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_GE_1", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x2", + "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_2", + "CounterMask": "2", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x2", + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "CounterMask": "3", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x2", + "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_4", + "CounterMask": "4", + "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.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x10", + "BriefDescription": "Counts the number of x87 uops dispatched.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.X87", + "PublicDescription": "Counts the number of x87 uops executed.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC0", + "UMask": "0x0", + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "Counter": "0,1,2,3", + "EventName": "INST_RETIRED.ANY_P", + "Errata": "SKL091, SKL044", + "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC0", + "UMask": "0x1", + "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", + "PEBS": "2", + "Counter": "1", + "EventName": "INST_RETIRED.PREC_DIST", + "Errata": "SKL091, SKL044", + "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.", + "SampleAfterValue": "2000003", + "CounterHTOff": "1" + }, + { + "Invert": "1", + "EventCode": "0xC0", + "UMask": "0x1", + "BriefDescription": "Number of cycles using always true condition applied to PEBS instructions retired event.", + "PEBS": "2", + "Counter": "0,2,3", + "EventName": "INST_RETIRED.TOTAL_CYCLES_PS", + "CounterMask": "10", + "Errata": "SKL091, SKL044", + "PublicDescription": "Number of cycles using an always true condition applied to PEBS instructions retired event. (inst_ret< 16)", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,2,3" + }, + { + "EventCode": "0xC1", + "UMask": "0x3f", + "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.", + "Counter": "0,1,2,3", + "EventName": "OTHER_ASSISTS.ANY", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC2", + "UMask": "0x2", + "BriefDescription": "Retirement slots used.", + "Counter": "0,1,2,3", + "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "PublicDescription": "Counts the retirement slots used.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "Invert": "1", + "EventCode": "0xC2", + "UMask": "0x2", + "BriefDescription": "Cycles without actually retired uops.", + "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.", + "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.", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EdgeDetect": "1", + "EventCode": "0xC3", + "UMask": "0x1", + "BriefDescription": "Number of machine clears (nukes) of any type. ", + "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" + }, + { + "EventCode": "0xC3", + "UMask": "0x4", + "BriefDescription": "Self-modifying code (SMC) detected.", + "Counter": "0,1,2,3", + "EventName": "MACHINE_CLEARS.SMC", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "UMask": "0x0", + "BriefDescription": "All (macro) branch instructions retired.", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "Errata": "SKL091", + "PublicDescription": "Counts all (macro) branch instructions retired.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "UMask": "0x1", + "BriefDescription": "Conditional branch instructions retired.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.CONDITIONAL", + "Errata": "SKL091", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that 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.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "Errata": "SKL091", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts both direct and indirect near call instructions retired.", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "UMask": "0x4", + "BriefDescription": "All (macro) branch instructions retired. ", + "PEBS": "2", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "Errata": "SKL091", + "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC4", + "UMask": "0x8", + "BriefDescription": "Return instructions retired.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "Errata": "SKL091", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts return instructions retired.", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "UMask": "0x10", + "BriefDescription": "Not taken branch instructions retired.", + "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.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "UMask": "0x20", + "BriefDescription": "Taken branch instructions retired.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "Errata": "SKL091", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts taken branch instructions retired.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "UMask": "0x40", + "BriefDescription": "Far branch instructions retired.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "Errata": "SKL091", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts far branch instructions retired.", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC5", + "UMask": "0x0", + "BriefDescription": "All mispredicted macro branch instructions retired.", + "Counter": "0,1,2,3", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC5", + "UMask": "0x1", + "BriefDescription": "Mispredicted conditional branch instructions retired.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_MISP_RETIRED.CONDITIONAL", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted conditional branch instructions retired.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC5", + "UMask": "0x2", + "BriefDescription": "Mispredicted direct and indirect near call instructions retired.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_MISP_RETIRED.NEAR_CALL", + "PublicDescription": "Counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC5", + "UMask": "0x4", + "BriefDescription": "Mispredicted macro branch instructions retired. ", + "PEBS": "2", + "Counter": "0,1,2,3", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", + "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC5", + "UMask": "0x20", + "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", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCC", + "UMask": "0x20", + "BriefDescription": "Increments whenever there is an update to the LBR array.", + "Counter": "0,1,2,3", + "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", + "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.", + "Counter": "0,1,2,3", + "EventName": "BACLEARS.ANY", + "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.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json new file mode 100644 index 000000000000..9c7e5f8beee2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json @@ -0,0 +1,172 @@ +[ + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_channel_ppd %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_self_refresh %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charges due to page misses", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for reads", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for writes", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Page Activate commands sent due to a write request", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M_ACT_COUNT.WR", + "PerPkg": "1", + "PublicDescription": "Counts DRAM Page Activate commands sent on this channel due to a write request to the iMC (Memory Controller). Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS (Column Access Select) command.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM CAS Commands issued", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.ALL", + "PerPkg": "1", + "PublicDescription": "Counts all CAS (Column Address Select) commands issued to DRAM per memory channel. CAS commands are issued to specify the address to read or write on DRAM, so this event increments for every read and write. This event counts whether AutoPrecharge (which closes the DRAM Page automatically after a read/write) is enabled or not.", + "UMask": "0xF", + "Unit": "iMC" + }, + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM Read CAS Commands issued (does not include underfills) ", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD_REG", + "PerPkg": "1", + "PublicDescription": "Counts CAS (Column Access Select) regular read commands issued to DRAM on a per channel basis. CAS commands are issued to specify the address to read or write on DRAM, and this event increments for every regular read. This event only counts regular reads and does not includes underfill reads due to partial write requests. This event counts whether AutoPrecharge (which closes the DRAM Page automatically after a read/write) is enabled or not.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Underfill Read CAS Commands issued", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD_UNDERFILL", + "PerPkg": "1", + "PublicDescription": "Counts CAS (Column Access Select) underfill read commands issued to DRAM due to a partial write, on a per channel basis. CAS commands are issued to specify the address to read or write on DRAM, and this command counts underfill reads. Partial writes must be completed by first reading in the underfill from DRAM and then merging in the partial write data before writing the full line back to DRAM. This event will generally count about the same as the number of partial writes, but may be slightly less because of partials hitting in the WPQ (due to a previous write request). ", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Allocations", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_M_RPQ_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of read requests allocated into the Read Pending Queue (RPQ). This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. The requests deallocate after the read CAS command has been issued to DRAM. This event counts both Isochronous and non-Isochronous requests which were issued to the RPQ. ", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Occupancy", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_M_RPQ_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries in the Read Pending Queue (RPQ) at each cycle. This can then be used to calculate both the average occupancy of the queue (in conjunction with the number of cycles not empty) and the average latency in the queue (in conjunction with the number of allocations). The RPQ is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. They deallocate from the RPQ after the CAS command has been issued to memory.", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Allocations", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "UNC_M_WPQ_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of writes requests allocated into the Write Pending Queue (WPQ). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (Memory Controller). The write requests deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC.", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Occupancy", + "Counter": "0,1,2,3", + "EventCode": "0x81", + "EventName": "UNC_M_WPQ_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests.", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json new file mode 100644 index 000000000000..de6e70e552e2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json @@ -0,0 +1,1156 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_CHA_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "config1=0x40e33", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "MMIO reads. Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "config1=0x40040e33", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "config1=0x40041e33", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "config1=0x41833", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "config1=0x41a33", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x03", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x02", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0x0C", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x04", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x08", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UPI_DATA_BANDWIDTH_TX", + "PerPkg": "1", + "ScaleUnit": "7.11E-06Bytes", + "UMask": "0x0F", + "Unit": "UPI LL" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "LLC_MISSES.PCIE_READ", + "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "MetricName": "LLC_MISSES.PCIE_READ", + "PerPkg": "1", + "PortMask": "0x01", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "LLC_MISSES.PCIE_WRITE", + "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "MetricName": "LLC_MISSES.PCIE_WRITE", + "PerPkg": "1", + "PortMask": "0x01", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 0", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "MetricName": "LLC_MISSES.PCIE_WRITE", + "PerPkg": "1", + "PortMask": "0x01", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 1", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 2", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 3", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 0", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "MetricName": "LLC_MISSES.PCIE_READ", + "PerPkg": "1", + "PortMask": "0x01", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 1", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 2", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 3", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Multiple Core Requests", + "Counter": "0,1,2,3", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Multiple Eviction", + "Counter": "0,1,2,3", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Not Needed", + "Counter": "0,1,2,3", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP", + "PerPkg": "1", + "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and therefore did not send a snoop because the Directory indicated it was not needed", + "UMask": "0x02", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Needed", + "Counter": "0,1,2,3", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.SNP", + "PerPkg": "1", + "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and sent one or more snoops, because the Directory indicated it was needed", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from the HA pipe", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.HA", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline Directory state updates memory writes issued from the HA pipe. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from TOR pipe", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.TOR", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline Directory state updates due to memory writes issued from the TOR pipe which are the result of remote transaction hitting the SF/LLC and returning data Core2Core. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x02", + "Unit": "CHA" + }, + { + "BriefDescription": "Read request from a remote socket which hit in the HitMe Cache to a line In the E state", + "Counter": "0,1,2,3", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.EX_RDS", + "PerPkg": "1", + "PublicDescription": "Counts read requests from a remote socket which hit in the HitME cache (used to cache the multi-socket Directory state) to a line in the E(Exclusive) state. This includes the following read opcodes (RdCode, RdData, RdDataMigratory, RdCur, RdInv*, Inv*)", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Normal priority reads issued to the memory controller from the CHA", + "Counter": "0,1,2,3", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued; Full Line Non-ISOCH", + "Counter": "0,1,2,3", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to the any of the memory controller channels.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Number of times that an RFO hit in S state.", + "Counter": "0,1,2,3", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RFO_HIT_S", + "PerPkg": "1", + "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a write) request hit a cacheline in the S (Shared) state.", + "UMask": "0x08", + "Unit": "CHA" + }, + { + "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a remote socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "RspCnflct* Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPCNFLCTS", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspCnflct* Snoop Response was received. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent. This triggers conflict resolution hardware. This covers both the opcode RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "RspI Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPI", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type RspI Snoop Response was received which indicates the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO: the Read for Ownership issued before a write hits non-modified data).", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "RspIFwd Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspIFwd Snoop Response was received which indicates a remote caching agent forwarded the data and the requesting agent is able to acquire the data in E (Exclusive) or M (modified) states. This is commonly returned with RFO (the Read for Ownership issued before a write) transactions. The snoop could have either been to a cacheline in the M,E,F (Modified, Exclusive or Forward) states.", + "UMask": "0x04", + "Unit": "CHA" + }, + { + "BriefDescription": "RspSFwd Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspSFwd Snoop Response was received which indicates a remote caching agent forwarded the data but held on to its current copy. This is common for data and code reads that hit in a remote socket in E (Exclusive) or F (Forward) state.", + "UMask": "0x08", + "Unit": "CHA" + }, + { + "BriefDescription": "Rsp*Fwd*WB Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type Rsp*Fwd*WB Snoop Response was received which indicates the data was written back to it's home socket, and the cacheline was forwarded to the requestor socket. This snoop response is only used in >= 4 socket systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to it's home socket to be written back to memory.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Rsp*WB Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSP_WBWB", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type Rsp*WB Snoop Response was received which indicates which indicates the data was written back to it's home. This is returned when a non-RFO request hits a cacheline in the Modified state. The Cache can either downgrade the cacheline to a S (Shared) or I (Invalid) state depending on how the system has been configured. This reponse will also be sent when a cache requests E (Exclusive) ownership of a cache line without receiving data, because the cache must acquire ownership.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Clockticks of the IIO Traffic Controller", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_IIO_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts clockticks of the 1GHz trafiic controller clock in the IIO unit.", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part0", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part0. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part1", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part2", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part3", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part0 by the CPU", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part1 by the CPU", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU ", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU ", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part0", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part0. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part1", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part2", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part3", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part0 by the CPU", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part1 by the CPU", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU ", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU ", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part0 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part1 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part2 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part3 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part0 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part1 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part2 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part3 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Traffic in which the M2M to iMC Bypass was not taken", + "Counter": "0,1,2,3", + "EventCode": "0x22", + "EventName": "UNC_M2M_BYPASS_M2M_Egress.NOT_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts traffic in which the M2M (Mesh to Memory) to iMC (Memory Controller) bypass was not taken", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "PublicDescription": "Counts cycles when direct to core mode (which bypasses the CHA) was disabled", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages sent direct to core (bypassing the CHA)", + "Counter": "0,1,2,3", + "EventCode": "0x23", + "EventName": "UNC_M2M_DIRECT2CORE_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts when messages were sent direct to core (bypassing the CHA)", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction were overridden", + "Counter": "0,1,2,3", + "EventCode": "0x25", + "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", + "PerPkg": "1", + "PublicDescription": "Counts reads in which direct to core transactions (which would have bypassed the CHA) were overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden", + "Counter": "0,1,2,3", + "EventCode": "0x28", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", + "PerPkg": "1", + "PublicDescription": "Counts reads in which direct to Intel Ultra Path Interconnect (UPI) transactions (which would have bypassed the CHA) were overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to Intel UPI was disabled", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the ability to send messages direct to the Intel Ultra Path Interconnect (bypassing the CHA) was disabled", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages sent direct to the Intel UPI", + "Counter": "0,1,2,3", + "EventCode": "0x26", + "EventName": "UNC_M2M_DIRECT2UPI_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts when messages were sent direct to the Intel Ultra Path Interconnect (bypassing the CHA)", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden", + "Counter": "0,1,2,3", + "EventCode": "0x29", + "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", + "PerPkg": "1", + "PublicDescription": "Counts when a read message that was sent direct to the Intel Ultra Path Interconnect (bypassing the CHA) was overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)", + "Counter": "0,1,2,3", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in Any State (A, I, S or unused)", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state) ", + "Counter": "0,1,2,3", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in the A (SnoopAll) state, indicating the cacheline is stored in another socket in any state, and we must snoop the other sockets to make sure we get the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state) ", + "Counter": "0,1,2,3", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the I (Invalid) state indicating the cacheline is not stored in another socket, and so there is no need to snoop the other sockets for the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state) ", + "Counter": "0,1,2,3", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the S (Shared) state indicating the cacheline is either stored in another socket in the S(hared) state , and so there is no need to snoop the other sockets for the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to I", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from A (SnoopAll) to I (Invalid)", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to S", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from A (SnoopAll) to S (Shared)", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from/to Any state ", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory to a new state", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to A", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from I (Invalid) to A (SnoopAll)", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to S", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from I (Invalid) to S (Shared)", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to A", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from S (Shared) to A (SnoopAll)", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to I", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from S (Shared) to I (Invalid)", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Reads to iMC issued", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.ALL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller). ", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Reads to iMC issued at Normal Priority (Non-Isochronous)", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.NORMAL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller). It only counts normal priority non-isochronous reads.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Writes to iMC issued", + "Counter": "0,1,2,3", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.ALL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues writes to the iMC (Memory Controller).", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Partial Non-Isochronous writes to the iMC", + "Counter": "0,1,2,3", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues partial writes to the iMC (Memory Controller). It only counts normal priority non-isochronous writes.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefecth requests that got turn into a demand request", + "Counter": "0,1,2,3", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_DEMAND_PROMOTIONS", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) promotes a outstanding request in the prefetch queue due to a subsequent demand read request that entered the M2M with the same address. Explanatory Side Note: The Prefecth queue is made of CAM (Content Addressable Memory)", + "Unit": "M2M" + }, + { + "BriefDescription": "Inserts into the Memory Controller Prefetch Queue", + "Counter": "0,1,2,3", + "EventCode": "0x57", + "EventName": "UNC_M2M_PREFCAM_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) recieves a prefetch request and inserts it into its outstanding prefetch queue. Explanatory Side Note: the prefect queue is made from CAM: Content Addressable Memory", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Queue Inserts", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M2M_RxC_AD_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts when the a new entry is Received(RxC) and then added to the AD (Address Ring) Ingress Queue from the CMS (Common Mesh Stop). This is generally used for reads, and ", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetches generated by the flow control queue of the M3UPI unit.", + "Counter": "0,1,2,3", + "EventCode": "0x29", + "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", + "PerPkg": "1", + "PublicDescription": "Count cases where flow control queue that sits between the Intel Ultra Path Interconnect (UPI) and the mesh spawns a prefetch to the iMC (Memory Controller)", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Clocks of the Intel Ultra Path Interconnect (UPI)", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_UPI_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts clockticks of the fixed frequency clock controlling the Intel Ultra Path Interconnect (UPI). This clock runs at1/8th the 'GT/s' speed of the UPI link. For example, a 9.6GT/s link will have a fixed Frequency of 1.2 Ghz.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Data Response packets that go direct to core", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C", + "PerPkg": "1", + "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to core bypassing the CHA.", + "UMask": "0x1", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Data Response packets that go direct to Intel UPI", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2U", + "PerPkg": "1", + "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to Intel Ultra Path Interconnect (UPI) bypassing the CHA .", + "UMask": "0x2", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Cycles Intel UPI is in L1 power mode (shutdown)", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_UPI_L1_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the Intel Ultra Path Interconnect (UPI) is in L1 power mode. L1 is a mode that totally shuts down the UPI link. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another, this event only coutns when both links are shutdown.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Cycles the Rx of the Intel UPI is in L0p power mode", + "Counter": "0,1,2,3", + "EventCode": "0x25", + "EventName": "UNC_UPI_RxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the the receive side (Rx) of the Intel Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", + "Counter": "0,1,2,3", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot0 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x1", + "Unit": "UPI LL" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", + "Counter": "0,1,2,3", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot1 RxQ buffer (Receive Queue) and passed directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x2", + "Unit": "UPI LL" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Recieve Buffer", + "Counter": "0,1,2,3", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) whcih bypassed the slot2 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x4", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid data FLITs received from any slot", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", + "PerPkg": "1", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) received from any of the 3 Intel Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", + "UMask": "0x0F", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Null FLITs received from any slot", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", + "PerPkg": "1", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) received from any of the 3 Intel Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", + "UMask": "0x27", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Protocol header and credit FLITs received from any slot", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) received from any of the 3 UPI slots on this UPI unit.", + "UMask": "0x97", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Cycles in which the Tx of the Intel Ultra Path Interconnect (UPI) is in L0p power mode", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the transmit side (Tx) of the Intel Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "FLITs that bypassed the TxL Buffer", + "Counter": "0,1,2,3", + "EventCode": "0x41", + "EventName": "UNC_UPI_TxL_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the TxL(transmit) FLIT buffer and pass directly out the UPI Link. Generally, when data is transmitted across the Intel Ultra Path Interconnect (UPI), it will bypass the TxQ and pass directly to the link. However, the TxQ will be used in L0p (Low Power) mode and (Link Layer Retry) LLR mode, increasing latency to transfer out to the link.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UPI_DATA_BANDWIDTH_TX", + "PerPkg": "1", + "ScaleUnit": "7.11E-06Bytes", + "UMask": "0x0F", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Null FLITs transmitted from any slot", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", + "PerPkg": "1", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel Ulra Path Interconnect (UPI) slots on this UPI unit.", + "UMask": "0x27", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Idle FLITs transmitted", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.IDLE", + "PerPkg": "1", + "PublicDescription": "Counts when the Intel Ultra Path Interconnect(UPI) transmits an idle FLIT(80 bit FLow control unITs). Every UPI cycle must be sending either data FLITs, protocol/credit FLITs or idle FLITs.", + "UMask": "0x47", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Protocol header and credit FLITs transmitted across any slot", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) transmitted across any of the 3 UPI (Ultra Path Interconnect) slots on this UPI unit.", + "UMask": "0x97", + "Unit": "UPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json new file mode 100644 index 000000000000..70750dab7ead --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json @@ -0,0 +1,284 @@ +[ + { + "EventCode": "0x08", + "UMask": "0x1", + "BriefDescription": "Load misses in all DTLB levels that cause page walks", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "UMask": "0x2", + "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts demand data loads that caused a completed page walk (4K page size). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "UMask": "0x4", + "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (2M/4M).", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts demand data loads that caused a completed page walk (2M and 4M page sizes). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "UMask": "0x8", + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts load misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "UMask": "0xe", + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "UMask": "0x10", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake. ", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture. ", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "UMask": "0x10", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake. ", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", + "CounterMask": "1", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "UMask": "0x20", + "BriefDescription": "Loads that miss the DTLB and hit the STLB.", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0x1", + "BriefDescription": "Store misses in all DTLB levels that cause page walks", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0x2", + "BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts demand data stores that caused a completed page walk (4K page size). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0x4", + "BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts demand data stores that caused a completed page walk (2M and 4M page sizes). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0x8", + "BriefDescription": "Store misses in all DTLB levels that cause completed page walks (1G)", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0xe", + "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0x10", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake. ", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture. ", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0x10", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake. ", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "CounterMask": "1", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0x20", + "BriefDescription": "Stores that miss the DTLB and hit the STLB.", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x4F", + "UMask": "0x10", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.", + "Counter": "0,1,2,3", + "EventName": "EPT.WALK_PENDING", + "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0x1", + "BriefDescription": "Misses at all ITLB levels that cause page walks", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0x2", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0x4", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0x8", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0xe", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (2M and 4M page sizes) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0x10", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake. ", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0x10", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_ACTIVE", + "CounterMask": "1", + "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0x20", + "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.STLB_HIT", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xAE", + "UMask": "0x1", + "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", + "Counter": "0,1,2,3", + "EventName": "ITLB.ITLB_FLUSH", + "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xBD", + "UMask": "0x1", + "BriefDescription": "DTLB flush attempts of the thread-specific entries", + "Counter": "0,1,2,3", + "EventName": "TLB_FLUSH.DTLB_THREAD", + "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xBD", + "UMask": "0x20", + "BriefDescription": "STLB flush attempts", + "Counter": "0,1,2,3", + "EventName": "TLB_FLUSH.STLB_ANY", + "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3,4,5,6,7" + } +]
\ No newline at end of file |