d/freebsd-dev
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

libpmc: Another update of x86 event definitions.

Browse Source 
MFC after:	1 month
This commit is contained in:
Alexander Motin 2022-05-26 22:07:42 -04:00
parent 8020c05683
commit 18054d0220
222 changed files with 100045 additions and 77480 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

729
lib/libpmc/pmu-events/arch/x86/alderlake/adl-metrics.json Normal file
View File

@ -0,0 +1,729 @@
[
{
"BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)",
"MetricExpr": "100 * (( BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) ) / TOPDOWN.SLOTS)",
"MetricGroup": "Ret",
"MetricName": "Branching_Overhead",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instructions Per Cycle (per Logical Processor)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Ret;Summary",
"MetricName": "IPC",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles Per Instruction (per Logical Processor)",
"MetricExpr": "1 / (INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "Pipeline;Mem",
"MetricName": "CPI",
"Unit": "cpu_core"
},
{
"BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Pipeline",
"MetricName": "CLKS",
"Unit": "cpu_core"
},
{
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
"MetricExpr": "TOPDOWN.SLOTS",
"MetricGroup": "TmaL1",
"MetricName": "SLOTS",
"Unit": "cpu_core"
},
{
"BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
"MetricExpr": "TOPDOWN.SLOTS / ( TOPDOWN.SLOTS / 2 ) if #SMT_on else 1",
"MetricGroup": "SMT",
"MetricName": "Slots_Utilization",
"Unit": "cpu_core"
},
{
"BriefDescription": "The ratio of Executed- by Issued-Uops",
"MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
"MetricGroup": "Cor;Pipeline",
"MetricName": "Execute_per_Issue",
"PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.DISTRIBUTED",
"MetricGroup": "Ret;SMT;TmaL1",
"MetricName": "CoreIPC",
"Unit": "cpu_core"
},
{
"BriefDescription": "Floating Point Operations Per Cycle",
"MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / CPU_CLK_UNHALTED.DISTRIBUTED",
"MetricGroup": "Ret;Flops",
"MetricName": "FLOPc",
"Unit": "cpu_core"
},
{
"BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width)",
"MetricExpr": "( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) ) / ( 2 * CPU_CLK_UNHALTED.DISTRIBUTED )",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "FP_Arith_Utilization",
"PublicDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). Values > 1 are possible due to Fused-Multiply Add (FMA) counting.",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
"MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
"MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
"MetricName": "ILP",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;BadSpec;BrMispredicts",
"MetricName": "IpMispredict",
"Unit": "cpu_core"
},
{
"BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
"MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
"MetricGroup": "InsType",
"MetricName": "IpLoad",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
"MetricGroup": "InsType",
"MetricName": "IpStore",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Branches;Fed;InsType",
"MetricName": "IpBranch",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "IpCall",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instruction per taken branch",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO",
"MetricName": "IpTB",
"Unit": "cpu_core"
},
{
"BriefDescription": "Branch instructions per taken branch. ",
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "BpTkBranch",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )",
"MetricGroup": "Flops;InsType",
"MetricName": "IpFLOP",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) )",
"MetricGroup": "Flops;InsType",
"MetricName": "IpArith",
"PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW.",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "IpArith_Scalar_SP",
"PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "IpArith_Scalar_DP",
"PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "IpArith_AVX128",
"PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "IpArith_AVX256",
"PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.",
"Unit": "cpu_core"
},
{
"BriefDescription": "Total number of retired Instructions, Sample with: INST_RETIRED.PREC_DIST",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary;TmaL1",
"MetricName": "Instructions",
"Unit": "cpu_core"
},
{
"BriefDescription": "Average number of Uops issued by front-end when it issued something",
"MetricExpr": "UOPS_ISSUED.ANY / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
"MetricGroup": "Fed;FetchBW",
"MetricName": "Fetch_UpC",
"Unit": "cpu_core"
},
{
"BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
"MetricExpr": "LSD.UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
"MetricGroup": "Fed;LSD",
"MetricName": "LSD_Coverage",
"Unit": "cpu_core"
},
{
"BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
"MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
"MetricGroup": "DSB;Fed;FetchBW",
"MetricName": "DSB_Coverage",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of Instructions per non-speculative DSB miss",
"MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
"MetricGroup": "DSBmiss;Fed",
"MetricName": "IpDSB_Miss_Ret",
"Unit": "cpu_core"
},
{
"BriefDescription": "Fraction of branches that are non-taken conditionals",
"MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;Branches;CodeGen;PGO",
"MetricName": "Cond_NT",
"Unit": "cpu_core"
},
{
"BriefDescription": "Fraction of branches that are taken conditionals",
"MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;Branches;CodeGen;PGO",
"MetricName": "Cond_TK",
"Unit": "cpu_core"
},
{
"BriefDescription": "Fraction of branches that are CALL or RET",
"MetricExpr": "( BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN ) / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;Branches",
"MetricName": "CallRet",
"Unit": "cpu_core"
},
{
"BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps",
"MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;Branches",
"MetricName": "Jump",
"Unit": "cpu_core"
},
{
"BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)",
"MetricExpr": "1 - ( (BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES) + (BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES) + (( BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN ) / BR_INST_RETIRED.ALL_BRANCHES) + ((BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES) )",
"MetricGroup": "Bad;Branches",
"MetricName": "Other_Branches",
"Unit": "cpu_core"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles)",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
"MetricGroup": "Mem;MemoryBound;MemoryLat",
"MetricName": "Load_Miss_Real_Latency",
"PublicDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles). Latency may be overestimated for multi-load instructions - e.g. repeat strings.",
"Unit": "cpu_core"
},
{
"BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
"MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
"MetricGroup": "Mem;MemoryBound;MemoryBW",
"MetricName": "MLP",
"Unit": "cpu_core"
},
{
"BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
"MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L1D_Cache_Fill_BW",
"Unit": "cpu_core"
},
{
"BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
"MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L2_Cache_Fill_BW",
"Unit": "cpu_core"
},
{
"BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
"MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L3_Cache_Fill_BW",
"Unit": "cpu_core"
},
{
"BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
"MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
"MetricGroup": "Mem;MemoryBW;Offcore",
"MetricName": "L3_Cache_Access_BW",
"Unit": "cpu_core"
},
{
"BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L1MPKI",
"Unit": "cpu_core"
},
{
"BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L1MPKI_Load",
"Unit": "cpu_core"
},
{
"BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;Backend;CacheMisses",
"MetricName": "L2MPKI",
"Unit": "cpu_core"
},
{
"BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses;Offcore",
"MetricName": "L2MPKI_All",
"Unit": "cpu_core"
},
{
"BriefDescription": "L2 cache misses per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2MPKI_Load",
"Unit": "cpu_core"
},
{
"BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
"MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2HPKI_All",
"Unit": "cpu_core"
},
{
"BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2HPKI_Load",
"Unit": "cpu_core"
},
{
"BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L3MPKI",
"Unit": "cpu_core"
},
{
"BriefDescription": "Fill Buffer (FB) true hits per kilo instructions for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "FB_HPKI",
"Unit": "cpu_core"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING ) / ( 4 * CPU_CLK_UNHALTED.DISTRIBUTED )",
"MetricGroup": "Mem;MemoryTLB",
"MetricName": "Page_Walks_Utilization",
"Unit": "cpu_core"
},
{
"BriefDescription": "Average CPU Utilization",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
"MetricGroup": "HPC;Summary",
"MetricName": "CPU_Utilization",
"Unit": "cpu_core"
},
{
"BriefDescription": "Measured Average Frequency for unhalted processors [GHz]",
"MetricExpr": "(CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time",
"MetricGroup": "Summary;Power",
"MetricName": "Average_Frequency",
"Unit": "cpu_core"
},
{
"BriefDescription": "Giga Floating Point Operations Per Second",
"MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 ) / duration_time",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "GFLOPs",
"Unit": "cpu_core"
},
{
"BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization",
"Unit": "cpu_core"
},
{
"BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
"MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0",
"MetricGroup": "SMT",
"MetricName": "SMT_2T_Utilization",
"Unit": "cpu_core"
},
{
"BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "OS",
"MetricName": "Kernel_Utilization",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
"MetricGroup": "OS",
"MetricName": "Kernel_CPI",
"Unit": "cpu_core"
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
"MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
"MetricGroup": "HPC;Mem;MemoryBW;SoC",
"MetricName": "DRAM_BW_Use",
"Unit": "cpu_core"
},
{
"BriefDescription": "Average number of parallel requests to external memory. Accounts for all requests",
"MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / arb@event\\=0x81\\,umask\\=0x1@",
"MetricGroup": "Mem;SoC",
"MetricName": "MEM_Parallel_Requests",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
"MetricGroup": "Branches;OS",
"MetricName": "IpFarBranch",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.",
"MetricExpr": "TOPDOWN_FE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL1",
"MetricName": "Frontend_Bound",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear",
"MetricExpr": "TOPDOWN_BAD_SPECULATION.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL1",
"MetricName": "Bad_Speculation",
"PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "TOPDOWN_BE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL1",
"MetricName": "Backend_Bound",
"PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls",
"MetricExpr": "TOPDOWN_BE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL1",
"MetricName": "Backend_Bound_Aux",
"PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation. ",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the numer of issue slots that result in retirement slots. ",
"MetricExpr": "TOPDOWN_RETIRING.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL1",
"MetricName": "Retiring",
"Unit": "cpu_atom"
},
{
"BriefDescription": "",
"MetricExpr": "CPU_CLK_UNHALTED.CORE",
"MetricName": "CLKS",
"Unit": "cpu_atom"
},
{
"BriefDescription": "",
"MetricExpr": "CPU_CLK_UNHALTED.CORE_P",
"MetricName": "CLKS_P",
"Unit": "cpu_atom"
},
{
"BriefDescription": "",
"MetricExpr": "5 * CPU_CLK_UNHALTED.CORE",
"MetricName": "SLOTS",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Instructions Per Cycle",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.CORE",
"MetricName": "IPC",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Cycles Per Instruction",
"MetricExpr": "CPU_CLK_UNHALTED.CORE / INST_RETIRED.ANY",
"MetricName": "CPI",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY",
"MetricName": "UPI",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block",
"MetricExpr": "100 * LD_BLOCKS.DATA_UNKNOWN / MEM_UOPS_RETIRED.ALL_LOADS",
"MetricName": "Store_Fwd_Blocks",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Percentage of total non-speculative loads with a address aliasing block",
"MetricExpr": "100 * LD_BLOCKS.4K_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS",
"MetricName": "Address_Alias_Blocks",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Percentage of total non-speculative loads that are splits",
"MetricExpr": "100 * MEM_UOPS_RETIRED.SPLIT_LOADS / MEM_UOPS_RETIRED.ALL_LOADS",
"MetricName": "Load_Splits",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"MetricName": "IpBranch",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Instruction per (near) call (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL",
"MetricName": "IpCall",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Instructions per Load",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
"MetricName": "IpLoad",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Instructions per Store",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
"MetricName": "IpStore",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Number of Instructions per non-speculative Branch Misprediction",
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricName": "IpMispredict",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Instructions per Far Branch",
"MetricExpr": "INST_RETIRED.ANY / ( BR_INST_RETIRED.FAR_BRANCH / 2 )",
"MetricName": "IpFarBranch",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Ratio of all branches which mispredict",
"MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES",
"MetricName": "Branch_Mispredict_Ratio",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Ratio between Mispredicted branches and unknown branches",
"MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY",
"MetricName": "Branch_Mispredict_to_Unknown_Branch_Ratio",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Percentage of all uops which are ucode ops",
"MetricExpr": "100 * UOPS_RETIRED.MS / UOPS_RETIRED.ALL",
"MetricName": "Microcode_Uop_Ratio",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Percentage of all uops which are FPDiv uops",
"MetricExpr": "100 * UOPS_RETIRED.FPDIV / UOPS_RETIRED.ALL",
"MetricName": "FPDiv_Uop_Ratio",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Percentage of all uops which are IDiv uops",
"MetricExpr": "100 * UOPS_RETIRED.IDIV / UOPS_RETIRED.ALL",
"MetricName": "IDiv_Uop_Ratio",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Percentage of all uops which are x87 uops",
"MetricExpr": "100 * UOPS_RETIRED.X87 / UOPS_RETIRED.ALL",
"MetricName": "X87_Uop_Ratio",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.CORE / CPU_CLK_UNHALTED.REF_TSC",
"MetricName": "Turbo_Utilization",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.CORE:k / CPU_CLK_UNHALTED.CORE",
"MetricName": "Kernel_Utilization",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Average CPU Utilization",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
"MetricName": "CPU_Utilization",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Estimated Pause cost. In percent",
"MetricExpr": "100 * SERIALIZATION.NON_C01_MS_SCB / ( 5 * CPU_CLK_UNHALTED.CORE )",
"MetricName": "Estimated_Pause_Cost",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Cycle cost per L2 hit",
"MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT",
"MetricName": "Cycles_per_Demand_Load_L2_Hit",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Cycle cost per LLC hit",
"MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT",
"MetricName": "Cycles_per_Demand_Load_L3_Hit",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Cycle cost per DRAM hit",
"MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
"MetricName": "Cycles_per_Demand_Load_DRAM_Hit",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Percent of instruction miss cost that hit in the L2",
"MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_L2_HIT / ( MEM_BOUND_STALLS.IFETCH )",
"MetricName": "Inst_Miss_Cost_L2Hit_Percent",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Percent of instruction miss cost that hit in the L3",
"MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_LLC_HIT / ( MEM_BOUND_STALLS.IFETCH )",
"MetricName": "Inst_Miss_Cost_L3Hit_Percent",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Percent of instruction miss cost that hit in DRAM",
"MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_DRAM_HIT / ( MEM_BOUND_STALLS.IFETCH )",
"MetricName": "Inst_Miss_Cost_DRAMHit_Percent",
"Unit": "cpu_atom"
},
{
"BriefDescription": "load ops retired per 1000 instruction",
"MetricExpr": "1000 * MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY",
"MetricName": "MemLoadPKI",
"Unit": "cpu_atom"
},
{
"BriefDescription": "C1 residency percent per core",
"MetricExpr": "(cstate_core@c1\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C1_Core_Residency"
},
{
"BriefDescription": "C6 residency percent per core",
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C6_Core_Residency"
},
{
"BriefDescription": "C7 residency percent per core",
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C7_Core_Residency"
},
{
"BriefDescription": "C2 residency percent per package",
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C2_Pkg_Residency"
},
{
"BriefDescription": "C3 residency percent per package",
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C3_Pkg_Residency"
},
{
"BriefDescription": "C6 residency percent per package",
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C6_Pkg_Residency"
},
{
"BriefDescription": "C7 residency percent per package",
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C7_Pkg_Residency"
},
{
"BriefDescription": "C8 residency percent per package",
"MetricExpr": "(cstate_pkg@c8\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C8_Pkg_Residency"
},
{
"BriefDescription": "C9 residency percent per package",
"MetricExpr": "(cstate_pkg@c9\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C9_Pkg_Residency"
},
{
"BriefDescription": "C10 residency percent per package",
"MetricExpr": "(cstate_pkg@c10\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C10_Pkg_Residency"
}
]

1140
lib/libpmc/pmu-events/arch/x86/alderlake/cache.json Normal file
View File

File diff suppressed because it is too large Load Diff

158
lib/libpmc/pmu-events/arch/x86/alderlake/floating-point.json Normal file
View File

@ -0,0 +1,158 @@
[
{
"BriefDescription": "Counts the number of floating point operations retired that required microcode assist.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.FP_ASSIST",
"PEBScounters": "0,1,2,3,4,5",
"SampleAfterValue": "20003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of floating point divide uops retired (x87 and SSE, including x87 sqrt).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.FPDIV",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_atom"
},
{
"BriefDescription": "TBD",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0xb0",
"EventName": "ARITH.FPDIV_ACTIVE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts all microcode FP assists.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.FP",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "TBD",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.SSE_AVX_MIX",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "TBD",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.PORT_0",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "TBD",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.PORT_1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "TBD",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.PORT_5",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. 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 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
}
]

491
lib/libpmc/pmu-events/arch/x86/alderlake/frontend.json Normal file
View File

@ -0,0 +1,491 @@
[
{
"BriefDescription": "Counts the total number of BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5",
"EventCode": "0xe6",
"EventName": "BACLEARS.ANY",
"PEBScounters": "0,1,2,3,4,5",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of requests to the instruction cache for one or more bytes of a cache line.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5",
"EventCode": "0x80",
"EventName": "ICACHE.ACCESSES",
"PEBScounters": "0,1,2,3,4,5",
"SampleAfterValue": "200003",
"UMask": "0x3",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of instruction cache misses.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5",
"EventCode": "0x80",
"EventName": "ICACHE.MISSES",
"PEBScounters": "0,1,2,3,4,5",
"SampleAfterValue": "200003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x87",
"EventName": "DECODE.LCP",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "500009",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "DSB-to-MITE switch true penalty cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x61",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired Instructions who experienced DSB miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x1",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired Instructions who experienced a critical DSB miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x11",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired Instructions who experienced iTLB true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x14",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L1I_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x12",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L2_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x13",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x600106",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
"MSRIndex": "0x3F7",
"MSRValue": "0x608006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
"MSRIndex": "0x3F7",
"MSRValue": "0x601006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
"MSRIndex": "0x3F7",
"MSRValue": "0x600206",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
"MSRIndex": "0x3F7",
"MSRValue": "0x610006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x100206",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
"MSRIndex": "0x3F7",
"MSRValue": "0x602006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
"MSRIndex": "0x3F7",
"MSRValue": "0x600406",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
"MSRIndex": "0x3F7",
"MSRValue": "0x620006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
"MSRIndex": "0x3F7",
"MSRValue": "0x604006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
"MSRIndex": "0x3F7",
"MSRValue": "0x600806",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.STLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x15",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "TBD",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
"MSRIndex": "0x3F7",
"MSRValue": "0x17",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "ICACHE_DATA.STALLS",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "500009",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x83",
"EventName": "ICACHE_TAG.STALLS",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_ANY",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles DSB is delivering optimal number of Uops",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "6",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_OK",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles MITE is delivering any Uop",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_ANY",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles MITE is delivering optimal number of Uops",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "6",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_OK",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_CYCLES_ANY",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "2000003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of switches from DSB or MITE to the MS",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_SWITCHES",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Uops delivered to IDQ while MS is busy",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.MS_UOPS",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"CounterMask": "6",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"Invert": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
}
]

318
lib/libpmc/pmu-events/arch/x86/alderlake/memory.json Normal file
View File

@ -0,0 +1,318 @@
[
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to any number of reasons, including an L1 miss, WCB full, pagewalk, store address block or store data block, on a load that retires.",
"Counter": "0,1,2,3,4,5",
"EventCode": "0x05",
"EventName": "LD_HEAD.ANY_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0xff",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a core bound stall including a store address match, a DTLB miss or a page walk that detains the load from retiring.",
"Counter": "0,1,2,3",
"EventCode": "0x05",
"EventName": "LD_HEAD.L1_BOUND_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0xf4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to other block cases when load subsequently retires when load subsequently retires.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5",
"EventCode": "0x05",
"EventName": "LD_HEAD.OTHER_AT_RET",
"PEBScounters": "0,1,2,3,4,5",
"SampleAfterValue": "1000003",
"UMask": "0xc0",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a pagewalk when load subsequently retires.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5",
"EventCode": "0x05",
"EventName": "LD_HEAD.PGWALK_AT_RET",
"PEBScounters": "0,1,2,3,4,5",
"SampleAfterValue": "1000003",
"UMask": "0xa0",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a store address match when load subsequently retires.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5",
"EventCode": "0x05",
"EventName": "LD_HEAD.ST_ADDR_AT_RET",
"PEBScounters": "0,1,2,3,4,5",
"SampleAfterValue": "1000003",
"UMask": "0x84",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of machine clears due to memory ordering caused by a snoop from an external agent. Does not count internally generated machine clears such as those due to memory disambiguation.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"PEBScounters": "0,1,2,3,4,5",
"SampleAfterValue": "20003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
"Counter": "0,1,2,3",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F84400001",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
"Counter": "0,1,2,3",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F84400002",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "6",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x6",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of machine clears due to memory ordering conflicts.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "2",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "3",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "TBD",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "5",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_core"
},
{
"BriefDescription": "TBD",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "9",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x9",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
"CollectPEBSRecord": "2",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"MSRValue": "0x80",
"PEBS": "2",
"PEBScounters": "1,2,3,4,5,6,7",
"SampleAfterValue": "1009",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
"CollectPEBSRecord": "2",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"MSRValue": "0x10",
"PEBS": "2",
"PEBScounters": "1,2,3,4,5,6,7",
"SampleAfterValue": "20011",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
"CollectPEBSRecord": "2",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"MSRValue": "0x100",
"PEBS": "2",
"PEBScounters": "1,2,3,4,5,6,7",
"SampleAfterValue": "503",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
"CollectPEBSRecord": "2",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"MSRValue": "0x20",
"PEBS": "2",
"PEBScounters": "1,2,3,4,5,6,7",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
"CollectPEBSRecord": "2",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"MSRValue": "0x4",
"PEBS": "2",
"PEBScounters": "1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
"CollectPEBSRecord": "2",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"MSRValue": "0x200",
"PEBS": "2",
"PEBScounters": "1,2,3,4,5,6,7",
"SampleAfterValue": "101",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
"CollectPEBSRecord": "2",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"MSRValue": "0x40",
"PEBS": "2",
"PEBScounters": "1,2,3,4,5,6,7",
"SampleAfterValue": "2003",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
"CollectPEBSRecord": "2",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"MSRValue": "0x8",
"PEBS": "2",
"PEBScounters": "1,2,3,4,5,6,7",
"SampleAfterValue": "50021",
"TakenAlone": "1",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions with at least 1 store uop. This PEBS event is the trigger for stores sampled by the PEBS Store Facility.",
"CollectPEBSRecord": "2",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
"PEBS": "2",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC00001",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC00002",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
}
]

146
lib/libpmc/pmu-events/arch/x86/alderlake/other.json Normal file
View File

@ -0,0 +1,146 @@
[
{
"BriefDescription": "Counts demand data reads that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10001",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10002",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts streaming stores that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0xB7",
"EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10800",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.ANY",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x1f",
"Unit": "cpu_core"
},
{
"BriefDescription": "Count all other microcode assist beyond FP, AVX_TILE_MIX and A/D assists (counted by their own sub-events). This includes assists at uop writeback like AVX* load/store (non-FP) assists, Null Assist in SNC (due to lack of FP precision format convert with FMA3x3 uarch) or assists generated by ROB (like assists to due to Missprediction for FSW register - fixed in SNC)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.HARDWARE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "TBD",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.PAGE_FAULT",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "TBD",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x28",
"EventName": "CORE_POWER.LICENSE_1",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "200003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "TBD",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x28",
"EventName": "CORE_POWER.LICENSE_2",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "TBD",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x28",
"EventName": "CORE_POWER.LICENSE_3",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "200003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts demand data reads that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10001",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10002",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts streaming stores that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10800",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "TBD",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x2d",
"EventName": "XQ.FULL_CYCLES",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
}
]

1721
lib/libpmc/pmu-events/arch/x86/alderlake/pipeline.json Normal file
View File

File diff suppressed because it is too large Load Diff

222
lib/libpmc/pmu-events/arch/x86/alderlake/uncore-memory.json Normal file
View File

@ -0,0 +1,222 @@
[
{
"BriefDescription": "Number of clocks",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x01",
"EventName": "UNC_M_CLOCKTICKS",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Incoming VC0 read request",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x02",
"EventName": "UNC_M_VC0_REQUESTS_RD",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Incoming VC0 write request",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x03",
"EventName": "UNC_M_VC0_REQUESTS_WR",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Incoming VC1 read request",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x04",
"EventName": "UNC_M_VC1_REQUESTS_RD",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Incoming VC1 write request",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x05",
"EventName": "UNC_M_VC1_REQUESTS_WR",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Incoming read prefetch request from IA",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x0A",
"EventName": "UNC_M_PREFETCH_RD",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Any Rank at Hot state",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x19",
"EventName": "UNC_M_DRAM_THERMAL_HOT",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Any Rank at Warm state",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x1A",
"EventName": "UNC_M_DRAM_THERMAL_WARM",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "incoming read request page status is Page Hit",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x1C",
"EventName": "UNC_M_DRAM_PAGE_HIT_RD",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "incoming read request page status is Page Empty",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x1D",
"EventName": "UNC_M_DRAM_PAGE_EMPTY_RD",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "incoming read request page status is Page Miss",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x1E",
"EventName": "UNC_M_DRAM_PAGE_MISS_RD",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "incoming write request page status is Page Hit",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x1F",
"EventName": "UNC_M_DRAM_PAGE_HIT_WR",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "incoming write request page status is Page Empty",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x20",
"EventName": "UNC_M_DRAM_PAGE_EMPTY_WR",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "incoming write request page status is Page Miss",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x21",
"EventName": "UNC_M_DRAM_PAGE_MISS_WR",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Read CAS command sent to DRAM",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x22",
"EventName": "UNC_M_CAS_COUNT_RD",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Write CAS command sent to DRAM",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x23",
"EventName": "UNC_M_CAS_COUNT_WR",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "ACT command for a read request sent to DRAM",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x24",
"EventName": "UNC_M_ACT_COUNT_RD",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "ACT command for a write request sent to DRAM",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x25",
"EventName": "UNC_M_ACT_COUNT_WR",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "ACT command sent to DRAM",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x26",
"EventName": "UNC_M_ACT_COUNT_TOTAL",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "PRE command sent to DRAM for a read/write request",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x27",
"EventName": "UNC_M_PRE_COUNT_PAGE_MISS",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "PRE command sent to DRAM due to page table idle timer expiration",
"Counter": "0,1,2,3,4",
"CounterType": "PGMABLE",
"EventCode": "0x28",
"EventName": "UNC_M_PRE_COUNT_IDLE",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Counts every 64B read request entering the Memory Controller 0 to DRAM (sum of all channels)",
"CounterType": "FREERUN",
"EventName": "UNC_MC0_RDCAS_COUNT_FREERUN",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Counts every 64B read request entering the Memory Controller 1 to DRAM (sum of all channels)",
"Counter": "3",
"CounterType": "FREERUN",
"EventName": "UNC_MC1_RDCAS_COUNT_FREERUN",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Counts every 64B write request entering the Memory Controller 0 to DRAM (sum of all channels). Each write request counts as a new request incrementing this counter. However, same cache line write requests (both full and partial) are combined to a single 64 byte data transfer to DRAM",
"Counter": "1",
"CounterType": "FREERUN",
"EventName": "UNC_MC0_WRCAS_COUNT_FREERUN",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Counts every 64B write request entering the Memory Controller 1 to DRAM (sum of all channels). Each write request counts as a new request incrementing this counter. However, same cache line write requests (both full and partial) are combined to a single 64 byte data transfer to DRAM",
"Counter": "4",
"CounterType": "FREERUN",
"EventName": "UNC_MC1_WRCAS_COUNT_FREERUN",
"PerPkg": "1",
"Unit": "iMC"
}
]

40
lib/libpmc/pmu-events/arch/x86/alderlake/uncore-other.json Normal file
View File

@ -0,0 +1,40 @@
[
{
"BriefDescription": "This 48-bit fixed counter counts the UCLK cycles",
"Counter": "Fixed",
"CounterType": "PGMABLE",
"EventCode": "0xff",
"EventName": "UNC_CLOCK.SOCKET",
"PerPkg": "1",
"Unit": "CLOCK"
},
{
"BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC",
"Counter": "0,1",
"CounterType": "PGMABLE",
"EventCode": "0x81",
"EventName": "UNC_ARB_TRK_REQUESTS.ALL",
"PerPkg": "1",
"UMask": "0x01",
"Unit": "ARB"
},
{
"BriefDescription": "Number of requests allocated in Coherency Tracker",
"Counter": "0,1",
"CounterType": "PGMABLE",
"EventCode": "0x84",
"EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
"PerPkg": "1",
"UMask": "0x01",
"Unit": "ARB"
},
{
"BriefDescription": "Each cycle counts number of all outgoing valid entries in ReqTrk. Such entry is defined as valid from its allocation in ReqTrk till deallocation. Accounts for Coherent and non-coherent traffic",
"CounterType": "PGMABLE",
"EventCode": "0x80",
"EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
"PerPkg": "1",
"UMask": "0x01",
"Unit": "ARB"
}
]

258
lib/libpmc/pmu-events/arch/x86/alderlake/virtual-memory.json Normal file
View File

@ -0,0 +1,258 @@
[
{
"BriefDescription": "Counts the number of page walks completed due to load DTLB misses to any page size.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"PEBScounters": "0,1,2,3,4,5",
"SampleAfterValue": "200003",
"UMask": "0xe",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of page walks completed due to store DTLB misses to any page size.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"PEBScounters": "0,1,2,3,4,5",
"SampleAfterValue": "2000003",
"UMask": "0xe",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a DTLB miss when load subsequently retires.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5",
"EventCode": "0x05",
"EventName": "LD_HEAD.DTLB_MISS_AT_RET",
"PEBScounters": "0,1,2,3,4,5",
"SampleAfterValue": "1000003",
"UMask": "0x90",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Loads that miss the DTLB and hit the STLB.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for a demand load.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0xe",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 1G page.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 4K page.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Stores that miss the DTLB and hit the STLB.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0xe",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 1G page.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 4K page.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_PENDING",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.STLB_HIT",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_ACTIVE",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0xe",
"Unit": "cpu_core"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_PENDING",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
}
]

1438
lib/libpmc/pmu-events/arch/x86/bonnell/cache.json
View File

File diff suppressed because it is too large Load Diff

468
lib/libpmc/pmu-events/arch/x86/bonnell/floating-point.json
View File

@ -1,261 +1,261 @@
[
{
"EventCode": "0x10",
"BriefDescription": "Floating point assists for retired operations.",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "X87_COMP_OPS_EXE.ANY.S",
"SampleAfterValue": "2000000",
"BriefDescription": "Floating point computational micro-ops executed."
},
{
"PEBS": "2",
"EventCode": "0x10",
"Counter": "0,1",
"UMask": "0x81",
"EventName": "X87_COMP_OPS_EXE.ANY.AR",
"SampleAfterValue": "2000000",
"BriefDescription": "Floating point computational micro-ops retired."
},
{
"EventCode": "0x10",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "X87_COMP_OPS_EXE.FXCH.S",
"SampleAfterValue": "2000000",
"BriefDescription": "FXCH uops executed."
},
{
"PEBS": "2",
"EventCode": "0x10",
"Counter": "0,1",
"UMask": "0x82",
"EventName": "X87_COMP_OPS_EXE.FXCH.AR",
"SampleAfterValue": "2000000",
"BriefDescription": "FXCH uops retired."
},
{
"EventCode": "0x11",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "FP_ASSIST.S",
"SampleAfterValue": "10000",
"BriefDescription": "Floating point assists."
},
{
"EventCode": "0x11",
"Counter": "0,1",
"UMask": "0x81",
"EventName": "FP_ASSIST.AR",
"SampleAfterValue": "10000",
"BriefDescription": "Floating point assists for retired operations."
"UMask": "0x81"
},
{
"EventCode": "0xB0",
"BriefDescription": "Floating point assists.",
"Counter": "0,1",
"UMask": "0x0",
"EventName": "SIMD_UOPS_EXEC.S",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD micro-ops executed (excluding stores)."
"EventCode": "0x11",
"EventName": "FP_ASSIST.S",
"SampleAfterValue": "10000",
"UMask": "0x1"
},
{
"PEBS": "2",
"EventCode": "0xB0",
"BriefDescription": "SIMD assists invoked.",
"Counter": "0,1",
"UMask": "0x80",
"EventName": "SIMD_UOPS_EXEC.AR",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD micro-ops retired (excluding stores)."
},
{
"EventCode": "0xB1",
"Counter": "0,1",
"UMask": "0x0",
"EventName": "SIMD_SAT_UOP_EXEC.S",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD saturated arithmetic micro-ops executed."
},
{
"EventCode": "0xB1",
"Counter": "0,1",
"UMask": "0x80",
"EventName": "SIMD_SAT_UOP_EXEC.AR",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD saturated arithmetic micro-ops retired."
},
{
"EventCode": "0xB3",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "SIMD_UOP_TYPE_EXEC.MUL.S",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD packed multiply micro-ops executed"
},
{
"EventCode": "0xB3",
"Counter": "0,1",
"UMask": "0x81",
"EventName": "SIMD_UOP_TYPE_EXEC.MUL.AR",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD packed multiply micro-ops retired"
},
{
"EventCode": "0xB3",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "SIMD_UOP_TYPE_EXEC.SHIFT.S",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD packed shift micro-ops executed"
},
{
"EventCode": "0xB3",
"Counter": "0,1",
"UMask": "0x82",
"EventName": "SIMD_UOP_TYPE_EXEC.SHIFT.AR",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD packed shift micro-ops retired"
},
{
"EventCode": "0xB3",
"Counter": "0,1",
"UMask": "0x4",
"EventName": "SIMD_UOP_TYPE_EXEC.PACK.S",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD packed micro-ops executed"
},
{
"EventCode": "0xB3",
"Counter": "0,1",
"UMask": "0x84",
"EventName": "SIMD_UOP_TYPE_EXEC.PACK.AR",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD packed micro-ops retired"
},
{
"EventCode": "0xB3",
"Counter": "0,1",
"UMask": "0x8",
"EventName": "SIMD_UOP_TYPE_EXEC.UNPACK.S",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD unpacked micro-ops executed"
},
{
"EventCode": "0xB3",
"Counter": "0,1",
"UMask": "0x88",
"EventName": "SIMD_UOP_TYPE_EXEC.UNPACK.AR",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD unpacked micro-ops retired"
},
{
"EventCode": "0xB3",
"Counter": "0,1",
"UMask": "0x10",
"EventName": "SIMD_UOP_TYPE_EXEC.LOGICAL.S",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD packed logical micro-ops executed"
},
{
"EventCode": "0xB3",
"Counter": "0,1",
"UMask": "0x90",
"EventName": "SIMD_UOP_TYPE_EXEC.LOGICAL.AR",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD packed logical micro-ops retired"
},
{
"EventCode": "0xB3",
"Counter": "0,1",
"UMask": "0x20",
"EventName": "SIMD_UOP_TYPE_EXEC.ARITHMETIC.S",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD packed arithmetic micro-ops executed"
},
{
"EventCode": "0xB3",
"Counter": "0,1",
"UMask": "0xa0",
"EventName": "SIMD_UOP_TYPE_EXEC.ARITHMETIC.AR",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD packed arithmetic micro-ops retired"
},
{
"EventCode": "0xC7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "SIMD_INST_RETIRED.PACKED_SINGLE",
"SampleAfterValue": "2000000",
"BriefDescription": "Retired Streaming SIMD Extensions (SSE) packed-single instructions."
},
{
"EventCode": "0xC7",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "SIMD_INST_RETIRED.SCALAR_SINGLE",
"SampleAfterValue": "2000000",
"BriefDescription": "Retired Streaming SIMD Extensions (SSE) scalar-single instructions."
},
{
"EventCode": "0xC7",
"Counter": "0,1",
"UMask": "0x8",
"EventName": "SIMD_INST_RETIRED.SCALAR_DOUBLE",
"SampleAfterValue": "2000000",
"BriefDescription": "Retired Streaming SIMD Extensions 2 (SSE2) scalar-double instructions."
},
{
"EventCode": "0xC7",
"Counter": "0,1",
"UMask": "0x10",
"EventName": "SIMD_INST_RETIRED.VECTOR",
"SampleAfterValue": "2000000",
"BriefDescription": "Retired Streaming SIMD Extensions 2 (SSE2) vector instructions."
},
{
"EventCode": "0xCA",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "SIMD_COMP_INST_RETIRED.PACKED_SINGLE",
"SampleAfterValue": "2000000",
"BriefDescription": "Retired computational Streaming SIMD Extensions (SSE) packed-single instructions."
},
{
"EventCode": "0xCA",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "SIMD_COMP_INST_RETIRED.SCALAR_SINGLE",
"SampleAfterValue": "2000000",
"BriefDescription": "Retired computational Streaming SIMD Extensions (SSE) scalar-single instructions."
},
{
"EventCode": "0xCA",
"Counter": "0,1",
"UMask": "0x8",
"EventName": "SIMD_COMP_INST_RETIRED.SCALAR_DOUBLE",
"SampleAfterValue": "2000000",
"BriefDescription": "Retired computational Streaming SIMD Extensions 2 (SSE2) scalar-double instructions."
},
{
"EventCode": "0xCD",
"Counter": "0,1",
"UMask": "0x0",
"EventName": "SIMD_ASSIST",
"SampleAfterValue": "100000",
"BriefDescription": "SIMD assists invoked."
"UMask": "0x0"
},
{
"EventCode": "0xCE",
"BriefDescription": "Retired computational Streaming SIMD Extensions (SSE) packed-single instructions.",
"Counter": "0,1",
"UMask": "0x0",
"EventCode": "0xCA",
"EventName": "SIMD_COMP_INST_RETIRED.PACKED_SINGLE",
"SampleAfterValue": "2000000",
"UMask": "0x1"
},
{
"BriefDescription": "Retired computational Streaming SIMD Extensions 2 (SSE2) scalar-double instructions.",
"Counter": "0,1",
"EventCode": "0xCA",
"EventName": "SIMD_COMP_INST_RETIRED.SCALAR_DOUBLE",
"SampleAfterValue": "2000000",
"UMask": "0x8"
},
{
"BriefDescription": "Retired computational Streaming SIMD Extensions (SSE) scalar-single instructions.",
"Counter": "0,1",
"EventCode": "0xCA",
"EventName": "SIMD_COMP_INST_RETIRED.SCALAR_SINGLE",
"SampleAfterValue": "2000000",
"UMask": "0x2"
},
{
"BriefDescription": "SIMD Instructions retired.",
"Counter": "0,1",
"EventCode": "0xCE",
"EventName": "SIMD_INSTR_RETIRED",
"SampleAfterValue": "2000000",
"BriefDescription": "SIMD Instructions retired."
"UMask": "0x0"
},
{
"EventCode": "0xCF",
"BriefDescription": "Retired Streaming SIMD Extensions (SSE) packed-single instructions.",
"Counter": "0,1",
"UMask": "0x0",
"EventCode": "0xC7",
"EventName": "SIMD_INST_RETIRED.PACKED_SINGLE",
"SampleAfterValue": "2000000",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Streaming SIMD Extensions 2 (SSE2) scalar-double instructions.",
"Counter": "0,1",
"EventCode": "0xC7",
"EventName": "SIMD_INST_RETIRED.SCALAR_DOUBLE",
"SampleAfterValue": "2000000",
"UMask": "0x8"
},
{
"BriefDescription": "Retired Streaming SIMD Extensions (SSE) scalar-single instructions.",
"Counter": "0,1",
"EventCode": "0xC7",
"EventName": "SIMD_INST_RETIRED.SCALAR_SINGLE",
"SampleAfterValue": "2000000",
"UMask": "0x2"
},
{
"BriefDescription": "Retired Streaming SIMD Extensions 2 (SSE2) vector instructions.",
"Counter": "0,1",
"EventCode": "0xC7",
"EventName": "SIMD_INST_RETIRED.VECTOR",
"SampleAfterValue": "2000000",
"UMask": "0x10"
},
{
"BriefDescription": "Saturated arithmetic instructions retired.",
"Counter": "0,1",
"EventCode": "0xCF",
"EventName": "SIMD_SAT_INSTR_RETIRED",
"SampleAfterValue": "2000000",
"BriefDescription": "Saturated arithmetic instructions retired."
"UMask": "0x0"
},
{
"BriefDescription": "SIMD saturated arithmetic micro-ops retired.",
"Counter": "0,1",
"EventCode": "0xB1",
"EventName": "SIMD_SAT_UOP_EXEC.AR",
"SampleAfterValue": "2000000",
"UMask": "0x80"
},
{
"BriefDescription": "SIMD saturated arithmetic micro-ops executed.",
"Counter": "0,1",
"EventCode": "0xB1",
"EventName": "SIMD_SAT_UOP_EXEC.S",
"SampleAfterValue": "2000000",
"UMask": "0x0"
},
{
"BriefDescription": "SIMD micro-ops retired (excluding stores).",
"Counter": "0,1",
"EventCode": "0xB0",
"EventName": "SIMD_UOPS_EXEC.AR",
"PEBS": "2",
"SampleAfterValue": "2000000",
"UMask": "0x80"
},
{
"BriefDescription": "SIMD micro-ops executed (excluding stores).",
"Counter": "0,1",
"EventCode": "0xB0",
"EventName": "SIMD_UOPS_EXEC.S",
"SampleAfterValue": "2000000",
"UMask": "0x0"
},
{
"BriefDescription": "SIMD packed arithmetic micro-ops retired",
"Counter": "0,1",
"EventCode": "0xB3",
"EventName": "SIMD_UOP_TYPE_EXEC.ARITHMETIC.AR",
"SampleAfterValue": "2000000",
"UMask": "0xa0"
},
{
"BriefDescription": "SIMD packed arithmetic micro-ops executed",
"Counter": "0,1",
"EventCode": "0xB3",
"EventName": "SIMD_UOP_TYPE_EXEC.ARITHMETIC.S",
"SampleAfterValue": "2000000",
"UMask": "0x20"
},
{
"BriefDescription": "SIMD packed logical micro-ops retired",
"Counter": "0,1",
"EventCode": "0xB3",
"EventName": "SIMD_UOP_TYPE_EXEC.LOGICAL.AR",
"SampleAfterValue": "2000000",
"UMask": "0x90"
},
{
"BriefDescription": "SIMD packed logical micro-ops executed",
"Counter": "0,1",
"EventCode": "0xB3",
"EventName": "SIMD_UOP_TYPE_EXEC.LOGICAL.S",
"SampleAfterValue": "2000000",
"UMask": "0x10"
},
{
"BriefDescription": "SIMD packed multiply micro-ops retired",
"Counter": "0,1",
"EventCode": "0xB3",
"EventName": "SIMD_UOP_TYPE_EXEC.MUL.AR",
"SampleAfterValue": "2000000",
"UMask": "0x81"
},
{
"BriefDescription": "SIMD packed multiply micro-ops executed",
"Counter": "0,1",
"EventCode": "0xB3",
"EventName": "SIMD_UOP_TYPE_EXEC.MUL.S",
"SampleAfterValue": "2000000",
"UMask": "0x1"
},
{
"BriefDescription": "SIMD packed micro-ops retired",
"Counter": "0,1",
"EventCode": "0xB3",
"EventName": "SIMD_UOP_TYPE_EXEC.PACK.AR",
"SampleAfterValue": "2000000",
"UMask": "0x84"
},
{
"BriefDescription": "SIMD packed micro-ops executed",
"Counter": "0,1",
"EventCode": "0xB3",
"EventName": "SIMD_UOP_TYPE_EXEC.PACK.S",
"SampleAfterValue": "2000000",
"UMask": "0x4"
},
{
"BriefDescription": "SIMD packed shift micro-ops retired",
"Counter": "0,1",
"EventCode": "0xB3",
"EventName": "SIMD_UOP_TYPE_EXEC.SHIFT.AR",
"SampleAfterValue": "2000000",
"UMask": "0x82"
},
{
"BriefDescription": "SIMD packed shift micro-ops executed",
"Counter": "0,1",
"EventCode": "0xB3",
"EventName": "SIMD_UOP_TYPE_EXEC.SHIFT.S",
"SampleAfterValue": "2000000",
"UMask": "0x2"
},
{
"BriefDescription": "SIMD unpacked micro-ops retired",
"Counter": "0,1",
"EventCode": "0xB3",
"EventName": "SIMD_UOP_TYPE_EXEC.UNPACK.AR",
"SampleAfterValue": "2000000",
"UMask": "0x88"
},
{
"BriefDescription": "SIMD unpacked micro-ops executed",
"Counter": "0,1",
"EventCode": "0xB3",
"EventName": "SIMD_UOP_TYPE_EXEC.UNPACK.S",
"SampleAfterValue": "2000000",
"UMask": "0x8"
},
{
"BriefDescription": "Floating point computational micro-ops retired.",
"Counter": "0,1",
"EventCode": "0x10",
"EventName": "X87_COMP_OPS_EXE.ANY.AR",
"PEBS": "2",
"SampleAfterValue": "2000000",
"UMask": "0x81"
},
{
"BriefDescription": "Floating point computational micro-ops executed.",
"Counter": "0,1",
"EventCode": "0x10",
"EventName": "X87_COMP_OPS_EXE.ANY.S",
"SampleAfterValue": "2000000",
"UMask": "0x1"
},
{
"BriefDescription": "FXCH uops retired.",
"Counter": "0,1",
"EventCode": "0x10",
"EventName": "X87_COMP_OPS_EXE.FXCH.AR",
"PEBS": "2",
"SampleAfterValue": "2000000",
"UMask": "0x82"
},
{
"BriefDescription": "FXCH uops executed.",
"Counter": "0,1",
"EventCode": "0x10",
"EventName": "X87_COMP_OPS_EXE.FXCH.S",
"SampleAfterValue": "2000000",
"UMask": "0x2"
}
]

106
lib/libpmc/pmu-events/arch/x86/bonnell/frontend.json
View File

@ -1,83 +1,91 @@
[
{
"EventCode": "0x80",
"BriefDescription": "BACLEARS asserted.",
"Counter": "0,1",
"UMask": "0x3",
"EventName": "ICACHE.ACCESSES",
"SampleAfterValue": "200000",
"BriefDescription": "Instruction fetches."
"EventCode": "0xE6",
"EventName": "BACLEARS.ANY",
"SampleAfterValue": "2000000",
"UMask": "0x1"
},
{
"EventCode": "0x80",
"BriefDescription": "Cycles during which instruction fetches are stalled.",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "ICACHE.HIT",
"SampleAfterValue": "200000",
"BriefDescription": "Icache hit"
},
{
"EventCode": "0x80",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "ICACHE.MISSES",
"SampleAfterValue": "200000",
"BriefDescription": "Icache miss"
},
{
"EventCode": "0x86",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "CYCLES_ICACHE_MEM_STALLED.ICACHE_MEM_STALLED",
"SampleAfterValue": "2000000",
"BriefDescription": "Cycles during which instruction fetches are stalled."
"UMask": "0x1"
},
{
"EventCode": "0x87",
"BriefDescription": "Decode stall due to IQ full",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "DECODE_STALL.PFB_EMPTY",
"SampleAfterValue": "2000000",
"BriefDescription": "Decode stall due to PFB empty"
},
{
"EventCode": "0x87",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "DECODE_STALL.IQ_FULL",
"SampleAfterValue": "2000000",
"BriefDescription": "Decode stall due to IQ full"
"UMask": "0x2"
},
{
"EventCode": "0xAA",
"BriefDescription": "Decode stall due to PFB empty",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "MACRO_INSTS.NON_CISC_DECODED",
"EventCode": "0x87",
"EventName": "DECODE_STALL.PFB_EMPTY",
"SampleAfterValue": "2000000",
"BriefDescription": "Non-CISC nacro instructions decoded"
"UMask": "0x1"
},
{
"EventCode": "0xAA",
"BriefDescription": "Instruction fetches.",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "MACRO_INSTS.CISC_DECODED",
"SampleAfterValue": "2000000",
"BriefDescription": "CISC macro instructions decoded"
"EventCode": "0x80",
"EventName": "ICACHE.ACCESSES",
"SampleAfterValue": "200000",
"UMask": "0x3"
},
{
"EventCode": "0xAA",
"BriefDescription": "Icache hit",
"Counter": "0,1",
"UMask": "0x3",
"EventCode": "0x80",
"EventName": "ICACHE.HIT",
"SampleAfterValue": "200000",
"UMask": "0x1"
},
{
"BriefDescription": "Icache miss",
"Counter": "0,1",
"EventCode": "0x80",
"EventName": "ICACHE.MISSES",
"SampleAfterValue": "200000",
"UMask": "0x2"
},
{
"BriefDescription": "All Instructions decoded",
"Counter": "0,1",
"EventCode": "0xAA",
"EventName": "MACRO_INSTS.ALL_DECODED",
"SampleAfterValue": "2000000",
"BriefDescription": "All Instructions decoded"
"UMask": "0x3"
},
{
"EventCode": "0xA9",
"BriefDescription": "CISC macro instructions decoded",
"Counter": "0,1",
"UMask": "0x1",
"EventCode": "0xAA",
"EventName": "MACRO_INSTS.CISC_DECODED",
"SampleAfterValue": "2000000",
"UMask": "0x2"
},
{
"BriefDescription": "Non-CISC nacro instructions decoded",
"Counter": "0,1",
"EventCode": "0xAA",
"EventName": "MACRO_INSTS.NON_CISC_DECODED",
"SampleAfterValue": "2000000",
"UMask": "0x1"
},
{
"BriefDescription": "This event counts the cycles where 1 or more uops are issued by the micro-sequencer (MS), including microcode assists and inserted flows, and written to the IQ.",
"Counter": "0,1",
"CounterMask": "1",
"EventCode": "0xA9",
"EventName": "UOPS.MS_CYCLES",
"SampleAfterValue": "2000000",
"BriefDescription": "This event counts the cycles where 1 or more uops are issued by the micro-sequencer (MS), including microcode assists and inserted flows, and written to the IQ.",
"CounterMask": "1"
"UMask": "0x1"
}
]

194
lib/libpmc/pmu-events/arch/x86/bonnell/memory.json
View File

@ -1,154 +1,154 @@
[
{
"EventCode": "0x5",
"BriefDescription": "Nonzero segbase 1 bubble",
"Counter": "0,1",
"UMask": "0xf",
"EventName": "MISALIGN_MEM_REF.SPLIT",
"SampleAfterValue": "200000",
"BriefDescription": "Memory references that cross an 8-byte boundary."
},
{
"EventCode": "0x5",
"Counter": "0,1",
"UMask": "0x9",
"EventName": "MISALIGN_MEM_REF.LD_SPLIT",
"SampleAfterValue": "200000",
"BriefDescription": "Load splits"
},
{
"EventCode": "0x5",
"Counter": "0,1",
"UMask": "0xa",
"EventName": "MISALIGN_MEM_REF.ST_SPLIT",
"SampleAfterValue": "200000",
"BriefDescription": "Store splits"
},
{
"EventCode": "0x5",
"Counter": "0,1",
"UMask": "0x8f",
"EventName": "MISALIGN_MEM_REF.SPLIT.AR",
"SampleAfterValue": "200000",
"BriefDescription": "Memory references that cross an 8-byte boundary (At Retirement)"
},
{
"EventCode": "0x5",
"Counter": "0,1",
"UMask": "0x89",
"EventName": "MISALIGN_MEM_REF.LD_SPLIT.AR",
"SampleAfterValue": "200000",
"BriefDescription": "Load splits (At Retirement)"
},
{
"EventCode": "0x5",
"Counter": "0,1",
"UMask": "0x8a",
"EventName": "MISALIGN_MEM_REF.ST_SPLIT.AR",
"SampleAfterValue": "200000",
"BriefDescription": "Store splits (Ar Retirement)"
},
{
"EventCode": "0x5",
"Counter": "0,1",
"UMask": "0x8c",
"EventName": "MISALIGN_MEM_REF.RMW_SPLIT",
"SampleAfterValue": "200000",
"BriefDescription": "ld-op-st splits"
},
{
"EventCode": "0x5",
"Counter": "0,1",
"UMask": "0x97",
"EventName": "MISALIGN_MEM_REF.BUBBLE",
"SampleAfterValue": "200000",
"BriefDescription": "Nonzero segbase 1 bubble"
"UMask": "0x97"
},
{
"EventCode": "0x5",
"BriefDescription": "Nonzero segbase load 1 bubble",
"Counter": "0,1",
"UMask": "0x91",
"EventCode": "0x5",
"EventName": "MISALIGN_MEM_REF.LD_BUBBLE",
"SampleAfterValue": "200000",
"BriefDescription": "Nonzero segbase load 1 bubble"
"UMask": "0x91"
},
{
"EventCode": "0x5",
"BriefDescription": "Load splits",
"Counter": "0,1",
"UMask": "0x92",
"EventName": "MISALIGN_MEM_REF.ST_BUBBLE",
"EventCode": "0x5",
"EventName": "MISALIGN_MEM_REF.LD_SPLIT",
"SampleAfterValue": "200000",
"BriefDescription": "Nonzero segbase store 1 bubble"
"UMask": "0x9"
},
{
"EventCode": "0x5",
"BriefDescription": "Load splits (At Retirement)",
"Counter": "0,1",
"UMask": "0x94",
"EventCode": "0x5",
"EventName": "MISALIGN_MEM_REF.LD_SPLIT.AR",
"SampleAfterValue": "200000",
"UMask": "0x89"
},
{
"BriefDescription": "Nonzero segbase ld-op-st 1 bubble",
"Counter": "0,1",
"EventCode": "0x5",
"EventName": "MISALIGN_MEM_REF.RMW_BUBBLE",
"SampleAfterValue": "200000",
"BriefDescription": "Nonzero segbase ld-op-st 1 bubble"
"UMask": "0x94"
},
{
"EventCode": "0x7",
"BriefDescription": "ld-op-st splits",
"Counter": "0,1",
"UMask": "0x81",
"EventName": "PREFETCH.PREFETCHT0",
"EventCode": "0x5",
"EventName": "MISALIGN_MEM_REF.RMW_SPLIT",
"SampleAfterValue": "200000",
"BriefDescription": "Streaming SIMD Extensions (SSE) PrefetchT0 instructions executed."
"UMask": "0x8c"
},
{
"EventCode": "0x7",
"BriefDescription": "Memory references that cross an 8-byte boundary.",
"Counter": "0,1",
"UMask": "0x82",
"EventName": "PREFETCH.PREFETCHT1",
"EventCode": "0x5",
"EventName": "MISALIGN_MEM_REF.SPLIT",
"SampleAfterValue": "200000",
"BriefDescription": "Streaming SIMD Extensions (SSE) PrefetchT1 instructions executed."
"UMask": "0xf"
},
{
"EventCode": "0x7",
"BriefDescription": "Memory references that cross an 8-byte boundary (At Retirement)",
"Counter": "0,1",
"UMask": "0x84",
"EventName": "PREFETCH.PREFETCHT2",
"EventCode": "0x5",
"EventName": "MISALIGN_MEM_REF.SPLIT.AR",
"SampleAfterValue": "200000",
"BriefDescription": "Streaming SIMD Extensions (SSE) PrefetchT2 instructions executed."
"UMask": "0x8f"
},
{
"EventCode": "0x7",
"BriefDescription": "Nonzero segbase store 1 bubble",
"Counter": "0,1",
"UMask": "0x86",
"EventName": "PREFETCH.SW_L2",
"EventCode": "0x5",
"EventName": "MISALIGN_MEM_REF.ST_BUBBLE",
"SampleAfterValue": "200000",
"BriefDescription": "Streaming SIMD Extensions (SSE) PrefetchT1 and PrefetchT2 instructions executed"
"UMask": "0x92"
},
{
"EventCode": "0x7",
"BriefDescription": "Store splits",
"Counter": "0,1",
"UMask": "0x88",
"EventName": "PREFETCH.PREFETCHNTA",
"EventCode": "0x5",
"EventName": "MISALIGN_MEM_REF.ST_SPLIT",
"SampleAfterValue": "200000",
"BriefDescription": "Streaming SIMD Extensions (SSE) Prefetch NTA instructions executed"
"UMask": "0xa"
},
{
"EventCode": "0x7",
"BriefDescription": "Store splits (Ar Retirement)",
"Counter": "0,1",
"UMask": "0x10",
"EventCode": "0x5",
"EventName": "MISALIGN_MEM_REF.ST_SPLIT.AR",
"SampleAfterValue": "200000",
"UMask": "0x8a"
},
{
"BriefDescription": "L1 hardware prefetch request",
"Counter": "0,1",
"EventCode": "0x7",
"EventName": "PREFETCH.HW_PREFETCH",
"SampleAfterValue": "2000000",
"BriefDescription": "L1 hardware prefetch request"
"UMask": "0x10"
},
{
"EventCode": "0x7",
"BriefDescription": "Streaming SIMD Extensions (SSE) Prefetch NTA instructions executed",
"Counter": "0,1",
"UMask": "0xf",
"EventCode": "0x7",
"EventName": "PREFETCH.PREFETCHNTA",
"SampleAfterValue": "200000",
"UMask": "0x88"
},
{
"BriefDescription": "Streaming SIMD Extensions (SSE) PrefetchT0 instructions executed.",
"Counter": "0,1",
"EventCode": "0x7",
"EventName": "PREFETCH.PREFETCHT0",
"SampleAfterValue": "200000",
"UMask": "0x81"
},
{
"BriefDescription": "Streaming SIMD Extensions (SSE) PrefetchT1 instructions executed.",
"Counter": "0,1",
"EventCode": "0x7",
"EventName": "PREFETCH.PREFETCHT1",
"SampleAfterValue": "200000",
"UMask": "0x82"
},
{
"BriefDescription": "Streaming SIMD Extensions (SSE) PrefetchT2 instructions executed.",
"Counter": "0,1",
"EventCode": "0x7",
"EventName": "PREFETCH.PREFETCHT2",
"SampleAfterValue": "200000",
"UMask": "0x84"
},
{
"BriefDescription": "Any Software prefetch",
"Counter": "0,1",
"EventCode": "0x7",
"EventName": "PREFETCH.SOFTWARE_PREFETCH",
"SampleAfterValue": "200000",
"BriefDescription": "Any Software prefetch"
"UMask": "0xf"
},
{
"EventCode": "0x7",
"BriefDescription": "Any Software prefetch",
"Counter": "0,1",
"UMask": "0x8f",
"EventCode": "0x7",
"EventName": "PREFETCH.SOFTWARE_PREFETCH.AR",
"SampleAfterValue": "200000",
"BriefDescription": "Any Software prefetch"
"UMask": "0x8f"
},
{
"BriefDescription": "Streaming SIMD Extensions (SSE) PrefetchT1 and PrefetchT2 instructions executed",
"Counter": "0,1",
"EventCode": "0x7",
"EventName": "PREFETCH.SW_L2",
"SampleAfterValue": "200000",
"UMask": "0x86"
}
]

828
lib/libpmc/pmu-events/arch/x86/bonnell/other.json
View File

@ -1,450 +1,450 @@
[
{
"EventCode": "0x6",
"BriefDescription": "Bus queue is empty.",
"Counter": "0,1",
"UMask": "0x80",
"EventName": "SEGMENT_REG_LOADS.ANY",
"SampleAfterValue": "200000",
"BriefDescription": "Number of segment register loads."
},
{
"EventCode": "0x9",
"Counter": "0,1",
"UMask": "0x20",
"EventName": "DISPATCH_BLOCKED.ANY",
"SampleAfterValue": "200000",
"BriefDescription": "Memory cluster signals to block micro-op dispatch for any reason"
},
{
"EventCode": "0x3A",
"Counter": "0,1",
"UMask": "0x0",
"EventName": "EIST_TRANS",
"SampleAfterValue": "200000",
"BriefDescription": "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions"
},
{
"EventCode": "0x3B",
"Counter": "0,1",
"UMask": "0xc0",
"EventName": "THERMAL_TRIP",
"SampleAfterValue": "200000",
"BriefDescription": "Number of thermal trips"
},
{
"EventCode": "0x60",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "BUS_REQUEST_OUTSTANDING.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "Outstanding cacheable data read bus requests duration."
},
{
"EventCode": "0x60",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_REQUEST_OUTSTANDING.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "Outstanding cacheable data read bus requests duration."
},
{
"EventCode": "0x61",
"Counter": "0,1",
"UMask": "0x20",
"EventName": "BUS_BNR_DRV.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "Number of Bus Not Ready signals asserted."
},
{
"EventCode": "0x61",
"Counter": "0,1",
"UMask": "0x0",
"EventName": "BUS_BNR_DRV.THIS_AGENT",
"SampleAfterValue": "200000",
"BriefDescription": "Number of Bus Not Ready signals asserted."
},
{
"EventCode": "0x62",
"Counter": "0,1",
"UMask": "0x20",
"EventName": "BUS_DRDY_CLOCKS.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "Bus cycles when data is sent on the bus."
},
{
"EventCode": "0x62",
"Counter": "0,1",
"UMask": "0x0",
"EventName": "BUS_DRDY_CLOCKS.THIS_AGENT",
"SampleAfterValue": "200000",
"BriefDescription": "Bus cycles when data is sent on the bus."
},
{
"EventCode": "0x63",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "BUS_LOCK_CLOCKS.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "Bus cycles when a LOCK signal is asserted."
},
{
"EventCode": "0x63",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_LOCK_CLOCKS.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "Bus cycles when a LOCK signal is asserted."
},
{
"EventCode": "0x64",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_DATA_RCV.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "Bus cycles while processor receives data."
},
{
"EventCode": "0x65",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "BUS_TRANS_BRD.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "Burst read bus transactions."
},
{
"EventCode": "0x65",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_TRANS_BRD.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "Burst read bus transactions."
},
{
"EventCode": "0x66",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "BUS_TRANS_RFO.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "RFO bus transactions."
},
{
"EventCode": "0x66",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_TRANS_RFO.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "RFO bus transactions."
},
{
"EventCode": "0x67",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "BUS_TRANS_WB.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "Explicit writeback bus transactions."
},
{
"EventCode": "0x67",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_TRANS_WB.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "Explicit writeback bus transactions."
},
{
"EventCode": "0x68",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "BUS_TRANS_IFETCH.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "Instruction-fetch bus transactions."
},
{
"EventCode": "0x68",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_TRANS_IFETCH.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "Instruction-fetch bus transactions."
},
{
"EventCode": "0x69",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "BUS_TRANS_INVAL.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "Invalidate bus transactions."
},
{
"EventCode": "0x69",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_TRANS_INVAL.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "Invalidate bus transactions."
},
{
"EventCode": "0x6A",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "BUS_TRANS_PWR.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "Partial write bus transaction."
},
{
"EventCode": "0x6A",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_TRANS_PWR.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "Partial write bus transaction."
},
{
"EventCode": "0x6B",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "BUS_TRANS_P.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "Partial bus transactions."
},
{
"EventCode": "0x6B",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_TRANS_P.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "Partial bus transactions."
},
{
"EventCode": "0x6C",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "BUS_TRANS_IO.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "IO bus transactions."
},
{
"EventCode": "0x6C",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_TRANS_IO.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "IO bus transactions."
},
{
"EventCode": "0x6D",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "BUS_TRANS_DEF.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "Deferred bus transactions."
},
{
"EventCode": "0x6D",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_TRANS_DEF.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "Deferred bus transactions."
},
{
"EventCode": "0x6E",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "BUS_TRANS_BURST.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "Burst (full cache-line) bus transactions."
},
{
"EventCode": "0x6E",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_TRANS_BURST.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "Burst (full cache-line) bus transactions."
},
{
"EventCode": "0x6F",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "BUS_TRANS_MEM.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "Memory bus transactions."
},
{
"EventCode": "0x6F",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_TRANS_MEM.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "Memory bus transactions."
},
{
"EventCode": "0x70",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "BUS_TRANS_ANY.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "All bus transactions."
},
{
"EventCode": "0x70",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_TRANS_ANY.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "All bus transactions."
},
{
"EventCode": "0x77",
"Counter": "0,1",
"UMask": "0xb",
"EventName": "EXT_SNOOP.THIS_AGENT.ANY",
"SampleAfterValue": "200000",
"BriefDescription": "External snoops."
},
{
"EventCode": "0x77",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "EXT_SNOOP.THIS_AGENT.CLEAN",
"SampleAfterValue": "200000",
"BriefDescription": "External snoops."
},
{
"EventCode": "0x77",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "EXT_SNOOP.THIS_AGENT.HIT",
"SampleAfterValue": "200000",
"BriefDescription": "External snoops."
},
{
"EventCode": "0x77",
"Counter": "0,1",
"UMask": "0x8",
"EventName": "EXT_SNOOP.THIS_AGENT.HITM",
"SampleAfterValue": "200000",
"BriefDescription": "External snoops."
},
{
"EventCode": "0x77",
"Counter": "0,1",
"UMask": "0x2b",
"EventName": "EXT_SNOOP.ALL_AGENTS.ANY",
"SampleAfterValue": "200000",
"BriefDescription": "External snoops."
},
{
"EventCode": "0x77",
"Counter": "0,1",
"UMask": "0x21",
"EventName": "EXT_SNOOP.ALL_AGENTS.CLEAN",
"SampleAfterValue": "200000",
"BriefDescription": "External snoops."
},
{
"EventCode": "0x77",
"Counter": "0,1",
"UMask": "0x22",
"EventName": "EXT_SNOOP.ALL_AGENTS.HIT",
"SampleAfterValue": "200000",
"BriefDescription": "External snoops."
},
{
"EventCode": "0x77",
"Counter": "0,1",
"UMask": "0x28",
"EventName": "EXT_SNOOP.ALL_AGENTS.HITM",
"SampleAfterValue": "200000",
"BriefDescription": "External snoops."
},
{
"EventCode": "0x7A",
"Counter": "0,1",
"UMask": "0x20",
"EventName": "BUS_HIT_DRV.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "HIT signal asserted."
},
{
"EventCode": "0x7A",
"Counter": "0,1",
"UMask": "0x0",
"EventName": "BUS_HIT_DRV.THIS_AGENT",
"SampleAfterValue": "200000",
"BriefDescription": "HIT signal asserted."
},
{
"EventCode": "0x7B",
"Counter": "0,1",
"UMask": "0x20",
"EventName": "BUS_HITM_DRV.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "HITM signal asserted."
},
{
"EventCode": "0x7B",
"Counter": "0,1",
"UMask": "0x0",
"EventName": "BUS_HITM_DRV.THIS_AGENT",
"SampleAfterValue": "200000",
"BriefDescription": "HITM signal asserted."
},
{
"EventCode": "0x7D",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUSQ_EMPTY.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "Bus queue is empty."
"UMask": "0x40"
},
{
"EventCode": "0x7E",
"BriefDescription": "Number of Bus Not Ready signals asserted.",
"Counter": "0,1",
"UMask": "0xe0",
"EventName": "SNOOP_STALL_DRV.ALL_AGENTS",
"EventCode": "0x61",
"EventName": "BUS_BNR_DRV.ALL_AGENTS",
"SampleAfterValue": "200000",
"BriefDescription": "Bus stalled for snoops."
"UMask": "0x20"
},
{
"EventCode": "0x7E",
"BriefDescription": "Number of Bus Not Ready signals asserted.",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "SNOOP_STALL_DRV.SELF",
"EventCode": "0x61",
"EventName": "BUS_BNR_DRV.THIS_AGENT",
"SampleAfterValue": "200000",
"BriefDescription": "Bus stalled for snoops."
"UMask": "0x0"
},
{
"BriefDescription": "Bus cycles while processor receives data.",
"Counter": "0,1",
"EventCode": "0x64",
"EventName": "BUS_DATA_RCV.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "Bus cycles when data is sent on the bus.",
"Counter": "0,1",
"EventCode": "0x62",
"EventName": "BUS_DRDY_CLOCKS.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0x20"
},
{
"BriefDescription": "Bus cycles when data is sent on the bus.",
"Counter": "0,1",
"EventCode": "0x62",
"EventName": "BUS_DRDY_CLOCKS.THIS_AGENT",
"SampleAfterValue": "200000",
"UMask": "0x0"
},
{
"BriefDescription": "HITM signal asserted.",
"Counter": "0,1",
"EventCode": "0x7B",
"EventName": "BUS_HITM_DRV.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0x20"
},
{
"BriefDescription": "HITM signal asserted.",
"Counter": "0,1",
"EventCode": "0x7B",
"EventName": "BUS_HITM_DRV.THIS_AGENT",
"SampleAfterValue": "200000",
"UMask": "0x0"
},
{
"BriefDescription": "HIT signal asserted.",
"Counter": "0,1",
"EventCode": "0x7A",
"EventName": "BUS_HIT_DRV.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0x20"
},
{
"BriefDescription": "HIT signal asserted.",
"Counter": "0,1",
"EventCode": "0x7A",
"EventName": "BUS_HIT_DRV.THIS_AGENT",
"SampleAfterValue": "200000",
"UMask": "0x0"
},
{
"BriefDescription": "IO requests waiting in the bus queue.",
"Counter": "0,1",
"EventCode": "0x7F",
"Counter": "0,1",
"UMask": "0x40",
"EventName": "BUS_IO_WAIT.SELF",
"SampleAfterValue": "200000",
"BriefDescription": "IO requests waiting in the bus queue."
"UMask": "0x40"
},
{
"EventCode": "0xC6",
"BriefDescription": "Bus cycles when a LOCK signal is asserted.",
"Counter": "0,1",
"UMask": "0x1",
"EventCode": "0x63",
"EventName": "BUS_LOCK_CLOCKS.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "Bus cycles when a LOCK signal is asserted.",
"Counter": "0,1",
"EventCode": "0x63",
"EventName": "BUS_LOCK_CLOCKS.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "Outstanding cacheable data read bus requests duration.",
"Counter": "0,1",
"EventCode": "0x60",
"EventName": "BUS_REQUEST_OUTSTANDING.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "Outstanding cacheable data read bus requests duration.",
"Counter": "0,1",
"EventCode": "0x60",
"EventName": "BUS_REQUEST_OUTSTANDING.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "All bus transactions.",
"Counter": "0,1",
"EventCode": "0x70",
"EventName": "BUS_TRANS_ANY.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "All bus transactions.",
"Counter": "0,1",
"EventCode": "0x70",
"EventName": "BUS_TRANS_ANY.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "Burst read bus transactions.",
"Counter": "0,1",
"EventCode": "0x65",
"EventName": "BUS_TRANS_BRD.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "Burst read bus transactions.",
"Counter": "0,1",
"EventCode": "0x65",
"EventName": "BUS_TRANS_BRD.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "Burst (full cache-line) bus transactions.",
"Counter": "0,1",
"EventCode": "0x6E",
"EventName": "BUS_TRANS_BURST.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "Burst (full cache-line) bus transactions.",
"Counter": "0,1",
"EventCode": "0x6E",
"EventName": "BUS_TRANS_BURST.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "Deferred bus transactions.",
"Counter": "0,1",
"EventCode": "0x6D",
"EventName": "BUS_TRANS_DEF.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "Deferred bus transactions.",
"Counter": "0,1",
"EventCode": "0x6D",
"EventName": "BUS_TRANS_DEF.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "Instruction-fetch bus transactions.",
"Counter": "0,1",
"EventCode": "0x68",
"EventName": "BUS_TRANS_IFETCH.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "Instruction-fetch bus transactions.",
"Counter": "0,1",
"EventCode": "0x68",
"EventName": "BUS_TRANS_IFETCH.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "Invalidate bus transactions.",
"Counter": "0,1",
"EventCode": "0x69",
"EventName": "BUS_TRANS_INVAL.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "Invalidate bus transactions.",
"Counter": "0,1",
"EventCode": "0x69",
"EventName": "BUS_TRANS_INVAL.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "IO bus transactions.",
"Counter": "0,1",
"EventCode": "0x6C",
"EventName": "BUS_TRANS_IO.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "IO bus transactions.",
"Counter": "0,1",
"EventCode": "0x6C",
"EventName": "BUS_TRANS_IO.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "Memory bus transactions.",
"Counter": "0,1",
"EventCode": "0x6F",
"EventName": "BUS_TRANS_MEM.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "Memory bus transactions.",
"Counter": "0,1",
"EventCode": "0x6F",
"EventName": "BUS_TRANS_MEM.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "Partial bus transactions.",
"Counter": "0,1",
"EventCode": "0x6B",
"EventName": "BUS_TRANS_P.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "Partial bus transactions.",
"Counter": "0,1",
"EventCode": "0x6B",
"EventName": "BUS_TRANS_P.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "Partial write bus transaction.",
"Counter": "0,1",
"EventCode": "0x6A",
"EventName": "BUS_TRANS_PWR.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "Partial write bus transaction.",
"Counter": "0,1",
"EventCode": "0x6A",
"EventName": "BUS_TRANS_PWR.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "RFO bus transactions.",
"Counter": "0,1",
"EventCode": "0x66",
"EventName": "BUS_TRANS_RFO.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "RFO bus transactions.",
"Counter": "0,1",
"EventCode": "0x66",
"EventName": "BUS_TRANS_RFO.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "Explicit writeback bus transactions.",
"Counter": "0,1",
"EventCode": "0x67",
"EventName": "BUS_TRANS_WB.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "Explicit writeback bus transactions.",
"Counter": "0,1",
"EventCode": "0x67",
"EventName": "BUS_TRANS_WB.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "Cycles during which interrupts are disabled.",
"Counter": "0,1",
"EventCode": "0xC6",
"EventName": "CYCLES_INT_MASKED.CYCLES_INT_MASKED",
"SampleAfterValue": "2000000",
"BriefDescription": "Cycles during which interrupts are disabled."
"UMask": "0x1"
},
{
"EventCode": "0xC6",
"BriefDescription": "Cycles during which interrupts are pending and disabled.",
"Counter": "0,1",
"UMask": "0x2",
"EventCode": "0xC6",
"EventName": "CYCLES_INT_MASKED.CYCLES_INT_PENDING_AND_MASKED",
"SampleAfterValue": "2000000",
"BriefDescription": "Cycles during which interrupts are pending and disabled."
"UMask": "0x2"
},
{
"EventCode": "0xC8",
"BriefDescription": "Memory cluster signals to block micro-op dispatch for any reason",
"Counter": "0,1",
"UMask": "0x0",
"EventCode": "0x9",
"EventName": "DISPATCH_BLOCKED.ANY",
"SampleAfterValue": "200000",
"UMask": "0x20"
},
{
"BriefDescription": "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions",
"Counter": "0,1",
"EventCode": "0x3A",
"EventName": "EIST_TRANS",
"SampleAfterValue": "200000",
"UMask": "0x0"
},
{
"BriefDescription": "External snoops.",
"Counter": "0,1",
"EventCode": "0x77",
"EventName": "EXT_SNOOP.ALL_AGENTS.ANY",
"SampleAfterValue": "200000",
"UMask": "0x2b"
},
{
"BriefDescription": "External snoops.",
"Counter": "0,1",
"EventCode": "0x77",
"EventName": "EXT_SNOOP.ALL_AGENTS.CLEAN",
"SampleAfterValue": "200000",
"UMask": "0x21"
},
{
"BriefDescription": "External snoops.",
"Counter": "0,1",
"EventCode": "0x77",
"EventName": "EXT_SNOOP.ALL_AGENTS.HIT",
"SampleAfterValue": "200000",
"UMask": "0x22"
},
{
"BriefDescription": "External snoops.",
"Counter": "0,1",
"EventCode": "0x77",
"EventName": "EXT_SNOOP.ALL_AGENTS.HITM",
"SampleAfterValue": "200000",
"UMask": "0x28"
},
{
"BriefDescription": "External snoops.",
"Counter": "0,1",
"EventCode": "0x77",
"EventName": "EXT_SNOOP.THIS_AGENT.ANY",
"SampleAfterValue": "200000",
"UMask": "0xb"
},
{
"BriefDescription": "External snoops.",
"Counter": "0,1",
"EventCode": "0x77",
"EventName": "EXT_SNOOP.THIS_AGENT.CLEAN",
"SampleAfterValue": "200000",
"UMask": "0x1"
},
{
"BriefDescription": "External snoops.",
"Counter": "0,1",
"EventCode": "0x77",
"EventName": "EXT_SNOOP.THIS_AGENT.HIT",
"SampleAfterValue": "200000",
"UMask": "0x2"
},
{
"BriefDescription": "External snoops.",
"Counter": "0,1",
"EventCode": "0x77",
"EventName": "EXT_SNOOP.THIS_AGENT.HITM",
"SampleAfterValue": "200000",
"UMask": "0x8"
},
{
"BriefDescription": "Hardware interrupts received.",
"Counter": "0,1",
"EventCode": "0xC8",
"EventName": "HW_INT_RCV",
"SampleAfterValue": "200000",
"BriefDescription": "Hardware interrupts received."
"UMask": "0x0"
},
{
"BriefDescription": "Number of segment register loads.",
"Counter": "0,1",
"EventCode": "0x6",
"EventName": "SEGMENT_REG_LOADS.ANY",
"SampleAfterValue": "200000",
"UMask": "0x80"
},
{
"BriefDescription": "Bus stalled for snoops.",
"Counter": "0,1",
"EventCode": "0x7E",
"EventName": "SNOOP_STALL_DRV.ALL_AGENTS",
"SampleAfterValue": "200000",
"UMask": "0xe0"
},
{
"BriefDescription": "Bus stalled for snoops.",
"Counter": "0,1",
"EventCode": "0x7E",
"EventName": "SNOOP_STALL_DRV.SELF",
"SampleAfterValue": "200000",
"UMask": "0x40"
},
{
"BriefDescription": "Number of thermal trips",
"Counter": "0,1",
"EventCode": "0x3B",
"EventName": "THERMAL_TRIP",
"SampleAfterValue": "200000",
"UMask": "0xc0"
}
]

676
lib/libpmc/pmu-events/arch/x86/bonnell/pipeline.json
View File

@ -1,364 +1,356 @@
[
{
"EventCode": "0x2",
"BriefDescription": "Bogus branches",
"Counter": "0,1",
"UMask": "0x83",
"EventName": "STORE_FORWARDS.ANY",
"SampleAfterValue": "200000",
"BriefDescription": "All store forwards"
},
{
"EventCode": "0x2",
"Counter": "0,1",
"UMask": "0x81",
"EventName": "STORE_FORWARDS.GOOD",
"SampleAfterValue": "200000",
"BriefDescription": "Good store forwards"
},
{
"EventCode": "0x3",
"Counter": "0,1",
"UMask": "0x7f",
"EventName": "REISSUE.ANY",
"SampleAfterValue": "200000",
"BriefDescription": "Micro-op reissues for any cause"
},
{
"EventCode": "0x3",
"Counter": "0,1",
"UMask": "0xff",
"EventName": "REISSUE.ANY.AR",
"SampleAfterValue": "200000",
"BriefDescription": "Micro-op reissues for any cause (At Retirement)"
},
{
"EventCode": "0x12",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "MUL.S",
"SampleAfterValue": "2000000",
"BriefDescription": "Multiply operations executed."
},
{
"EventCode": "0x12",
"Counter": "0,1",
"UMask": "0x81",
"EventName": "MUL.AR",
"SampleAfterValue": "2000000",
"BriefDescription": "Multiply operations retired"
},
{
"EventCode": "0x13",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "DIV.S",
"SampleAfterValue": "2000000",
"BriefDescription": "Divide operations executed."
},
{
"EventCode": "0x13",
"Counter": "0,1",
"UMask": "0x81",
"EventName": "DIV.AR",
"SampleAfterValue": "2000000",
"BriefDescription": "Divide operations retired"
},
{
"EventCode": "0x14",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "CYCLES_DIV_BUSY",
"SampleAfterValue": "2000000",
"BriefDescription": "Cycles the divider is busy."
},
{
"EventCode": "0x3C",
"Counter": "0,1",
"UMask": "0x0",
"EventName": "CPU_CLK_UNHALTED.CORE_P",
"SampleAfterValue": "2000000",
"BriefDescription": "Core cycles when core is not halted"
},
{
"EventCode": "0x3C",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "CPU_CLK_UNHALTED.BUS",
"SampleAfterValue": "200000",
"BriefDescription": "Bus cycles when core is not halted"
},
{
"EventCode": "0xA",
"Counter": "Fixed counter 2",
"UMask": "0x0",
"EventName": "CPU_CLK_UNHALTED.CORE",
"SampleAfterValue": "2000000",
"BriefDescription": "Core cycles when core is not halted"
},
{
"EventCode": "0xA",
"Counter": "Fixed counter 3",
"UMask": "0x0",
"EventName": "CPU_CLK_UNHALTED.REF",
"SampleAfterValue": "2000000",
"BriefDescription": "Reference cycles when core is not halted."
},
{
"EventCode": "0x88",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "BR_INST_TYPE_RETIRED.COND",
"SampleAfterValue": "2000000",
"BriefDescription": "All macro conditional branch instructions."
},
{
"EventCode": "0x88",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "BR_INST_TYPE_RETIRED.UNCOND",
"SampleAfterValue": "2000000",
"BriefDescription": "All macro unconditional branch instructions, excluding calls and indirects"
},
{
"EventCode": "0x88",
"Counter": "0,1",
"UMask": "0x4",
"EventName": "BR_INST_TYPE_RETIRED.IND",
"SampleAfterValue": "2000000",
"BriefDescription": "All indirect branches that are not calls."
},
{
"EventCode": "0x88",
"Counter": "0,1",
"UMask": "0x8",
"EventName": "BR_INST_TYPE_RETIRED.RET",
"SampleAfterValue": "2000000",
"BriefDescription": "All indirect branches that have a return mnemonic"
},
{
"EventCode": "0x88",
"Counter": "0,1",
"UMask": "0x10",
"EventName": "BR_INST_TYPE_RETIRED.DIR_CALL",
"SampleAfterValue": "2000000",
"BriefDescription": "All non-indirect calls"
},
{
"EventCode": "0x88",
"Counter": "0,1",
"UMask": "0x20",
"EventName": "BR_INST_TYPE_RETIRED.IND_CALL",
"SampleAfterValue": "2000000",
"BriefDescription": "All indirect calls, including both register and memory indirect."
},
{
"EventCode": "0x88",
"Counter": "0,1",
"UMask": "0x41",
"EventName": "BR_INST_TYPE_RETIRED.COND_TAKEN",
"SampleAfterValue": "2000000",
"BriefDescription": "Only taken macro conditional branch instructions"
},
{
"EventCode": "0x89",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "BR_MISSP_TYPE_RETIRED.COND",
"SampleAfterValue": "200000",
"BriefDescription": "Mispredicted cond branch instructions retired"
},
{
"EventCode": "0x89",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "BR_MISSP_TYPE_RETIRED.IND",
"SampleAfterValue": "200000",
"BriefDescription": "Mispredicted ind branches that are not calls"
},
{
"EventCode": "0x89",
"Counter": "0,1",
"UMask": "0x4",
"EventName": "BR_MISSP_TYPE_RETIRED.RETURN",
"SampleAfterValue": "200000",
"BriefDescription": "Mispredicted return branches"
},
{
"EventCode": "0x89",
"Counter": "0,1",
"UMask": "0x8",
"EventName": "BR_MISSP_TYPE_RETIRED.IND_CALL",
"SampleAfterValue": "200000",
"BriefDescription": "Mispredicted indirect calls, including both register and memory indirect."
},
{
"EventCode": "0x89",
"Counter": "0,1",
"UMask": "0x11",
"EventName": "BR_MISSP_TYPE_RETIRED.COND_TAKEN",
"SampleAfterValue": "200000",
"BriefDescription": "Mispredicted and taken cond branch instructions retired"
},
{
"PEBS": "2",
"EventCode": "0xC0",
"Counter": "0,1",
"UMask": "0x0",
"EventName": "INST_RETIRED.ANY_P",
"SampleAfterValue": "2000000",
"BriefDescription": "Instructions retired (precise event)."
},
{
"EventCode": "0xA",
"Counter": "Fixed counter 1",
"UMask": "0x0",
"EventName": "INST_RETIRED.ANY",
"SampleAfterValue": "2000000",
"BriefDescription": "Instructions retired."
},
{
"EventCode": "0xC2",
"Counter": "0,1",
"UMask": "0x10",
"EventName": "UOPS_RETIRED.ANY",
"SampleAfterValue": "2000000",
"BriefDescription": "Micro-ops retired."
},
{
"EventCode": "0xC2",
"Counter": "0,1",
"UMask": "0x10",
"EventName": "UOPS_RETIRED.STALLED_CYCLES",
"SampleAfterValue": "2000000",
"BriefDescription": "Cycles no micro-ops retired."
},
{
"EventCode": "0xC2",
"Counter": "0,1",
"UMask": "0x10",
"EventName": "UOPS_RETIRED.STALLS",
"SampleAfterValue": "2000000",
"BriefDescription": "Periods no micro-ops retired."
},
{
"EventCode": "0xC3",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "MACHINE_CLEARS.SMC",
"SampleAfterValue": "200000",
"BriefDescription": "Self-Modifying Code detected."
},
{
"EventCode": "0xC4",
"Counter": "0,1",
"UMask": "0x0",
"EventName": "BR_INST_RETIRED.ANY",
"SampleAfterValue": "2000000",
"BriefDescription": "Retired branch instructions."
},
{
"EventCode": "0xC4",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "BR_INST_RETIRED.PRED_NOT_TAKEN",
"SampleAfterValue": "2000000",
"BriefDescription": "Retired branch instructions that were predicted not-taken."
},
{
"EventCode": "0xC4",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "BR_INST_RETIRED.MISPRED_NOT_TAKEN",
"SampleAfterValue": "200000",
"BriefDescription": "Retired branch instructions that were mispredicted not-taken."
},
{
"EventCode": "0xC4",
"Counter": "0,1",
"UMask": "0x4",
"EventName": "BR_INST_RETIRED.PRED_TAKEN",
"SampleAfterValue": "2000000",
"BriefDescription": "Retired branch instructions that were predicted taken."
},
{
"EventCode": "0xC4",
"Counter": "0,1",
"UMask": "0x8",
"EventName": "BR_INST_RETIRED.MISPRED_TAKEN",
"SampleAfterValue": "200000",
"BriefDescription": "Retired branch instructions that were mispredicted taken."
},
{
"EventCode": "0xC4",
"Counter": "0,1",
"UMask": "0xc",
"EventName": "BR_INST_RETIRED.TAKEN",
"SampleAfterValue": "2000000",
"BriefDescription": "Retired taken branch instructions."
},
{
"EventCode": "0xC4",
"Counter": "0,1",
"UMask": "0xf",
"EventName": "BR_INST_RETIRED.ANY1",
"SampleAfterValue": "2000000",
"BriefDescription": "Retired branch instructions."
},
{
"PEBS": "1",
"EventCode": "0xC5",
"Counter": "0,1",
"UMask": "0x0",
"EventName": "BR_INST_RETIRED.MISPRED",
"SampleAfterValue": "200000",
"BriefDescription": "Retired mispredicted branch instructions (precise event)."
},
{
"EventCode": "0xDC",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "RESOURCE_STALLS.DIV_BUSY",
"SampleAfterValue": "2000000",
"BriefDescription": "Cycles issue is stalled due to div busy."
},
{
"EventCode": "0xE0",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "BR_INST_DECODED",
"SampleAfterValue": "2000000",
"BriefDescription": "Branch instructions decoded"
},
{
"EventCode": "0xE4",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "BOGUS_BR",
"SampleAfterValue": "2000000",
"BriefDescription": "Bogus branches"
"UMask": "0x1"
},
{
"EventCode": "0xE6",
"BriefDescription": "Branch instructions decoded",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "BACLEARS.ANY",
"EventCode": "0xE0",
"EventName": "BR_INST_DECODED",
"SampleAfterValue": "2000000",
"BriefDescription": "BACLEARS asserted."
"UMask": "0x1"
},
{
"EventCode": "0x3",
"BriefDescription": "Retired branch instructions.",
"Counter": "0,1",
"UMask": "0x1",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.ANY",
"SampleAfterValue": "2000000",
"UMask": "0x0"
},
{
"BriefDescription": "Retired branch instructions.",
"Counter": "0,1",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.ANY1",
"SampleAfterValue": "2000000",
"UMask": "0xf"
},
{
"BriefDescription": "Retired mispredicted branch instructions (precise event).",
"Counter": "0,1",
"EventCode": "0xC5",
"EventName": "BR_INST_RETIRED.MISPRED",
"PEBS": "1",
"SampleAfterValue": "200000",
"UMask": "0x0"
},
{
"BriefDescription": "Retired branch instructions that were mispredicted not-taken.",
"Counter": "0,1",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.MISPRED_NOT_TAKEN",
"SampleAfterValue": "200000",
"UMask": "0x2"
},
{
"BriefDescription": "Retired branch instructions that were mispredicted taken.",
"Counter": "0,1",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.MISPRED_TAKEN",
"SampleAfterValue": "200000",
"UMask": "0x8"
},
{
"BriefDescription": "Retired branch instructions that were predicted not-taken.",
"Counter": "0,1",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.PRED_NOT_TAKEN",
"SampleAfterValue": "2000000",
"UMask": "0x1"
},
{
"BriefDescription": "Retired branch instructions that were predicted taken.",
"Counter": "0,1",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.PRED_TAKEN",
"SampleAfterValue": "2000000",
"UMask": "0x4"
},
{
"BriefDescription": "Retired taken branch instructions.",
"Counter": "0,1",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.TAKEN",
"SampleAfterValue": "2000000",
"UMask": "0xc"
},
{
"BriefDescription": "All macro conditional branch instructions.",
"Counter": "0,1",
"EventCode": "0x88",
"EventName": "BR_INST_TYPE_RETIRED.COND",
"SampleAfterValue": "2000000",
"UMask": "0x1"
},
{
"BriefDescription": "Only taken macro conditional branch instructions",
"Counter": "0,1",
"EventCode": "0x88",
"EventName": "BR_INST_TYPE_RETIRED.COND_TAKEN",
"SampleAfterValue": "2000000",
"UMask": "0x41"
},
{
"BriefDescription": "All non-indirect calls",
"Counter": "0,1",
"EventCode": "0x88",
"EventName": "BR_INST_TYPE_RETIRED.DIR_CALL",
"SampleAfterValue": "2000000",
"UMask": "0x10"
},
{
"BriefDescription": "All indirect branches that are not calls.",
"Counter": "0,1",
"EventCode": "0x88",
"EventName": "BR_INST_TYPE_RETIRED.IND",
"SampleAfterValue": "2000000",
"UMask": "0x4"
},
{
"BriefDescription": "All indirect calls, including both register and memory indirect.",
"Counter": "0,1",
"EventCode": "0x88",
"EventName": "BR_INST_TYPE_RETIRED.IND_CALL",
"SampleAfterValue": "2000000",
"UMask": "0x20"
},
{
"BriefDescription": "All indirect branches that have a return mnemonic",
"Counter": "0,1",
"EventCode": "0x88",
"EventName": "BR_INST_TYPE_RETIRED.RET",
"SampleAfterValue": "2000000",
"UMask": "0x8"
},
{
"BriefDescription": "All macro unconditional branch instructions, excluding calls and indirects",
"Counter": "0,1",
"EventCode": "0x88",
"EventName": "BR_INST_TYPE_RETIRED.UNCOND",
"SampleAfterValue": "2000000",
"UMask": "0x2"
},
{
"BriefDescription": "Mispredicted cond branch instructions retired",
"Counter": "0,1",
"EventCode": "0x89",
"EventName": "BR_MISSP_TYPE_RETIRED.COND",
"SampleAfterValue": "200000",
"UMask": "0x1"
},
{
"BriefDescription": "Mispredicted and taken cond branch instructions retired",
"Counter": "0,1",
"EventCode": "0x89",
"EventName": "BR_MISSP_TYPE_RETIRED.COND_TAKEN",
"SampleAfterValue": "200000",
"UMask": "0x11"
},
{
"BriefDescription": "Mispredicted ind branches that are not calls",
"Counter": "0,1",
"EventCode": "0x89",
"EventName": "BR_MISSP_TYPE_RETIRED.IND",
"SampleAfterValue": "200000",
"UMask": "0x2"
},
{
"BriefDescription": "Mispredicted indirect calls, including both register and memory indirect.",
"Counter": "0,1",
"EventCode": "0x89",
"EventName": "BR_MISSP_TYPE_RETIRED.IND_CALL",
"SampleAfterValue": "200000",
"UMask": "0x8"
},
{
"BriefDescription": "Mispredicted return branches",
"Counter": "0,1",
"EventCode": "0x89",
"EventName": "BR_MISSP_TYPE_RETIRED.RETURN",
"SampleAfterValue": "200000",
"UMask": "0x4"
},
{
"BriefDescription": "Bus cycles when core is not halted",
"Counter": "0,1",
"EventCode": "0x3C",
"EventName": "CPU_CLK_UNHALTED.BUS",
"SampleAfterValue": "200000",
"UMask": "0x1"
},
{
"BriefDescription": "Core cycles when core is not halted",
"Counter": "Fixed counter 2",
"EventCode": "0xA",
"EventName": "CPU_CLK_UNHALTED.CORE",
"SampleAfterValue": "2000000",
"UMask": "0x0"
},
{
"BriefDescription": "Core cycles when core is not halted",
"Counter": "0,1",
"EventCode": "0x3C",
"EventName": "CPU_CLK_UNHALTED.CORE_P",
"SampleAfterValue": "2000000",
"UMask": "0x0"
},
{
"BriefDescription": "Reference cycles when core is not halted.",
"Counter": "Fixed counter 3",
"EventCode": "0xA",
"EventName": "CPU_CLK_UNHALTED.REF",
"SampleAfterValue": "2000000",
"UMask": "0x0"
},
{
"BriefDescription": "Cycles the divider is busy.",
"Counter": "0,1",
"EventCode": "0x14",
"EventName": "CYCLES_DIV_BUSY",
"SampleAfterValue": "2000000",
"UMask": "0x1"
},
{
"BriefDescription": "Divide operations retired",
"Counter": "0,1",
"EventCode": "0x13",
"EventName": "DIV.AR",
"SampleAfterValue": "2000000",
"UMask": "0x81"
},
{
"BriefDescription": "Divide operations executed.",
"Counter": "0,1",
"EventCode": "0x13",
"EventName": "DIV.S",
"SampleAfterValue": "2000000",
"UMask": "0x1"
},
{
"BriefDescription": "Instructions retired.",
"Counter": "Fixed counter 1",
"EventCode": "0xA",
"EventName": "INST_RETIRED.ANY",
"SampleAfterValue": "2000000",
"UMask": "0x0"
},
{
"BriefDescription": "Instructions retired (precise event).",
"Counter": "0,1",
"EventCode": "0xC0",
"EventName": "INST_RETIRED.ANY_P",
"PEBS": "2",
"SampleAfterValue": "2000000",
"UMask": "0x0"
},
{
"BriefDescription": "Self-Modifying Code detected.",
"Counter": "0,1",
"EventCode": "0xC3",
"EventName": "MACHINE_CLEARS.SMC",
"SampleAfterValue": "200000",
"UMask": "0x1"
},
{
"BriefDescription": "Multiply operations retired",
"Counter": "0,1",
"EventCode": "0x12",
"EventName": "MUL.AR",
"SampleAfterValue": "2000000",
"UMask": "0x81"
},
{
"BriefDescription": "Multiply operations executed.",
"Counter": "0,1",
"EventCode": "0x12",
"EventName": "MUL.S",
"SampleAfterValue": "2000000",
"UMask": "0x1"
},
{
"BriefDescription": "Micro-op reissues for any cause",
"Counter": "0,1",
"EventCode": "0x3",
"EventName": "REISSUE.ANY",
"SampleAfterValue": "200000",
"UMask": "0x7f"
},
{
"BriefDescription": "Micro-op reissues for any cause (At Retirement)",
"Counter": "0,1",
"EventCode": "0x3",
"EventName": "REISSUE.ANY.AR",
"SampleAfterValue": "200000",
"UMask": "0xff"
},
{
"BriefDescription": "Micro-op reissues on a store-load collision",
"Counter": "0,1",
"EventCode": "0x3",
"EventName": "REISSUE.OVERLAP_STORE",
"SampleAfterValue": "200000",
"BriefDescription": "Micro-op reissues on a store-load collision"
"UMask": "0x1"
},
{
"EventCode": "0x3",
"BriefDescription": "Micro-op reissues on a store-load collision (At Retirement)",
"Counter": "0,1",
"UMask": "0x81",
"EventCode": "0x3",
"EventName": "REISSUE.OVERLAP_STORE.AR",
"SampleAfterValue": "200000",
"BriefDescription": "Micro-op reissues on a store-load collision (At Retirement)"
"UMask": "0x81"
},
{
"BriefDescription": "Cycles issue is stalled due to div busy.",
"Counter": "0,1",
"EventCode": "0xDC",
"EventName": "RESOURCE_STALLS.DIV_BUSY",
"SampleAfterValue": "2000000",
"UMask": "0x2"
},
{
"BriefDescription": "All store forwards",
"Counter": "0,1",
"EventCode": "0x2",
"EventName": "STORE_FORWARDS.ANY",
"SampleAfterValue": "200000",
"UMask": "0x83"
},
{
"BriefDescription": "Good store forwards",
"Counter": "0,1",
"EventCode": "0x2",
"EventName": "STORE_FORWARDS.GOOD",
"SampleAfterValue": "200000",
"UMask": "0x81"
},
{
"BriefDescription": "Micro-ops retired.",
"Counter": "0,1",
"EventCode": "0xC2",
"EventName": "UOPS_RETIRED.ANY",
"SampleAfterValue": "2000000",
"UMask": "0x10"
},
{
"BriefDescription": "Cycles no micro-ops retired.",
"Counter": "0,1",
"EventCode": "0xC2",
"EventName": "UOPS_RETIRED.STALLED_CYCLES",
"SampleAfterValue": "2000000",
"UMask": "0x10"
},
{
"BriefDescription": "Periods no micro-ops retired.",
"Counter": "0,1",
"EventCode": "0xC2",
"EventName": "UOPS_RETIRED.STALLS",
"SampleAfterValue": "2000000",
"UMask": "0x10"
}
]

174
lib/libpmc/pmu-events/arch/x86/bonnell/virtual-memory.json
View File

@ -1,124 +1,124 @@
[
{
"EventCode": "0x8",
"BriefDescription": "Memory accesses that missed the DTLB.",
"Counter": "0,1",
"UMask": "0x7",
"EventCode": "0x8",
"EventName": "DATA_TLB_MISSES.DTLB_MISS",
"SampleAfterValue": "200000",
"BriefDescription": "Memory accesses that missed the DTLB."
"UMask": "0x7"
},
{
"EventCode": "0x8",
"BriefDescription": "DTLB misses due to load operations.",
"Counter": "0,1",
"UMask": "0x5",
"EventCode": "0x8",
"EventName": "DATA_TLB_MISSES.DTLB_MISS_LD",
"SampleAfterValue": "200000",
"BriefDescription": "DTLB misses due to load operations."
"UMask": "0x5"
},
{
"EventCode": "0x8",
"BriefDescription": "DTLB misses due to store operations.",
"Counter": "0,1",
"UMask": "0x9",
"EventName": "DATA_TLB_MISSES.L0_DTLB_MISS_LD",
"SampleAfterValue": "200000",
"BriefDescription": "L0 DTLB misses due to load operations."
},
{
"EventCode": "0x8",
"Counter": "0,1",
"UMask": "0x6",
"EventName": "DATA_TLB_MISSES.DTLB_MISS_ST",
"SampleAfterValue": "200000",
"BriefDescription": "DTLB misses due to store operations."
"UMask": "0x6"
},
{
"EventCode": "0x8",
"BriefDescription": "L0 DTLB misses due to load operations.",
"Counter": "0,1",
"UMask": "0xa",
"EventCode": "0x8",
"EventName": "DATA_TLB_MISSES.L0_DTLB_MISS_LD",
"SampleAfterValue": "200000",
"UMask": "0x9"
},
{
"BriefDescription": "L0 DTLB misses due to store operations",
"Counter": "0,1",
"EventCode": "0x8",
"EventName": "DATA_TLB_MISSES.L0_DTLB_MISS_ST",
"SampleAfterValue": "200000",
"BriefDescription": "L0 DTLB misses due to store operations"
"UMask": "0xa"
},
{
"EventCode": "0xC",
"BriefDescription": "ITLB flushes.",
"Counter": "0,1",
"UMask": "0x3",
"EventName": "PAGE_WALKS.WALKS",
"SampleAfterValue": "200000",
"BriefDescription": "Number of page-walks executed."
},
{
"EventCode": "0xC",
"Counter": "0,1",
"UMask": "0x3",
"EventName": "PAGE_WALKS.CYCLES",
"SampleAfterValue": "2000000",
"BriefDescription": "Duration of page-walks in core cycles"
},
{
"EventCode": "0xC",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "PAGE_WALKS.D_SIDE_WALKS",
"SampleAfterValue": "200000",
"BriefDescription": "Number of D-side only page walks"
},
{
"EventCode": "0xC",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "PAGE_WALKS.D_SIDE_CYCLES",
"SampleAfterValue": "2000000",
"BriefDescription": "Duration of D-side only page walks"
},
{
"EventCode": "0xC",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "PAGE_WALKS.I_SIDE_WALKS",
"SampleAfterValue": "200000",
"BriefDescription": "Number of I-Side page walks"
},
{
"EventCode": "0xC",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "PAGE_WALKS.I_SIDE_CYCLES",
"SampleAfterValue": "2000000",
"BriefDescription": "Duration of I-Side page walks"
},
{
"EventCode": "0x82",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "ITLB.HIT",
"SampleAfterValue": "200000",
"BriefDescription": "ITLB hits."
},
{
"EventCode": "0x82",
"Counter": "0,1",
"UMask": "0x4",
"EventName": "ITLB.FLUSH",
"SampleAfterValue": "200000",
"BriefDescription": "ITLB flushes."
"UMask": "0x4"
},
{
"PEBS": "2",
"BriefDescription": "ITLB hits.",
"Counter": "0,1",
"EventCode": "0x82",
"Counter": "0,1",
"UMask": "0x2",
"EventName": "ITLB.MISSES",
"EventName": "ITLB.HIT",
"SampleAfterValue": "200000",
"BriefDescription": "ITLB misses."
"UMask": "0x1"
},
{
"PEBS": "1",
"EventCode": "0xCB",
"BriefDescription": "ITLB misses.",
"Counter": "0,1",
"UMask": "0x4",
"EventName": "MEM_LOAD_RETIRED.DTLB_MISS",
"EventCode": "0x82",
"EventName": "ITLB.MISSES",
"PEBS": "2",
"SampleAfterValue": "200000",
"BriefDescription": "Retired loads that miss the DTLB (precise event)."
"UMask": "0x2"
},
{
"BriefDescription": "Retired loads that miss the DTLB (precise event).",
"Counter": "0,1",
"EventCode": "0xCB",
"EventName": "MEM_LOAD_RETIRED.DTLB_MISS",
"PEBS": "1",
"SampleAfterValue": "200000",
"UMask": "0x4"
},
{
"BriefDescription": "Duration of page-walks in core cycles",
"Counter": "0,1",
"EventCode": "0xC",
"EventName": "PAGE_WALKS.CYCLES",
"SampleAfterValue": "2000000",
"UMask": "0x3"
},
{
"BriefDescription": "Duration of D-side only page walks",
"Counter": "0,1",
"EventCode": "0xC",
"EventName": "PAGE_WALKS.D_SIDE_CYCLES",
"SampleAfterValue": "2000000",
"UMask": "0x1"
},
{
"BriefDescription": "Number of D-side only page walks",
"Counter": "0,1",
"EventCode": "0xC",
"EventName": "PAGE_WALKS.D_SIDE_WALKS",
"SampleAfterValue": "200000",
"UMask": "0x1"
},
{
"BriefDescription": "Duration of I-Side page walks",
"Counter": "0,1",
"EventCode": "0xC",
"EventName": "PAGE_WALKS.I_SIDE_CYCLES",
"SampleAfterValue": "2000000",
"UMask": "0x2"
},
{
"BriefDescription": "Number of I-Side page walks",
"Counter": "0,1",
"EventCode": "0xC",
"EventName": "PAGE_WALKS.I_SIDE_WALKS",
"SampleAfterValue": "200000",
"UMask": "0x2"
},
{
"BriefDescription": "Number of page-walks executed.",
"Counter": "0,1",
"EventCode": "0xC",
"EventName": "PAGE_WALKS.WALKS",
"SampleAfterValue": "200000",
"UMask": "0x3"
}
]

353
lib/libpmc/pmu-events/arch/x86/broadwell/bdw-metrics.json
View File

@ -1,196 +1,170 @@
[
{
"BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Frontend_Bound",
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound."
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound."
},
{
"BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Frontend_Bound_SMT",
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Bad_Speculation",
"PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example."
},
{
"BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Bad_Speculation_SMT",
"PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) )",
"MetricGroup": "TopdownL1",
"MetricName": "Backend_Bound",
"PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound."
},
{
"BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) )",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Backend_Bound_SMT",
"PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Retiring",
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. "
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. "
},
{
"BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Retiring_SMT",
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU."
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "Instructions Per Cycle (per Logical Processor)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "TopDownL1",
"MetricGroup": "Ret;Summary",
"MetricName": "IPC"
},
{
"BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
"MetricGroup": "Pipeline;Retire",
"MetricGroup": "Pipeline;Ret;Retire",
"MetricName": "UPI"
},
{
"BriefDescription": "Instruction per taken branch",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fetch_BW;PGO",
"MetricName": "IpTB"
},
{
"BriefDescription": "Branch instructions per taken branch. ",
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;PGO",
"MetricName": "BpTB"
},
{
"BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
"MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
"MetricGroup": "PGO;IcMiss",
"MetricName": "IFetch_Line_Utilization"
},
{
"BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
"MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
"MetricGroup": "DSB;Fetch_BW",
"MetricName": "DSB_Coverage"
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW",
"MetricName": "UpTB"
},
{
"BriefDescription": "Cycles Per Instruction (per Logical Processor)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
"MetricGroup": "Pipeline;Summary",
"MetricExpr": "1 / (INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "Pipeline;Mem",
"MetricName": "CPI"
},
{
"BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Summary",
"MetricGroup": "Pipeline",
"MetricName": "CLKS"
},
{
"BriefDescription": "Total issue-pipeline slots (per-Physical Core)",
"MetricExpr": "4 * cycles",
"MetricGroup": "TopDownL1",
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
"MetricExpr": "4 * CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "TmaL1",
"MetricName": "SLOTS"
},
{
"BriefDescription": "Total issue-pipeline slots (per-Physical Core)",
"MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopDownL1_SMT",
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
"MetricExpr": "4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "TmaL1_SMT",
"MetricName": "SLOTS_SMT"
},
{
"BriefDescription": "Instructions per Load (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
"MetricGroup": "Instruction_Type",
"MetricName": "IpL"
"BriefDescription": "The ratio of Executed- by Issued-Uops",
"MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
"MetricGroup": "Cor;Pipeline",
"MetricName": "Execute_per_Issue",
"PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
},
{
"BriefDescription": "Instructions per Store (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
"MetricGroup": "Instruction_Type",
"MetricName": "IpS"
},
{
"BriefDescription": "Instructions per Branch (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Branches;Instruction_Type",
"MetricName": "IpB"
},
{
"BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
"MetricGroup": "Branches",
"MetricName": "IpCall"
},
{
"BriefDescription": "Total number of retired Instructions",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
"BriefDescription": "Instructions Per Cycle (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / cycles",
"MetricGroup": "SMT",
"BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Ret;SMT;TmaL1",
"MetricName": "CoreIPC"
},
{
"BriefDescription": "Instructions Per Cycle (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "SMT",
"BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "Ret;SMT;TmaL1_SMT",
"MetricName": "CoreIPC_SMT"
},
{
"BriefDescription": "Floating Point Operations Per Cycle",
"MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles",
"MetricGroup": "FLOPS",
"MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Ret;Flops",
"MetricName": "FLOPc"
},
{
"BriefDescription": "Floating Point Operations Per Cycle",
"MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "FLOPS_SMT",
"MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "Ret;Flops_SMT",
"MetricName": "FLOPc_SMT"
},
{
"BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width)",
"MetricExpr": "( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) ) / ( 2 * CPU_CLK_UNHALTED.THREAD )",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "FP_Arith_Utilization",
"PublicDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). Values > 1 are possible due to Fused-Multiply Add (FMA) counting."
},
{
"BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) ) / ( 2 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ) )",
"MetricGroup": "Cor;Flops;HPC_SMT",
"MetricName": "FP_Arith_Utilization_SMT",
"PublicDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). Values > 1 are possible due to Fused-Multiply Add (FMA) counting. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
"MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
"MetricGroup": "Pipeline",
"MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
"MetricName": "ILP"
},
{
"BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)",
"MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "BrMispredicts",
"BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
"MetricExpr": " ( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) * (BR_MISP_RETIRED.ALL_BRANCHES * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / CPU_CLK_UNHALTED.THREAD) / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY )) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) ) * (4 * CPU_CLK_UNHALTED.THREAD) / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;BrMispredicts",
"MetricName": "Branch_Misprediction_Cost"
},
{
"BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)",
"MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "BrMispredicts_SMT",
"BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
"MetricExpr": " ( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * (BR_MISP_RETIRED.ALL_BRANCHES * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / CPU_CLK_UNHALTED.THREAD) / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY )) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) ) * (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;BrMispredicts_SMT",
"MetricName": "Branch_Misprediction_Cost_SMT"
},
{
"BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "BrMispredicts",
"MetricGroup": "Bad;BadSpec;BrMispredicts",
"MetricName": "IpMispredict"
},
{
@ -200,87 +174,196 @@
"MetricName": "CORE_CLKS"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
"MetricGroup": "InsType",
"MetricName": "IpLoad"
},
{
"BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
"MetricGroup": "InsType",
"MetricName": "IpStore"
},
{
"BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Branches;Fed;InsType",
"MetricName": "IpBranch"
},
{
"BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "IpCall"
},
{
"BriefDescription": "Instruction per taken branch",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO",
"MetricName": "IpTB"
},
{
"BriefDescription": "Branch instructions per taken branch. ",
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "BpTkBranch"
},
{
"BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )",
"MetricGroup": "Flops;InsType",
"MetricName": "IpFLOP"
},
{
"BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) )",
"MetricGroup": "Flops;InsType",
"MetricName": "IpArith",
"PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW."
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "IpArith_Scalar_SP",
"PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "IpArith_Scalar_DP",
"PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "IpArith_AVX128",
"PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "IpArith_AVX256",
"PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Total number of retired Instructions, Sample with: INST_RETIRED.PREC_DIST",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary;TmaL1",
"MetricName": "Instructions"
},
{
"BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
"MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
"MetricGroup": "DSB;Fed;FetchBW",
"MetricName": "DSB_Coverage"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles)",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
"MetricGroup": "Mem;MemoryBound;MemoryLat",
"MetricName": "Load_Miss_Real_Latency",
"PublicDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles). Latency may be overestimated for multi-load instructions - e.g. repeat strings."
},
{
"BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
"MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
"MetricGroup": "Memory_Bound;Memory_BW",
"MetricGroup": "Mem;MemoryBound;MemoryBW",
"MetricName": "MLP"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / cycles",
"MetricGroup": "TLB",
"MetricName": "Page_Walks_Utilization"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TLB_SMT",
"MetricName": "Page_Walks_Utilization_SMT"
},
{
"BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
"MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
"MetricGroup": "Memory_BW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L1D_Cache_Fill_BW"
},
{
"BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
"MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
"MetricGroup": "Memory_BW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L2_Cache_Fill_BW"
},
{
"BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
"MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
"MetricGroup": "Memory_BW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L3_Cache_Fill_BW"
},
{
"BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L1MPKI"
},
{
"BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;Backend;CacheMisses",
"MetricName": "L2MPKI"
},
{
"BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;CacheMisses;Offcore",
"MetricName": "L2MPKI_All"
},
{
"BriefDescription": "L2 cache misses per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2MPKI_Load"
},
{
"BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
"MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2HPKI_All"
},
{
"BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2HPKI_Load"
},
{
"BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L3MPKI"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Mem;MemoryTLB",
"MetricName": "Page_Walks_Utilization"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "Mem;MemoryTLB_SMT",
"MetricName": "Page_Walks_Utilization_SMT"
},
{
"BriefDescription": "Average CPU Utilization",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
"MetricGroup": "Summary",
"MetricGroup": "HPC;Summary",
"MetricName": "CPU_Utilization"
},
{
"BriefDescription": "Measured Average Frequency for unhalted processors [GHz]",
"MetricExpr": "(CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time",
"MetricGroup": "Summary;Power",
"MetricName": "Average_Frequency"
},
{
"BriefDescription": "Giga Floating Point Operations Per Second",
"MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
"MetricGroup": "FLOPS;Summary",
"MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 ) / duration_time",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "GFLOPs"
},
{
@ -291,22 +374,46 @@
},
{
"BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
"MetricGroup": "SMT;Summary",
"MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
"MetricGroup": "SMT",
"MetricName": "SMT_2T_Utilization"
},
{
"BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Summary",
"BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "OS",
"MetricName": "Kernel_Utilization"
},
{
"BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
"MetricGroup": "OS",
"MetricName": "Kernel_CPI"
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
"MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
"MetricGroup": "Memory_BW",
"MetricGroup": "HPC;Mem;MemoryBW;SoC",
"MetricName": "DRAM_BW_Use"
},
{
"BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)",
"MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / arb@event\\=0x81\\,umask\\=0x1@",
"MetricGroup": "Mem;SoC",
"MetricName": "MEM_Request_Latency"
},
{
"BriefDescription": "Average number of parallel requests to external memory. Accounts for all requests",
"MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / arb@event\\=0x81\\,umask\\=0x1@",
"MetricGroup": "Mem;SoC",
"MetricName": "MEM_Parallel_Requests"
},
{
"BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
"MetricGroup": "Branches;OS",
"MetricName": "IpFarBranch"
},
{
"BriefDescription": "C3 residency percent per core",
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",

6295
lib/libpmc/pmu-events/arch/x86/broadwell/cache.json
View File

File diff suppressed because it is too large Load Diff

271
lib/libpmc/pmu-events/arch/x86/broadwell/floating-point.json
View File

@ -1,172 +1,193 @@
[
{
"PEBS": "1",
"PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
"EventCode": "0xC1",
"BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"Counter": "0,1,2,3",
"UMask": "0x8",
"Errata": "BDM30",
"EventName": "OTHER_ASSISTS.AVX_TO_SSE",
"SampleAfterValue": "100003",
"BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable (Precise Event)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PEBS": "1",
"PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
"EventCode": "0xC1",
"Counter": "0,1,2,3",
"UMask": "0x10",
"Errata": "BDM30",
"EventName": "OTHER_ASSISTS.SSE_TO_AVX",
"SampleAfterValue": "100003",
"BriefDescription": "Number of transitions from legacy SSE to AVX-256 when penalty applicable (Precise Event)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC7",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"SampleAfterValue": "2000003",
"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.",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC7",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"SampleAfterValue": "2000003",
"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.",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC7",
"Counter": "0,1,2,3",
"UMask": "0x3",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single precision?)",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xC7",
"Counter": "0,1,2,3",
"UMask": "0x4",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x4"
},
{
"EventCode": "0xC7",
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 4 calculations per element.",
"Counter": "0,1,2,3",
"UMask": "0x8",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x8"
},
{
"EventCode": "0xC7",
"BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 4 calculations per element.",
"Counter": "0,1,2,3",
"UMask": "0x10",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x10"
},
{
"EventCode": "0xC7",
"BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 8 calculations per element.",
"Counter": "0,1,2,3",
"UMask": "0x15",
"EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
"SampleAfterValue": "2000006",
"BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"CounterHTOff": "0,1,2,3"
},
{
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"Counter": "0,1,2,3",
"UMask": "0x20",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x20"
},
{
"EventCode": "0xC7",
"BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"UMask": "0x2a",
"EventName": "FP_ARITH_INST_RETIRED.SINGLE",
"SampleAfterValue": "2000005",
"BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"CounterHTOff": "0,1,2,3"
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
"SampleAfterValue": "2000006",
"UMask": "0x15"
},
{
"EventCode": "0xC7",
"BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* packed double and single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP 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",
"UMask": "0x3c",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.PACKED",
"SampleAfterValue": "2000004",
"BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single-precision?)",
"CounterHTOff": "0,1,2,3"
"UMask": "0x3c"
},
{
"PEBS": "1",
"PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
"EventCode": "0xCA",
"BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation operation. Applies to SSE* and AVX* scalar double and single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "FP_ASSIST.X87_OUTPUT",
"SampleAfterValue": "100003",
"BriefDescription": "output - Numeric Overflow, Numeric Underflow, Inexact Result (Precise Event)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR",
"SampleAfterValue": "2000003",
"UMask": "0x3"
},
{
"PEBS": "1",
"PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
"EventCode": "0xCA",
"BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. 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",
"UMask": "0x4",
"EventName": "FP_ASSIST.X87_INPUT",
"SampleAfterValue": "100003",
"BriefDescription": "input - Invalid Operation, Denormal Operand, SNaN Operand (Precise Event)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"PEBS": "1",
"PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
"EventCode": "0xCA",
"BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"UMask": "0x8",
"EventName": "FP_ASSIST.SIMD_OUTPUT",
"SampleAfterValue": "100003",
"BriefDescription": "SSE* FP micro-code assist when output value is invalid. (Precise Event)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"PEBS": "1",
"PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts any input SSE* floating-point (FP) assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
"EventCode": "0xCA",
"BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar and packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP 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",
"UMask": "0x10",
"EventName": "FP_ASSIST.SIMD_INPUT",
"SampleAfterValue": "100003",
"BriefDescription": "Any input SSE* FP Assist - (Precise Event)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SINGLE",
"SampleAfterValue": "2000005",
"UMask": "0x2a"
},
{
"PEBS": "1",
"PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1. Uses PEBS.",
"EventCode": "0xCA",
"BriefDescription": "Cycles with any input/output SSE or FP assist",
"Counter": "0,1,2,3",
"UMask": "0x1e",
"EventName": "FP_ASSIST.ANY",
"SampleAfterValue": "100003",
"BriefDescription": "Counts any FP_ASSIST umask was incrementing (Precise Event)",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3"
"EventCode": "0xCA",
"EventName": "FP_ASSIST.ANY",
"PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
"SampleAfterValue": "100003",
"UMask": "0x1e"
},
{
"BriefDescription": "Number of SIMD FP assists due to input values",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.SIMD_INPUT",
"PublicDescription": "This event counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Number of SIMD FP assists due to Output values",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.SIMD_OUTPUT",
"PublicDescription": "This event counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of X87 assists due to input value.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.X87_INPUT",
"PublicDescription": "This event counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of X87 assists due to output value.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.X87_OUTPUT",
"PublicDescription": "This event counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of SIMD Move Elimination candidate uops that were eliminated.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x58",
"EventName": "MOVE_ELIMINATION.SIMD_ELIMINATED",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of SIMD Move Elimination candidate uops that were not eliminated.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x58",
"EventName": "MOVE_ELIMINATION.SIMD_NOT_ELIMINATED",
"SampleAfterValue": "1000003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM30",
"EventCode": "0xC1",
"EventName": "OTHER_ASSISTS.AVX_TO_SSE",
"PublicDescription": "This event counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM30",
"EventCode": "0xC1",
"EventName": "OTHER_ASSISTS.SSE_TO_AVX",
"PublicDescription": "This event counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Micro-op dispatches cancelled due to insufficient SIMD physical register file read ports",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xA0",
"EventName": "UOP_DISPATCHES_CANCELLED.SIMD_PRF",
"PublicDescription": "This event counts the number of micro-operations cancelled after they were dispatched from the scheduler to the execution units when the total number of physical register read ports across all dispatch ports exceeds the read bandwidth of the physical register file. The SIMD_PRF subevent applies to the following instructions: VDPPS, DPPS, VPCMPESTRI, PCMPESTRI, VPCMPESTRM, PCMPESTRM, VFMADD*, VFMADDSUB*, VFMSUB*, VMSUBADD*, VFNMADD*, VFNMSUB*. See the Broadwell Optimization Guide for more information.",
"SampleAfterValue": "2000003",
"UMask": "0x3"
}
]

431
lib/libpmc/pmu-events/arch/x86/broadwell/frontend.json
View File

@ -1,286 +1,295 @@
[
{
"PublicDescription": "This counts the number of cycles that the instruction decoder queue is empty and can indicate that the application may be bound in the front end. It does not determine whether there are uops being delivered to the Alloc stage since uops can be delivered by bypass skipping the Instruction Decode Queue (IDQ) when it is empty.",
"EventCode": "0x79",
"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",
"UMask": "0x2",
"EventName": "IDQ.EMPTY",
"SampleAfterValue": "2000003",
"BriefDescription": "Instruction Decode Queue (IDQ) empty cycles",
"CounterHTOff": "0,1,2,3"
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xe6",
"EventName": "BACLEARS.ANY",
"SampleAfterValue": "100003",
"UMask": "0x1f"
},
{
"PublicDescription": "This event 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).",
"EventCode": "0x79",
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "IDQ.MITE_UOPS",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xAB",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x2"
},
{
"PublicDescription": "This event 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.",
"EventCode": "0x79",
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "IDQ.MITE_CYCLES",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.HIT",
"PublicDescription": "This event counts the number of both cacheable and noncacheable Instruction Cache, Streaming Buffer and Victim Cache Reads including UC fetches.",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"PublicDescription": "This event 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.",
"EventCode": "0x79",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
"Counter": "0,1,2,3",
"UMask": "0x8",
"EventName": "IDQ.DSB_UOPS",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.IFDATA_STALL",
"PublicDescription": "This event counts cycles during which the demand fetch waits for data (wfdM104H) from L2 or iSB (opportunistic hit).",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x4"
},
{
"PublicDescription": "This event 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.",
"EventCode": "0x79",
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Misses. Includes Uncacheable accesses.",
"Counter": "0,1,2,3",
"UMask": "0x8",
"EventName": "IDQ.DSB_CYCLES",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.MISSES",
"PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes UC accesses.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "IDQ.MS_DSB_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event 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.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "IDQ.MS_DSB_CYCLES",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts the number of deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EdgeDetect": "1",
"EventName": "IDQ.MS_DSB_OCCUR",
"SampleAfterValue": "2000003",
"BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x18",
"EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "4",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
"PublicDescription": "This event counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"PublicDescription": "This event counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x18",
"EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
"PublicDescription": "This event counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x20",
"EventName": "IDQ.MS_MITE_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts the number of cycles 4 uops were 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).",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x24",
"EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles MITE is delivering 4 Uops",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "4",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"EventCode": "0x79",
"EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
"PublicDescription": "This event counts the number of cycles 4 uops were 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",
"UMask": "0x24"
},
{
"PublicDescription": "This event counts the number of cycles uops were 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).",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x24",
"EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles MITE is delivering any Uop",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"EventCode": "0x79",
"EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
"PublicDescription": "This event counts the number of cycles uops were 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",
"UMask": "0x24"
},
{
"PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
"EventCode": "0x79",
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
"Counter": "0,1,2,3",
"UMask": "0x30",
"EventName": "IDQ.MS_UOPS",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES",
"PublicDescription": "This event 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",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x8"
},
{
"PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
"EventCode": "0x79",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"Counter": "0,1,2,3",
"UMask": "0x30",
"EventName": "IDQ.MS_CYCLES",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
"PublicDescription": "This event 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",
"UMask": "0x8"
},
{
"BriefDescription": "Instruction Decode Queue (IDQ) empty cycles",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.EMPTY",
"PublicDescription": "This counts the number of cycles that the instruction decoder queue is empty and can indicate that the application may be bound in the front end. It does not determine whether there are uops being delivered to the Alloc stage since uops can be delivered by bypass skipping the Instruction Decode Queue (IDQ) when it is empty.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MITE_ALL_UOPS",
"PublicDescription": "This event 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",
"UMask": "0x3c"
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES",
"PublicDescription": "This event 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",
"UMask": "0x4"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
"PublicDescription": "This event 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",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"EventCode": "0x79",
"EventName": "IDQ.MS_CYCLES",
"PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
"SampleAfterValue": "2000003",
"UMask": "0x30"
},
{
"EventCode": "0x79",
"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",
"UMask": "0x30",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_CYCLES",
"PublicDescription": "This event 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",
"UMask": "0x10"
},
{
"BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_OCCUR",
"PublicDescription": "This event counts the number of deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_UOPS",
"PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that 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",
"UMask": "0x10"
},
{
"BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_MITE_UOPS",
"PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ.",
"SampleAfterValue": "2000003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_SWITCHES",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x30"
},
{
"PublicDescription": "This event 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).",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x3c",
"EventName": "IDQ.MITE_ALL_UOPS",
"EventName": "IDQ.MS_UOPS",
"PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x30"
},
{
"PublicDescription": "This event counts the number of both cacheable and noncacheable Instruction Cache, Streaming Buffer and Victim Cache Reads including UC fetches.",
"EventCode": "0x80",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "ICACHE.HIT",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes UC accesses.",
"EventCode": "0x80",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "ICACHE.MISSES",
"SampleAfterValue": "200003",
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Misses. Includes Uncacheable accesses.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts cycles during which the demand fetch waits for data (wfdM104H) from L2 or iSB (opportunistic hit).",
"EventCode": "0x80",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "ICACHE.IFDATA_STALL",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
"EventCode": "0x9C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
"CounterHTOff": "0,1,2,3"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
"PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"PublicDescription": "This event counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.",
"EventCode": "0x9C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "4",
"CounterHTOff": "0,1,2,3"
},
{
"PublicDescription": "This event 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.",
"EventCode": "0x9C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
"PublicDescription": "This event 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",
"BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
"CounterMask": "3",
"CounterHTOff": "0,1,2,3"
"UMask": "0x1"
},
{
"EventCode": "0x9C",
"BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
"Counter": "0,1,2,3",
"UMask": "0x1",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"Invert": "1",
"SampleAfterValue": "2000003",
"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",
"CounterHTOff": "0,1,2,3",
"CounterMask": "3",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
"PublicDescription": "This event 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",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "2",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
"CounterMask": "2",
"CounterHTOff": "0,1,2,3"
"UMask": "0x1"
},
{
"EventCode": "0x9C",
"BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
"Counter": "0,1,2,3",
"UMask": "0x1",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0x9C",
"Invert": "1",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"SampleAfterValue": "2000003",
"BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3"
},
{
"PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.",
"EventCode": "0xAB",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"SampleAfterValue": "2000003",
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
}
]

5930
lib/libpmc/pmu-events/arch/x86/broadwell/memory.json
View File

File diff suppressed because it is too large Load Diff

58
lib/libpmc/pmu-events/arch/x86/broadwell/other.json
View File

@ -1,44 +1,44 @@
[
{
"PublicDescription": "This event counts the unhalted core cycles during which the thread is in the ring 0 privileged mode.",
"EventCode": "0x5C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "CPL_CYCLES.RING0",
"SampleAfterValue": "2000003",
"BriefDescription": "Unhalted core cycles when the thread is in ring 0",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING0",
"PublicDescription": "This event counts the unhalted core cycles during which the thread is in the ring 0 privileged mode.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"PublicDescription": "This event counts when there is a transition from ring 1,2 or 3 to ring0.",
"EventCode": "0x5C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EdgeDetect": "1",
"EventName": "CPL_CYCLES.RING0_TRANS",
"SampleAfterValue": "100007",
"BriefDescription": "Number of intervals between processor halts while thread is in ring 0",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts unhalted core cycles during which the thread is in rings 1, 2, or 3.",
"EdgeDetect": "1",
"EventCode": "0x5C",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "CPL_CYCLES.RING123",
"SampleAfterValue": "2000003",
"BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"EventName": "CPL_CYCLES.RING0_TRANS",
"PublicDescription": "This event counts when there is a transition from ring 1,2 or 3 to ring0.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"PublicDescription": "This event counts cycles in which the L1 and L2 are locked due to a UC lock or split lock. A lock is asserted in case of locked memory access, due to noncacheable memory, locked operation that spans two cache lines, or a page walk from the noncacheable page table. L1D and L2 locks have a very high performance penalty and it is highly recommended to avoid such access.",
"EventCode": "0x63",
"BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING123",
"PublicDescription": "This event counts unhalted core cycles during which the thread is in rings 1, 2, or 3.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x63",
"EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION",
"PublicDescription": "This event counts cycles in which the L1 and L2 are locked due to a UC lock or split lock. A lock is asserted in case of locked memory access, due to noncacheable memory, locked operation that spans two cache lines, or a page walk from the noncacheable page table. L1D and L2 locks have a very high performance penalty and it is highly recommended to avoid such access.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
}
]

2677
lib/libpmc/pmu-events/arch/x86/broadwell/pipeline.json
View File

File diff suppressed because it is too large Load Diff

498
lib/libpmc/pmu-events/arch/x86/broadwell/virtual-memory.json
View File

@ -1,388 +1,388 @@
[
{
"PublicDescription": "This event counts load misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x1",
"Errata": "BDM69",
"EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
"SampleAfterValue": "100003",
"BriefDescription": "Load misses in all DTLB levels that cause page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x2",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"SampleAfterValue": "2000003",
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x4",
"Errata": "BDM69",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"SampleAfterValue": "2000003",
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (2M/4M).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event 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.",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x8",
"Errata": "BDM69",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
"SampleAfterValue": "2000003",
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0xe",
"Errata": "BDM69",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "This event counts load misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"EventCode": "0x08",
"BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
"Counter": "0,1,2,3",
"UMask": "0x10",
"Errata": "BDM69",
"EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles when PMH is busy with page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x20",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_4K",
"SampleAfterValue": "2000003",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (4K).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x40",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_2M",
"SampleAfterValue": "2000003",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (2M).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x60",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"SampleAfterValue": "2000003",
"BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x60"
},
{
"PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"EventCode": "0x49",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"UMask": "0x1",
"Errata": "BDM69",
"EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
"SampleAfterValue": "100003",
"BriefDescription": "Store misses in all DTLB levels that cause page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_2M",
"SampleAfterValue": "2000003",
"UMask": "0x40"
},
{
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
"EventCode": "0x49",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"UMask": "0x2",
"Errata": "BDM69",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"SampleAfterValue": "100003",
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_4K",
"SampleAfterValue": "2000003",
"UMask": "0x20"
},
{
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"EventCode": "0x49",
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
"Counter": "0,1,2,3",
"UMask": "0x4",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"SampleAfterValue": "100003",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0xe"
},
{
"PublicDescription": "This event 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.",
"EventCode": "0x49",
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"UMask": "0x8",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
"SampleAfterValue": "100003",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (1G)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "This event 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",
"UMask": "0x8"
},
{
"EventCode": "0x49",
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (2M/4M).",
"Counter": "0,1,2,3",
"UMask": "0xe",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"SampleAfterValue": "100003",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"EventCode": "0x49",
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).",
"Counter": "0,1,2,3",
"UMask": "0x10",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventName": "DTLB_STORE_MISSES.WALK_DURATION",
"SampleAfterValue": "100003",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"EventCode": "0x49",
"BriefDescription": "Store misses in all DTLB levels that cause page walks",
"Counter": "0,1,2,3",
"UMask": "0x20",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_4K",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (4K).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"EventCode": "0x49",
"BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
"Counter": "0,1,2,3",
"UMask": "0x40",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_2M",
"SampleAfterValue": "100003",
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (2M).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"Counter": "0,1,2,3",
"UMask": "0x60",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"SampleAfterValue": "100003",
"BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x60"
},
{
"PublicDescription": "This event counts cycles for an extended page table walk. The Extended Page directory cache differs from standard TLB caches by the operating system that use it. Virtual machine operating systems use the extended page directory cache, while guest operating systems use the standard TLB caches.",
"EventCode": "0x4F",
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "EPT.WALK_CYCLES",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycle count for an Extended Page table walk.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x1",
"Errata": "BDM69",
"EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_2M",
"SampleAfterValue": "100003",
"BriefDescription": "Misses at all ITLB levels that cause page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x40"
},
{
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
"EventCode": "0x85",
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"UMask": "0x2",
"Errata": "BDM69",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_4K",
"SampleAfterValue": "100003",
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x20"
},
{
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"EventCode": "0x85",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
"Counter": "0,1,2,3",
"UMask": "0x4",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"SampleAfterValue": "100003",
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0xe"
},
{
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (1G)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "This event 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.",
"EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x8",
"Errata": "BDM69",
"EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
"SampleAfterValue": "100003",
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (1G)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x8"
},
{
"EventCode": "0x85",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)",
"Counter": "0,1,2,3",
"UMask": "0xe",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x4"
},
{
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"EventCode": "0x85",
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3",
"UMask": "0x10",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventName": "ITLB_MISSES.WALK_DURATION",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x20",
"EventName": "ITLB_MISSES.STLB_HIT_4K",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_DURATION",
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"SampleAfterValue": "100003",
"BriefDescription": "Core misses that miss the DTLB and hit the STLB (4K).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x10"
},
{
"EventCode": "0x85",
"BriefDescription": "Cycle count for an Extended Page table walk.",
"Counter": "0,1,2,3",
"UMask": "0x40",
"EventName": "ITLB_MISSES.STLB_HIT_2M",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x4F",
"EventName": "EPT.WALK_CYCLES",
"PublicDescription": "This event counts cycles for an extended page table walk. The Extended Page directory cache differs from standard TLB caches by the operating system that use it. Virtual machine operating systems use the extended page directory cache, while guest operating systems use the standard TLB caches.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xAE",
"EventName": "ITLB.ITLB_FLUSH",
"PublicDescription": "This event 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",
"UMask": "0x1"
},
{
"BriefDescription": "Misses at all ITLB levels that cause page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"BriefDescription": "Code misses that miss the DTLB and hit the STLB (2M).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"EventCode": "0x85",
"BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
"Counter": "0,1,2,3",
"UMask": "0x60",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT",
"SampleAfterValue": "100003",
"BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x60"
},
{
"PublicDescription": "This event 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).",
"EventCode": "0xAE",
"BriefDescription": "Code misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "ITLB.ITLB_FLUSH",
"SampleAfterValue": "100007",
"BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT_2M",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"EventCode": "0xBC",
"BriefDescription": "Core misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"UMask": "0x11",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT_4K",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "This event 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",
"UMask": "0x8"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_DURATION",
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Number of DTLB page walker hits in the L1+FB.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L1",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of DTLB page walker hits in the L1+FB.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x11"
},
{
"EventCode": "0xBC",
"BriefDescription": "Number of DTLB page walker hits in the L2.",
"Counter": "0,1,2,3",
"UMask": "0x12",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L2",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of DTLB page walker hits in the L2.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x12"
},
{
"EventCode": "0xBC",
"BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP.",
"Counter": "0,1,2,3",
"UMask": "0x14",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L3",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x14"
},
{
"EventCode": "0xBC",
"BriefDescription": "Number of DTLB page walker hits in Memory.",
"Counter": "0,1,2,3",
"UMask": "0x18",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of DTLB page walker hits in Memory.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x18"
},
{
"EventCode": "0xBC",
"BriefDescription": "Number of ITLB page walker hits in the L1+FB.",
"Counter": "0,1,2,3",
"UMask": "0x21",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L1",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of ITLB page walker hits in the L1+FB.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x21"
},
{
"EventCode": "0xBC",
"BriefDescription": "Number of ITLB page walker hits in the L2.",
"Counter": "0,1,2,3",
"UMask": "0x22",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L2",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of ITLB page walker hits in the L2.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x22"
},
{
"EventCode": "0xBC",
"BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP.",
"Counter": "0,1,2,3",
"UMask": "0x24",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L3",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x24"
},
{
"PublicDescription": "This event counts the number of DTLB flush attempts of the thread-specific entries.",
"EventCode": "0xBD",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "TLB_FLUSH.DTLB_THREAD",
"SampleAfterValue": "100007",
"BriefDescription": "DTLB flush attempts of the thread-specific entries",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.DTLB_THREAD",
"PublicDescription": "This event counts the number of DTLB flush attempts of the thread-specific entries.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"PublicDescription": "This event counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, and so on).",
"EventCode": "0xBD",
"Counter": "0,1,2,3",
"UMask": "0x20",
"EventName": "TLB_FLUSH.STLB_ANY",
"SampleAfterValue": "100007",
"BriefDescription": "STLB flush attempts",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.STLB_ANY",
"PublicDescription": "This event counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, and so on).",
"SampleAfterValue": "100007",
"UMask": "0x20"
}
]

409
lib/libpmc/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
View File

@ -1,104 +1,369 @@
[
{
"BriefDescription": "Instructions Per Cycle (per logical thread)",
"BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Frontend_Bound",
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound."
},
{
"BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Frontend_Bound_SMT",
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Bad_Speculation",
"PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example."
},
{
"BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Bad_Speculation_SMT",
"PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) )",
"MetricGroup": "TopdownL1",
"MetricName": "Backend_Bound",
"PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound."
},
{
"BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) )",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Backend_Bound_SMT",
"PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Retiring",
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided."
},
{
"BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Retiring_SMT",
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "Instructions Per Cycle (per Logical Processor)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "TopDownL1",
"MetricGroup": "Ret;Summary",
"MetricName": "IPC"
},
{
"BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
"MetricGroup": "Pipeline",
"MetricGroup": "Pipeline;Ret;Retire",
"MetricName": "UPI"
},
{
"BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
"MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
"MetricGroup": "Frontend",
"MetricName": "IFetch_Line_Utilization"
"BriefDescription": "Instruction per taken branch",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW",
"MetricName": "UpTB"
},
{
"BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
"MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
"MetricGroup": "DSB; Frontend_Bandwidth",
"MetricName": "DSB_Coverage"
},
{
"BriefDescription": "Cycles Per Instruction (threaded)",
"MetricExpr": "1 / INST_RETIRED.ANY / cycles",
"MetricGroup": "Pipeline;Summary",
"BriefDescription": "Cycles Per Instruction (per Logical Processor)",
"MetricExpr": "1 / (INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "Pipeline;Mem",
"MetricName": "CPI"
},
{
"BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
"BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Summary",
"MetricGroup": "Pipeline",
"MetricName": "CLKS"
},
{
"BriefDescription": "Total issue-pipeline slots",
"MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
"MetricGroup": "TopDownL1",
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
"MetricExpr": "4 * CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "TmaL1",
"MetricName": "SLOTS"
},
{
"BriefDescription": "Total number of retired Instructions",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary",
"MetricName": "Instructions"
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
"MetricExpr": "4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "TmaL1_SMT",
"MetricName": "SLOTS_SMT"
},
{
"BriefDescription": "Instructions Per Cycle (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
"MetricGroup": "SMT",
"BriefDescription": "The ratio of Executed- by Issued-Uops",
"MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
"MetricGroup": "Cor;Pipeline",
"MetricName": "Execute_per_Issue",
"PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
},
{
"BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Ret;SMT;TmaL1",
"MetricName": "CoreIPC"
},
{
"BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "Ret;SMT;TmaL1_SMT",
"MetricName": "CoreIPC_SMT"
},
{
"BriefDescription": "Floating Point Operations Per Cycle",
"MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Ret;Flops",
"MetricName": "FLOPc"
},
{
"BriefDescription": "Floating Point Operations Per Cycle",
"MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "Ret;Flops_SMT",
"MetricName": "FLOPc_SMT"
},
{
"BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width)",
"MetricExpr": "( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) ) / ( 2 * CPU_CLK_UNHALTED.THREAD )",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "FP_Arith_Utilization",
"PublicDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). Values > 1 are possible due to Fused-Multiply Add (FMA) counting."
},
{
"BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) ) / ( 2 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ) )",
"MetricGroup": "Cor;Flops;HPC_SMT",
"MetricName": "FP_Arith_Utilization_SMT",
"PublicDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). Values > 1 are possible due to Fused-Multiply Add (FMA) counting. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
"MetricExpr": "UOPS_EXECUTED.THREAD / ( cpu@uops_executed.core\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
"MetricGroup": "Pipeline;Ports_Utilization",
"MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
"MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
"MetricName": "ILP"
},
{
"BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
"MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - ( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED ) ) / RS_EVENTS.EMPTY_END",
"MetricGroup": "Unknown_Branches",
"MetricName": "BAClear_Cost"
"BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
"MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) * (BR_MISP_RETIRED.ALL_BRANCHES * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / CPU_CLK_UNHALTED.THREAD) / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY )) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) ) * (4 * CPU_CLK_UNHALTED.THREAD) / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;BrMispredicts",
"MetricName": "Branch_Misprediction_Cost"
},
{
"BriefDescription": "Core actual clocks when any thread is active on the physical core",
"MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
"BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
"MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * (BR_MISP_RETIRED.ALL_BRANCHES * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / CPU_CLK_UNHALTED.THREAD) / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY )) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) ) * (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;BrMispredicts_SMT",
"MetricName": "Branch_Misprediction_Cost_SMT"
},
{
"BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;BadSpec;BrMispredicts",
"MetricName": "IpMispredict"
},
{
"BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
"MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
"BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
"MetricGroup": "InsType",
"MetricName": "IpLoad"
},
{
"BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES",
"MetricGroup": "Memory_Bound;Memory_BW",
"BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
"MetricGroup": "InsType",
"MetricName": "IpStore"
},
{
"BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Branches;Fed;InsType",
"MetricName": "IpBranch"
},
{
"BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "IpCall"
},
{
"BriefDescription": "Instruction per taken branch",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO",
"MetricName": "IpTB"
},
{
"BriefDescription": "Branch instructions per taken branch.",
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "BpTkBranch"
},
{
"BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )",
"MetricGroup": "Flops;InsType",
"MetricName": "IpFLOP"
},
{
"BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) )",
"MetricGroup": "Flops;InsType",
"MetricName": "IpArith",
"PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW."
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "IpArith_Scalar_SP",
"PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "IpArith_Scalar_DP",
"PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "IpArith_AVX128",
"PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "IpArith_AVX256",
"PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Total number of retired Instructions, Sample with: INST_RETIRED.PREC_DIST",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary;TmaL1",
"MetricName": "Instructions"
},
{
"BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
"MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
"MetricGroup": "DSB;Fed;FetchBW",
"MetricName": "DSB_Coverage"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles)",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
"MetricGroup": "Mem;MemoryBound;MemoryLat",
"MetricName": "Load_Miss_Real_Latency",
"PublicDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles). Latency may be overestimated for multi-load instructions - e.g. repeat strings."
},
{
"BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
"MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
"MetricGroup": "Mem;MemoryBound;MemoryBW",
"MetricName": "MLP"
},
{
"BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
"MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L1D_Cache_Fill_BW"
},
{
"BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
"MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L2_Cache_Fill_BW"
},
{
"BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
"MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L3_Cache_Fill_BW"
},
{
"BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L1MPKI"
},
{
"BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;Backend;CacheMisses",
"MetricName": "L2MPKI"
},
{
"BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses;Offcore",
"MetricName": "L2MPKI_All"
},
{
"BriefDescription": "L2 cache misses per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2MPKI_Load"
},
{
"BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
"MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2HPKI_All"
},
{
"BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2HPKI_Load"
},
{
"BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L3MPKI"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
"MetricGroup": "TLB",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Mem;MemoryTLB",
"MetricName": "Page_Walks_Utilization"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "Mem;MemoryTLB_SMT",
"MetricName": "Page_Walks_Utilization_SMT"
},
{
"BriefDescription": "Average CPU Utilization",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
"MetricGroup": "Summary",
"MetricGroup": "HPC;Summary",
"MetricName": "CPU_Utilization"
},
{
"BriefDescription": "Measured Average Frequency for unhalted processors [GHz]",
"MetricExpr": "(CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time",
"MetricGroup": "Summary;Power",
"MetricName": "Average_Frequency"
},
{
"BriefDescription": "Giga Floating Point Operations Per Second",
"MetricExpr": "( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 / duration_time",
"MetricGroup": "FLOPS;Summary",
"MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 ) / duration_time",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "GFLOPs"
},
{
@ -108,17 +373,53 @@
"MetricName": "Turbo_Utilization"
},
{
"BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
"MetricGroup": "SMT;Summary",
"BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
"MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
"MetricGroup": "SMT",
"MetricName": "SMT_2T_Utilization"
},
{
"BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Summary",
"BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "OS",
"MetricName": "Kernel_Utilization"
},
{
"BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
"MetricGroup": "OS",
"MetricName": "Kernel_CPI"
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
"MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
"MetricGroup": "HPC;Mem;MemoryBW;SoC",
"MetricName": "DRAM_BW_Use"
},
{
"BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
"MetricExpr": "1000000000 * ( cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x35\\,umask\\=0x3\\,filter_opc\\=0x182@ ) / ( cbox_0@event\\=0x0@ / duration_time )",
"MetricGroup": "Mem;MemoryLat;SoC",
"MetricName": "MEM_Read_Latency"
},
{
"BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
"MetricExpr": "cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182\\,thresh\\=1@",
"MetricGroup": "Mem;MemoryBW;SoC",
"MetricName": "MEM_Parallel_Reads"
},
{
"BriefDescription": "Socket actual clocks when any core is active on that socket",
"MetricExpr": "cbox_0@event\\=0x0@",
"MetricGroup": "SoC",
"MetricName": "Socket_CLKS"
},
{
"BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
"MetricGroup": "Branches;OS",
"MetricName": "IpFarBranch"
},
{
"BriefDescription": "C3 residency percent per core",
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",

1520
lib/libpmc/pmu-events/arch/x86/broadwellde/cache.json
View File

File diff suppressed because it is too large Load Diff

246
lib/libpmc/pmu-events/arch/x86/broadwellde/floating-point.json
View File

@ -1,165 +1,193 @@
[
{
"EventCode": "0xC1",
"UMask": "0x8",
"BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
"Counter": "0,1,2,3",
"EventName": "OTHER_ASSISTS.AVX_TO_SSE",
"Errata": "BDM30",
"PublicDescription": "This event counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC1",
"UMask": "0x10",
"BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
"Counter": "0,1,2,3",
"EventName": "OTHER_ASSISTS.SSE_TO_AVX",
"Errata": "BDM30",
"PublicDescription": "This event counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"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"
},
{
"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"
},
{
"EventCode": "0xC7",
"UMask": "0x3",
"BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"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",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x4"
},
{
"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",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x8"
},
{
"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",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x10"
},
{
"EventCode": "0xC7",
"UMask": "0x15",
"BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
"SampleAfterValue": "2000006",
"CounterHTOff": "0,1,2,3"
},
{
"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",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x20"
},
{
"EventCode": "0xC7",
"UMask": "0x2a",
"BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
"BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.SINGLE",
"SampleAfterValue": "2000005",
"CounterHTOff": "0,1,2,3"
"CounterHTOff": "0,1,2,3",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
"SampleAfterValue": "2000006",
"UMask": "0x15"
},
{
"EventCode": "0xC7",
"UMask": "0x3c",
"BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.PACKED",
"SampleAfterValue": "2000004",
"CounterHTOff": "0,1,2,3"
"UMask": "0x3c"
},
{
"EventCode": "0xCA",
"UMask": "0x2",
"BriefDescription": "Number of X87 assists due to output value.",
"BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ASSIST.X87_OUTPUT",
"PublicDescription": "This event counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR",
"SampleAfterValue": "2000003",
"UMask": "0x3"
},
{
"EventCode": "0xCA",
"UMask": "0x4",
"BriefDescription": "Number of X87 assists due to input value.",
"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_ASSIST.X87_INPUT",
"PublicDescription": "This event counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"EventCode": "0xCA",
"UMask": "0x8",
"BriefDescription": "Number of SIMD FP assists due to Output values",
"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_ASSIST.SIMD_OUTPUT",
"PublicDescription": "This event counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.SINGLE",
"SampleAfterValue": "2000005",
"UMask": "0x2a"
},
{
"BriefDescription": "Cycles with any input/output SSE or FP assist",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0xCA",
"UMask": "0x10",
"EventName": "FP_ASSIST.ANY",
"PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
"SampleAfterValue": "100003",
"UMask": "0x1e"
},
{
"BriefDescription": "Number of SIMD FP assists due to input values",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.SIMD_INPUT",
"PublicDescription": "This event counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x10"
},
{
"EventCode": "0xCA",
"UMask": "0x1e",
"BriefDescription": "Cycles with any input/output SSE or FP assist",
"BriefDescription": "Number of SIMD FP assists due to Output values",
"Counter": "0,1,2,3",
"EventName": "FP_ASSIST.ANY",
"CounterMask": "1",
"PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.SIMD_OUTPUT",
"PublicDescription": "This event counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x8"
},
{
"BriefDescription": "Number of X87 assists due to input value.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.X87_INPUT",
"PublicDescription": "This event counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of X87 assists due to output value.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.X87_OUTPUT",
"PublicDescription": "This event counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of SIMD Move Elimination candidate uops that were eliminated.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x58",
"EventName": "MOVE_ELIMINATION.SIMD_ELIMINATED",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of SIMD Move Elimination candidate uops that were not eliminated.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x58",
"EventName": "MOVE_ELIMINATION.SIMD_NOT_ELIMINATED",
"SampleAfterValue": "1000003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM30",
"EventCode": "0xC1",
"EventName": "OTHER_ASSISTS.AVX_TO_SSE",
"PublicDescription": "This event counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM30",
"EventCode": "0xC1",
"EventName": "OTHER_ASSISTS.SSE_TO_AVX",
"PublicDescription": "This event counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Micro-op dispatches cancelled due to insufficient SIMD physical register file read ports",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xA0",
"EventName": "UOP_DISPATCHES_CANCELLED.SIMD_PRF",
"PublicDescription": "This event counts the number of micro-operations cancelled after they were dispatched from the scheduler to the execution units when the total number of physical register read ports across all dispatch ports exceeds the read bandwidth of the physical register file. The SIMD_PRF subevent applies to the following instructions: VDPPS, DPPS, VPCMPESTRI, PCMPESTRI, VPCMPESTRM, PCMPESTRM, VFMADD*, VFMADDSUB*, VFMSUB*, VMSUBADD*, VFNMADD*, VFNMSUB*. See the Broadwell Optimization Guide for more information.",
"SampleAfterValue": "2000003",
"UMask": "0x3"
}
]

557
lib/libpmc/pmu-events/arch/x86/broadwellde/frontend.json
View File

@ -1,286 +1,295 @@
[
{
"EventCode": "0x79",
"UMask": "0x2",
"BriefDescription": "Instruction Decode Queue (IDQ) empty cycles",
"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": "IDQ.EMPTY",
"PublicDescription": "This counts the number of cycles that the instruction decoder queue is empty and can indicate that the application may be bound in the front end. It does not determine whether there are uops being delivered to the Alloc stage since uops can be delivered by bypass skipping the Instruction Decode Queue (IDQ) when it is empty.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xe6",
"EventName": "BACLEARS.ANY",
"SampleAfterValue": "100003",
"UMask": "0x1f"
},
{
"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": "This event 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": "This event 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": "This event 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": "This event 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": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"EventName": "IDQ.MS_DSB_UOPS",
"PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that 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": "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": "This event 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"
},
{
"EdgeDetect": "1",
"EventCode": "0x79",
"UMask": "0x10",
"BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"EventName": "IDQ.MS_DSB_OCCUR",
"CounterMask": "1",
"PublicDescription": "This event counts the number of deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) 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": "This event counts the number of cycles 4 uops were 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": "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": "This event counts the number of cycles uops were 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": "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": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (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": "This event counts the number of cycles 4 uops were 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": "0x24",
"BriefDescription": "Cycles MITE is delivering any Uop",
"Counter": "0,1,2,3",
"EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
"CounterMask": "1",
"PublicDescription": "This event counts the number of cycles uops were 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": "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": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (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"
},
{
"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": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (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",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x3c",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"EventName": "IDQ.MITE_ALL_UOPS",
"PublicDescription": "This event 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": "0x80",
"UMask": "0x1",
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches",
"Counter": "0,1,2,3",
"EventName": "ICACHE.HIT",
"PublicDescription": "This event counts the number of both cacheable and noncacheable Instruction Cache, Streaming Buffer and Victim Cache Reads including UC fetches.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x80",
"UMask": "0x2",
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Misses. Includes Uncacheable accesses.",
"Counter": "0,1,2,3",
"EventName": "ICACHE.MISSES",
"PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes UC accesses.",
"SampleAfterValue": "200003",
"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.IFDATA_STALL",
"PublicDescription": "This event counts cycles during which the demand fetch waits for data (wfdM104H) from L2 or iSB (opportunistic hit).",
"SampleAfterValue": "2000003",
"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": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"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": "This event 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"
},
{
"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": "This event 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"
},
{
"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",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"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",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"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"
},
{
"EventCode": "0xAB",
"UMask": "0x2",
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xAB",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x2"
},
{
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.HIT",
"PublicDescription": "This event counts the number of both cacheable and noncacheable Instruction Cache, Streaming Buffer and Victim Cache Reads including UC fetches.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.IFDATA_STALL",
"PublicDescription": "This event counts cycles during which the demand fetch waits for data (wfdM104H) from L2 or iSB (opportunistic hit).",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Misses. Includes Uncacheable accesses.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.MISSES",
"PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes UC accesses.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
"PublicDescription": "This event counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
"PublicDescription": "This event counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Cycles MITE is delivering 4 Uops",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
"PublicDescription": "This event counts the number of cycles 4 uops were 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",
"UMask": "0x24"
},
{
"BriefDescription": "Cycles MITE is delivering any Uop",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
"PublicDescription": "This event counts the number of cycles uops were 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",
"UMask": "0x24"
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES",
"PublicDescription": "This event 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",
"UMask": "0x8"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
"PublicDescription": "This event 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",
"UMask": "0x8"
},
{
"BriefDescription": "Instruction Decode Queue (IDQ) empty cycles",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.EMPTY",
"PublicDescription": "This counts the number of cycles that the instruction decoder queue is empty and can indicate that the application may be bound in the front end. It does not determine whether there are uops being delivered to the Alloc stage since uops can be delivered by bypass skipping the Instruction Decode Queue (IDQ) when it is empty.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MITE_ALL_UOPS",
"PublicDescription": "This event 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",
"UMask": "0x3c"
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES",
"PublicDescription": "This event 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",
"UMask": "0x4"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
"PublicDescription": "This event 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",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_CYCLES",
"PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
"SampleAfterValue": "2000003",
"UMask": "0x30"
},
{
"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",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_CYCLES",
"PublicDescription": "This event 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",
"UMask": "0x10"
},
{
"BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_OCCUR",
"PublicDescription": "This event counts the number of deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_UOPS",
"PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that 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",
"UMask": "0x10"
},
{
"BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_MITE_UOPS",
"PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ.",
"SampleAfterValue": "2000003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_SWITCHES",
"SampleAfterValue": "2000003",
"UMask": "0x30"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_UOPS",
"PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
"SampleAfterValue": "2000003",
"UMask": "0x30"
},
{
"BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
"PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
"SampleAfterValue": "2000003",
"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",
"CounterHTOff": "0,1,2,3",
"CounterMask": "4",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
"PublicDescription": "This event 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",
"UMask": "0x1"
},
{
"BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"Invert": "1",
"SampleAfterValue": "2000003",
"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",
"CounterHTOff": "0,1,2,3",
"CounterMask": "3",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
"PublicDescription": "This event 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",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "2",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"UMask": "0x1"
}
]

644
lib/libpmc/pmu-events/arch/x86/broadwellde/memory.json
View File

@ -1,432 +1,432 @@
[
{
"EventCode": "0x05",
"UMask": "0x1",
"BriefDescription": "Speculative cache line split load uops dispatched to L1 cache",
"Counter": "0,1,2,3",
"EventName": "MISALIGN_MEM_REF.LOADS",
"PublicDescription": "This event counts speculative cache-line split load uops dispatched to the L1 cache.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x05",
"UMask": "0x2",
"BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache",
"Counter": "0,1,2,3",
"EventName": "MISALIGN_MEM_REF.STORES",
"PublicDescription": "This event counts speculative cache line split store-address (STA) uops dispatched to the L1 cache.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x54",
"UMask": "0x1",
"BriefDescription": "Number of times a TSX line had a cache conflict",
"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 TSX Abort was triggered due to an evicted line caused by a transaction overflow",
"Counter": "0,1,2,3",
"EventName": "TX_MEM.ABORT_CAPACITY_WRITE",
"PublicDescription": "Number of times a TSX Abort was triggered due to an evicted line caused by a transaction overflow.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x54",
"UMask": "0x4",
"BriefDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock",
"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 a TSX Abort was triggered due to commit but Lock Buffer not empty",
"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 a TSX Abort was triggered due to release/commit but data and address mismatch",
"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 a TSX Abort was triggered due to attempting an unsupported alignment from Lock 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 we could not allocate Lock Buffer",
"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",
"SampleAfterValue": "2000003",
"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",
"PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:\n1. memory disambiguation,\n2. external snoop, or\n3. 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 we entered an HLE region; does not count nested transactions",
"Counter": "0,1,2,3",
"EventName": "HLE_RETIRED.START",
"PublicDescription": "Number of times we entered an HLE region\n does not count nested transactions.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xc8",
"UMask": "0x2",
"BriefDescription": "Number of times HLE commit succeeded",
"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 HLE abort was triggered (PEBS)",
"PEBS": "1",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED",
"PEBS": "1",
"PublicDescription": "Number of times HLE abort was triggered (PEBS).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x4"
},
{
"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",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED_MISC1",
"PublicDescription": "Number of times an HLE abort was attributed to a Memory condition (See TSX_Memory event for additional details).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x8"
},
{
"EventCode": "0xc8",
"UMask": "0x10",
"BriefDescription": "Number of times an HLE execution aborted due to uncommon conditions",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED_MISC2",
"PublicDescription": "Number of times the TSX watchdog signaled an HLE abort.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x10"
},
{
"EventCode": "0xc8",
"UMask": "0x20",
"BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED_MISC3",
"PublicDescription": "Number of times a disallowed operation caused an HLE abort.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x20"
},
{
"EventCode": "0xc8",
"UMask": "0x40",
"BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED_MISC4",
"PublicDescription": "Number of times HLE caused a fault.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x40"
},
{
"EventCode": "0xc8",
"UMask": "0x80",
"BriefDescription": "Number of times an HLE execution aborted due to none of the previous 4 categories (e.g. interrupts)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED_MISC5",
"PublicDescription": "Number of times HLE aborted and was not due to the abort conditions in subevents 3-6.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x80"
},
{
"EventCode": "0xc9",
"UMask": "0x1",
"BriefDescription": "Number of times we entered an RTM region; does not count nested transactions",
"BriefDescription": "Number of times HLE commit succeeded",
"Counter": "0,1,2,3",
"EventName": "RTM_RETIRED.START",
"PublicDescription": "Number of times we entered an RTM region\n does not count nested transactions.",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.COMMIT",
"PublicDescription": "Number of times HLE commit succeeded.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x2"
},
{
"EventCode": "0xc9",
"UMask": "0x2",
"BriefDescription": "Number of times RTM commit succeeded",
"BriefDescription": "Number of times we entered an HLE region; does not count nested transactions",
"Counter": "0,1,2,3",
"EventName": "RTM_RETIRED.COMMIT",
"PublicDescription": "Number of times RTM commit succeeded.",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.START",
"PublicDescription": "Number of times we entered an HLE region\n does not count nested transactions.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x1"
},
{
"BriefDescription": "Counts the number of machine clears due to memory order conflicts.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xC3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:\n1. memory disambiguation,\n2. external snoop, or\n3. cross SMT-HW-thread snoop (stores) hitting load buffer.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Loads with latency value being above 128",
"Counter": "3",
"CounterHTOff": "3",
"Errata": "BDM100, BDM35",
"EventCode": "0xCD",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"MSRValue": "0x80",
"PEBS": "2",
"PublicDescription": "This event counts loads with latency value being above 128.",
"SampleAfterValue": "1009",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Loads with latency value being above 16",
"Counter": "3",
"CounterHTOff": "3",
"Errata": "BDM100, BDM35",
"EventCode": "0xCD",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"MSRValue": "0x10",
"PEBS": "2",
"PublicDescription": "This event counts loads with latency value being above 16.",
"SampleAfterValue": "20011",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Loads with latency value being above 256",
"Counter": "3",
"CounterHTOff": "3",
"Errata": "BDM100, BDM35",
"EventCode": "0xCD",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"MSRValue": "0x100",
"PEBS": "2",
"PublicDescription": "This event counts loads with latency value being above 256.",
"SampleAfterValue": "503",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Loads with latency value being above 32",
"Counter": "3",
"CounterHTOff": "3",
"Errata": "BDM100, BDM35",
"EventCode": "0xCD",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"MSRValue": "0x20",
"PEBS": "2",
"PublicDescription": "This event counts loads with latency value being above 32.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Loads with latency value being above 4",
"Counter": "3",
"CounterHTOff": "3",
"Errata": "BDM100, BDM35",
"EventCode": "0xCD",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"MSRValue": "0x4",
"PEBS": "2",
"PublicDescription": "This event counts loads with latency value being above four.",
"SampleAfterValue": "100003",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Loads with latency value being above 512",
"Counter": "3",
"CounterHTOff": "3",
"Errata": "BDM100, BDM35",
"EventCode": "0xCD",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"MSRValue": "0x200",
"PEBS": "2",
"PublicDescription": "This event counts loads with latency value being above 512.",
"SampleAfterValue": "101",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Loads with latency value being above 64",
"Counter": "3",
"CounterHTOff": "3",
"Errata": "BDM100, BDM35",
"EventCode": "0xCD",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"MSRValue": "0x40",
"PEBS": "2",
"PublicDescription": "This event counts loads with latency value being above 64.",
"SampleAfterValue": "2003",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Loads with latency value being above 8",
"Counter": "3",
"CounterHTOff": "3",
"Errata": "BDM100, BDM35",
"EventCode": "0xCD",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"MSRValue": "0x8",
"PEBS": "2",
"PublicDescription": "This event counts loads with latency value being above eight.",
"SampleAfterValue": "50021",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Speculative cache line split load uops dispatched to L1 cache",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "MISALIGN_MEM_REF.LOADS",
"PublicDescription": "This event counts speculative cache-line split load uops dispatched to the L1 cache.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "MISALIGN_MEM_REF.STORES",
"PublicDescription": "This event counts speculative cache line split store-address (STA) uops dispatched to the L1 cache.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"EventCode": "0xc9",
"UMask": "0x4",
"BriefDescription": "Number of times RTM abort was triggered (PEBS)",
"PEBS": "1",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED",
"PEBS": "1",
"PublicDescription": "Number of times RTM abort was triggered (PEBS).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x4"
},
{
"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",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MISC1",
"PublicDescription": "Number of times an RTM abort was attributed to a Memory condition (See TSX_Memory event for additional details).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x8"
},
{
"EventCode": "0xc9",
"UMask": "0x10",
"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",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MISC2",
"PublicDescription": "Number of times the TSX watchdog signaled an RTM abort.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x10"
},
{
"EventCode": "0xc9",
"UMask": "0x20",
"BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MISC3",
"PublicDescription": "Number of times a disallowed operation caused an RTM abort.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x20"
},
{
"EventCode": "0xc9",
"UMask": "0x40",
"BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MISC4",
"PublicDescription": "Number of times a RTM caused a fault.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x40"
},
{
"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",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MISC5",
"PublicDescription": "Number of times RTM aborted and was not due to the abort conditions in subevents 3-6.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x80"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
"BriefDescription": "Loads with latency value being above 4",
"PEBS": "2",
"MSRValue": "0x4",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
"PublicDescription": "This event counts loads with latency value being above four.",
"TakenAlone": "1",
"SampleAfterValue": "100003",
"CounterHTOff": "3"
"BriefDescription": "Number of times RTM commit succeeded",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.COMMIT",
"PublicDescription": "Number of times RTM commit succeeded.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
"BriefDescription": "Loads with latency value being above 8",
"PEBS": "2",
"MSRValue": "0x8",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
"PublicDescription": "This event counts loads with latency value being above eight.",
"TakenAlone": "1",
"SampleAfterValue": "50021",
"CounterHTOff": "3"
"BriefDescription": "Number of times we entered an RTM region; does not count nested transactions",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.START",
"PublicDescription": "Number of times we entered an RTM region\n does not count nested transactions.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
"BriefDescription": "Loads with latency value being above 16",
"PEBS": "2",
"MSRValue": "0x10",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
"PublicDescription": "This event counts loads with latency value being above 16.",
"TakenAlone": "1",
"SampleAfterValue": "20011",
"CounterHTOff": "3"
"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",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5d",
"EventName": "TX_EXEC.MISC1",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
"BriefDescription": "Loads with latency value being above 32",
"PEBS": "2",
"MSRValue": "0x20",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
"PublicDescription": "This event counts loads with latency value being above 32.",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "3"
"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",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5d",
"EventName": "TX_EXEC.MISC2",
"PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
"BriefDescription": "Loads with latency value being above 64",
"PEBS": "2",
"MSRValue": "0x40",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
"PublicDescription": "This event counts loads with latency value being above 64.",
"TakenAlone": "1",
"SampleAfterValue": "2003",
"CounterHTOff": "3"
"BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5d",
"EventName": "TX_EXEC.MISC3",
"PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
"BriefDescription": "Loads with latency value being above 128",
"PEBS": "2",
"MSRValue": "0x80",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
"PublicDescription": "This event counts loads with latency value being above 128.",
"TakenAlone": "1",
"SampleAfterValue": "1009",
"CounterHTOff": "3"
"BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5d",
"EventName": "TX_EXEC.MISC4",
"PublicDescription": "RTM region detected inside HLE.",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
"BriefDescription": "Loads with latency value being above 256",
"PEBS": "2",
"MSRValue": "0x100",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
"PublicDescription": "This event counts loads with latency value being above 256.",
"TakenAlone": "1",
"SampleAfterValue": "503",
"CounterHTOff": "3"
"BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5d",
"EventName": "TX_EXEC.MISC5",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
"BriefDescription": "Loads with latency value being above 512",
"PEBS": "2",
"MSRValue": "0x200",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
"PublicDescription": "This event counts loads with latency value being above 512.",
"TakenAlone": "1",
"SampleAfterValue": "101",
"CounterHTOff": "3"
"BriefDescription": "Number of times a TSX Abort was triggered due to an evicted line caused by a transaction overflow",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_WRITE",
"PublicDescription": "Number of times a TSX Abort was triggered due to an evicted line caused by a transaction overflow.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times a TSX line had a cache conflict",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CONFLICT",
"PublicDescription": "Number of times a TSX line had a cache conflict.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x54",
"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",
"UMask": "0x10"
},
{
"BriefDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x54",
"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",
"UMask": "0x8"
},
{
"BriefDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x54",
"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",
"UMask": "0x20"
},
{
"BriefDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x54",
"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",
"UMask": "0x4"
},
{
"BriefDescription": "Number of times we could not allocate Lock Buffer",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x54",
"EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL",
"PublicDescription": "Number of times we could not allocate Lock Buffer.",
"SampleAfterValue": "2000003",
"UMask": "0x40"
}
]

28
lib/libpmc/pmu-events/arch/x86/broadwellde/other.json
View File

@ -1,44 +1,44 @@
[
{
"EventCode": "0x5C",
"UMask": "0x1",
"BriefDescription": "Unhalted core cycles when the thread is in ring 0",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING0",
"PublicDescription": "This event counts the unhalted core cycles during which the thread is in the ring 0 privileged mode.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"EdgeDetect": "1",
"EventCode": "0x5C",
"UMask": "0x1",
"BriefDescription": "Number of intervals between processor halts while thread is in ring 0",
"Counter": "0,1,2,3",
"EventName": "CPL_CYCLES.RING0_TRANS",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING0_TRANS",
"PublicDescription": "This event counts when there is a transition from ring 1,2 or 3 to ring0.",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"EventCode": "0x5C",
"UMask": "0x2",
"BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING123",
"PublicDescription": "This event counts unhalted core cycles during which the thread is in rings 1, 2, or 3.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x2"
},
{
"EventCode": "0x63",
"UMask": "0x1",
"BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x63",
"EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION",
"PublicDescription": "This event counts cycles in which the L1 and L2 are locked due to a UC lock or split lock. A lock is asserted in case of locked memory access, due to noncacheable memory, locked operation that spans two cache lines, or a page walk from the noncacheable page table. L1D and L2 locks have a very high performance penalty and it is highly recommended to avoid such access.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
}
]

2552
lib/libpmc/pmu-events/arch/x86/broadwellde/pipeline.json
View File

File diff suppressed because it is too large Load Diff

536
lib/libpmc/pmu-events/arch/x86/broadwellde/virtual-memory.json
View File

@ -1,388 +1,388 @@
[
{
"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",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "This event counts load misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"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",
"Errata": "BDM69",
"PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (4K 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": "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",
"Errata": "BDM69",
"PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). 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",
"Errata": "BDM69",
"PublicDescription": "This event 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": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"Errata": "BDM69",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x10",
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
"Errata": "BDM69",
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x20",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_4K",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x40",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_2M",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x60",
"BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x60"
},
{
"EventCode": "0x49",
"UMask": "0x1",
"BriefDescription": "Store misses in all DTLB levels that cause page walks",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
"Errata": "BDM69",
"PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_2M",
"SampleAfterValue": "2000003",
"UMask": "0x40"
},
{
"EventCode": "0x49",
"UMask": "0x2",
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"Errata": "BDM69",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_4K",
"SampleAfterValue": "2000003",
"UMask": "0x20"
},
{
"EventCode": "0x49",
"UMask": "0x4",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)",
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0xe"
},
{
"EventCode": "0x49",
"UMask": "0x8",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (1G)",
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"PublicDescription": "This event 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": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "This event 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",
"UMask": "0x8"
},
{
"EventCode": "0x49",
"UMask": "0xe",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
"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_STORE_MISSES.WALK_COMPLETED",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"EventCode": "0x49",
"UMask": "0x10",
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_DURATION",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"EventCode": "0x49",
"UMask": "0x20",
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (4K).",
"BriefDescription": "Store misses in all DTLB levels that cause page walks",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_4K",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"EventCode": "0x49",
"UMask": "0x40",
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_2M",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0x60",
"BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x60"
},
{
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_2M",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_4K",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (1G)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "This event 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",
"UMask": "0x8"
},
{
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_DURATION",
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"EventCode": "0x4F",
"UMask": "0x10",
"BriefDescription": "Cycle count for an Extended Page table walk.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x4F",
"EventName": "EPT.WALK_CYCLES",
"PublicDescription": "This event counts cycles for an extended page table walk. The Extended Page directory cache differs from standard TLB caches by the operating system that use it. Virtual machine operating systems use the extended page directory cache, while guest operating systems use the standard TLB caches.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x10"
},
{
"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",
"Errata": "BDM69",
"PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"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",
"Errata": "BDM69",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (4K 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": "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",
"Errata": "BDM69",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). 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": "Store miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
"Errata": "BDM69",
"PublicDescription": "This event 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": "Misses in all ITLB levels that cause completed page walks.",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"Errata": "BDM69",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x10",
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_DURATION",
"Errata": "BDM69",
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x20",
"BriefDescription": "Core misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.STLB_HIT_4K",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x40",
"BriefDescription": "Code misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.STLB_HIT_2M",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x60",
"BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
"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",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xAE",
"EventName": "ITLB.ITLB_FLUSH",
"PublicDescription": "This event 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"
"UMask": "0x1"
},
{
"BriefDescription": "Misses at all ITLB levels that cause page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT",
"SampleAfterValue": "100003",
"UMask": "0x60"
},
{
"BriefDescription": "Code misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT_2M",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Core misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT_4K",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "This event 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",
"UMask": "0x8"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_DURATION",
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"EventCode": "0xBC",
"UMask": "0x11",
"BriefDescription": "Number of DTLB page walker hits in the L1+FB.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.DTLB_L1",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x11"
},
{
"EventCode": "0xBC",
"UMask": "0x12",
"BriefDescription": "Number of DTLB page walker hits in the L2.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.DTLB_L2",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L2",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x12"
},
{
"EventCode": "0xBC",
"UMask": "0x14",
"BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.DTLB_L3",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L3",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x14"
},
{
"EventCode": "0xBC",
"UMask": "0x18",
"BriefDescription": "Number of DTLB page walker hits in Memory.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x18"
},
{
"EventCode": "0xBC",
"UMask": "0x21",
"BriefDescription": "Number of ITLB page walker hits in the L1+FB.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.ITLB_L1",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x21"
},
{
"EventCode": "0xBC",
"UMask": "0x22",
"BriefDescription": "Number of ITLB page walker hits in the L2.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.ITLB_L2",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L2",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x22"
},
{
"EventCode": "0xBC",
"UMask": "0x24",
"BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.ITLB_L3",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L3",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x24"
},
{
"EventCode": "0xBD",
"UMask": "0x1",
"BriefDescription": "DTLB flush attempts of the thread-specific entries",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.DTLB_THREAD",
"PublicDescription": "This event counts the number of DTLB flush attempts of the thread-specific entries.",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"EventCode": "0xBD",
"UMask": "0x20",
"BriefDescription": "STLB flush attempts",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.STLB_ANY",
"PublicDescription": "This event counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, and so on).",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x20"
}
]

351
lib/libpmc/pmu-events/arch/x86/broadwellx/bdx-metrics.json
View File

@ -1,196 +1,170 @@
[
{
"BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Frontend_Bound",
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound."
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound."
},
{
"BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Frontend_Bound_SMT",
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Bad_Speculation",
"PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example."
},
{
"BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Bad_Speculation_SMT",
"PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) )",
"MetricGroup": "TopdownL1",
"MetricName": "Backend_Bound",
"PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound."
},
{
"BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) )",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Backend_Bound_SMT",
"PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Retiring",
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. "
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. "
},
{
"BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Retiring_SMT",
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU."
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "Instructions Per Cycle (per Logical Processor)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "TopDownL1",
"MetricGroup": "Ret;Summary",
"MetricName": "IPC"
},
{
"BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
"MetricGroup": "Pipeline;Retire",
"MetricGroup": "Pipeline;Ret;Retire",
"MetricName": "UPI"
},
{
"BriefDescription": "Instruction per taken branch",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fetch_BW;PGO",
"MetricName": "IpTB"
},
{
"BriefDescription": "Branch instructions per taken branch. ",
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;PGO",
"MetricName": "BpTB"
},
{
"BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
"MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
"MetricGroup": "PGO;IcMiss",
"MetricName": "IFetch_Line_Utilization"
},
{
"BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
"MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
"MetricGroup": "DSB;Fetch_BW",
"MetricName": "DSB_Coverage"
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW",
"MetricName": "UpTB"
},
{
"BriefDescription": "Cycles Per Instruction (per Logical Processor)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
"MetricGroup": "Pipeline;Summary",
"MetricExpr": "1 / (INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "Pipeline;Mem",
"MetricName": "CPI"
},
{
"BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Summary",
"MetricGroup": "Pipeline",
"MetricName": "CLKS"
},
{
"BriefDescription": "Total issue-pipeline slots (per-Physical Core)",
"MetricExpr": "4 * cycles",
"MetricGroup": "TopDownL1",
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
"MetricExpr": "4 * CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "TmaL1",
"MetricName": "SLOTS"
},
{
"BriefDescription": "Total issue-pipeline slots (per-Physical Core)",
"MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopDownL1_SMT",
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
"MetricExpr": "4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "TmaL1_SMT",
"MetricName": "SLOTS_SMT"
},
{
"BriefDescription": "Instructions per Load (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
"MetricGroup": "Instruction_Type",
"MetricName": "IpL"
"BriefDescription": "The ratio of Executed- by Issued-Uops",
"MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
"MetricGroup": "Cor;Pipeline",
"MetricName": "Execute_per_Issue",
"PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
},
{
"BriefDescription": "Instructions per Store (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
"MetricGroup": "Instruction_Type",
"MetricName": "IpS"
},
{
"BriefDescription": "Instructions per Branch (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Branches;Instruction_Type",
"MetricName": "IpB"
},
{
"BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
"MetricGroup": "Branches",
"MetricName": "IpCall"
},
{
"BriefDescription": "Total number of retired Instructions",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
"BriefDescription": "Instructions Per Cycle (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / cycles",
"MetricGroup": "SMT",
"BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Ret;SMT;TmaL1",
"MetricName": "CoreIPC"
},
{
"BriefDescription": "Instructions Per Cycle (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "SMT",
"BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "Ret;SMT;TmaL1_SMT",
"MetricName": "CoreIPC_SMT"
},
{
"BriefDescription": "Floating Point Operations Per Cycle",
"MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles",
"MetricGroup": "FLOPS",
"MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Ret;Flops",
"MetricName": "FLOPc"
},
{
"BriefDescription": "Floating Point Operations Per Cycle",
"MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "FLOPS_SMT",
"MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "Ret;Flops_SMT",
"MetricName": "FLOPc_SMT"
},
{
"BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width)",
"MetricExpr": "( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) ) / ( 2 * CPU_CLK_UNHALTED.THREAD )",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "FP_Arith_Utilization",
"PublicDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). Values > 1 are possible due to Fused-Multiply Add (FMA) counting."
},
{
"BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) ) / ( 2 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ) )",
"MetricGroup": "Cor;Flops;HPC_SMT",
"MetricName": "FP_Arith_Utilization_SMT",
"PublicDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). Values > 1 are possible due to Fused-Multiply Add (FMA) counting. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
"MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
"MetricGroup": "Pipeline",
"MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
"MetricName": "ILP"
},
{
"BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)",
"MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "BrMispredicts",
"BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
"MetricExpr": " ( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) * (BR_MISP_RETIRED.ALL_BRANCHES * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / CPU_CLK_UNHALTED.THREAD) / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY )) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) ) * (4 * CPU_CLK_UNHALTED.THREAD) / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;BrMispredicts",
"MetricName": "Branch_Misprediction_Cost"
},
{
"BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)",
"MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "BrMispredicts_SMT",
"BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
"MetricExpr": " ( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * (BR_MISP_RETIRED.ALL_BRANCHES * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / CPU_CLK_UNHALTED.THREAD) / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY )) / #(4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) ) * (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;BrMispredicts_SMT",
"MetricName": "Branch_Misprediction_Cost_SMT"
},
{
"BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "BrMispredicts",
"MetricGroup": "Bad;BadSpec;BrMispredicts",
"MetricName": "IpMispredict"
},
{
@ -200,87 +174,196 @@
"MetricName": "CORE_CLKS"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
"MetricGroup": "InsType",
"MetricName": "IpLoad"
},
{
"BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
"MetricGroup": "InsType",
"MetricName": "IpStore"
},
{
"BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Branches;Fed;InsType",
"MetricName": "IpBranch"
},
{
"BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "IpCall"
},
{
"BriefDescription": "Instruction per taken branch",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO",
"MetricName": "IpTB"
},
{
"BriefDescription": "Branch instructions per taken branch. ",
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "BpTkBranch"
},
{
"BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )",
"MetricGroup": "Flops;InsType",
"MetricName": "IpFLOP"
},
{
"BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) )",
"MetricGroup": "Flops;InsType",
"MetricName": "IpArith",
"PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW."
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "IpArith_Scalar_SP",
"PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "IpArith_Scalar_DP",
"PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "IpArith_AVX128",
"PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "IpArith_AVX256",
"PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Total number of retired Instructions, Sample with: INST_RETIRED.PREC_DIST",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary;TmaL1",
"MetricName": "Instructions"
},
{
"BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
"MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
"MetricGroup": "DSB;Fed;FetchBW",
"MetricName": "DSB_Coverage"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles)",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
"MetricGroup": "Mem;MemoryBound;MemoryLat",
"MetricName": "Load_Miss_Real_Latency",
"PublicDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles). Latency may be overestimated for multi-load instructions - e.g. repeat strings."
},
{
"BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
"MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
"MetricGroup": "Memory_Bound;Memory_BW",
"MetricGroup": "Mem;MemoryBound;MemoryBW",
"MetricName": "MLP"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( 2 * cycles )",
"MetricGroup": "TLB",
"MetricName": "Page_Walks_Utilization"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )",
"MetricGroup": "TLB_SMT",
"MetricName": "Page_Walks_Utilization_SMT"
},
{
"BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
"MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
"MetricGroup": "Memory_BW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L1D_Cache_Fill_BW"
},
{
"BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
"MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
"MetricGroup": "Memory_BW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L2_Cache_Fill_BW"
},
{
"BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
"MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
"MetricGroup": "Memory_BW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L3_Cache_Fill_BW"
},
{
"BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L1MPKI"
},
{
"BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;Backend;CacheMisses",
"MetricName": "L2MPKI"
},
{
"BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;CacheMisses;Offcore",
"MetricName": "L2MPKI_All"
},
{
"BriefDescription": "L2 cache misses per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2MPKI_Load"
},
{
"BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
"MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2HPKI_All"
},
{
"BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2HPKI_Load"
},
{
"BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L3MPKI"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( 2 * CPU_CLK_UNHALTED.THREAD )",
"MetricGroup": "Mem;MemoryTLB",
"MetricName": "Page_Walks_Utilization"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( 2 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ) )",
"MetricGroup": "Mem;MemoryTLB_SMT",
"MetricName": "Page_Walks_Utilization_SMT"
},
{
"BriefDescription": "Average CPU Utilization",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
"MetricGroup": "Summary",
"MetricGroup": "HPC;Summary",
"MetricName": "CPU_Utilization"
},
{
"BriefDescription": "Measured Average Frequency for unhalted processors [GHz]",
"MetricExpr": "(CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time",
"MetricGroup": "Summary;Power",
"MetricName": "Average_Frequency"
},
{
"BriefDescription": "Giga Floating Point Operations Per Second",
"MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
"MetricGroup": "FLOPS;Summary",
"MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 ) / duration_time",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "GFLOPs"
},
{
@ -291,40 +374,52 @@
},
{
"BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
"MetricGroup": "SMT;Summary",
"MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
"MetricGroup": "SMT",
"MetricName": "SMT_2T_Utilization"
},
{
"BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Summary",
"BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "OS",
"MetricName": "Kernel_Utilization"
},
{
"BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
"MetricGroup": "OS",
"MetricName": "Kernel_CPI"
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
"MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
"MetricGroup": "Memory_BW",
"MetricGroup": "HPC;Mem;MemoryBW;SoC",
"MetricName": "DRAM_BW_Use"
},
{
"BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
"MetricExpr": "1000000000 * ( cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x35\\,umask\\=0x3\\,filter_opc\\=0x182@ ) / ( cbox_0@event\\=0x0@ / duration_time )",
"MetricGroup": "Memory_Lat",
"MetricName": "DRAM_Read_Latency"
"MetricGroup": "Mem;MemoryLat;SoC",
"MetricName": "MEM_Read_Latency"
},
{
"BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
"MetricExpr": "cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182\\,thresh\\=1@",
"MetricGroup": "Memory_BW",
"MetricName": "DRAM_Parallel_Reads"
"MetricGroup": "Mem;MemoryBW;SoC",
"MetricName": "MEM_Parallel_Reads"
},
{
"BriefDescription": "Socket actual clocks when any core is active on that socket",
"MetricExpr": "cbox_0@event\\=0x0@",
"MetricGroup": "",
"MetricGroup": "SoC",
"MetricName": "Socket_CLKS"
},
{
"BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
"MetricGroup": "Branches;OS",
"MetricName": "IpFarBranch"
},
{
"BriefDescription": "C3 residency percent per core",
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",

1844
lib/libpmc/pmu-events/arch/x86/broadwellx/cache.json
View File

File diff suppressed because it is too large Load Diff

254
lib/libpmc/pmu-events/arch/x86/broadwellx/floating-point.json
View File

@ -1,165 +1,193 @@
[
{
"EventCode": "0xC1",
"UMask": "0x8",
"BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
"Counter": "0,1,2,3",
"EventName": "OTHER_ASSISTS.AVX_TO_SSE",
"Errata": "BDM30",
"PublicDescription": "This event counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC1",
"UMask": "0x10",
"BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
"Counter": "0,1,2,3",
"EventName": "OTHER_ASSISTS.SSE_TO_AVX",
"Errata": "BDM30",
"PublicDescription": "This event counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"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"
},
{
"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"
},
{
"EventCode": "0xC7",
"UMask": "0x3",
"BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single precision?)",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"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 HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x4"
},
{
"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 HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 4 calculations per element.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x8"
},
{
"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 HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 4 calculations per element.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x10"
},
{
"EventCode": "0xC7",
"UMask": "0x15",
"BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 8 calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
"SampleAfterValue": "2000006",
"CounterHTOff": "0,1,2,3"
},
{
"CounterHTOff": "0,1,2,3",
"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 HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x20"
},
{
"EventCode": "0xC7",
"UMask": "0x2a",
"BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.SINGLE",
"SampleAfterValue": "2000005",
"CounterHTOff": "0,1,2,3"
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
"SampleAfterValue": "2000006",
"UMask": "0x15"
},
{
"EventCode": "0xC7",
"UMask": "0x3c",
"BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single-precision?)",
"BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* packed double and single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP 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",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.PACKED",
"SampleAfterValue": "2000004",
"CounterHTOff": "0,1,2,3"
"UMask": "0x3c"
},
{
"EventCode": "0xCA",
"UMask": "0x2",
"BriefDescription": "Number of X87 assists due to output value.",
"BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation operation. Applies to SSE* and AVX* scalar double and single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP 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_ASSIST.X87_OUTPUT",
"PublicDescription": "This event counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR",
"SampleAfterValue": "2000003",
"UMask": "0x3"
},
{
"EventCode": "0xCA",
"UMask": "0x4",
"BriefDescription": "Number of X87 assists due to input value.",
"BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. 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_ASSIST.X87_INPUT",
"PublicDescription": "This event counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"EventCode": "0xCA",
"UMask": "0x8",
"BriefDescription": "Number of SIMD FP assists due to Output values",
"BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP 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_ASSIST.SIMD_OUTPUT",
"PublicDescription": "This event counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar and packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP 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",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SINGLE",
"SampleAfterValue": "2000005",
"UMask": "0x2a"
},
{
"BriefDescription": "Cycles with any input/output SSE or FP assist",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0xCA",
"UMask": "0x10",
"EventName": "FP_ASSIST.ANY",
"PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
"SampleAfterValue": "100003",
"UMask": "0x1e"
},
{
"BriefDescription": "Number of SIMD FP assists due to input values",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.SIMD_INPUT",
"PublicDescription": "This event counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x10"
},
{
"EventCode": "0xCA",
"UMask": "0x1e",
"BriefDescription": "Cycles with any input/output SSE or FP assist",
"BriefDescription": "Number of SIMD FP assists due to Output values",
"Counter": "0,1,2,3",
"EventName": "FP_ASSIST.ANY",
"CounterMask": "1",
"PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.SIMD_OUTPUT",
"PublicDescription": "This event counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x8"
},
{
"BriefDescription": "Number of X87 assists due to input value.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.X87_INPUT",
"PublicDescription": "This event counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of X87 assists due to output value.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.X87_OUTPUT",
"PublicDescription": "This event counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of SIMD Move Elimination candidate uops that were eliminated.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x58",
"EventName": "MOVE_ELIMINATION.SIMD_ELIMINATED",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of SIMD Move Elimination candidate uops that were not eliminated.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x58",
"EventName": "MOVE_ELIMINATION.SIMD_NOT_ELIMINATED",
"SampleAfterValue": "1000003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM30",
"EventCode": "0xC1",
"EventName": "OTHER_ASSISTS.AVX_TO_SSE",
"PublicDescription": "This event counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM30",
"EventCode": "0xC1",
"EventName": "OTHER_ASSISTS.SSE_TO_AVX",
"PublicDescription": "This event counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Micro-op dispatches cancelled due to insufficient SIMD physical register file read ports",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xA0",
"EventName": "UOP_DISPATCHES_CANCELLED.SIMD_PRF",
"PublicDescription": "This event counts the number of micro-operations cancelled after they were dispatched from the scheduler to the execution units when the total number of physical register read ports across all dispatch ports exceeds the read bandwidth of the physical register file. The SIMD_PRF subevent applies to the following instructions: VDPPS, DPPS, VPCMPESTRI, PCMPESTRI, VPCMPESTRM, PCMPESTRM, VFMADD*, VFMADDSUB*, VFMSUB*, VMSUBADD*, VFNMADD*, VFNMSUB*. See the Broadwell Optimization Guide for more information.",
"SampleAfterValue": "2000003",
"UMask": "0x3"
}
]

557
lib/libpmc/pmu-events/arch/x86/broadwellx/frontend.json
View File

@ -1,286 +1,295 @@
[
{
"EventCode": "0x79",
"UMask": "0x2",
"BriefDescription": "Instruction Decode Queue (IDQ) empty cycles",
"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": "IDQ.EMPTY",
"PublicDescription": "This counts the number of cycles that the instruction decoder queue is empty and can indicate that the application may be bound in the front end. It does not determine whether there are uops being delivered to the Alloc stage since uops can be delivered by bypass skipping the Instruction Decode Queue (IDQ) when it is empty.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xe6",
"EventName": "BACLEARS.ANY",
"SampleAfterValue": "100003",
"UMask": "0x1f"
},
{
"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": "This event 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": "This event 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": "This event 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": "This event 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": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"EventName": "IDQ.MS_DSB_UOPS",
"PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that 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": "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": "This event 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"
},
{
"EdgeDetect": "1",
"EventCode": "0x79",
"UMask": "0x10",
"BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"EventName": "IDQ.MS_DSB_OCCUR",
"CounterMask": "1",
"PublicDescription": "This event counts the number of deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) 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": "This event counts the number of cycles 4 uops were 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": "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": "This event counts the number of cycles uops were 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": "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": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (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": "This event counts the number of cycles 4 uops were 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": "0x24",
"BriefDescription": "Cycles MITE is delivering any Uop",
"Counter": "0,1,2,3",
"EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
"CounterMask": "1",
"PublicDescription": "This event counts the number of cycles uops were 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": "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": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (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"
},
{
"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": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (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",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x3c",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"EventName": "IDQ.MITE_ALL_UOPS",
"PublicDescription": "This event 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": "0x80",
"UMask": "0x1",
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches",
"Counter": "0,1,2,3",
"EventName": "ICACHE.HIT",
"PublicDescription": "This event counts the number of both cacheable and noncacheable Instruction Cache, Streaming Buffer and Victim Cache Reads including UC fetches.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x80",
"UMask": "0x2",
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Misses. Includes Uncacheable accesses.",
"Counter": "0,1,2,3",
"EventName": "ICACHE.MISSES",
"PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes UC accesses.",
"SampleAfterValue": "200003",
"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.IFDATA_STALL",
"PublicDescription": "This event counts cycles during which the demand fetch waits for data (wfdM104H) from L2 or iSB (opportunistic hit).",
"SampleAfterValue": "2000003",
"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": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"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": "This event 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"
},
{
"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": "This event 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"
},
{
"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",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"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",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"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"
},
{
"EventCode": "0xAB",
"UMask": "0x2",
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xAB",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x2"
},
{
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.HIT",
"PublicDescription": "This event counts the number of both cacheable and noncacheable Instruction Cache, Streaming Buffer and Victim Cache Reads including UC fetches.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.IFDATA_STALL",
"PublicDescription": "This event counts cycles during which the demand fetch waits for data (wfdM104H) from L2 or iSB (opportunistic hit).",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Misses. Includes Uncacheable accesses.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.MISSES",
"PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes UC accesses.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
"PublicDescription": "This event counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
"PublicDescription": "This event counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Cycles MITE is delivering 4 Uops",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
"PublicDescription": "This event counts the number of cycles 4 uops were 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",
"UMask": "0x24"
},
{
"BriefDescription": "Cycles MITE is delivering any Uop",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
"PublicDescription": "This event counts the number of cycles uops were 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",
"UMask": "0x24"
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES",
"PublicDescription": "This event 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",
"UMask": "0x8"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
"PublicDescription": "This event 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",
"UMask": "0x8"
},
{
"BriefDescription": "Instruction Decode Queue (IDQ) empty cycles",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.EMPTY",
"PublicDescription": "This counts the number of cycles that the instruction decoder queue is empty and can indicate that the application may be bound in the front end. It does not determine whether there are uops being delivered to the Alloc stage since uops can be delivered by bypass skipping the Instruction Decode Queue (IDQ) when it is empty.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MITE_ALL_UOPS",
"PublicDescription": "This event 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",
"UMask": "0x3c"
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES",
"PublicDescription": "This event 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",
"UMask": "0x4"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
"PublicDescription": "This event 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",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_CYCLES",
"PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
"SampleAfterValue": "2000003",
"UMask": "0x30"
},
{
"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",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_CYCLES",
"PublicDescription": "This event 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",
"UMask": "0x10"
},
{
"BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_OCCUR",
"PublicDescription": "This event counts the number of deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_UOPS",
"PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that 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",
"UMask": "0x10"
},
{
"BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_MITE_UOPS",
"PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ.",
"SampleAfterValue": "2000003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_SWITCHES",
"SampleAfterValue": "2000003",
"UMask": "0x30"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_UOPS",
"PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
"SampleAfterValue": "2000003",
"UMask": "0x30"
},
{
"BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
"PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
"SampleAfterValue": "2000003",
"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",
"CounterHTOff": "0,1,2,3",
"CounterMask": "4",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
"PublicDescription": "This event 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",
"UMask": "0x1"
},
{
"BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"Invert": "1",
"SampleAfterValue": "2000003",
"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",
"CounterHTOff": "0,1,2,3",
"CounterMask": "3",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
"PublicDescription": "This event 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",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "2",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"UMask": "0x1"
}
]

1094
lib/libpmc/pmu-events/arch/x86/broadwellx/memory.json
View File

File diff suppressed because it is too large Load Diff

28
lib/libpmc/pmu-events/arch/x86/broadwellx/other.json
View File

@ -1,44 +1,44 @@
[
{
"EventCode": "0x5C",
"UMask": "0x1",
"BriefDescription": "Unhalted core cycles when the thread is in ring 0",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING0",
"PublicDescription": "This event counts the unhalted core cycles during which the thread is in the ring 0 privileged mode.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"EdgeDetect": "1",
"EventCode": "0x5C",
"UMask": "0x1",
"BriefDescription": "Number of intervals between processor halts while thread is in ring 0",
"Counter": "0,1,2,3",
"EventName": "CPL_CYCLES.RING0_TRANS",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING0_TRANS",
"PublicDescription": "This event counts when there is a transition from ring 1,2 or 3 to ring0.",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"EventCode": "0x5C",
"UMask": "0x2",
"BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING123",
"PublicDescription": "This event counts unhalted core cycles during which the thread is in rings 1, 2, or 3.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x2"
},
{
"EventCode": "0x63",
"UMask": "0x1",
"BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x63",
"EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION",
"PublicDescription": "This event counts cycles in which the L1 and L2 are locked due to a UC lock or split lock. A lock is asserted in case of locked memory access, due to noncacheable memory, locked operation that spans two cache lines, or a page walk from the noncacheable page table. L1D and L2 locks have a very high performance penalty and it is highly recommended to avoid such access.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
}
]

2551
lib/libpmc/pmu-events/arch/x86/broadwellx/pipeline.json
View File

File diff suppressed because it is too large Load Diff

536
lib/libpmc/pmu-events/arch/x86/broadwellx/virtual-memory.json
View File

@ -1,388 +1,388 @@
[
{
"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",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "This event counts load misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"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",
"Errata": "BDM69",
"PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (4K 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": "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",
"Errata": "BDM69",
"PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). 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",
"Errata": "BDM69",
"PublicDescription": "This event 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": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"Errata": "BDM69",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x10",
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
"Errata": "BDM69",
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x20",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_4K",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x40",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_2M",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x60",
"BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x60"
},
{
"EventCode": "0x49",
"UMask": "0x1",
"BriefDescription": "Store misses in all DTLB levels that cause page walks",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
"Errata": "BDM69",
"PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_2M",
"SampleAfterValue": "2000003",
"UMask": "0x40"
},
{
"EventCode": "0x49",
"UMask": "0x2",
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"Errata": "BDM69",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_4K",
"SampleAfterValue": "2000003",
"UMask": "0x20"
},
{
"EventCode": "0x49",
"UMask": "0x4",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)",
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0xe"
},
{
"EventCode": "0x49",
"UMask": "0x8",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (1G)",
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"PublicDescription": "This event 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": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "This event 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",
"UMask": "0x8"
},
{
"EventCode": "0x49",
"UMask": "0xe",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
"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_STORE_MISSES.WALK_COMPLETED",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"EventCode": "0x49",
"UMask": "0x10",
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_DURATION",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"EventCode": "0x49",
"UMask": "0x20",
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (4K).",
"BriefDescription": "Store misses in all DTLB levels that cause page walks",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_4K",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"EventCode": "0x49",
"UMask": "0x40",
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_2M",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0x60",
"BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x60"
},
{
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_2M",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_4K",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (1G)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "This event 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",
"UMask": "0x8"
},
{
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_DURATION",
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"EventCode": "0x4F",
"UMask": "0x10",
"BriefDescription": "Cycle count for an Extended Page table walk.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x4F",
"EventName": "EPT.WALK_CYCLES",
"PublicDescription": "This event counts cycles for an extended page table walk. The Extended Page directory cache differs from standard TLB caches by the operating system that use it. Virtual machine operating systems use the extended page directory cache, while guest operating systems use the standard TLB caches.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x10"
},
{
"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",
"Errata": "BDM69",
"PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"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",
"Errata": "BDM69",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (4K 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": "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",
"Errata": "BDM69",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). 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": "Store miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
"Errata": "BDM69",
"PublicDescription": "This event 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": "Misses in all ITLB levels that cause completed page walks.",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"Errata": "BDM69",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x10",
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_DURATION",
"Errata": "BDM69",
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x20",
"BriefDescription": "Core misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.STLB_HIT_4K",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x40",
"BriefDescription": "Code misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.STLB_HIT_2M",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x60",
"BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
"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",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xAE",
"EventName": "ITLB.ITLB_FLUSH",
"PublicDescription": "This event 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"
"UMask": "0x1"
},
{
"BriefDescription": "Misses at all ITLB levels that cause page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT",
"SampleAfterValue": "100003",
"UMask": "0x60"
},
{
"BriefDescription": "Code misses that miss the DTLB and hit the STLB (2M).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT_2M",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Core misses that miss the DTLB and hit the STLB (4K).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT_4K",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "This event 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",
"UMask": "0x8"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "BDM69",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_DURATION",
"PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"EventCode": "0xBC",
"UMask": "0x11",
"BriefDescription": "Number of DTLB page walker hits in the L1+FB.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.DTLB_L1",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x11"
},
{
"EventCode": "0xBC",
"UMask": "0x12",
"BriefDescription": "Number of DTLB page walker hits in the L2.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.DTLB_L2",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L2",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x12"
},
{
"EventCode": "0xBC",
"UMask": "0x14",
"BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.DTLB_L3",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L3",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x14"
},
{
"EventCode": "0xBC",
"UMask": "0x18",
"BriefDescription": "Number of DTLB page walker hits in Memory.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x18"
},
{
"EventCode": "0xBC",
"UMask": "0x21",
"BriefDescription": "Number of ITLB page walker hits in the L1+FB.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.ITLB_L1",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x21"
},
{
"EventCode": "0xBC",
"UMask": "0x22",
"BriefDescription": "Number of ITLB page walker hits in the L2.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.ITLB_L2",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L2",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x22"
},
{
"EventCode": "0xBC",
"UMask": "0x24",
"BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.ITLB_L3",
"CounterHTOff": "0,1,2,3",
"Errata": "BDM69, BDM98",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L3",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x24"
},
{
"EventCode": "0xBD",
"UMask": "0x1",
"BriefDescription": "DTLB flush attempts of the thread-specific entries",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.DTLB_THREAD",
"PublicDescription": "This event counts the number of DTLB flush attempts of the thread-specific entries.",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"EventCode": "0xBD",
"UMask": "0x20",
"BriefDescription": "STLB flush attempts",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.STLB_ANY",
"PublicDescription": "This event counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, and so on).",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x20"
}
]

7711
lib/libpmc/pmu-events/arch/x86/cascadelakex/cache.json
View File

File diff suppressed because it is too large Load Diff

469
lib/libpmc/pmu-events/arch/x86/cascadelakex/clx-metrics.json
View File

File diff suppressed because one or more lines are too long

50
lib/libpmc/pmu-events/arch/x86/cascadelakex/floating-point.json
View File

@ -1,37 +1,41 @@
[
{
"BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT14 RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"BriefDescription": "Counts once for most SIMD 128-bit packed computational double precision floating-point instructions retired. Counts twice for DPP and FM(N)ADD/SUB instructions retired.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"PublicDescription": "Counts once for most SIMD 128-bit packed computational double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"BriefDescription": "Counts once for most SIMD 128-bit packed computational single precision floating-point instruction retired. Counts twice for DPP and FM(N)ADD/SUB instructions retired.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"PublicDescription": "Counts once for most SIMD 128-bit packed computational single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"BriefDescription": "Counts once for most SIMD 256-bit packed double computational precision floating-point instructions retired. Counts twice for DPP and FM(N)ADD/SUB instructions retired.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"PublicDescription": "Counts once for most SIMD 256-bit packed double computational precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"BriefDescription": "Counts once for most SIMD 256-bit packed single computational precision floating-point instructions retired. Counts twice for DPP and FM(N)ADD/SUB instructions retired.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"PublicDescription": "Counts once for most SIMD 256-bit packed single computational precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "2000003",
"UMask": "0x20"
},
@ -41,6 +45,7 @@
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
"PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "2000003",
"UMask": "0x40"
},
@ -50,27 +55,60 @@
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
"PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "2000003",
"UMask": "0x80"
},
{
"BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"BriefDescription": "Counts once for most SIMD scalar computational double precision floating-point instructions retired. Counts twice for DPP and FM(N)ADD/SUB instructions retired.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"PublicDescription": "Counts once for most SIMD scalar computational double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SIMD 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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"BriefDescription": "Counts once for most SIMD scalar computational single precision floating-point instructions retired. Counts twice for DPP and FM(N)ADD/SUB instructions retired.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xC7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"PublicDescription": "Counts once for most SIMD scalar computational single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SIMD scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Intel AVX-512 computational 512-bit packed BFloat16 instructions retired.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCF",
"EventName": "FP_ARITH_INST_RETIRED2.128BIT_PACKED_BF16",
"PublicDescription": "Counts once for each Intel AVX-512 computational 512-bit packed BFloat16 floating-point instruction retired. Applies to the ZMM based VDPBF16PS instruction. Each count represents 64 computation operations. This event is only supported on products formerly named Cooper Lake and is not supported on products formerly named Cascade Lake.",
"SampleAfterValue": "2000003",
"UMask": "0x20"
},
{
"BriefDescription": "Intel AVX-512 computational 128-bit packed BFloat16 instructions retired.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCF",
"EventName": "FP_ARITH_INST_RETIRED2.256BIT_PACKED_BF16",
"PublicDescription": "Counts once for each Intel AVX-512 computational 128-bit packed BFloat16 floating-point instruction retired. Applies to the XMM based VDPBF16PS instruction. Each count represents 16 computation operations. This event is only supported on products formerly named Cooper Lake and is not supported on products formerly named Cascade Lake.",
"SampleAfterValue": "2000003",
"UMask": "0x40"
},
{
"BriefDescription": "Intel AVX-512 computational 256-bit packed BFloat16 instructions retired.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCF",
"EventName": "FP_ARITH_INST_RETIRED2.512BIT_PACKED_BF16",
"PublicDescription": "Counts once for each Intel AVX-512 computational 256-bit packed BFloat16 floating-point instruction retired. Applies to the YMM based VDPBF16PS instruction. Each count represents 32 computation operations. This event is only supported on products formerly named Cooper Lake and is not supported on products formerly named Cascade Lake.",
"SampleAfterValue": "2000003",
"UMask": "0x80"
},
{
"BriefDescription": "Cycles with any input/output SSE or FP assist",
"Counter": "0,1,2,3",

18
lib/libpmc/pmu-events/arch/x86/cascadelakex/frontend.json
View File

@ -30,7 +30,21 @@
"UMask": "0x2"
},
{
"BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss.",
"BriefDescription": "Retired Instructions who experienced DSB miss.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xC6",
"EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x1",
"PEBS": "1",
"PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced a critical DSB miss.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xC6",
@ -38,7 +52,7 @@
"MSRIndex": "0x3F7",
"MSRValue": "0x11",
"PEBS": "1",
"PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
"PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"

1710
lib/libpmc/pmu-events/arch/x86/cascadelakex/memory.json
View File

File diff suppressed because it is too large Load Diff

6968
lib/libpmc/pmu-events/arch/x86/cascadelakex/other.json
View File

File diff suppressed because it is too large Load Diff

25
lib/libpmc/pmu-events/arch/x86/cascadelakex/pipeline.json
View File

@ -416,6 +416,16 @@
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Instruction decoders utilized in a cycle",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x55",
"EventName": "INST_DECODED.DECODERS",
"PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Instructions retired from execution.",
"Counter": "Fixed counter 0",
@ -435,6 +445,17 @@
"PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).",
"SampleAfterValue": "2000003"
},
{
"BriefDescription": "Number of all retired NOP instructions.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "SKL091, SKL044",
"EventCode": "0xC0",
"EventName": "INST_RETIRED.NOP",
"PEBS": "1",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution",
"Counter": "1",
@ -958,7 +979,7 @@
"BriefDescription": "Cycles with less than 10 actually retired uops.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "10",
"CounterMask": "16",
"EventCode": "0xC2",
"EventName": "UOPS_RETIRED.TOTAL_CYCLES",
"Invert": "1",
@ -966,4 +987,4 @@
"SampleAfterValue": "2000003",
"UMask": "0x2"
}
]
]

61
lib/libpmc/pmu-events/arch/x86/cascadelakex/uncore-memory.json
View File

@ -9,6 +9,16 @@
"UMask": "0x3",
"Unit": "iMC"
},
{
"BriefDescription": "read requests to memory controller",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_M_CAS_COUNT.RD",
"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",
@ -19,6 +29,16 @@
"UMask": "0xC",
"Unit": "iMC"
},
{
"BriefDescription": "write requests to memory controller",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_M_CAS_COUNT.WR",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0xC",
"Unit": "iMC"
},
{
"BriefDescription": "Memory controller clock ticks",
"Counter": "0,1,2,3",
@ -89,6 +109,15 @@
"ScaleUnit": "6.103515625E-5MB/sec",
"Unit": "iMC"
},
{
"BriefDescription": "Intel Optane DC persistent memory bandwidth read (MB/sec)",
"Counter": "0,1,2,3",
"EventCode": "0xE3",
"EventName": "UNC_M_PMM_RPQ_INSERTS",
"PerPkg": "1",
"ScaleUnit": "6.103515625E-5MB/sec",
"Unit": "iMC"
},
{
"BriefDescription": "Intel Optane DC persistent memory bandwidth write (MB/sec). Derived from unc_m_pmm_wpq_inserts",
"Counter": "0,1,2,3",
@ -98,6 +127,15 @@
"ScaleUnit": "6.103515625E-5MB/sec",
"Unit": "iMC"
},
{
"BriefDescription": "Intel Optane DC persistent memory bandwidth write (MB/sec)",
"Counter": "0,1,2,3",
"EventCode": "0xE7",
"EventName": "UNC_M_PMM_WPQ_INSERTS",
"PerPkg": "1",
"ScaleUnit": "6.103515625E-5MB/sec",
"Unit": "iMC"
},
{
"BriefDescription": "Intel Optane DC persistent memory bandwidth total (MB/sec). Derived from unc_m_pmm_rpq_inserts",
"Counter": "0,1,2,3",
@ -109,6 +147,17 @@
"ScaleUnit": "6.103515625E-5MB/sec",
"Unit": "iMC"
},
{
"BriefDescription": "Intel Optane DC persistent memory bandwidth total (MB/sec)",
"Counter": "0,1,2,3",
"EventCode": "0xE3",
"EventName": "UNC_M_PMM_RPQ_INSERTS",
"MetricExpr": "UNC_M_PMM_RPQ_INSERTS + UNC_M_PMM_WPQ_INSERTS",
"MetricName": "UNC_M_PMM_BANDWIDTH.TOTAL",
"PerPkg": "1",
"ScaleUnit": "6.103515625E-5MB/sec",
"Unit": "iMC"
},
{
"BriefDescription": "Read Pending Queue Occupancy of all read requests for Intel Optane DC persistent memory",
"Counter": "0,1,2,3",
@ -130,6 +179,18 @@
"UMask": "0x1",
"Unit": "iMC"
},
{
"BriefDescription": "Intel Optane DC persistent memory read latency (ns)",
"Counter": "0,1,2,3",
"EventCode": "0xE0",
"EventName": "UNC_M_PMM_RPQ_OCCUPANCY.ALL",
"MetricExpr": "UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS / UNC_M_CLOCKTICKS",
"MetricName": "UNC_M_PMM_READ_LATENCY",
"PerPkg": "1",
"ScaleUnit": "6000000000ns",
"UMask": "0x1",
"Unit": "iMC"
},
{
"BriefDescription": "DRAM Page Activate commands sent due to a write request",
"Counter": "0,1,2,3",

131
lib/libpmc/pmu-events/arch/x86/cascadelakex/uncore-other.json
View File

@ -16,6 +16,16 @@
"UMask": "0x21",
"Unit": "CHA"
},
{
"BriefDescription": "LLC misses - Uncacheable reads (from cpu) ",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS",
"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",
@ -26,6 +36,16 @@
"UMask": "0x21",
"Unit": "CHA"
},
{
"BriefDescription": "MMIO reads",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS",
"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",
@ -36,6 +56,16 @@
"UMask": "0x21",
"Unit": "CHA"
},
{
"BriefDescription": "MMIO writes",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS",
"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",
@ -47,6 +77,17 @@
"UMask": "0x21",
"Unit": "CHA"
},
{
"BriefDescription": "Streaming stores (full cache line)",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS",
"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",
@ -58,6 +99,17 @@
"UMask": "0x21",
"Unit": "CHA"
},
{
"BriefDescription": "Streaming stores (partial cache line)",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS",
"Filter": "config1=0x41a33",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x21",
"Unit": "CHA"
},
{
"BriefDescription": "read requests from home agent",
"Counter": "0,1,2,3",
@ -113,6 +165,16 @@
"UMask": "0xf",
"Unit": "UPI LL"
},
{
"BriefDescription": "UPI interconnect send bandwidth for payload",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_UPI_TxL_FLITS.ALL_DATA",
"PerPkg": "1",
"ScaleUnit": "7.11E-06Bytes",
"UMask": "0xf",
"Unit": "UPI LL"
},
{
"BriefDescription": "PCI Express bandwidth writing at IIO, part 0",
"Counter": "0,1",
@ -176,6 +238,21 @@
"UMask": "0x01",
"Unit": "IIO"
},
{
"BriefDescription": "PCI Express bandwidth writing at IIO",
"Counter": "0,1",
"EventCode": "0x83",
"EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0",
"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 reading at IIO, part 0",
"Counter": "0,1",
@ -239,6 +316,21 @@
"UMask": "0x04",
"Unit": "IIO"
},
{
"BriefDescription": "PCI Express bandwidth reading at IIO",
"Counter": "0,1",
"EventCode": "0x83",
"EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0",
"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": "Core Cross Snoops Issued; Multiple Core Requests",
"Counter": "0,1,2,3",
@ -514,7 +606,7 @@
"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.",
"PublicDescription": "Counts when a transaction with the opcode type Rsp*Fwd*WB Snoop Response was received which indicates the data was written back to its 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 its home socket to be written back to memory.",
"UMask": "0x20",
"Unit": "CHA"
},
@ -524,7 +616,7 @@
"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.",
"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 its 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 response 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"
},
@ -558,6 +650,18 @@
"PublicDescription": "Counts clockticks of the 1GHz trafiic controller clock in the IIO unit.",
"Unit": "IIO"
},
{
"BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0-3",
"Counter": "0,1,2,3",
"EventCode": "0xC2",
"EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL_PARTS",
"FCMask": "0x4",
"PerPkg": "1",
"PortMask": "0x0f",
"PublicDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0-3",
"UMask": "0x03",
"Unit": "IIO"
},
{
"BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0",
"Counter": "0,1,2,3",
@ -606,6 +710,17 @@
"UMask": "0x03",
"Unit": "IIO"
},
{
"BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 0-3",
"Counter": "2,3",
"EventCode": "0xD5",
"EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS",
"FCMask": "0x04",
"PerPkg": "1",
"PublicDescription": "PCIe Completion Buffer occupancy of completions with data: Part 0-3",
"UMask": "0x0f",
"Unit": "IIO"
},
{
"BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 0",
"Counter": "2,3",
@ -1499,7 +1614,7 @@
"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 A (SnoopAll) to I (Invalid)",
"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"
},
@ -1509,7 +1624,7 @@
"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 A (SnoopAll) to S (Shared)",
"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"
},
@ -1529,7 +1644,7 @@
"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 I (Invalid) to A (SnoopAll)",
"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"
},
@ -1539,7 +1654,7 @@
"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 I (Invalid) to S (Shared)",
"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"
},
@ -1549,7 +1664,7 @@
"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 S (Shared) to A (SnoopAll)",
"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"
},
@ -1559,7 +1674,7 @@
"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 S (Shared) to I (Invalid)",
"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"
},

254
lib/libpmc/pmu-events/arch/x86/elkhartlake/other.json
View File

@ -1,15 +1,4 @@
[
{
"BriefDescription": "Counts the total number of BTCLEARS.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xe8",
"EventName": "BTCLEAR.ANY",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the total number of BTCLEARS which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
"SampleAfterValue": "200003"
},
{
"BriefDescription": "This event is deprecated. Refer to new event BUS_LOCK.SELF_LOCKS",
"CollectPEBSRecord": "2",
@ -179,246 +168,5 @@
"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",
"UMask": "0x1"
},
{
"BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x73",
"EventName": "TOPDOWN_BAD_SPECULATION.ALL",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
"SampleAfterValue": "1000003",
"UMask": "0x6"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to fast nukes such as memory ordering and memory disambiguation machine clears.",
"Counter": "0,1,2,3",
"EventCode": "0x73",
"EventName": "TOPDOWN_BAD_SPECULATION.FASTNUKE",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.",
"Counter": "0,1,2,3",
"EventCode": "0x73",
"EventName": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to branch mispredicts.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x73",
"EventName": "TOPDOWN_BAD_SPECULATION.MISPREDICT",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
{
"BriefDescription": "This event is deprecated. Refer to new event TOPDOWN_BAD_SPECULATION.FASTNUKE",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x73",
"EventName": "TOPDOWN_BAD_SPECULATION.MONUKE",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts the total number of issue slots every cycle that were not consumed by the backend due to backend stalls.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.ALL",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to certain allocation restrictions.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.MEM_SCHEDULER",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x8"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.REGISTER",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x20"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to the reorder buffer being full (ROB stalls).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.REORDER_BUFFER",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x40"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.SERIALIZATION",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x10"
},
{
"BriefDescription": "This event is deprecated.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.STORE_BUFFER",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to frontend stalls.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.ALL",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BACLEARS.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.BRANCH_DETECT",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BTCLEARS.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.BRANCH_RESTEER",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
"SampleAfterValue": "1000003",
"UMask": "0x40"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to the microcode sequencer (MS).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.CISC",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to decode stalls.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.DECODE",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x8"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to ITLB misses.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.ITLB",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.",
"SampleAfterValue": "1000003",
"UMask": "0x10"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to other common frontend stalls not categorized.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.OTHER",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x80"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to wrong predecodes.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.PREDECODE",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
{
"BriefDescription": "Counts the total number of consumed retirement slots.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xc2",
"EventName": "TOPDOWN_RETIRING.ALL",
"PEBS": "1",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003"
}
]
]

254
lib/libpmc/pmu-events/arch/x86/elkhartlake/pipeline.json
View File

@ -153,6 +153,17 @@
"SampleAfterValue": "200003",
"UMask": "0xfe"
},
{
"BriefDescription": "Counts the total number of BTCLEARS.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xe8",
"EventName": "BTCLEAR.ANY",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the total number of BTCLEARS which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
"SampleAfterValue": "200003"
},
{
"BriefDescription": "Counts the number of unhalted core clock cycles. (Fixed event)",
"CollectPEBSRecord": "2",
@ -262,6 +273,247 @@
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "20003"
},
{
"BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x73",
"EventName": "TOPDOWN_BAD_SPECULATION.ALL",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
"SampleAfterValue": "1000003",
"UMask": "0x6"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to fast nukes such as memory ordering and memory disambiguation machine clears.",
"Counter": "0,1,2,3",
"EventCode": "0x73",
"EventName": "TOPDOWN_BAD_SPECULATION.FASTNUKE",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.",
"Counter": "0,1,2,3",
"EventCode": "0x73",
"EventName": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to branch mispredicts.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x73",
"EventName": "TOPDOWN_BAD_SPECULATION.MISPREDICT",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
{
"BriefDescription": "This event is deprecated. Refer to new event TOPDOWN_BAD_SPECULATION.FASTNUKE",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x73",
"EventName": "TOPDOWN_BAD_SPECULATION.MONUKE",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts the total number of issue slots every cycle that were not consumed by the backend due to backend stalls.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.ALL",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to certain allocation restrictions.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.MEM_SCHEDULER",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x8"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.REGISTER",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x20"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to the reorder buffer being full (ROB stalls).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.REORDER_BUFFER",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x40"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.SERIALIZATION",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x10"
},
{
"BriefDescription": "This event is deprecated.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "TOPDOWN_BE_BOUND.STORE_BUFFER",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to frontend stalls.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.ALL",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BACLEARS.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.BRANCH_DETECT",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BTCLEARS.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.BRANCH_RESTEER",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
"SampleAfterValue": "1000003",
"UMask": "0x40"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to the microcode sequencer (MS).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.CISC",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to decode stalls.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.DECODE",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x8"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to ITLB misses.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.ITLB",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.",
"SampleAfterValue": "1000003",
"UMask": "0x10"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to other common frontend stalls not categorized.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.OTHER",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x80"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to wrong predecodes.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.PREDECODE",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
{
"BriefDescription": "Counts the total number of consumed retirement slots.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xc2",
"EventName": "TOPDOWN_RETIRING.ALL",
"PEBS": "1",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003"
},
{
"BriefDescription": "Counts the number of uops that are from complex flows issued by the micro-sequencer (MS).",
"CollectPEBSRecord": "2",
@ -275,4 +527,4 @@
"SampleAfterValue": "2000003",
"UMask": "0x1"
}
]
]

2192
lib/libpmc/pmu-events/arch/x86/goldmont/cache.json
View File

File diff suppressed because it is too large Load Diff

33
lib/libpmc/pmu-events/arch/x86/goldmont/floating-point.json Normal file
View File

@ -0,0 +1,33 @@
[
{
"BriefDescription": "Cycles the FP divide unit is busy",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xCD",
"EventName": "CYCLES_DIV_BUSY.FPDIV",
"PublicDescription": "Counts core cycles the floating point divide unit is busy.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Machine clears due to FP assists",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xC3",
"EventName": "MACHINE_CLEARS.FP_ASSIST",
"PublicDescription": "Counts machine clears due to floating point (FP) operations needing assists. For instance, if the result was a floating point denormal, the hardware clears the pipeline and reissues uops to produce the correct IEEE compliant denormal result.",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Floating point divide uops retired. (Precise Event Capable)",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xC2",
"EventName": "UOPS_RETIRED.FPDIV",
"PEBS": "2",
"PublicDescription": "Counts the number of floating point divide uops retired.",
"SampleAfterValue": "2000003",
"UMask": "0x8"
}
]

86
lib/libpmc/pmu-events/arch/x86/goldmont/frontend.json
View File

@ -1,52 +1,82 @@
[
{
"BriefDescription": "BACLEARs asserted for any branch type",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line and that cache line is in the ICache (hit). The event strives to count on a cache line basis, so that multiple accesses which hit in a single cache line count as one ICACHE.HIT. Specifically, the event counts when straight line code crosses the cache line boundary, or when a branch target is to a new line, and that cache line is in the ICache. This event counts differently than Intel processors based on Silvermont microarchitecture.",
"EventCode": "0x80",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "ICACHE.HIT",
"EventCode": "0xE6",
"EventName": "BACLEARS.ALL",
"PublicDescription": "Counts the number of times a BACLEAR is signaled for any reason, including, but not limited to indirect branch/call, Jcc (Jump on Conditional Code/Jump if Condition is Met) branch, unconditional branch/call, and returns.",
"SampleAfterValue": "200003",
"BriefDescription": "References per ICache line that are available in the ICache (hit). This event counts differently than Intel processors based on Silvermont microarchitecture"
"UMask": "0x1"
},
{
"BriefDescription": "BACLEARs asserted for conditional branch",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line and that cache line is not in the ICache (miss). The event strives to count on a cache line basis, so that multiple accesses which miss in a single cache line count as one ICACHE.MISS. Specifically, the event counts when straight line code crosses the cache line boundary, or when a branch target is to a new line, and that cache line is not in the ICache. This event counts differently than Intel processors based on Silvermont microarchitecture.",
"EventCode": "0x80",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "ICACHE.MISSES",
"EventCode": "0xE6",
"EventName": "BACLEARS.COND",
"PublicDescription": "Counts BACLEARS on Jcc (Jump on Conditional Code/Jump if Condition is Met) branches.",
"SampleAfterValue": "200003",
"BriefDescription": "References per ICache line that are not available in the ICache (miss). This event counts differently than Intel processors based on Silvermont microarchitecture"
"UMask": "0x10"
},
{
"BriefDescription": "BACLEARs asserted for return branch",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line. The event strives to count on a cache line basis, so that multiple fetches to a single cache line count as one ICACHE.ACCESS. Specifically, the event counts when accesses from straight line code crosses the cache line boundary, or when a branch target is to a new line.\r\nThis event counts differently than Intel processors based on Silvermont microarchitecture.",
"EventCode": "0x80",
"Counter": "0,1,2,3",
"UMask": "0x3",
"EventName": "ICACHE.ACCESSES",
"EventCode": "0xE6",
"EventName": "BACLEARS.RETURN",
"PublicDescription": "Counts BACLEARS on return instructions.",
"SampleAfterValue": "200003",
"BriefDescription": "References per ICache line. This event counts differently than Intel processors based on Silvermont microarchitecture"
"UMask": "0x8"
},
{
"BriefDescription": "Decode restrictions due to predicting wrong instruction length",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of times the Microcode Sequencer (MS) starts a flow of uops from the MSROM. It does not count every time a uop is read from the MSROM. The most common case that this counts is when a micro-coded instruction is encountered by the front end of the machine. Other cases include when an instruction encounters a fault, trap, or microcode assist of any sort that initiates a flow of uops. The event will count MS startups for uops that are speculative, and subsequently cleared by branch mispredict or a machine clear.",
"EventCode": "0xE7",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "MS_DECODED.MS_ENTRY",
"SampleAfterValue": "200003",
"BriefDescription": "MS decode starts"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of times the prediction (from the predecode cache) for instruction length is incorrect.",
"EventCode": "0xE9",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "DECODE_RESTRICTION.PREDECODE_WRONG",
"PublicDescription": "Counts the number of times the prediction (from the predecode cache) for instruction length is incorrect.",
"SampleAfterValue": "200003",
"BriefDescription": "Decode restrictions due to predicting wrong instruction length"
"UMask": "0x1"
},
{
"BriefDescription": "References per ICache line. This event counts differently than Intel processors based on Silvermont microarchitecture",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "ICACHE.ACCESSES",
"PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line. The event strives to count on a cache line basis, so that multiple fetches to a single cache line count as one ICACHE.ACCESS. Specifically, the event counts when accesses from straight line code crosses the cache line boundary, or when a branch target is to a new line.\r\nThis event counts differently than Intel processors based on Silvermont microarchitecture.",
"SampleAfterValue": "200003",
"UMask": "0x3"
},
{
"BriefDescription": "References per ICache line that are available in the ICache (hit). This event counts differently than Intel processors based on Silvermont microarchitecture",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "ICACHE.HIT",
"PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line and that cache line is in the ICache (hit). The event strives to count on a cache line basis, so that multiple accesses which hit in a single cache line count as one ICACHE.HIT. Specifically, the event counts when straight line code crosses the cache line boundary, or when a branch target is to a new line, and that cache line is in the ICache. This event counts differently than Intel processors based on Silvermont microarchitecture.",
"SampleAfterValue": "200003",
"UMask": "0x1"
},
{
"BriefDescription": "References per ICache line that are not available in the ICache (miss). This event counts differently than Intel processors based on Silvermont microarchitecture",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "ICACHE.MISSES",
"PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line and that cache line is not in the ICache (miss). The event strives to count on a cache line basis, so that multiple accesses which miss in a single cache line count as one ICACHE.MISS. Specifically, the event counts when straight line code crosses the cache line boundary, or when a branch target is to a new line, and that cache line is not in the ICache. This event counts differently than Intel processors based on Silvermont microarchitecture.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "MS decode starts",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xE7",
"EventName": "MS_DECODED.MS_ENTRY",
"PublicDescription": "Counts the number of times the Microcode Sequencer (MS) starts a flow of uops from the MSROM. It does not count every time a uop is read from the MSROM. The most common case that this counts is when a micro-coded instruction is encountered by the front end of the machine. Other cases include when an instruction encounters a fault, trap, or microcode assist of any sort that initiates a flow of uops. The event will count MS startups for uops that are speculative, and subsequently cleared by branch mispredict or a machine clear.",
"SampleAfterValue": "200003",
"UMask": "0x1"
}
]

52
lib/libpmc/pmu-events/arch/x86/goldmont/memory.json
View File

@ -1,34 +1,34 @@
[
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts when a memory load of a uop spans a page boundary (a split) is retired.",
"EventCode": "0x13",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT",
"SampleAfterValue": "200003",
"BriefDescription": "Load uops that split a page (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts when a memory store of a uop spans a page boundary (a split) is retired.",
"EventCode": "0x13",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT",
"SampleAfterValue": "200003",
"BriefDescription": "Store uops that split a page (Precise event capable)"
},
{
"BriefDescription": "Machine clears due to memory ordering issue",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts machine clears due to memory ordering issues. This occurs when a snoop request happens and the machine is uncertain if memory ordering will be preserved as another core is in the process of modifying the data.",
"EventCode": "0xC3",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventCode": "0xC3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"PublicDescription": "Counts machine clears due to memory ordering issues. This occurs when a snoop request happens and the machine is uncertain if memory ordering will be preserved as another core is in the process of modifying the data.",
"SampleAfterValue": "200003",
"BriefDescription": "Machine clears due to memory ordering issue"
"UMask": "0x2"
},
{
"BriefDescription": "Load uops that split a page (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT",
"PEBS": "2",
"PublicDescription": "Counts when a memory load of a uop spans a page boundary (a split) is retired.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Store uops that split a page (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT",
"PEBS": "2",
"PublicDescription": "Counts when a memory store of a uop spans a page boundary (a split) is retired.",
"SampleAfterValue": "200003",
"UMask": "0x4"
}
]

83
lib/libpmc/pmu-events/arch/x86/goldmont/other.json
View File

@ -1,82 +1,51 @@
[
{
"BriefDescription": "Cycles code-fetch stalled due to any reason.",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes. This will include cycles due to an ITLB miss, ICache miss and other events.",
"EventCode": "0x86",
"Counter": "0,1,2,3",
"UMask": "0x0",
"EventCode": "0x86",
"EventName": "FETCH_STALL.ALL",
"SampleAfterValue": "200003",
"BriefDescription": "Cycles code-fetch stalled due to any reason."
"PublicDescription": "Counts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes. This will include cycles due to an ITLB miss, ICache miss and other events.",
"SampleAfterValue": "200003"
},
{
"BriefDescription": "Cycles code-fetch stalled due to an outstanding ITLB miss.",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ITLB miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ITLB miss. Note: this event is not the same as page walk cycles to retrieve an instruction translation.",
"Counter": "0,1,2,3",
"EventCode": "0x86",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "FETCH_STALL.ITLB_FILL_PENDING_CYCLES",
"PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ITLB miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ITLB miss. Note: this event is not the same as page walk cycles to retrieve an instruction translation.",
"SampleAfterValue": "200003",
"BriefDescription": "Cycles code-fetch stalled due to an outstanding ITLB miss."
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of issue slots per core cycle that were not consumed by the backend due to either a full resource in the backend (RESOURCE_FULL) or due to the processor recovering from some event (RECOVERY).",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x0",
"EventName": "ISSUE_SLOTS_NOT_CONSUMED.ANY",
"SampleAfterValue": "200003",
"BriefDescription": "Unfilled issue slots per cycle"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of issue slots per core cycle that were not consumed because of a full resource in the backend. Including but not limited to resources such as the Re-order Buffer (ROB), reservation stations (RS), load/store buffers, physical registers, or any other needed machine resource that is currently unavailable. Note that uops must be available for consumption in order for this event to fire. If a uop is not available (Instruction Queue is empty), this event will not count.",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "ISSUE_SLOTS_NOT_CONSUMED.RESOURCE_FULL",
"SampleAfterValue": "200003",
"BriefDescription": "Unfilled issue slots per cycle because of a full resource in the backend"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of issue slots per core cycle that were not consumed by the backend because allocation is stalled waiting for a mispredicted jump to retire or other branch-like conditions (e.g. the event is relevant during certain microcode flows). Counts all issue slots blocked while within this window including slots where uops were not available in the Instruction Queue.",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "ISSUE_SLOTS_NOT_CONSUMED.RECOVERY",
"SampleAfterValue": "200003",
"BriefDescription": "Unfilled issue slots per cycle to recover"
"UMask": "0x1"
},
{
"BriefDescription": "Cycles hardware interrupts are masked",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts hardware interrupts received by the processor.",
"EventCode": "0xCB",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "HW_INTERRUPTS.RECEIVED",
"SampleAfterValue": "203",
"BriefDescription": "Hardware interrupts received"
},
{
"CollectPEBSRecord": "2",
"PublicDescription": "Counts the number of core cycles during which interrupts are masked (disabled). Increments by 1 each core cycle that EFLAGS.IF is 0, regardless of whether interrupts are pending or not.",
"EventCode": "0xCB",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "HW_INTERRUPTS.MASKED",
"PublicDescription": "Counts the number of core cycles during which interrupts are masked (disabled). Increments by 1 each core cycle that EFLAGS.IF is 0, regardless of whether interrupts are pending or not.",
"SampleAfterValue": "200003",
"BriefDescription": "Cycles hardware interrupts are masked"
"UMask": "0x2"
},
{
"BriefDescription": "Cycles pending interrupts are masked",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts core cycles during which there are pending interrupts, but interrupts are masked (EFLAGS.IF = 0).",
"EventCode": "0xCB",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventCode": "0xCB",
"EventName": "HW_INTERRUPTS.PENDING_AND_MASKED",
"PublicDescription": "Counts core cycles during which there are pending interrupts, but interrupts are masked (EFLAGS.IF = 0).",
"SampleAfterValue": "200003",
"BriefDescription": "Cycles pending interrupts are masked"
"UMask": "0x4"
},
{
"BriefDescription": "Hardware interrupts received",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xCB",
"EventName": "HW_INTERRUPTS.RECEIVED",
"PublicDescription": "Counts hardware interrupts received by the processor.",
"SampleAfterValue": "203",
"UMask": "0x1"
}
]
]

703
lib/libpmc/pmu-events/arch/x86/goldmont/pipeline.json
View File

@ -1,452 +1,411 @@
[
{
"PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. You cannot collect a PEBs record for this event.",
"Counter": "Fixed counter 0",
"UMask": "0x1",
"EventName": "INST_RETIRED.ANY",
"SampleAfterValue": "2000003",
"BriefDescription": "Instructions retired (Fixed event)"
},
{
"PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. This event uses fixed counter 1. You cannot collect a PEBs record for this event.",
"Counter": "Fixed counter 1",
"UMask": "0x2",
"EventName": "CPU_CLK_UNHALTED.CORE",
"SampleAfterValue": "2000003",
"BriefDescription": "Core cycles when core is not halted (Fixed event)"
},
{
"PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. This event uses fixed counter 2. You cannot collect a PEBs record for this event.",
"Counter": "Fixed counter 2",
"UMask": "0x3",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
"SampleAfterValue": "2000003",
"BriefDescription": "Reference cycles when core is not halted (Fixed event)"
},
{
"PEBS": "2",
"BriefDescription": "Retired branch instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts a load blocked from using a store forward, but did not occur because the store data was not available at the right time. The forward might occur subsequently when the data is available.",
"EventCode": "0x03",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "LD_BLOCKS.DATA_UNKNOWN",
"SampleAfterValue": "200003",
"BriefDescription": "Loads blocked due to store data not ready (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts a load blocked from using a store forward because of an address/size mismatch, only one of the loads blocked from each store will be counted.",
"EventCode": "0x03",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "LD_BLOCKS.STORE_FORWARD",
"SampleAfterValue": "200003",
"BriefDescription": "Loads blocked due to store forward restriction (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts loads that block because their address modulo 4K matches a pending store.",
"EventCode": "0x03",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "LD_BLOCKS.4K_ALIAS",
"SampleAfterValue": "200003",
"BriefDescription": "Loads blocked because address has 4k partial address false dependence (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts loads blocked because they are unable to find their physical address in the micro TLB (UTLB).",
"EventCode": "0x03",
"Counter": "0,1,2,3",
"UMask": "0x8",
"EventName": "LD_BLOCKS.UTLB_MISS",
"SampleAfterValue": "200003",
"BriefDescription": "Loads blocked because address in not in the UTLB (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts anytime a load that retires is blocked for any reason.",
"EventCode": "0x03",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "LD_BLOCKS.ALL_BLOCK",
"SampleAfterValue": "200003",
"BriefDescription": "Loads blocked (Precise event capable)"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts uops issued by the front end and allocated into the back end of the machine. This event counts uops that retire as well as uops that were speculatively executed but didn't retire. The sort of speculative uops that might be counted includes, but is not limited to those uops issued in the shadow of a miss-predicted branch, those uops that are inserted during an assist (such as for a denormal floating point result), and (previously allocated) uops that might be canceled during a machine clear.",
"EventCode": "0x0E",
"Counter": "0,1,2,3",
"UMask": "0x0",
"EventName": "UOPS_ISSUED.ANY",
"SampleAfterValue": "200003",
"BriefDescription": "Uops issued to the back end per cycle"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Core cycles when core is not halted. This event uses a (_P)rogrammable general purpose performance counter.",
"EventCode": "0x3C",
"Counter": "0,1,2,3",
"UMask": "0x0",
"EventName": "CPU_CLK_UNHALTED.CORE_P",
"SampleAfterValue": "2000003",
"BriefDescription": "Core cycles when core is not halted"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Reference cycles when core is not halted. This event uses a programmable general purpose performance counter.",
"EventCode": "0x3C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "CPU_CLK_UNHALTED.REF",
"SampleAfterValue": "2000003",
"BriefDescription": "Reference cycles when core is not halted"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "This event used to measure front-end inefficiencies. I.e. when front-end of the machine is not delivering uops to the back-end and the back-end has is not stalled. This event can be used to identify if the machine is truly front-end bound. When this event occurs, it is an indication that the front-end of the machine is operating at less than its theoretical peak performance. Background: We can think of the processor pipeline as being divided into 2 broader parts: Front-end and Back-end. Front-end is responsible for fetching the instruction, decoding into uops in machine understandable format and putting them into a uop queue to be consumed by back end. The back-end then takes these uops, allocates the required resources. When all resources are ready, uops are executed. If the back-end is not ready to accept uops from the front-end, then we do not want to count these as front-end bottlenecks. However, whenever we have bottlenecks in the back-end, we will have allocation unit stalls and eventually forcing the front-end to wait until the back-end is ready to receive more uops. This event counts only when back-end is requesting more uops and front-end is not able to provide them. When 3 uops are requested and no uops are delivered, the event counts 3. When 3 are requested, and only 1 is delivered, the event counts 2. When only 2 are delivered, the event counts 1. Alternatively stated, the event will not count if 3 uops are delivered, or if the back end is stalled and not requesting any uops at all. Counts indicate missed opportunities for the front-end to deliver a uop to the back end. Some examples of conditions that cause front-end efficiencies are: ICache misses, ITLB misses, and decoder restrictions that limit the front-end bandwidth. Known Issues: Some uops require multiple allocation slots. These uops will not be charged as a front end 'not delivered' opportunity, and will be regarded as a back end problem. For example, the INC instruction has one uop that requires 2 issue slots. A stream of INC instructions will not count as UOPS_NOT_DELIVERED, even though only one instruction can be issued per clock. The low uop issue rate for a stream of INC instructions is considered to be a back end issue.",
"EventCode": "0x9C",
"Counter": "0,1,2,3",
"UMask": "0x0",
"EventName": "UOPS_NOT_DELIVERED.ANY",
"SampleAfterValue": "200003",
"BriefDescription": "Uops requested but not-delivered to the back-end per cycle"
},
{
"PEBS": "2",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The event continues counting during hardware interrupts, traps, and inside interrupt handlers. This is an architectural performance event. This event uses a (_P)rogrammable general purpose performance counter. *This event is Precise Event capable: The EventingRIP field in the PEBS record is precise to the address of the instruction which caused the event. Note: Because PEBS records can be collected only on IA32_PMC0, only one event can use the PEBS facility at a time.",
"EventCode": "0xC0",
"Counter": "0,1,2,3",
"UMask": "0x0",
"EventName": "INST_RETIRED.ANY_P",
"SampleAfterValue": "2000003",
"BriefDescription": "Instructions retired (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts uops which retired.",
"EventCode": "0xC2",
"Counter": "0,1,2,3",
"UMask": "0x0",
"EventName": "UOPS_RETIRED.ANY",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops retired (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts uops retired that are from the complex flows issued by the micro-sequencer (MS). Counts both the uops from a micro-coded instruction, and the uops that might be generated from a micro-coded assist.",
"EventCode": "0xC2",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "UOPS_RETIRED.MS",
"SampleAfterValue": "2000003",
"BriefDescription": "MS uops retired (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of floating point divide uops retired.",
"EventCode": "0xC2",
"Counter": "0,1,2,3",
"UMask": "0x8",
"EventName": "UOPS_RETIRED.FPDIV",
"SampleAfterValue": "2000003",
"BriefDescription": "Floating point divide uops retired. (Precise Event Capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of integer divide uops retired.",
"EventCode": "0xC2",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "UOPS_RETIRED.IDIV",
"SampleAfterValue": "2000003",
"BriefDescription": "Integer divide uops retired. (Precise Event Capable)"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts machine clears for any reason.",
"EventCode": "0xC3",
"Counter": "0,1,2,3",
"UMask": "0x0",
"EventName": "MACHINE_CLEARS.ALL",
"SampleAfterValue": "200003",
"BriefDescription": "All machine clears"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel\u00ae architecture processors.",
"EventCode": "0xC3",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "MACHINE_CLEARS.SMC",
"SampleAfterValue": "200003",
"BriefDescription": "Self-Modifying Code detected"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts machine clears due to floating point (FP) operations needing assists. For instance, if the result was a floating point denormal, the hardware clears the pipeline and reissues uops to produce the correct IEEE compliant denormal result.",
"EventCode": "0xC3",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "MACHINE_CLEARS.FP_ASSIST",
"SampleAfterValue": "200003",
"BriefDescription": "Machine clears due to FP assists"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts machine clears due to memory disambiguation. Memory disambiguation happens when a load which has been issued conflicts with a previous unretired store in the pipeline whose address was not known at issue time, but is later resolved to be the same as the load address.",
"EventCode": "0xC3",
"Counter": "0,1,2,3",
"UMask": "0x8",
"EventName": "MACHINE_CLEARS.DISAMBIGUATION",
"SampleAfterValue": "200003",
"BriefDescription": "Machine clears due to memory disambiguation"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts branch instructions retired for all branch types. This is an architectural performance event.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0x0",
"EventName": "BR_INST_RETIRED.ALL_BRANCHES",
"SampleAfterValue": "200003",
"BriefDescription": "Retired branch instructions (Precise event capable)"
"PEBS": "2",
"PublicDescription": "Counts branch instructions retired for all branch types. This is an architectural performance event.",
"SampleAfterValue": "200003"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was taken and when it was not taken.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0x7e",
"EventName": "BR_INST_RETIRED.JCC",
"SampleAfterValue": "200003",
"BriefDescription": "Retired conditional branch instructions (Precise event capable)"
},
{
"PEBS": "2",
"BriefDescription": "Retired taken branch instructions (Precise event capable)",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of taken branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0x80",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.ALL_TAKEN_BRANCHES",
"PEBS": "2",
"PublicDescription": "Counts the number of taken branch instructions retired.",
"SampleAfterValue": "200003",
"BriefDescription": "Retired taken branch instructions (Precise event capable)"
"UMask": "0x80"
},
{
"PEBS": "2",
"BriefDescription": "Retired near call instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts far branch instructions retired. This includes far jump, far call and return, and Interrupt call and return.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0xbf",
"EventName": "BR_INST_RETIRED.FAR_BRANCH",
"SampleAfterValue": "200003",
"BriefDescription": "Retired far branch instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts near indirect call or near indirect jmp branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0xeb",
"EventName": "BR_INST_RETIRED.NON_RETURN_IND",
"SampleAfterValue": "200003",
"BriefDescription": "Retired instructions of near indirect Jmp or call (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts near return branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0xf7",
"EventName": "BR_INST_RETIRED.RETURN",
"SampleAfterValue": "200003",
"BriefDescription": "Retired near return instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts near CALL branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0xf9",
"EventName": "BR_INST_RETIRED.CALL",
"PEBS": "2",
"PublicDescription": "Counts near CALL branch instructions retired.",
"SampleAfterValue": "200003",
"BriefDescription": "Retired near call instructions (Precise event capable)"
"UMask": "0xf9"
},
{
"PEBS": "2",
"BriefDescription": "Retired far branch instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts near indirect CALL branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0xfb",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.FAR_BRANCH",
"PEBS": "2",
"PublicDescription": "Counts far branch instructions retired. This includes far jump, far call and return, and Interrupt call and return.",
"SampleAfterValue": "200003",
"UMask": "0xbf"
},
{
"BriefDescription": "Retired near indirect call instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.IND_CALL",
"PEBS": "2",
"PublicDescription": "Counts near indirect CALL branch instructions retired.",
"SampleAfterValue": "200003",
"BriefDescription": "Retired near indirect call instructions (Precise event capable)"
"UMask": "0xfb"
},
{
"PEBS": "2",
"BriefDescription": "Retired conditional branch instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts near relative CALL branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0xfd",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.JCC",
"PEBS": "2",
"PublicDescription": "Counts retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was taken and when it was not taken.",
"SampleAfterValue": "200003",
"UMask": "0x7e"
},
{
"BriefDescription": "Retired instructions of near indirect Jmp or call (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.NON_RETURN_IND",
"PEBS": "2",
"PublicDescription": "Counts near indirect call or near indirect jmp branch instructions retired.",
"SampleAfterValue": "200003",
"UMask": "0xeb"
},
{
"BriefDescription": "Retired near relative call instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.REL_CALL",
"PEBS": "2",
"PublicDescription": "Counts near relative CALL branch instructions retired.",
"SampleAfterValue": "200003",
"BriefDescription": "Retired near relative call instructions (Precise event capable)"
"UMask": "0xfd"
},
{
"PEBS": "2",
"BriefDescription": "Retired near return instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were taken and does not count when the Jcc branch instruction were not taken.",
"Counter": "0,1,2,3",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.RETURN",
"PEBS": "2",
"PublicDescription": "Counts near return branch instructions retired.",
"SampleAfterValue": "200003",
"UMask": "0xf7"
},
{
"BriefDescription": "Retired conditional branch instructions that were taken (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"UMask": "0xfe",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.TAKEN_JCC",
"PEBS": "2",
"PublicDescription": "Counts Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were taken and does not count when the Jcc branch instruction were not taken.",
"SampleAfterValue": "200003",
"BriefDescription": "Retired conditional branch instructions that were taken (Precise event capable)"
"UMask": "0xfe"
},
{
"PEBS": "2",
"BriefDescription": "Retired mispredicted branch instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts mispredicted branch instructions retired including all branch types.",
"EventCode": "0xC5",
"Counter": "0,1,2,3",
"UMask": "0x0",
"EventCode": "0xC5",
"EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
"SampleAfterValue": "200003",
"BriefDescription": "Retired mispredicted branch instructions (Precise event capable)"
"PEBS": "2",
"PublicDescription": "Counts mispredicted branch instructions retired including all branch types.",
"SampleAfterValue": "200003"
},
{
"PEBS": "2",
"BriefDescription": "Retired mispredicted near indirect call instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was supposed to be taken and when it was not supposed to be taken (but the processor predicted the opposite condition).",
"EventCode": "0xC5",
"Counter": "0,1,2,3",
"UMask": "0x7e",
"EventName": "BR_MISP_RETIRED.JCC",
"SampleAfterValue": "200003",
"BriefDescription": "Retired mispredicted conditional branch instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts mispredicted branch instructions retired that were near indirect call or near indirect jmp, where the target address taken was not what the processor predicted.",
"EventCode": "0xC5",
"Counter": "0,1,2,3",
"UMask": "0xeb",
"EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
"SampleAfterValue": "200003",
"BriefDescription": "Retired mispredicted instructions of near indirect Jmp or near indirect call. (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts mispredicted near RET branch instructions retired, where the return address taken was not what the processor predicted.",
"EventCode": "0xC5",
"Counter": "0,1,2,3",
"UMask": "0xf7",
"EventName": "BR_MISP_RETIRED.RETURN",
"SampleAfterValue": "200003",
"BriefDescription": "Retired mispredicted near return instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts mispredicted near indirect CALL branch instructions retired, where the target address taken was not what the processor predicted.",
"EventCode": "0xC5",
"Counter": "0,1,2,3",
"UMask": "0xfb",
"EventName": "BR_MISP_RETIRED.IND_CALL",
"SampleAfterValue": "200003",
"BriefDescription": "Retired mispredicted near indirect call instructions (Precise event capable)"
},
{
"PEBS": "2",
"PublicDescription": "Counts mispredicted near indirect CALL branch instructions retired, where the target address taken was not what the processor predicted.",
"SampleAfterValue": "200003",
"UMask": "0xfb"
},
{
"BriefDescription": "Retired mispredicted conditional branch instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were supposed to be taken but the processor predicted that it would not be taken.",
"Counter": "0,1,2,3",
"EventCode": "0xC5",
"EventName": "BR_MISP_RETIRED.JCC",
"PEBS": "2",
"PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was supposed to be taken and when it was not supposed to be taken (but the processor predicted the opposite condition).",
"SampleAfterValue": "200003",
"UMask": "0x7e"
},
{
"BriefDescription": "Retired mispredicted instructions of near indirect Jmp or near indirect call. (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"UMask": "0xfe",
"EventCode": "0xC5",
"EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
"PEBS": "2",
"PublicDescription": "Counts mispredicted branch instructions retired that were near indirect call or near indirect jmp, where the target address taken was not what the processor predicted.",
"SampleAfterValue": "200003",
"UMask": "0xeb"
},
{
"BriefDescription": "Retired mispredicted near return instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC5",
"EventName": "BR_MISP_RETIRED.RETURN",
"PEBS": "2",
"PublicDescription": "Counts mispredicted near RET branch instructions retired, where the return address taken was not what the processor predicted.",
"SampleAfterValue": "200003",
"UMask": "0xf7"
},
{
"BriefDescription": "Retired mispredicted conditional branch instructions that were taken (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC5",
"EventName": "BR_MISP_RETIRED.TAKEN_JCC",
"PEBS": "2",
"PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were supposed to be taken but the processor predicted that it would not be taken.",
"SampleAfterValue": "200003",
"BriefDescription": "Retired mispredicted conditional branch instructions that were taken (Precise event capable)"
"UMask": "0xfe"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts core cycles if either divide unit is busy.",
"EventCode": "0xCD",
"Counter": "0,1,2,3",
"UMask": "0x0",
"EventName": "CYCLES_DIV_BUSY.ALL",
"BriefDescription": "Core cycles when core is not halted (Fixed event)",
"Counter": "Fixed counter 1",
"EventName": "CPU_CLK_UNHALTED.CORE",
"PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. This event uses fixed counter 1. You cannot collect a PEBs record for this event.",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles a divider is busy"
"UMask": "0x2"
},
{
"BriefDescription": "Core cycles when core is not halted",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts core cycles the integer divide unit is busy.",
"EventCode": "0xCD",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventCode": "0x3C",
"EventName": "CPU_CLK_UNHALTED.CORE_P",
"PublicDescription": "Core cycles when core is not halted. This event uses a (_P)rogrammable general purpose performance counter.",
"SampleAfterValue": "2000003"
},
{
"BriefDescription": "Reference cycles when core is not halted",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x3C",
"EventName": "CPU_CLK_UNHALTED.REF",
"PublicDescription": "Reference cycles when core is not halted. This event uses a programmable general purpose performance counter.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Reference cycles when core is not halted (Fixed event)",
"Counter": "Fixed counter 2",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
"PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. This event uses fixed counter 2. You cannot collect a PEBs record for this event.",
"SampleAfterValue": "2000003",
"UMask": "0x3"
},
{
"BriefDescription": "Cycles a divider is busy",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xCD",
"EventName": "CYCLES_DIV_BUSY.ALL",
"PublicDescription": "Counts core cycles if either divide unit is busy.",
"SampleAfterValue": "2000003"
},
{
"BriefDescription": "Cycles the integer divide unit is busy",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xCD",
"EventName": "CYCLES_DIV_BUSY.IDIV",
"PublicDescription": "Counts core cycles the integer divide unit is busy.",
"SampleAfterValue": "200003",
"BriefDescription": "Cycles the integer divide unit is busy"
"UMask": "0x1"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts core cycles the floating point divide unit is busy.",
"EventCode": "0xCD",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "CYCLES_DIV_BUSY.FPDIV",
"SampleAfterValue": "200003",
"BriefDescription": "Cycles the FP divide unit is busy"
"BriefDescription": "Instructions retired (Fixed event)",
"Counter": "Fixed counter 0",
"EventName": "INST_RETIRED.ANY",
"PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. You cannot collect a PEBs record for this event.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Instructions retired (Precise event capable)",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of times a BACLEAR is signaled for any reason, including, but not limited to indirect branch/call, Jcc (Jump on Conditional Code/Jump if Condition is Met) branch, unconditional branch/call, and returns.",
"EventCode": "0xE6",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "BACLEARS.ALL",
"SampleAfterValue": "200003",
"BriefDescription": "BACLEARs asserted for any branch type"
"EventCode": "0xC0",
"EventName": "INST_RETIRED.ANY_P",
"PEBS": "2",
"PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The event continues counting during hardware interrupts, traps, and inside interrupt handlers. This is an architectural performance event. This event uses a (_P)rogrammable general purpose performance counter. *This event is Precise Event capable: The EventingRIP field in the PEBS record is precise to the address of the instruction which caused the event. Note: Because PEBS records can be collected only on IA32_PMC0, only one event can use the PEBS facility at a time.",
"SampleAfterValue": "2000003"
},
{
"BriefDescription": "Unfilled issue slots per cycle",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts BACLEARS on return instructions.",
"EventCode": "0xE6",
"Counter": "0,1,2,3",
"UMask": "0x8",
"EventName": "BACLEARS.RETURN",
"SampleAfterValue": "200003",
"BriefDescription": "BACLEARs asserted for return branch"
"EventCode": "0xCA",
"EventName": "ISSUE_SLOTS_NOT_CONSUMED.ANY",
"PublicDescription": "Counts the number of issue slots per core cycle that were not consumed by the backend due to either a full resource in the backend (RESOURCE_FULL) or due to the processor recovering from some event (RECOVERY).",
"SampleAfterValue": "200003"
},
{
"BriefDescription": "Unfilled issue slots per cycle to recover",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts BACLEARS on Jcc (Jump on Conditional Code/Jump if Condition is Met) branches.",
"EventCode": "0xE6",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "BACLEARS.COND",
"EventCode": "0xCA",
"EventName": "ISSUE_SLOTS_NOT_CONSUMED.RECOVERY",
"PublicDescription": "Counts the number of issue slots per core cycle that were not consumed by the backend because allocation is stalled waiting for a mispredicted jump to retire or other branch-like conditions (e.g. the event is relevant during certain microcode flows). Counts all issue slots blocked while within this window including slots where uops were not available in the Instruction Queue.",
"SampleAfterValue": "200003",
"BriefDescription": "BACLEARs asserted for conditional branch"
"UMask": "0x2"
},
{
"BriefDescription": "Unfilled issue slots per cycle because of a full resource in the backend",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xCA",
"EventName": "ISSUE_SLOTS_NOT_CONSUMED.RESOURCE_FULL",
"PublicDescription": "Counts the number of issue slots per core cycle that were not consumed because of a full resource in the backend. Including but not limited to resources such as the Re-order Buffer (ROB), reservation stations (RS), load/store buffers, physical registers, or any other needed machine resource that is currently unavailable. Note that uops must be available for consumption in order for this event to fire. If a uop is not available (Instruction Queue is empty), this event will not count.",
"SampleAfterValue": "200003",
"UMask": "0x1"
},
{
"BriefDescription": "Loads blocked because address has 4k partial address false dependence (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.4K_ALIAS",
"PEBS": "2",
"PublicDescription": "Counts loads that block because their address modulo 4K matches a pending store.",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Loads blocked (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.ALL_BLOCK",
"PEBS": "2",
"PublicDescription": "Counts anytime a load that retires is blocked for any reason.",
"SampleAfterValue": "200003",
"UMask": "0x10"
},
{
"BriefDescription": "Loads blocked due to store data not ready (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.DATA_UNKNOWN",
"PEBS": "2",
"PublicDescription": "Counts a load blocked from using a store forward, but did not occur because the store data was not available at the right time. The forward might occur subsequently when the data is available.",
"SampleAfterValue": "200003",
"UMask": "0x1"
},
{
"BriefDescription": "Loads blocked due to store forward restriction (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.STORE_FORWARD",
"PEBS": "2",
"PublicDescription": "Counts a load blocked from using a store forward because of an address/size mismatch, only one of the loads blocked from each store will be counted.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Loads blocked because address in not in the UTLB (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.UTLB_MISS",
"PEBS": "2",
"PublicDescription": "Counts loads blocked because they are unable to find their physical address in the micro TLB (UTLB).",
"SampleAfterValue": "200003",
"UMask": "0x8"
},
{
"BriefDescription": "All machine clears",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xC3",
"EventName": "MACHINE_CLEARS.ALL",
"PublicDescription": "Counts machine clears for any reason.",
"SampleAfterValue": "200003"
},
{
"BriefDescription": "Machine clears due to memory disambiguation",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xC3",
"EventName": "MACHINE_CLEARS.DISAMBIGUATION",
"PublicDescription": "Counts machine clears due to memory disambiguation. Memory disambiguation happens when a load which has been issued conflicts with a previous unretired store in the pipeline whose address was not known at issue time, but is later resolved to be the same as the load address.",
"SampleAfterValue": "200003",
"UMask": "0x8"
},
{
"BriefDescription": "Self-Modifying Code detected",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xC3",
"EventName": "MACHINE_CLEARS.SMC",
"PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.",
"SampleAfterValue": "200003",
"UMask": "0x1"
},
{
"BriefDescription": "Uops issued to the back end per cycle",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x0E",
"EventName": "UOPS_ISSUED.ANY",
"PublicDescription": "Counts uops issued by the front end and allocated into the back end of the machine. This event counts uops that retire as well as uops that were speculatively executed but didn't retire. The sort of speculative uops that might be counted includes, but is not limited to those uops issued in the shadow of a miss-predicted branch, those uops that are inserted during an assist (such as for a denormal floating point result), and (previously allocated) uops that might be canceled during a machine clear.",
"SampleAfterValue": "200003"
},
{
"BriefDescription": "Uops requested but not-delivered to the back-end per cycle",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x9C",
"EventName": "UOPS_NOT_DELIVERED.ANY",
"PublicDescription": "This event used to measure front-end inefficiencies. I.e. when front-end of the machine is not delivering uops to the back-end and the back-end has is not stalled. This event can be used to identify if the machine is truly front-end bound. When this event occurs, it is an indication that the front-end of the machine is operating at less than its theoretical peak performance. Background: We can think of the processor pipeline as being divided into 2 broader parts: Front-end and Back-end. Front-end is responsible for fetching the instruction, decoding into uops in machine understandable format and putting them into a uop queue to be consumed by back end. The back-end then takes these uops, allocates the required resources. When all resources are ready, uops are executed. If the back-end is not ready to accept uops from the front-end, then we do not want to count these as front-end bottlenecks. However, whenever we have bottlenecks in the back-end, we will have allocation unit stalls and eventually forcing the front-end to wait until the back-end is ready to receive more uops. This event counts only when back-end is requesting more uops and front-end is not able to provide them. When 3 uops are requested and no uops are delivered, the event counts 3. When 3 are requested, and only 1 is delivered, the event counts 2. When only 2 are delivered, the event counts 1. Alternatively stated, the event will not count if 3 uops are delivered, or if the back end is stalled and not requesting any uops at all. Counts indicate missed opportunities for the front-end to deliver a uop to the back end. Some examples of conditions that cause front-end efficiencies are: ICache misses, ITLB misses, and decoder restrictions that limit the front-end bandwidth. Known Issues: Some uops require multiple allocation slots. These uops will not be charged as a front end 'not delivered' opportunity, and will be regarded as a back end problem. For example, the INC instruction has one uop that requires 2 issue slots. A stream of INC instructions will not count as UOPS_NOT_DELIVERED, even though only one instruction can be issued per clock. The low uop issue rate for a stream of INC instructions is considered to be a back end issue.",
"SampleAfterValue": "200003"
},
{
"BriefDescription": "Uops retired (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC2",
"EventName": "UOPS_RETIRED.ANY",
"PEBS": "2",
"PublicDescription": "Counts uops which retired.",
"SampleAfterValue": "2000003"
},
{
"BriefDescription": "Integer divide uops retired. (Precise Event Capable)",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xC2",
"EventName": "UOPS_RETIRED.IDIV",
"PEBS": "2",
"PublicDescription": "Counts the number of integer divide uops retired.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "MS uops retired (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC2",
"EventName": "UOPS_RETIRED.MS",
"PEBS": "2",
"PublicDescription": "Counts uops retired that are from the complex flows issued by the micro-sequencer (MS). Counts both the uops from a micro-coded instruction, and the uops that might be generated from a micro-coded assist.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
}
]
]

132
lib/libpmc/pmu-events/arch/x86/goldmont/virtual-memory.json
View File

@ -1,78 +1,78 @@
[
{
"BriefDescription": "ITLB misses",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts every core cycle when a Data-side (walks due to a data operation) page walk is in progress.",
"EventCode": "0x05",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "PAGE_WALKS.D_SIDE_CYCLES",
"SampleAfterValue": "200003",
"BriefDescription": "Duration of D-side page-walks in cycles"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts every core cycle when a Instruction-side (walks due to an instruction fetch) page walk is in progress.",
"EventCode": "0x05",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "PAGE_WALKS.I_SIDE_CYCLES",
"SampleAfterValue": "200003",
"BriefDescription": "Duration of I-side pagewalks in cycles"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts every core cycle a page-walk is in progress due to either a data memory operation or an instruction fetch.",
"EventCode": "0x05",
"Counter": "0,1,2,3",
"UMask": "0x3",
"EventName": "PAGE_WALKS.CYCLES",
"SampleAfterValue": "200003",
"BriefDescription": "Duration of page-walks in cycles"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of times the machine was unable to find a translation in the Instruction Translation Lookaside Buffer (ITLB) for a linear address of an instruction fetch. It counts when new translation are filled into the ITLB. The event is speculative in nature, but will not count translations (page walks) that are begun and not finished, or translations that are finished but not filled into the ITLB.",
"EventCode": "0x81",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "ITLB.MISS",
"PublicDescription": "Counts the number of times the machine was unable to find a translation in the Instruction Translation Lookaside Buffer (ITLB) for a linear address of an instruction fetch. It counts when new translation are filled into the ITLB. The event is speculative in nature, but will not count translations (page walks) that are begun and not finished, or translations that are finished but not filled into the ITLB.",
"SampleAfterValue": "200003",
"BriefDescription": "ITLB misses"
"UMask": "0x4"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts load uops retired that caused a DTLB miss.",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x11",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
"SampleAfterValue": "200003",
"BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)",
"Data_LA": "1"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts store uops retired that caused a DTLB miss.",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x12",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
"SampleAfterValue": "200003",
"BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)",
"Data_LA": "1"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts uops retired that had a DTLB miss on load, store or either. Note that when two distinct memory operations to the same page miss the DTLB, only one of them will be recorded as a DTLB miss.",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x13",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
"SampleAfterValue": "200003",
"BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)",
"Data_LA": "1"
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xD0",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
"PEBS": "2",
"PublicDescription": "Counts uops retired that had a DTLB miss on load, store or either. Note that when two distinct memory operations to the same page miss the DTLB, only one of them will be recorded as a DTLB miss.",
"SampleAfterValue": "200003",
"UMask": "0x13"
},
{
"BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xD0",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
"PEBS": "2",
"PublicDescription": "Counts load uops retired that caused a DTLB miss.",
"SampleAfterValue": "200003",
"UMask": "0x11"
},
{
"BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xD0",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
"PEBS": "2",
"PublicDescription": "Counts store uops retired that caused a DTLB miss.",
"SampleAfterValue": "200003",
"UMask": "0x12"
},
{
"BriefDescription": "Duration of page-walks in cycles",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x05",
"EventName": "PAGE_WALKS.CYCLES",
"PublicDescription": "Counts every core cycle a page-walk is in progress due to either a data memory operation or an instruction fetch.",
"SampleAfterValue": "200003",
"UMask": "0x3"
},
{
"BriefDescription": "Duration of D-side page-walks in cycles",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x05",
"EventName": "PAGE_WALKS.D_SIDE_CYCLES",
"PublicDescription": "Counts every core cycle when a Data-side (walks due to a data operation) page walk is in progress.",
"SampleAfterValue": "200003",
"UMask": "0x1"
},
{
"BriefDescription": "Duration of I-side pagewalks in cycles",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x05",
"EventName": "PAGE_WALKS.I_SIDE_CYCLES",
"PublicDescription": "Counts every core cycle when a Instruction-side (walks due to an instruction fetch) page walk is in progress.",
"SampleAfterValue": "200003",
"UMask": "0x2"
}
]

2786
lib/libpmc/pmu-events/arch/x86/goldmontplus/cache.json
View File

File diff suppressed because it is too large Load Diff

38
lib/libpmc/pmu-events/arch/x86/goldmontplus/floating-point.json Normal file
View File

@ -0,0 +1,38 @@
[
{
"BriefDescription": "Cycles the FP divide unit is busy",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xCD",
"EventName": "CYCLES_DIV_BUSY.FPDIV",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts core cycles the floating point divide unit is busy.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Machine clears due to FP assists",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xC3",
"EventName": "MACHINE_CLEARS.FP_ASSIST",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts machine clears due to floating point (FP) operations needing assists. For instance, if the result was a floating point denormal, the hardware clears the pipeline and reissues uops to produce the correct IEEE compliant denormal result.",
"SampleAfterValue": "20003",
"UMask": "0x4"
},
{
"BriefDescription": "Floating point divide uops retired (Precise Event Capable)",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xC2",
"EventName": "UOPS_RETIRED.FPDIV",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of floating point divide uops retired.",
"SampleAfterValue": "2000003",
"UMask": "0x8"
}
]

104
lib/libpmc/pmu-events/arch/x86/goldmontplus/frontend.json
View File

@ -1,62 +1,98 @@
[
{
"BriefDescription": "BACLEARs asserted for any branch type",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line and that cache line is in the ICache (hit). The event strives to count on a cache line basis, so that multiple accesses which hit in a single cache line count as one ICACHE.HIT. Specifically, the event counts when straight line code crosses the cache line boundary, or when a branch target is to a new line, and that cache line is in the ICache. This event counts differently than Intel processors based on Silvermont microarchitecture.",
"EventCode": "0x80",
"Counter": "0,1,2,3",
"UMask": "0x1",
"PEBScounters": "0,1,2,3",
"EventName": "ICACHE.HIT",
"EventCode": "0xE6",
"EventName": "BACLEARS.ALL",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times a BACLEAR is signaled for any reason, including, but not limited to indirect branch/call, Jcc (Jump on Conditional Code/Jump if Condition is Met) branch, unconditional branch/call, and returns.",
"SampleAfterValue": "200003",
"BriefDescription": "References per ICache line that are available in the ICache (hit). This event counts differently than Intel processors based on Silvermont microarchitecture"
"UMask": "0x1"
},
{
"BriefDescription": "BACLEARs asserted for conditional branch",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line and that cache line is not in the ICache (miss). The event strives to count on a cache line basis, so that multiple accesses which miss in a single cache line count as one ICACHE.MISS. Specifically, the event counts when straight line code crosses the cache line boundary, or when a branch target is to a new line, and that cache line is not in the ICache. This event counts differently than Intel processors based on Silvermont microarchitecture.",
"EventCode": "0x80",
"Counter": "0,1,2,3",
"UMask": "0x2",
"PEBScounters": "0,1,2,3",
"EventName": "ICACHE.MISSES",
"EventCode": "0xE6",
"EventName": "BACLEARS.COND",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts BACLEARS on Jcc (Jump on Conditional Code/Jump if Condition is Met) branches.",
"SampleAfterValue": "200003",
"BriefDescription": "References per ICache line that are not available in the ICache (miss). This event counts differently than Intel processors based on Silvermont microarchitecture"
"UMask": "0x10"
},
{
"BriefDescription": "BACLEARs asserted for return branch",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line. The event strives to count on a cache line basis, so that multiple fetches to a single cache line count as one ICACHE.ACCESS. Specifically, the event counts when accesses from straight line code crosses the cache line boundary, or when a branch target is to a new line.\r\nThis event counts differently than Intel processors based on Silvermont microarchitecture.",
"EventCode": "0x80",
"Counter": "0,1,2,3",
"UMask": "0x3",
"PEBScounters": "0,1,2,3",
"EventName": "ICACHE.ACCESSES",
"EventCode": "0xE6",
"EventName": "BACLEARS.RETURN",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts BACLEARS on return instructions.",
"SampleAfterValue": "200003",
"BriefDescription": "References per ICache line. This event counts differently than Intel processors based on Silvermont microarchitecture"
"UMask": "0x8"
},
{
"BriefDescription": "Decode restrictions due to predicting wrong instruction length",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of times the Microcode Sequencer (MS) starts a flow of uops from the MSROM. It does not count every time a uop is read from the MSROM. The most common case that this counts is when a micro-coded instruction is encountered by the front end of the machine. Other cases include when an instruction encounters a fault, trap, or microcode assist of any sort that initiates a flow of uops. The event will count MS startups for uops that are speculative, and subsequently cleared by branch mispredict or a machine clear.",
"EventCode": "0xE7",
"Counter": "0,1,2,3",
"UMask": "0x1",
"PEBScounters": "0,1,2,3",
"EventName": "MS_DECODED.MS_ENTRY",
"PDIR_COUNTER": "na",
"SampleAfterValue": "200003",
"BriefDescription": "MS decode starts"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of times the prediction (from the predecode cache) for instruction length is incorrect.",
"EventCode": "0xE9",
"Counter": "0,1,2,3",
"UMask": "0x1",
"PEBScounters": "0,1,2,3",
"EventName": "DECODE_RESTRICTION.PREDECODE_WRONG",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times the prediction (from the predecode cache) for instruction length is incorrect.",
"SampleAfterValue": "200003",
"BriefDescription": "Decode restrictions due to predicting wrong instruction length"
"UMask": "0x1"
},
{
"BriefDescription": "References per ICache line. This event counts differently than Intel processors based on Silvermont microarchitecture",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "ICACHE.ACCESSES",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line. The event strives to count on a cache line basis, so that multiple fetches to a single cache line count as one ICACHE.ACCESS. Specifically, the event counts when accesses from straight line code crosses the cache line boundary, or when a branch target is to a new line.\r\nThis event counts differently than Intel processors based on Silvermont microarchitecture.",
"SampleAfterValue": "200003",
"UMask": "0x3"
},
{
"BriefDescription": "References per ICache line that are available in the ICache (hit). This event counts differently than Intel processors based on Silvermont microarchitecture",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "ICACHE.HIT",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line and that cache line is in the ICache (hit). The event strives to count on a cache line basis, so that multiple accesses which hit in a single cache line count as one ICACHE.HIT. Specifically, the event counts when straight line code crosses the cache line boundary, or when a branch target is to a new line, and that cache line is in the ICache. This event counts differently than Intel processors based on Silvermont microarchitecture.",
"SampleAfterValue": "200003",
"UMask": "0x1"
},
{
"BriefDescription": "References per ICache line that are not available in the ICache (miss). This event counts differently than Intel processors based on Silvermont microarchitecture",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "ICACHE.MISSES",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line and that cache line is not in the ICache (miss). The event strives to count on a cache line basis, so that multiple accesses which miss in a single cache line count as one ICACHE.MISS. Specifically, the event counts when straight line code crosses the cache line boundary, or when a branch target is to a new line, and that cache line is not in the ICache. This event counts differently than Intel processors based on Silvermont microarchitecture.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "MS decode starts",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xE7",
"EventName": "MS_DECODED.MS_ENTRY",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times the Microcode Sequencer (MS) starts a flow of uops from the MSROM. It does not count every time a uop is read from the MSROM. The most common case that this counts is when a micro-coded instruction is encountered by the front end of the machine. Other cases include when an instruction encounters a fault, trap, or microcode assist of any sort that initiates a flow of uops. The event will count MS startups for uops that are speculative, and subsequently cleared by branch mispredict or a machine clear.",
"SampleAfterValue": "200003",
"UMask": "0x1"
}
]

58
lib/libpmc/pmu-events/arch/x86/goldmontplus/memory.json
View File

@ -1,38 +1,38 @@
[
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts when a memory load of a uop spans a page boundary (a split) is retired.",
"EventCode": "0x13",
"Counter": "0,1,2,3",
"UMask": "0x2",
"PEBScounters": "0,1,2,3",
"EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT",
"SampleAfterValue": "200003",
"BriefDescription": "Load uops that split a page (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts when a memory store of a uop spans a page boundary (a split) is retired.",
"EventCode": "0x13",
"Counter": "0,1,2,3",
"UMask": "0x4",
"PEBScounters": "0,1,2,3",
"EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT",
"SampleAfterValue": "200003",
"BriefDescription": "Store uops that split a page (Precise event capable)"
},
{
"BriefDescription": "Machine clears due to memory ordering issue",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts machine clears due to memory ordering issues. This occurs when a snoop request happens and the machine is uncertain if memory ordering will be preserved - as another core is in the process of modifying the data.",
"EventCode": "0xC3",
"Counter": "0,1,2,3",
"UMask": "0x2",
"PEBScounters": "0,1,2,3",
"EventCode": "0xC3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts machine clears due to memory ordering issues. This occurs when a snoop request happens and the machine is uncertain if memory ordering will be preserved - as another core is in the process of modifying the data.",
"SampleAfterValue": "20003",
"BriefDescription": "Machine clears due to memory ordering issue"
"UMask": "0x2"
},
{
"BriefDescription": "Load uops that split a page (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts when a memory load of a uop spans a page boundary (a split) is retired.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Store uops that split a page (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts when a memory store of a uop spans a page boundary (a split) is retired.",
"SampleAfterValue": "200003",
"UMask": "0x4"
}
]

99
lib/libpmc/pmu-events/arch/x86/goldmontplus/other.json
View File

@ -1,98 +1,61 @@
[
{
"BriefDescription": "Cycles code-fetch stalled due to any reason.",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes. This will include cycles due to an ITLB miss, ICache miss and other events.",
"EventCode": "0x86",
"Counter": "0,1,2,3",
"UMask": "0x0",
"PEBScounters": "0,1,2,3",
"EventCode": "0x86",
"EventName": "FETCH_STALL.ALL",
"PDIR_COUNTER": "na",
"SampleAfterValue": "200003",
"BriefDescription": "Cycles code-fetch stalled due to any reason."
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes. This will include cycles due to an ITLB miss, ICache miss and other events.",
"SampleAfterValue": "200003"
},
{
"BriefDescription": "Cycles the code-fetch stalls and an ITLB miss is outstanding.",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ITLB miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ITLB miss. Note: this event is not the same as page walk cycles to retrieve an instruction translation.",
"EventCode": "0x86",
"Counter": "0,1,2,3",
"UMask": "0x1",
"PEBScounters": "0,1,2,3",
"EventCode": "0x86",
"EventName": "FETCH_STALL.ITLB_FILL_PENDING_CYCLES",
"PDIR_COUNTER": "na",
"SampleAfterValue": "200003",
"BriefDescription": "Cycles the code-fetch stalls and an ITLB miss is outstanding."
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of issue slots per core cycle that were not consumed by the backend due to either a full resource in the backend (RESOURCE_FULL) or due to the processor recovering from some event (RECOVERY).",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x0",
"PEBScounters": "0,1,2,3",
"EventName": "ISSUE_SLOTS_NOT_CONSUMED.ANY",
"PDIR_COUNTER": "na",
"PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ITLB miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ITLB miss. Note: this event is not the same as page walk cycles to retrieve an instruction translation.",
"SampleAfterValue": "200003",
"BriefDescription": "Unfilled issue slots per cycle"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of issue slots per core cycle that were not consumed because of a full resource in the backend. Including but not limited to resources such as the Re-order Buffer (ROB), reservation stations (RS), load/store buffers, physical registers, or any other needed machine resource that is currently unavailable. Note that uops must be available for consumption in order for this event to fire. If a uop is not available (Instruction Queue is empty), this event will not count.",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x1",
"PEBScounters": "0,1,2,3",
"EventName": "ISSUE_SLOTS_NOT_CONSUMED.RESOURCE_FULL",
"PDIR_COUNTER": "na",
"SampleAfterValue": "200003",
"BriefDescription": "Unfilled issue slots per cycle because of a full resource in the backend"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of issue slots per core cycle that were not consumed by the backend because allocation is stalled waiting for a mispredicted jump to retire or other branch-like conditions (e.g. the event is relevant during certain microcode flows). Counts all issue slots blocked while within this window including slots where uops were not available in the Instruction Queue.",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x2",
"PEBScounters": "0,1,2,3",
"EventName": "ISSUE_SLOTS_NOT_CONSUMED.RECOVERY",
"PDIR_COUNTER": "na",
"SampleAfterValue": "200003",
"BriefDescription": "Unfilled issue slots per cycle to recover"
"UMask": "0x1"
},
{
"BriefDescription": "Cycles hardware interrupts are masked",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts hardware interrupts received by the processor.",
"EventCode": "0xCB",
"Counter": "0,1,2,3",
"UMask": "0x1",
"PEBScounters": "0,1,2,3",
"EventName": "HW_INTERRUPTS.RECEIVED",
"PDIR_COUNTER": "na",
"SampleAfterValue": "203",
"BriefDescription": "Hardware interrupts received"
},
{
"CollectPEBSRecord": "2",
"PublicDescription": "Counts the number of core cycles during which interrupts are masked (disabled). Increments by 1 each core cycle that EFLAGS.IF is 0, regardless of whether interrupts are pending or not.",
"EventCode": "0xCB",
"Counter": "0,1,2,3",
"UMask": "0x2",
"PEBScounters": "0,1,2,3",
"EventName": "HW_INTERRUPTS.MASKED",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of core cycles during which interrupts are masked (disabled). Increments by 1 each core cycle that EFLAGS.IF is 0, regardless of whether interrupts are pending or not.",
"SampleAfterValue": "200003",
"BriefDescription": "Cycles hardware interrupts are masked"
"UMask": "0x2"
},
{
"BriefDescription": "Cycles pending interrupts are masked",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts core cycles during which there are pending interrupts, but interrupts are masked (EFLAGS.IF = 0).",
"EventCode": "0xCB",
"Counter": "0,1,2,3",
"UMask": "0x4",
"PEBScounters": "0,1,2,3",
"EventCode": "0xCB",
"EventName": "HW_INTERRUPTS.PENDING_AND_MASKED",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts core cycles during which there are pending interrupts, but interrupts are masked (EFLAGS.IF = 0).",
"SampleAfterValue": "200003",
"BriefDescription": "Cycles pending interrupts are masked"
"UMask": "0x4"
},
{
"BriefDescription": "Hardware interrupts received",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xCB",
"EventName": "HW_INTERRUPTS.RECEIVED",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts hardware interrupts received by the processor.",
"SampleAfterValue": "203",
"UMask": "0x1"
}
]
]

911
lib/libpmc/pmu-events/arch/x86/goldmontplus/pipeline.json
View File

@ -1,541 +1,494 @@
[
{
"BriefDescription": "Retired branch instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.ALL_BRANCHES",
"PEBS": "2",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. You cannot collect a PEBs record for this event.",
"Counter": "Fixed counter 0",
"UMask": "0x1",
"PEBScounters": "32",
"EventName": "INST_RETIRED.ANY",
"PDIR_COUNTER": "na",
"SampleAfterValue": "2000003",
"BriefDescription": "Instructions retired (Fixed event)"
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts branch instructions retired for all branch types. This is an architectural performance event.",
"SampleAfterValue": "200003"
},
{
"BriefDescription": "Retired taken branch instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.ALL_TAKEN_BRANCHES",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of taken branch instructions retired.",
"SampleAfterValue": "200003",
"UMask": "0x80"
},
{
"BriefDescription": "Retired near call instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.CALL",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts near CALL branch instructions retired.",
"SampleAfterValue": "200003",
"UMask": "0xf9"
},
{
"BriefDescription": "Retired far branch instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.FAR_BRANCH",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts far branch instructions retired. This includes far jump, far call and return, and Interrupt call and return.",
"SampleAfterValue": "200003",
"UMask": "0xbf"
},
{
"BriefDescription": "Retired near indirect call instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.IND_CALL",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts near indirect CALL branch instructions retired.",
"SampleAfterValue": "200003",
"UMask": "0xfb"
},
{
"BriefDescription": "Retired conditional branch instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.JCC",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was taken and when it was not taken.",
"SampleAfterValue": "200003",
"UMask": "0x7e"
},
{
"BriefDescription": "Retired instructions of near indirect Jmp or call (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.NON_RETURN_IND",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts near indirect call or near indirect jmp branch instructions retired.",
"SampleAfterValue": "200003",
"UMask": "0xeb"
},
{
"BriefDescription": "Retired near relative call instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.REL_CALL",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts near relative CALL branch instructions retired.",
"SampleAfterValue": "200003",
"UMask": "0xfd"
},
{
"BriefDescription": "Retired near return instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.RETURN",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts near return branch instructions retired.",
"SampleAfterValue": "200003",
"UMask": "0xf7"
},
{
"BriefDescription": "Retired conditional branch instructions that were taken (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC4",
"EventName": "BR_INST_RETIRED.TAKEN_JCC",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were taken and does not count when the Jcc branch instruction were not taken.",
"SampleAfterValue": "200003",
"UMask": "0xfe"
},
{
"BriefDescription": "Retired mispredicted branch instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC5",
"EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts mispredicted branch instructions retired including all branch types.",
"SampleAfterValue": "200003"
},
{
"BriefDescription": "Retired mispredicted near indirect call instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC5",
"EventName": "BR_MISP_RETIRED.IND_CALL",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts mispredicted near indirect CALL branch instructions retired, where the target address taken was not what the processor predicted.",
"SampleAfterValue": "200003",
"UMask": "0xfb"
},
{
"BriefDescription": "Retired mispredicted conditional branch instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC5",
"EventName": "BR_MISP_RETIRED.JCC",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was supposed to be taken and when it was not supposed to be taken (but the processor predicted the opposite condition).",
"SampleAfterValue": "200003",
"UMask": "0x7e"
},
{
"BriefDescription": "Retired mispredicted instructions of near indirect Jmp or near indirect call (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC5",
"EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts mispredicted branch instructions retired that were near indirect call or near indirect jmp, where the target address taken was not what the processor predicted.",
"SampleAfterValue": "200003",
"UMask": "0xeb"
},
{
"BriefDescription": "Retired mispredicted near return instructions (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC5",
"EventName": "BR_MISP_RETIRED.RETURN",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts mispredicted near RET branch instructions retired, where the return address taken was not what the processor predicted.",
"SampleAfterValue": "200003",
"UMask": "0xf7"
},
{
"BriefDescription": "Retired mispredicted conditional branch instructions that were taken (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC5",
"EventName": "BR_MISP_RETIRED.TAKEN_JCC",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were supposed to be taken but the processor predicted that it would not be taken.",
"SampleAfterValue": "200003",
"UMask": "0xfe"
},
{
"BriefDescription": "Core cycles when core is not halted (Fixed event)",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. This event uses fixed counter 1. You cannot collect a PEBs record for this event.",
"Counter": "Fixed counter 1",
"UMask": "0x2",
"PEBScounters": "33",
"EventName": "CPU_CLK_UNHALTED.CORE",
"PDIR_COUNTER": "na",
"PEBScounters": "33",
"PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. This event uses fixed counter 1. You cannot collect a PEBs record for this event.",
"SampleAfterValue": "2000003",
"BriefDescription": "Core cycles when core is not halted (Fixed event)"
"UMask": "0x2"
},
{
"BriefDescription": "Core cycles when core is not halted",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. This event uses fixed counter 2. You cannot collect a PEBs record for this event.",
"Counter": "Fixed counter 2",
"UMask": "0x3",
"PEBScounters": "34",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
"PDIR_COUNTER": "na",
"SampleAfterValue": "2000003",
"BriefDescription": "Reference cycles when core is not halted (Fixed event)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts a load blocked from using a store forward, but did not occur because the store data was not available at the right time. The forward might occur subsequently when the data is available.",
"EventCode": "0x03",
"Counter": "0,1,2,3",
"UMask": "0x1",
"PEBScounters": "0,1,2,3",
"EventName": "LD_BLOCKS.DATA_UNKNOWN",
"SampleAfterValue": "200003",
"BriefDescription": "Loads blocked due to store data not ready (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts a load blocked from using a store forward because of an address/size mismatch, only one of the loads blocked from each store will be counted.",
"EventCode": "0x03",
"Counter": "0,1,2,3",
"UMask": "0x2",
"PEBScounters": "0,1,2,3",
"EventName": "LD_BLOCKS.STORE_FORWARD",
"SampleAfterValue": "200003",
"BriefDescription": "Loads blocked due to store forward restriction (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts loads that block because their address modulo 4K matches a pending store.",
"EventCode": "0x03",
"Counter": "0,1,2,3",
"UMask": "0x4",
"PEBScounters": "0,1,2,3",
"EventName": "LD_BLOCKS.4K_ALIAS",
"SampleAfterValue": "200003",
"BriefDescription": "Loads blocked because address has 4k partial address false dependence (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts loads blocked because they are unable to find their physical address in the micro TLB (UTLB).",
"EventCode": "0x03",
"Counter": "0,1,2,3",
"UMask": "0x8",
"PEBScounters": "0,1,2,3",
"EventName": "LD_BLOCKS.UTLB_MISS",
"SampleAfterValue": "200003",
"BriefDescription": "Loads blocked because address in not in the UTLB (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts anytime a load that retires is blocked for any reason.",
"EventCode": "0x03",
"Counter": "0,1,2,3",
"UMask": "0x10",
"PEBScounters": "0,1,2,3",
"EventName": "LD_BLOCKS.ALL_BLOCK",
"SampleAfterValue": "200003",
"BriefDescription": "Loads blocked (Precise event capable)"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts uops issued by the front end and allocated into the back end of the machine. This event counts uops that retire as well as uops that were speculatively executed but didn't retire. The sort of speculative uops that might be counted includes, but is not limited to those uops issued in the shadow of a miss-predicted branch, those uops that are inserted during an assist (such as for a denormal floating point result), and (previously allocated) uops that might be canceled during a machine clear.",
"EventCode": "0x0E",
"Counter": "0,1,2,3",
"UMask": "0x0",
"PEBScounters": "0,1,2,3",
"EventName": "UOPS_ISSUED.ANY",
"PDIR_COUNTER": "na",
"SampleAfterValue": "200003",
"BriefDescription": "Uops issued to the back end per cycle"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Core cycles when core is not halted. This event uses a (_P)rogrammable general purpose performance counter.",
"EventCode": "0x3C",
"Counter": "0,1,2,3",
"UMask": "0x0",
"PEBScounters": "0,1,2,3",
"EventName": "CPU_CLK_UNHALTED.CORE_P",
"PDIR_COUNTER": "na",
"SampleAfterValue": "2000003",
"BriefDescription": "Core cycles when core is not halted"
"PEBScounters": "0,1,2,3",
"PublicDescription": "Core cycles when core is not halted. This event uses a (_P)rogrammable general purpose performance counter.",
"SampleAfterValue": "2000003"
},
{
"BriefDescription": "Reference cycles when core is not halted",
"CollectPEBSRecord": "1",
"PublicDescription": "Reference cycles when core is not halted. This event uses a (_P)rogrammable general purpose performance counter.",
"EventCode": "0x3C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"PEBScounters": "0,1,2,3",
"EventCode": "0x3C",
"EventName": "CPU_CLK_UNHALTED.REF",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Reference cycles when core is not halted. This event uses a (_P)rogrammable general purpose performance counter.",
"SampleAfterValue": "2000003",
"BriefDescription": "Reference cycles when core is not halted"
"UMask": "0x1"
},
{
"BriefDescription": "Reference cycles when core is not halted (Fixed event)",
"CollectPEBSRecord": "1",
"PublicDescription": "This event used to measure front-end inefficiencies. I.e. when front-end of the machine is not delivering uops to the back-end and the back-end has is not stalled. This event can be used to identify if the machine is truly front-end bound. When this event occurs, it is an indication that the front-end of the machine is operating at less than its theoretical peak performance. Background: We can think of the processor pipeline as being divided into 2 broader parts: Front-end and Back-end. Front-end is responsible for fetching the instruction, decoding into uops in machine understandable format and putting them into a uop queue to be consumed by back end. The back-end then takes these uops, allocates the required resources. When all resources are ready, uops are executed. If the back-end is not ready to accept uops from the front-end, then we do not want to count these as front-end bottlenecks. However, whenever we have bottlenecks in the back-end, we will have allocation unit stalls and eventually forcing the front-end to wait until the back-end is ready to receive more uops. This event counts only when back-end is requesting more uops and front-end is not able to provide them. When 3 uops are requested and no uops are delivered, the event counts 3. When 3 are requested, and only 1 is delivered, the event counts 2. When only 2 are delivered, the event counts 1. Alternatively stated, the event will not count if 3 uops are delivered, or if the back end is stalled and not requesting any uops at all. Counts indicate missed opportunities for the front-end to deliver a uop to the back end. Some examples of conditions that cause front-end efficiencies are: ICache misses, ITLB misses, and decoder restrictions that limit the front-end bandwidth. Known Issues: Some uops require multiple allocation slots. These uops will not be charged as a front end 'not delivered' opportunity, and will be regarded as a back end problem. For example, the INC instruction has one uop that requires 2 issue slots. A stream of INC instructions will not count as UOPS_NOT_DELIVERED, even though only one instruction can be issued per clock. The low uop issue rate for a stream of INC instructions is considered to be a back end issue.",
"EventCode": "0x9C",
"Counter": "0,1,2,3",
"UMask": "0x0",
"PEBScounters": "0,1,2,3",
"EventName": "UOPS_NOT_DELIVERED.ANY",
"Counter": "Fixed counter 2",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
"PDIR_COUNTER": "na",
"SampleAfterValue": "200003",
"BriefDescription": "Uops requested but not-delivered to the back-end per cycle"
},
{
"PEBS": "2",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The event continues counting during hardware interrupts, traps, and inside interrupt handlers. This is an architectural performance event. This event uses a (_P)rogrammable general purpose performance counter. *This event is Precise Event capable: The EventingRIP field in the PEBS record is precise to the address of the instruction which caused the event. Note: Because PEBS records can be collected only on IA32_PMC0, only one event can use the PEBS facility at a time.",
"EventCode": "0xC0",
"Counter": "0,1,2,3",
"UMask": "0x0",
"PEBScounters": "0,1,2,3",
"EventName": "INST_RETIRED.ANY_P",
"PEBScounters": "34",
"PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. This event uses fixed counter 2. You cannot collect a PEBs record for this event.",
"SampleAfterValue": "2000003",
"BriefDescription": "Instructions retired (Precise event capable)"
"UMask": "0x3"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts INST_RETIRED.ANY using the Reduced Skid PEBS feature that reduces the shadow in which events aren't counted allowing for a more unbiased distribution of samples across instructions retired.",
"EventCode": "0xC0",
"Counter": "0,1,2,3",
"UMask": "0x0",
"EventName": "INST_RETIRED.PREC_DIST",
"SampleAfterValue": "2000003",
"BriefDescription": "Instructions retired - using Reduced Skid PEBS feature"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts uops which retired.",
"EventCode": "0xC2",
"Counter": "0,1,2,3",
"UMask": "0x0",
"PEBScounters": "0,1,2,3",
"EventName": "UOPS_RETIRED.ANY",
"PDIR_COUNTER": "na",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops retired (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts uops retired that are from the complex flows issued by the micro-sequencer (MS). Counts both the uops from a micro-coded instruction, and the uops that might be generated from a micro-coded assist.",
"EventCode": "0xC2",
"Counter": "0,1,2,3",
"UMask": "0x1",
"PEBScounters": "0,1,2,3",
"EventName": "UOPS_RETIRED.MS",
"PDIR_COUNTER": "na",
"SampleAfterValue": "2000003",
"BriefDescription": "MS uops retired (Precise event capable)"
},
{
"PEBS": "2",
"BriefDescription": "Cycles a divider is busy",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of floating point divide uops retired.",
"EventCode": "0xC2",
"Counter": "0,1,2,3",
"UMask": "0x8",
"PEBScounters": "0,1,2,3",
"EventName": "UOPS_RETIRED.FPDIV",
"SampleAfterValue": "2000003",
"BriefDescription": "Floating point divide uops retired (Precise Event Capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of integer divide uops retired.",
"EventCode": "0xC2",
"Counter": "0,1,2,3",
"UMask": "0x10",
"PEBScounters": "0,1,2,3",
"EventName": "UOPS_RETIRED.IDIV",
"SampleAfterValue": "2000003",
"BriefDescription": "Integer divide uops retired (Precise Event Capable)"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts machine clears for any reason.",
"EventCode": "0xC3",
"Counter": "0,1,2,3",
"UMask": "0x0",
"PEBScounters": "0,1,2,3",
"EventName": "MACHINE_CLEARS.ALL",
"PDIR_COUNTER": "na",
"SampleAfterValue": "20003",
"BriefDescription": "All machine clears"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel\u00ae architecture processors.",
"EventCode": "0xC3",
"Counter": "0,1,2,3",
"UMask": "0x1",
"PEBScounters": "0,1,2,3",
"EventName": "MACHINE_CLEARS.SMC",
"PDIR_COUNTER": "na",
"SampleAfterValue": "20003",
"BriefDescription": "Self-Modifying Code detected"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts machine clears due to floating point (FP) operations needing assists. For instance, if the result was a floating point denormal, the hardware clears the pipeline and reissues uops to produce the correct IEEE compliant denormal result.",
"EventCode": "0xC3",
"Counter": "0,1,2,3",
"UMask": "0x4",
"PEBScounters": "0,1,2,3",
"EventName": "MACHINE_CLEARS.FP_ASSIST",
"PDIR_COUNTER": "na",
"SampleAfterValue": "20003",
"BriefDescription": "Machine clears due to FP assists"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts machine clears due to memory disambiguation. Memory disambiguation happens when a load which has been issued conflicts with a previous unretired store in the pipeline whose address was not known at issue time, but is later resolved to be the same as the load address.",
"EventCode": "0xC3",
"Counter": "0,1,2,3",
"UMask": "0x8",
"PEBScounters": "0,1,2,3",
"EventName": "MACHINE_CLEARS.DISAMBIGUATION",
"PDIR_COUNTER": "na",
"SampleAfterValue": "20003",
"BriefDescription": "Machine clears due to memory disambiguation"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of times that the machines clears due to a page fault. Covers both I-side and D-side(Loads/Stores) page faults. A page fault occurs when either page is not present, or an access violation",
"EventCode": "0xC3",
"Counter": "0,1,2,3",
"UMask": "0x20",
"PEBScounters": "0,1,2,3",
"EventName": "MACHINE_CLEARS.PAGE_FAULT",
"PDIR_COUNTER": "na",
"SampleAfterValue": "20003",
"BriefDescription": "Machines clear due to a page fault"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts branch instructions retired for all branch types. This is an architectural performance event.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0x0",
"PEBScounters": "0,1,2,3",
"EventName": "BR_INST_RETIRED.ALL_BRANCHES",
"SampleAfterValue": "200003",
"BriefDescription": "Retired branch instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was taken and when it was not taken.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0x7e",
"PEBScounters": "0,1,2,3",
"EventName": "BR_INST_RETIRED.JCC",
"SampleAfterValue": "200003",
"BriefDescription": "Retired conditional branch instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts the number of taken branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0x80",
"PEBScounters": "0,1,2,3",
"EventName": "BR_INST_RETIRED.ALL_TAKEN_BRANCHES",
"SampleAfterValue": "200003",
"BriefDescription": "Retired taken branch instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts far branch instructions retired. This includes far jump, far call and return, and Interrupt call and return.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0xbf",
"PEBScounters": "0,1,2,3",
"EventName": "BR_INST_RETIRED.FAR_BRANCH",
"SampleAfterValue": "200003",
"BriefDescription": "Retired far branch instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts near indirect call or near indirect jmp branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0xeb",
"PEBScounters": "0,1,2,3",
"EventName": "BR_INST_RETIRED.NON_RETURN_IND",
"SampleAfterValue": "200003",
"BriefDescription": "Retired instructions of near indirect Jmp or call (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts near return branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0xf7",
"PEBScounters": "0,1,2,3",
"EventName": "BR_INST_RETIRED.RETURN",
"SampleAfterValue": "200003",
"BriefDescription": "Retired near return instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts near CALL branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0xf9",
"PEBScounters": "0,1,2,3",
"EventName": "BR_INST_RETIRED.CALL",
"SampleAfterValue": "200003",
"BriefDescription": "Retired near call instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts near indirect CALL branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0xfb",
"PEBScounters": "0,1,2,3",
"EventName": "BR_INST_RETIRED.IND_CALL",
"SampleAfterValue": "200003",
"BriefDescription": "Retired near indirect call instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts near relative CALL branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0xfd",
"PEBScounters": "0,1,2,3",
"EventName": "BR_INST_RETIRED.REL_CALL",
"SampleAfterValue": "200003",
"BriefDescription": "Retired near relative call instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were taken and does not count when the Jcc branch instruction were not taken.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0xfe",
"PEBScounters": "0,1,2,3",
"EventName": "BR_INST_RETIRED.TAKEN_JCC",
"SampleAfterValue": "200003",
"BriefDescription": "Retired conditional branch instructions that were taken (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts mispredicted branch instructions retired including all branch types.",
"EventCode": "0xC5",
"Counter": "0,1,2,3",
"UMask": "0x0",
"PEBScounters": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
"SampleAfterValue": "200003",
"BriefDescription": "Retired mispredicted branch instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was supposed to be taken and when it was not supposed to be taken (but the processor predicted the opposite condition).",
"EventCode": "0xC5",
"Counter": "0,1,2,3",
"UMask": "0x7e",
"PEBScounters": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.JCC",
"SampleAfterValue": "200003",
"BriefDescription": "Retired mispredicted conditional branch instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts mispredicted branch instructions retired that were near indirect call or near indirect jmp, where the target address taken was not what the processor predicted.",
"EventCode": "0xC5",
"Counter": "0,1,2,3",
"UMask": "0xeb",
"PEBScounters": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
"SampleAfterValue": "200003",
"BriefDescription": "Retired mispredicted instructions of near indirect Jmp or near indirect call (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts mispredicted near RET branch instructions retired, where the return address taken was not what the processor predicted.",
"EventCode": "0xC5",
"Counter": "0,1,2,3",
"UMask": "0xf7",
"PEBScounters": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.RETURN",
"SampleAfterValue": "200003",
"BriefDescription": "Retired mispredicted near return instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts mispredicted near indirect CALL branch instructions retired, where the target address taken was not what the processor predicted.",
"EventCode": "0xC5",
"Counter": "0,1,2,3",
"UMask": "0xfb",
"PEBScounters": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.IND_CALL",
"SampleAfterValue": "200003",
"BriefDescription": "Retired mispredicted near indirect call instructions (Precise event capable)"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were supposed to be taken but the processor predicted that it would not be taken.",
"EventCode": "0xC5",
"Counter": "0,1,2,3",
"UMask": "0xfe",
"PEBScounters": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.TAKEN_JCC",
"SampleAfterValue": "200003",
"BriefDescription": "Retired mispredicted conditional branch instructions that were taken (Precise event capable)"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts core cycles if either divide unit is busy.",
"EventCode": "0xCD",
"Counter": "0,1,2,3",
"UMask": "0x0",
"PEBScounters": "0,1,2,3",
"EventName": "CYCLES_DIV_BUSY.ALL",
"PDIR_COUNTER": "na",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles a divider is busy"
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts core cycles if either divide unit is busy.",
"SampleAfterValue": "2000003"
},
{
"BriefDescription": "Cycles the integer divide unit is busy",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts core cycles the integer divide unit is busy.",
"EventCode": "0xCD",
"Counter": "0,1,2,3",
"UMask": "0x1",
"PEBScounters": "0,1,2,3",
"EventCode": "0xCD",
"EventName": "CYCLES_DIV_BUSY.IDIV",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts core cycles the integer divide unit is busy.",
"SampleAfterValue": "200003",
"BriefDescription": "Cycles the integer divide unit is busy"
"UMask": "0x1"
},
{
"BriefDescription": "Instructions retired (Fixed event)",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts core cycles the floating point divide unit is busy.",
"EventCode": "0xCD",
"Counter": "0,1,2,3",
"UMask": "0x2",
"PEBScounters": "0,1,2,3",
"EventName": "CYCLES_DIV_BUSY.FPDIV",
"Counter": "Fixed counter 0",
"EventName": "INST_RETIRED.ANY",
"PDIR_COUNTER": "na",
"SampleAfterValue": "200003",
"BriefDescription": "Cycles the FP divide unit is busy"
"PEBS": "2",
"PEBScounters": "32",
"PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. You cannot collect a PEBs record for this event.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Instructions retired (Precise event capable)",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of times a BACLEAR is signaled for any reason, including, but not limited to indirect branch/call, Jcc (Jump on Conditional Code/Jump if Condition is Met) branch, unconditional branch/call, and returns.",
"EventCode": "0xE6",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventCode": "0xC0",
"EventName": "INST_RETIRED.ANY_P",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "BACLEARS.ALL",
"PDIR_COUNTER": "na",
"SampleAfterValue": "200003",
"BriefDescription": "BACLEARs asserted for any branch type"
"PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The event continues counting during hardware interrupts, traps, and inside interrupt handlers. This is an architectural performance event. This event uses a (_P)rogrammable general purpose performance counter. *This event is Precise Event capable: The EventingRIP field in the PEBS record is precise to the address of the instruction which caused the event. Note: Because PEBS records can be collected only on IA32_PMC0, only one event can use the PEBS facility at a time.",
"SampleAfterValue": "2000003"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts BACLEARS on return instructions.",
"EventCode": "0xE6",
"BriefDescription": "Instructions retired - using Reduced Skid PEBS feature",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"UMask": "0x8",
"PEBScounters": "0,1,2,3",
"EventName": "BACLEARS.RETURN",
"PDIR_COUNTER": "na",
"SampleAfterValue": "200003",
"BriefDescription": "BACLEARs asserted for return branch"
"EventCode": "0xC0",
"EventName": "INST_RETIRED.PREC_DIST",
"PEBS": "2",
"PublicDescription": "Counts INST_RETIRED.ANY using the Reduced Skid PEBS feature that reduces the shadow in which events aren't counted allowing for a more unbiased distribution of samples across instructions retired.",
"SampleAfterValue": "2000003"
},
{
"BriefDescription": "Unfilled issue slots per cycle",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts BACLEARS on Jcc (Jump on Conditional Code/Jump if Condition is Met) branches.",
"EventCode": "0xE6",
"Counter": "0,1,2,3",
"UMask": "0x10",
"PEBScounters": "0,1,2,3",
"EventName": "BACLEARS.COND",
"EventCode": "0xCA",
"EventName": "ISSUE_SLOTS_NOT_CONSUMED.ANY",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of issue slots per core cycle that were not consumed by the backend due to either a full resource in the backend (RESOURCE_FULL) or due to the processor recovering from some event (RECOVERY).",
"SampleAfterValue": "200003"
},
{
"BriefDescription": "Unfilled issue slots per cycle to recover",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xCA",
"EventName": "ISSUE_SLOTS_NOT_CONSUMED.RECOVERY",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of issue slots per core cycle that were not consumed by the backend because allocation is stalled waiting for a mispredicted jump to retire or other branch-like conditions (e.g. the event is relevant during certain microcode flows). Counts all issue slots blocked while within this window including slots where uops were not available in the Instruction Queue.",
"SampleAfterValue": "200003",
"BriefDescription": "BACLEARs asserted for conditional branch"
"UMask": "0x2"
},
{
"BriefDescription": "Unfilled issue slots per cycle because of a full resource in the backend",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xCA",
"EventName": "ISSUE_SLOTS_NOT_CONSUMED.RESOURCE_FULL",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of issue slots per core cycle that were not consumed because of a full resource in the backend. Including but not limited to resources such as the Re-order Buffer (ROB), reservation stations (RS), load/store buffers, physical registers, or any other needed machine resource that is currently unavailable. Note that uops must be available for consumption in order for this event to fire. If a uop is not available (Instruction Queue is empty), this event will not count.",
"SampleAfterValue": "200003",
"UMask": "0x1"
},
{
"BriefDescription": "Loads blocked because address has 4k partial address false dependence (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.4K_ALIAS",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts loads that block because their address modulo 4K matches a pending store.",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Loads blocked (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.ALL_BLOCK",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts anytime a load that retires is blocked for any reason.",
"SampleAfterValue": "200003",
"UMask": "0x10"
},
{
"BriefDescription": "Loads blocked due to store data not ready (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.DATA_UNKNOWN",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts a load blocked from using a store forward, but did not occur because the store data was not available at the right time. The forward might occur subsequently when the data is available.",
"SampleAfterValue": "200003",
"UMask": "0x1"
},
{
"BriefDescription": "Loads blocked due to store forward restriction (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.STORE_FORWARD",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts a load blocked from using a store forward because of an address/size mismatch, only one of the loads blocked from each store will be counted.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Loads blocked because address in not in the UTLB (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.UTLB_MISS",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts loads blocked because they are unable to find their physical address in the micro TLB (UTLB).",
"SampleAfterValue": "200003",
"UMask": "0x8"
},
{
"BriefDescription": "All machine clears",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xC3",
"EventName": "MACHINE_CLEARS.ALL",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts machine clears for any reason.",
"SampleAfterValue": "20003"
},
{
"BriefDescription": "Machine clears due to memory disambiguation",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xC3",
"EventName": "MACHINE_CLEARS.DISAMBIGUATION",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts machine clears due to memory disambiguation. Memory disambiguation happens when a load which has been issued conflicts with a previous unretired store in the pipeline whose address was not known at issue time, but is later resolved to be the same as the load address.",
"SampleAfterValue": "20003",
"UMask": "0x8"
},
{
"BriefDescription": "Machines clear due to a page fault",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xC3",
"EventName": "MACHINE_CLEARS.PAGE_FAULT",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times that the machines clears due to a page fault. Covers both I-side and D-side(Loads/Stores) page faults. A page fault occurs when either page is not present, or an access violation",
"SampleAfterValue": "20003",
"UMask": "0x20"
},
{
"BriefDescription": "Self-Modifying Code detected",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xC3",
"EventName": "MACHINE_CLEARS.SMC",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.",
"SampleAfterValue": "20003",
"UMask": "0x1"
},
{
"BriefDescription": "Uops issued to the back end per cycle",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x0E",
"EventName": "UOPS_ISSUED.ANY",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts uops issued by the front end and allocated into the back end of the machine. This event counts uops that retire as well as uops that were speculatively executed but didn't retire. The sort of speculative uops that might be counted includes, but is not limited to those uops issued in the shadow of a miss-predicted branch, those uops that are inserted during an assist (such as for a denormal floating point result), and (previously allocated) uops that might be canceled during a machine clear.",
"SampleAfterValue": "200003"
},
{
"BriefDescription": "Uops requested but not-delivered to the back-end per cycle",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x9C",
"EventName": "UOPS_NOT_DELIVERED.ANY",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "This event used to measure front-end inefficiencies. I.e. when front-end of the machine is not delivering uops to the back-end and the back-end has is not stalled. This event can be used to identify if the machine is truly front-end bound. When this event occurs, it is an indication that the front-end of the machine is operating at less than its theoretical peak performance. Background: We can think of the processor pipeline as being divided into 2 broader parts: Front-end and Back-end. Front-end is responsible for fetching the instruction, decoding into uops in machine understandable format and putting them into a uop queue to be consumed by back end. The back-end then takes these uops, allocates the required resources. When all resources are ready, uops are executed. If the back-end is not ready to accept uops from the front-end, then we do not want to count these as front-end bottlenecks. However, whenever we have bottlenecks in the back-end, we will have allocation unit stalls and eventually forcing the front-end to wait until the back-end is ready to receive more uops. This event counts only when back-end is requesting more uops and front-end is not able to provide them. When 3 uops are requested and no uops are delivered, the event counts 3. When 3 are requested, and only 1 is delivered, the event counts 2. When only 2 are delivered, the event counts 1. Alternatively stated, the event will not count if 3 uops are delivered, or if the back end is stalled and not requesting any uops at all. Counts indicate missed opportunities for the front-end to deliver a uop to the back end. Some examples of conditions that cause front-end efficiencies are: ICache misses, ITLB misses, and decoder restrictions that limit the front-end bandwidth. Known Issues: Some uops require multiple allocation slots. These uops will not be charged as a front end 'not delivered' opportunity, and will be regarded as a back end problem. For example, the INC instruction has one uop that requires 2 issue slots. A stream of INC instructions will not count as UOPS_NOT_DELIVERED, even though only one instruction can be issued per clock. The low uop issue rate for a stream of INC instructions is considered to be a back end issue.",
"SampleAfterValue": "200003"
},
{
"BriefDescription": "Uops retired (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC2",
"EventName": "UOPS_RETIRED.ANY",
"PDIR_COUNTER": "na",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts uops which retired.",
"SampleAfterValue": "2000003"
},
{
"BriefDescription": "Integer divide uops retired (Precise Event Capable)",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xC2",
"EventName": "UOPS_RETIRED.IDIV",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of integer divide uops retired.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "MS uops retired (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xC2",
"EventName": "UOPS_RETIRED.MS",
"PDIR_COUNTER": "na",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts uops retired that are from the complex flows issued by the micro-sequencer (MS). Counts both the uops from a micro-coded instruction, and the uops that might be generated from a micro-coded assist.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
}
]
]

300
lib/libpmc/pmu-events/arch/x86/goldmontplus/virtual-memory.json
View File

@ -1,221 +1,221 @@
[
{
"BriefDescription": "Page walk completed due to a demand load to a 1GB page",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 4K pages. The page walks can end with or without a page fault.",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x2",
"PEBScounters": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"PDIR_COUNTER": "na",
"SampleAfterValue": "200003",
"BriefDescription": "Page walk completed due to a demand load to a 4K page"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 2M or 4M pages. The page walks can end with or without a page fault.",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x4",
"PEBScounters": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PDIR_COUNTER": "na",
"SampleAfterValue": "200003",
"BriefDescription": "Page walk completed due to a demand load to a 2M or 4M page"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 1GB pages. The page walks can end with or without a page fault.",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x8",
"PEBScounters": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1GB",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 1GB pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "200003",
"BriefDescription": "Page walk completed due to a demand load to a 1GB page"
"UMask": "0x8"
},
{
"BriefDescription": "Page walk completed due to a demand load to a 2M or 4M page",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts once per cycle for each page walk occurring due to a load (demand data loads or SW prefetches). Includes cycles spent traversing the Extended Page Table (EPT). Average cycles per walk can be calculated by dividing by the number of walks.",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 2M or 4M pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Page walk completed due to a demand load to a 4K page",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 4K pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Page walks outstanding due to a demand load every cycle.",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts once per cycle for each page walk occurring due to a load (demand data loads or SW prefetches). Includes cycles spent traversing the Extended Page Table (EPT). Average cycles per walk can be calculated by dividing by the number of walks.",
"SampleAfterValue": "200003",
"BriefDescription": "Page walks outstanding due to a demand load every cycle."
"UMask": "0x10"
},
{
"BriefDescription": "Page walk completed due to a demand data store to a 1GB page",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.",
"EventCode": "0x49",
"Counter": "0,1,2,3",
"UMask": "0x2",
"PEBScounters": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"PDIR_COUNTER": "na",
"SampleAfterValue": "2000003",
"BriefDescription": "Page walk completed due to a demand data store to a 4K page"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M or 4M pages. The page walks can end with or without a page fault.",
"EventCode": "0x49",
"Counter": "0,1,2,3",
"UMask": "0x4",
"PEBScounters": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PDIR_COUNTER": "na",
"SampleAfterValue": "2000003",
"BriefDescription": "Page walk completed due to a demand data store to a 2M or 4M page"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1GB pages. The page walks can end with or without a page fault.",
"EventCode": "0x49",
"Counter": "0,1,2,3",
"UMask": "0x8",
"PEBScounters": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1GB",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1GB pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "2000003",
"BriefDescription": "Page walk completed due to a demand data store to a 1GB page"
"UMask": "0x8"
},
{
"BriefDescription": "Page walk completed due to a demand data store to a 2M or 4M page",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts once per cycle for each page walk occurring due to a demand data store. Includes cycles spent traversing the Extended Page Table (EPT). Average cycles per walk can be calculated by dividing by the number of walks.",
"EventCode": "0x49",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M or 4M pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Page walk completed due to a demand data store to a 4K page",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Page walks outstanding due to a demand data store every cycle.",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_PENDING",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts once per cycle for each page walk occurring due to a demand data store. Includes cycles spent traversing the Extended Page Table (EPT). Average cycles per walk can be calculated by dividing by the number of walks.",
"SampleAfterValue": "200003",
"BriefDescription": "Page walks outstanding due to a demand data store every cycle."
"UMask": "0x10"
},
{
"BriefDescription": "Page walks outstanding due to walking the EPT every cycle",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts once per cycle for each page walk only while traversing the Extended Page Table (EPT), and does not count during the rest of the translation. The EPT is used for translating Guest-Physical Addresses to Physical Addresses for Virtual Machine Monitors (VMMs). Average cycles per walk can be calculated by dividing the count by number of walks.",
"EventCode": "0x4F",
"Counter": "0,1,2,3",
"UMask": "0x10",
"PEBScounters": "0,1,2,3",
"EventCode": "0x4F",
"EventName": "EPT.WALK_PENDING",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts once per cycle for each page walk only while traversing the Extended Page Table (EPT), and does not count during the rest of the translation. The EPT is used for translating Guest-Physical Addresses to Physical Addresses for Virtual Machine Monitors (VMMs). Average cycles per walk can be calculated by dividing the count by number of walks.",
"SampleAfterValue": "200003",
"BriefDescription": "Page walks outstanding due to walking the EPT every cycle"
"UMask": "0x10"
},
{
"BriefDescription": "ITLB misses",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of times the machine was unable to find a translation in the Instruction Translation Lookaside Buffer (ITLB) for a linear address of an instruction fetch. It counts when new translation are filled into the ITLB. The event is speculative in nature, but will not count translations (page walks) that are begun and not finished, or translations that are finished but not filled into the ITLB.",
"EventCode": "0x81",
"Counter": "0,1,2,3",
"UMask": "0x4",
"PEBScounters": "0,1,2,3",
"EventCode": "0x81",
"EventName": "ITLB.MISS",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times the machine was unable to find a translation in the Instruction Translation Lookaside Buffer (ITLB) for a linear address of an instruction fetch. It counts when new translation are filled into the ITLB. The event is speculative in nature, but will not count translations (page walks) that are begun and not finished, or translations that are finished but not filled into the ITLB.",
"SampleAfterValue": "200003",
"BriefDescription": "ITLB misses"
"UMask": "0x4"
},
{
"BriefDescription": "Page walk completed due to an instruction fetch in a 1GB page",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.",
"EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x2",
"PEBScounters": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PDIR_COUNTER": "na",
"SampleAfterValue": "2000003",
"BriefDescription": "Page walk completed due to an instruction fetch in a 4K page"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 2M or 4M pages. The page walks can end with or without a page fault.",
"EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x4",
"PEBScounters": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PDIR_COUNTER": "na",
"SampleAfterValue": "2000003",
"BriefDescription": "Page walk completed due to an instruction fetch in a 2M or 4M page"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 1GB pages. The page walks can end with or without a page fault.",
"EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x8",
"PEBScounters": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED_1GB",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 1GB pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "2000003",
"BriefDescription": "Page walk completed due to an instruction fetch in a 1GB page"
"UMask": "0x8"
},
{
"BriefDescription": "Page walk completed due to an instruction fetch in a 2M or 4M page",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts once per cycle for each page walk occurring due to an instruction fetch. Includes cycles spent traversing the Extended Page Table (EPT). Average cycles per walk can be calculated by dividing by the number of walks.",
"EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 2M or 4M pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Page walk completed due to an instruction fetch in a 4K page",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Page walks outstanding due to an instruction fetch every cycle.",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_PENDING",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts once per cycle for each page walk occurring due to an instruction fetch. Includes cycles spent traversing the Extended Page Table (EPT). Average cycles per walk can be calculated by dividing by the number of walks.",
"SampleAfterValue": "200003",
"BriefDescription": "Page walks outstanding due to an instruction fetch every cycle."
"UMask": "0x10"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts STLB flushes. The TLBs are flushed on instructions like INVLPG and MOV to CR3.",
"EventCode": "0xBD",
"BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"UMask": "0x20",
"Data_LA": "1",
"EventCode": "0xD0",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts uops retired that had a DTLB miss on load, store or either. Note that when two distinct memory operations to the same page miss the DTLB, only one of them will be recorded as a DTLB miss.",
"SampleAfterValue": "200003",
"UMask": "0x13"
},
{
"BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xD0",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts load uops retired that caused a DTLB miss.",
"SampleAfterValue": "200003",
"UMask": "0x11"
},
{
"BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xD0",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts store uops retired that caused a DTLB miss.",
"SampleAfterValue": "200003",
"UMask": "0x12"
},
{
"BriefDescription": "STLB flushes",
"CollectPEBSRecord": "1",
"Counter": "0,1,2,3",
"EventCode": "0xBD",
"EventName": "TLB_FLUSHES.STLB_ANY",
"PDIR_COUNTER": "na",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts STLB flushes. The TLBs are flushed on instructions like INVLPG and MOV to CR3.",
"SampleAfterValue": "20003",
"BriefDescription": "STLB flushes"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts load uops retired that caused a DTLB miss.",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x11",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
"SampleAfterValue": "200003",
"BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)",
"Data_LA": "1"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts store uops retired that caused a DTLB miss.",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x12",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
"SampleAfterValue": "200003",
"BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)",
"Data_LA": "1"
},
{
"PEBS": "2",
"CollectPEBSRecord": "2",
"PublicDescription": "Counts uops retired that had a DTLB miss on load, store or either. Note that when two distinct memory operations to the same page miss the DTLB, only one of them will be recorded as a DTLB miss.",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x13",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
"SampleAfterValue": "200003",
"BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)",
"Data_LA": "1"
"UMask": "0x20"
}
]

1824
lib/libpmc/pmu-events/arch/x86/haswell/cache.json
View File

File diff suppressed because it is too large Load Diff

167
lib/libpmc/pmu-events/arch/x86/haswell/floating-point.json
View File

@ -1,92 +1,103 @@
[
{
"PEBS": "1",
"PublicDescription": "",
"EventCode": "0xC1",
"BriefDescription": "Approximate counts of AVX & AVX2 256-bit instructions, including non-arithmetic instructions, loads, and stores. May count non-AVX instructions that employ 256-bit operations, including (but not necessarily limited to) rep string instructions that use 256-bit loads and stores for optimized performance, XSAVE* and XRSTOR*, and operations that transition the x87 FPU data registers between x87 and MMX.",
"Counter": "0,1,2,3",
"UMask": "0x8",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xC6",
"EventName": "AVX_INSTS.ALL",
"PublicDescription": "Note that a whole rep string only counts AVX_INST.ALL once.",
"SampleAfterValue": "2000003",
"UMask": "0x7"
},
{
"BriefDescription": "Cycles with any input/output SSE or FP assist",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.ANY",
"PublicDescription": "Cycles with any input/output SSE* or FP assists.",
"SampleAfterValue": "100003",
"UMask": "0x1e"
},
{
"BriefDescription": "Number of SIMD FP assists due to input values",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.SIMD_INPUT",
"PublicDescription": "Number of SIMD FP assists due to input values.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Number of SIMD FP assists due to Output values",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.SIMD_OUTPUT",
"PublicDescription": "Number of SIMD FP assists due to output values.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of X87 assists due to input value.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.X87_INPUT",
"PublicDescription": "Number of X87 FP assists due to input values.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of X87 assists due to output value.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.X87_OUTPUT",
"PublicDescription": "Number of X87 FP assists due to output values.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of SIMD Move Elimination candidate uops that were eliminated.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x58",
"EventName": "MOVE_ELIMINATION.SIMD_ELIMINATED",
"PublicDescription": "Number of SIMD move elimination candidate uops that were eliminated.",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of SIMD Move Elimination candidate uops that were not eliminated.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x58",
"EventName": "MOVE_ELIMINATION.SIMD_NOT_ELIMINATED",
"PublicDescription": "Number of SIMD move elimination candidate uops that were not eliminated.",
"SampleAfterValue": "1000003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "HSD56, HSM57",
"EventCode": "0xC1",
"EventName": "OTHER_ASSISTS.AVX_TO_SSE",
"SampleAfterValue": "100003",
"BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x8"
},
{
"PEBS": "1",
"PublicDescription": "",
"EventCode": "0xC1",
"BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
"Counter": "0,1,2,3",
"UMask": "0x10",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "HSD56, HSM57",
"EventCode": "0xC1",
"EventName": "OTHER_ASSISTS.SSE_TO_AVX",
"SampleAfterValue": "100003",
"BriefDescription": "Number of transitions from legacy SSE to AVX-256 when penalty applicable",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Note that a whole rep string only counts AVX_INST.ALL once.",
"EventCode": "0xC6",
"Counter": "0,1,2,3",
"UMask": "0x7",
"EventName": "AVX_INSTS.ALL",
"SampleAfterValue": "2000003",
"BriefDescription": "Approximate counts of AVX & AVX2 256-bit instructions, including non-arithmetic instructions, loads, and stores. May count non-AVX instructions that employ 256-bit operations, including (but not necessarily limited to) rep string instructions that use 256-bit loads and stores for optimized performance, XSAVE* and XRSTOR*, and operations that transition the x87 FPU data registers between x87 and MMX.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PEBS": "1",
"PublicDescription": "",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "FP_ASSIST.X87_OUTPUT",
"SampleAfterValue": "100003",
"BriefDescription": "output - Numeric Overflow, Numeric Underflow, Inexact Result",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PEBS": "1",
"PublicDescription": "",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "FP_ASSIST.X87_INPUT",
"SampleAfterValue": "100003",
"BriefDescription": "input - Invalid Operation, Denormal Operand, SNaN Operand",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PEBS": "1",
"PublicDescription": "",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x8",
"EventName": "FP_ASSIST.SIMD_OUTPUT",
"SampleAfterValue": "100003",
"BriefDescription": "SSE* FP micro-code assist when output value is invalid.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PEBS": "1",
"PublicDescription": "",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "FP_ASSIST.SIMD_INPUT",
"SampleAfterValue": "100003",
"BriefDescription": "Any input SSE* FP Assist",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PEBS": "1",
"PublicDescription": "",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x1e",
"EventName": "FP_ASSIST.ANY",
"SampleAfterValue": "100003",
"BriefDescription": "Counts any FP_ASSIST umask was incrementing",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3"
"UMask": "0x10"
}
]

576
lib/libpmc/pmu-events/arch/x86/haswell/frontend.json
View File

@ -1,294 +1,304 @@
[
{
"PublicDescription": "Counts cycles the IDQ is empty.",
"EventCode": "0x79",
"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",
"UMask": "0x2",
"Errata": "HSD135",
"EventName": "IDQ.EMPTY",
"SampleAfterValue": "2000003",
"BriefDescription": "Instruction Decode Queue (IDQ) empty cycles",
"CounterHTOff": "0,1,2,3"
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xe6",
"EventName": "BACLEARS.ANY",
"PublicDescription": "Number of front end re-steers due to BPU misprediction.",
"SampleAfterValue": "100003",
"UMask": "0x1f"
},
{
"PublicDescription": "Increment each cycle # of uops delivered to IDQ from MITE path. Set Cmask = 1 to count cycles.",
"EventCode": "0x79",
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "IDQ.MITE_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "IDQ.MITE_CYCLES",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x8",
"EventName": "IDQ.DSB_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x8",
"EventName": "IDQ.DSB_CYCLES",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "IDQ.MS_DSB_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "IDQ.MS_DSB_CYCLES",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EdgeDetect": "1",
"EventName": "IDQ.MS_DSB_OCCUR",
"SampleAfterValue": "2000003",
"BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Counts cycles DSB is delivered four uops. Set Cmask = 4.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x18",
"EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
"CounterMask": "4",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Counts cycles DSB is delivered at least one uops. Set Cmask = 1.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x18",
"EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x20",
"EventName": "IDQ.MS_MITE_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Counts cycles MITE is delivered four uops. Set Cmask = 4.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x24",
"EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles MITE is delivering 4 Uops",
"CounterMask": "4",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Counts cycles MITE is delivered at least one uop. Set Cmask = 1.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x24",
"EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles MITE is delivering any Uop",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts uops delivered by the Front-end with the assistance of the microcode sequencer. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x30",
"EventName": "IDQ.MS_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts cycles during which the microcode sequencer assisted the Front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x30",
"EventName": "IDQ.MS_CYCLES",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x30",
"EdgeDetect": "1",
"EventName": "IDQ.MS_SWITCHES",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Number of uops delivered to IDQ from any path.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
"UMask": "0x3c",
"EventName": "IDQ.MITE_ALL_UOPS",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x80",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "ICACHE.HIT",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts Instruction Cache (ICACHE) misses.",
"EventCode": "0x80",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "ICACHE.MISSES",
"SampleAfterValue": "200003",
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Misses. Includes Uncacheable accesses.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x80",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "ICACHE.IFETCH_STALL",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x80",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "ICACHE.IFDATA_STALL",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event count the number of undelivered (unallocated) uops from the Front-end to the Resource Allocation Table (RAT) while the Back-end of the processor is not stalled. The Front-end can allocate up to 4 uops per cycle so this event can increment 0-4 times per cycle depending on the number of unallocated uops. This event is counted on a per-core basis.",
"EventCode": "0x9C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"Errata": "HSD135",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
"SampleAfterValue": "2000003",
"BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
"CounterHTOff": "0,1,2,3"
},
{
"PublicDescription": "This event counts the number cycles during which the Front-end allocated exactly zero uops to the Resource Allocation Table (RAT) while the Back-end of the processor is not stalled. This event is counted on a per-core basis.",
"EventCode": "0x9C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"Errata": "HSD135",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
"CounterMask": "4",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0x9C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"Errata": "HSD135",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.",
"CounterMask": "3",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0x9C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"Errata": "HSD135",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
"CounterMask": "2",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0x9C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"Errata": "HSD135",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0x9C",
"Invert": "1",
"Counter": "0,1,2,3",
"UMask": "0x1",
"Errata": "HSD135",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"SampleAfterValue": "2000003",
"BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3"
},
{
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xAB",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"SampleAfterValue": "2000003",
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x2"
},
{
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.HIT",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.IFDATA_STALL",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.IFETCH_STALL",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Misses. Includes Uncacheable accesses.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.MISSES",
"PublicDescription": "This event counts Instruction Cache (ICACHE) misses.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
"PublicDescription": "Counts cycles DSB is delivered four uops. Set Cmask = 4.",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
"PublicDescription": "Counts cycles DSB is delivered at least one uops. Set Cmask = 1.",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Cycles MITE is delivering 4 Uops",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
"PublicDescription": "Counts cycles MITE is delivered four uops. Set Cmask = 4.",
"SampleAfterValue": "2000003",
"UMask": "0x24"
},
{
"BriefDescription": "Cycles MITE is delivering any Uop",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
"PublicDescription": "Counts cycles MITE is delivered at least one uop. Set Cmask = 1.",
"SampleAfterValue": "2000003",
"UMask": "0x24"
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
"PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Instruction Decode Queue (IDQ) empty cycles",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"Errata": "HSD135",
"EventCode": "0x79",
"EventName": "IDQ.EMPTY",
"PublicDescription": "Counts cycles the IDQ is empty.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MITE_ALL_UOPS",
"PublicDescription": "Number of uops delivered to IDQ from any path.",
"SampleAfterValue": "2000003",
"UMask": "0x3c"
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
"PublicDescription": "Increment each cycle # of uops delivered to IDQ from MITE path. Set Cmask = 1 to count cycles.",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_CYCLES",
"PublicDescription": "This event counts cycles during which the microcode sequencer assisted the Front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance.",
"SampleAfterValue": "2000003",
"UMask": "0x30"
},
{
"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",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_CYCLES",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_OCCUR",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_UOPS",
"PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_MITE_UOPS",
"PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.",
"SampleAfterValue": "2000003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_SWITCHES",
"SampleAfterValue": "2000003",
"UMask": "0x30"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_UOPS",
"PublicDescription": "This event counts uops delivered by the Front-end with the assistance of the microcode sequencer. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance.",
"SampleAfterValue": "2000003",
"UMask": "0x30"
},
{
"BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"Errata": "HSD135",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
"PublicDescription": "This event count the number of undelivered (unallocated) uops from the Front-end to the Resource Allocation Table (RAT) while the Back-end of the processor is not stalled. The Front-end can allocate up to 4 uops per cycle so this event can increment 0-4 times per cycle depending on the number of unallocated uops. This event is counted on a per-core basis.",
"SampleAfterValue": "2000003",
"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",
"CounterHTOff": "0,1,2,3",
"CounterMask": "4",
"Errata": "HSD135",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
"PublicDescription": "This event counts the number cycles during which the Front-end allocated exactly zero uops to the Resource Allocation Table (RAT) while the Back-end of the processor is not stalled. This event is counted on a per-core basis.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"Errata": "HSD135",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"Invert": "1",
"SampleAfterValue": "2000003",
"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",
"CounterHTOff": "0,1,2,3",
"CounterMask": "3",
"Errata": "HSD135",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "2",
"Errata": "HSD135",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"Errata": "HSD135",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"UMask": "0x1"
}
]

267
lib/libpmc/pmu-events/arch/x86/haswell/hsw-metrics.json
View File

@ -1,172 +1,125 @@
[
{
"BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Frontend_Bound",
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound."
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound."
},
{
"BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Frontend_Bound_SMT",
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Bad_Speculation",
"PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example."
},
{
"BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Bad_Speculation_SMT",
"PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) )",
"MetricGroup": "TopdownL1",
"MetricName": "Backend_Bound",
"PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound."
},
{
"BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) )",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Backend_Bound_SMT",
"PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Retiring",
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. "
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. "
},
{
"BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Retiring_SMT",
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU."
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "Instructions Per Cycle (per Logical Processor)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "TopDownL1",
"MetricGroup": "Ret;Summary",
"MetricName": "IPC"
},
{
"BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
"MetricGroup": "Pipeline;Retire",
"MetricGroup": "Pipeline;Ret;Retire",
"MetricName": "UPI"
},
{
"BriefDescription": "Instruction per taken branch",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fetch_BW;PGO",
"MetricName": "IpTB"
},
{
"BriefDescription": "Branch instructions per taken branch. ",
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;PGO",
"MetricName": "BpTB"
},
{
"BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
"MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
"MetricGroup": "PGO;IcMiss",
"MetricName": "IFetch_Line_Utilization"
},
{
"BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
"MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
"MetricGroup": "DSB;Fetch_BW",
"MetricName": "DSB_Coverage"
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW",
"MetricName": "UpTB"
},
{
"BriefDescription": "Cycles Per Instruction (per Logical Processor)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
"MetricGroup": "Pipeline;Summary",
"MetricExpr": "1 / (INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "Pipeline;Mem",
"MetricName": "CPI"
},
{
"BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Summary",
"MetricGroup": "Pipeline",
"MetricName": "CLKS"
},
{
"BriefDescription": "Total issue-pipeline slots (per-Physical Core)",
"MetricExpr": "4 * cycles",
"MetricGroup": "TopDownL1",
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
"MetricExpr": "4 * CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "TmaL1",
"MetricName": "SLOTS"
},
{
"BriefDescription": "Total issue-pipeline slots (per-Physical Core)",
"MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopDownL1_SMT",
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
"MetricExpr": "4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "TmaL1_SMT",
"MetricName": "SLOTS_SMT"
},
{
"BriefDescription": "Instructions per Load (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
"MetricGroup": "Instruction_Type",
"MetricName": "IpL"
},
{
"BriefDescription": "Instructions per Store (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
"MetricGroup": "Instruction_Type",
"MetricName": "IpS"
},
{
"BriefDescription": "Instructions per Branch (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Branches;Instruction_Type",
"MetricName": "IpB"
},
{
"BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
"MetricGroup": "Branches",
"MetricName": "IpCall"
},
{
"BriefDescription": "Total number of retired Instructions",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
"BriefDescription": "Instructions Per Cycle (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / cycles",
"MetricGroup": "SMT",
"BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Ret;SMT;TmaL1",
"MetricName": "CoreIPC"
},
{
"BriefDescription": "Instructions Per Cycle (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "SMT",
"BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "Ret;SMT;TmaL1_SMT",
"MetricName": "CoreIPC_SMT"
},
{
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
"MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
"MetricGroup": "Pipeline",
"MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
"MetricName": "ILP"
},
{
"BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "BrMispredicts",
"MetricGroup": "Bad;BadSpec;BrMispredicts",
"MetricName": "IpMispredict"
},
{
@ -176,83 +129,127 @@
"MetricName": "CORE_CLKS"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
"MetricGroup": "InsType",
"MetricName": "IpLoad"
},
{
"BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
"MetricGroup": "InsType",
"MetricName": "IpStore"
},
{
"BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Branches;Fed;InsType",
"MetricName": "IpBranch"
},
{
"BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "IpCall"
},
{
"BriefDescription": "Instruction per taken branch",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO",
"MetricName": "IpTB"
},
{
"BriefDescription": "Branch instructions per taken branch. ",
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "BpTkBranch"
},
{
"BriefDescription": "Total number of retired Instructions, Sample with: INST_RETIRED.PREC_DIST",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary;TmaL1",
"MetricName": "Instructions"
},
{
"BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
"MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
"MetricGroup": "DSB;Fed;FetchBW",
"MetricName": "DSB_Coverage"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles)",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
"MetricGroup": "Mem;MemoryBound;MemoryLat",
"MetricName": "Load_Miss_Real_Latency",
"PublicDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles). Latency may be overestimated for multi-load instructions - e.g. repeat strings."
},
{
"BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
"MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
"MetricGroup": "Memory_Bound;Memory_BW",
"MetricGroup": "Mem;MemoryBound;MemoryBW",
"MetricName": "MLP"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles",
"MetricGroup": "TLB",
"MetricName": "Page_Walks_Utilization"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TLB_SMT",
"MetricName": "Page_Walks_Utilization_SMT"
},
{
"BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
"MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
"MetricGroup": "Memory_BW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L1D_Cache_Fill_BW"
},
{
"BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
"MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
"MetricGroup": "Memory_BW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L2_Cache_Fill_BW"
},
{
"BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
"MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
"MetricGroup": "Memory_BW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L3_Cache_Fill_BW"
},
{
"BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L1MPKI"
},
{
"BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;Backend;CacheMisses",
"MetricName": "L2MPKI"
},
{
"BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricName": "L2MPKI_All"
},
{
"BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricName": "L2HPKI_All"
},
{
"BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L3MPKI"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Mem;MemoryTLB",
"MetricName": "Page_Walks_Utilization"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "Mem;MemoryTLB_SMT",
"MetricName": "Page_Walks_Utilization_SMT"
},
{
"BriefDescription": "Average CPU Utilization",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
"MetricGroup": "Summary",
"MetricGroup": "HPC;Summary",
"MetricName": "CPU_Utilization"
},
{
"BriefDescription": "Measured Average Frequency for unhalted processors [GHz]",
"MetricExpr": "(CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time",
"MetricGroup": "Summary;Power",
"MetricName": "Average_Frequency"
},
{
"BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
@ -261,22 +258,46 @@
},
{
"BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
"MetricGroup": "SMT;Summary",
"MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
"MetricGroup": "SMT",
"MetricName": "SMT_2T_Utilization"
},
{
"BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Summary",
"BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "OS",
"MetricName": "Kernel_Utilization"
},
{
"BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
"MetricGroup": "OS",
"MetricName": "Kernel_CPI"
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
"MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
"MetricGroup": "Memory_BW",
"MetricGroup": "HPC;Mem;MemoryBW;SoC",
"MetricName": "DRAM_BW_Use"
},
{
"BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)",
"MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / arb@event\\=0x81\\,umask\\=0x1@",
"MetricGroup": "Mem;SoC",
"MetricName": "MEM_Request_Latency"
},
{
"BriefDescription": "Average number of parallel requests to external memory. Accounts for all requests",
"MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / arb@event\\=0x81\\,umask\\=0x1@",
"MetricGroup": "Mem;SoC",
"MetricName": "MEM_Parallel_Requests"
},
{
"BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
"MetricGroup": "Branches;OS",
"MetricName": "IpFarBranch"
},
{
"BriefDescription": "C3 residency percent per core",
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",

1110
lib/libpmc/pmu-events/arch/x86/haswell/memory.json
View File

File diff suppressed because it is too large Load Diff

52
lib/libpmc/pmu-events/arch/x86/haswell/other.json
View File

@ -1,43 +1,43 @@
[
{
"PublicDescription": "Unhalted core cycles when the thread is in ring 0.",
"EventCode": "0x5C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "CPL_CYCLES.RING0",
"SampleAfterValue": "2000003",
"BriefDescription": "Unhalted core cycles when the thread is in ring 0",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING0",
"PublicDescription": "Unhalted core cycles when the thread is in ring 0.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"EventCode": "0x5C",
"BriefDescription": "Number of intervals between processor halts while thread is in ring 0.",
"Counter": "0,1,2,3",
"UMask": "0x1",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING0_TRANS",
"SampleAfterValue": "100003",
"BriefDescription": "Number of intervals between processor halts while thread is in ring 0.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"PublicDescription": "Unhalted core cycles when the thread is not in ring 0.",
"EventCode": "0x5C",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "CPL_CYCLES.RING123",
"SampleAfterValue": "2000003",
"BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING123",
"PublicDescription": "Unhalted core cycles when the thread is not in ring 0.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"PublicDescription": "Cycles in which the L1D and L2 are locked, due to a UC lock or split lock.",
"EventCode": "0x63",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x63",
"EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION",
"PublicDescription": "Cycles in which the L1D and L2 are locked, due to a UC lock or split lock.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
}
]

2452
lib/libpmc/pmu-events/arch/x86/haswell/pipeline.json
View File

File diff suppressed because it is too large Load Diff

252
lib/libpmc/pmu-events/arch/x86/haswell/uncore-cache.json Normal file
View File

@ -0,0 +1,252 @@
[
{
"BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES",
"PerPkg": "1",
"PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
"UMask": "0x86",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup any request that access cache and found line in I-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I",
"PerPkg": "1",
"PublicDescription": "L3 Lookup any request that access cache and found line in I-state.",
"UMask": "0x88",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup any request that access cache and found line in M-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M",
"PerPkg": "1",
"PublicDescription": "L3 Lookup any request that access cache and found line in M-state.",
"UMask": "0x81",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI",
"PerPkg": "1",
"PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
"UMask": "0x8f",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_ES",
"PerPkg": "1",
"PublicDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.",
"UMask": "0x46",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup external snoop request that access cache and found line in I-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_I",
"PerPkg": "1",
"PublicDescription": "L3 Lookup external snoop request that access cache and found line in I-state.",
"UMask": "0x48",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup external snoop request that access cache and found line in M-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_M",
"PerPkg": "1",
"PublicDescription": "L3 Lookup external snoop request that access cache and found line in M-state.",
"UMask": "0x41",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_MESI",
"PerPkg": "1",
"PublicDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.",
"UMask": "0x4f",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES",
"PerPkg": "1",
"PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
"UMask": "0x16",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup read request that access cache and found line in I-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.READ_I",
"PerPkg": "1",
"PublicDescription": "L3 Lookup read request that access cache and found line in I-state.",
"UMask": "0x18",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup read request that access cache and found line in M-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.READ_M",
"PerPkg": "1",
"PublicDescription": "L3 Lookup read request that access cache and found line in M-state.",
"UMask": "0x11",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI",
"PerPkg": "1",
"PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
"UMask": "0x1f",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES",
"PerPkg": "1",
"PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
"UMask": "0x26",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup write request that access cache and found line in I-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_I",
"PerPkg": "1",
"PublicDescription": "L3 Lookup write request that access cache and found line in I-state.",
"UMask": "0x28",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup write request that access cache and found line in M-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M",
"PerPkg": "1",
"PublicDescription": "L3 Lookup write request that access cache and found line in M-state.",
"UMask": "0x21",
"Unit": "CBO"
},
{
"BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI",
"PerPkg": "1",
"PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
"UMask": "0x2f",
"Unit": "CBO"
},
{
"BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.",
"Counter": "0,1",
"EventCode": "0x22",
"EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EVICTION",
"PerPkg": "1",
"PublicDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.",
"UMask": "0x88",
"Unit": "CBO"
},
{
"BriefDescription": "An external snoop hits a modified line in some processor core.",
"Counter": "0,1",
"EventCode": "0x22",
"EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EXTERNAL",
"PerPkg": "1",
"PublicDescription": "An external snoop hits a modified line in some processor core.",
"UMask": "0x28",
"Unit": "CBO"
},
{
"BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
"Counter": "0,1",
"EventCode": "0x22",
"EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE",
"PerPkg": "1",
"PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
"UMask": "0x48",
"Unit": "CBO"
},
{
"BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.",
"Counter": "0,1",
"EventCode": "0x22",
"EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EVICTION",
"PerPkg": "1",
"PublicDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.",
"UMask": "0x84",
"Unit": "CBO"
},
{
"BriefDescription": "An external snoop hits a non-modified line in some processor core.",
"Counter": "0,1",
"EventCode": "0x22",
"EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EXTERNAL",
"PerPkg": "1",
"PublicDescription": "An external snoop hits a non-modified line in some processor core.",
"UMask": "0x24",
"Unit": "CBO"
},
{
"BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
"Counter": "0,1",
"EventCode": "0x22",
"EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE",
"PerPkg": "1",
"PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
"UMask": "0x44",
"Unit": "CBO"
},
{
"BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
"Counter": "0,1",
"EventCode": "0x22",
"EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION",
"PerPkg": "1",
"PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
"UMask": "0x81",
"Unit": "CBO"
},
{
"BriefDescription": "An external snoop misses in some processor core.",
"Counter": "0,1",
"EventCode": "0x22",
"EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EXTERNAL",
"PerPkg": "1",
"PublicDescription": "An external snoop misses in some processor core.",
"UMask": "0x21",
"Unit": "CBO"
},
{
"BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
"Counter": "0,1",
"EventCode": "0x22",
"EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE",
"PerPkg": "1",
"PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
"UMask": "0x41",
"Unit": "CBO"
}
]

69
lib/libpmc/pmu-events/arch/x86/haswell/uncore-other.json Normal file
View File

@ -0,0 +1,69 @@
[
{
"BriefDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory)",
"EventCode": "0x83",
"EventName": "UNC_ARB_COH_TRK_OCCUPANCY.All",
"PerPkg": "1",
"PublicDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory).",
"UMask": "0x01",
"Unit": "ARB"
},
{
"BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
"Counter": "0,1",
"EventCode": "0x84",
"EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
"PerPkg": "1",
"PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
"UMask": "0x01",
"Unit": "ARB"
},
{
"BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
"EventCode": "0x80",
"EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
"PerPkg": "1",
"PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
"UMask": "0x01",
"Unit": "ARB"
},
{
"BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
"Counter": "0,",
"CounterMask": "1",
"EventCode": "0x80",
"EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
"PerPkg": "1",
"UMask": "0x01",
"Unit": "ARB"
},
{
"BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
"Counter": "0,1",
"EventCode": "0x81",
"EventName": "UNC_ARB_TRK_REQUESTS.ALL",
"PerPkg": "1",
"PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
"UMask": "0x01",
"Unit": "ARB"
},
{
"BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
"Counter": "0,1",
"EventCode": "0x81",
"EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
"PerPkg": "1",
"PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
"UMask": "0x20",
"Unit": "ARB"
},
{
"BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.",
"Counter": "FIXED",
"EventCode": "0xff",
"EventName": "UNC_CLOCK.SOCKET",
"PerPkg": "1",
"PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
"Unit": "NCU"
}
]

672
lib/libpmc/pmu-events/arch/x86/haswell/virtual-memory.json
View File

@ -1,484 +1,484 @@
[
{
"PublicDescription": "Misses in all TLB levels that cause a page walk of any page size.",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
"SampleAfterValue": "100003",
"BriefDescription": "Load misses in all DTLB levels that cause page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "Misses in all TLB levels that cause a page walk of any page size.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"PublicDescription": "Completed page walks due to demand load misses that caused 4K page walks in any TLB levels.",
"EventCode": "0x08",
"BriefDescription": "DTLB demand load misses with low part of linear-to-physical address translation missed",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.PDE_CACHE_MISS",
"PublicDescription": "DTLB demand load misses with low part of linear-to-physical address translation missed.",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"PublicDescription": "Number of cache load STLB hits. No page walk.",
"SampleAfterValue": "2000003",
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x60"
},
{
"PublicDescription": "Completed page walks due to demand load misses that caused 2M/4M page walks in any TLB levels.",
"EventCode": "0x08",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (2M)",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_2M",
"PublicDescription": "This event counts load operations from a 2M page that miss the first DTLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "2000003",
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (2M/4M).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x40"
},
{
"EventCode": "0x08",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (4K)",
"Counter": "0,1,2,3",
"UMask": "0x8",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_4K",
"PublicDescription": "This event counts load operations from a 4K page that miss the first DTLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "2000003",
"UMask": "0x20"
},
{
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"PublicDescription": "Completed page walks in any TLB of any page size due to demand load misses.",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
"SampleAfterValue": "2000003",
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x8"
},
{
"PublicDescription": "Completed page walks in any TLB of any page size due to demand load misses.",
"EventCode": "0x08",
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (2M/4M).",
"Counter": "0,1,2,3",
"UMask": "0xe",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"SampleAfterValue": "100003",
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB load misses.",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Completed page walks due to demand load misses that caused 2M/4M page walks in any TLB levels.",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Completed page walks due to demand load misses that caused 4K page walks in any TLB levels.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts load operations from a 4K page that miss the first DTLB level but hit the second and do not cause page walks.",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x20",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_4K",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
"PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB load misses.",
"SampleAfterValue": "2000003",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (4K)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x10"
},
{
"PublicDescription": "This event counts load operations from a 2M page that miss the first DTLB level but hit the second and do not cause page walks.",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x40",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_2M",
"SampleAfterValue": "2000003",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (2M)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Number of cache load STLB hits. No page walk.",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x60",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"SampleAfterValue": "2000003",
"BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "DTLB demand load misses with low part of linear-to-physical address translation missed.",
"EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x80",
"EventName": "DTLB_LOAD_MISSES.PDE_CACHE_MISS",
"SampleAfterValue": "100003",
"BriefDescription": "DTLB demand load misses with low part of linear-to-physical address translation missed",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Miss in all TLB levels causes a page walk of any page size (4K/2M/4M/1G).",
"EventCode": "0x49",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
"SampleAfterValue": "100003",
"BriefDescription": "Store misses in all DTLB levels that cause page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Completed page walks due to store misses in one or more TLB levels of 4K page structure.",
"EventCode": "0x49",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "Miss in all TLB levels causes a page walk of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"PublicDescription": "Completed page walks due to store misses in one or more TLB levels of 2M/4M page structure.",
"EventCode": "0x49",
"BriefDescription": "DTLB store misses with low part of linear-to-physical address translation missed",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.PDE_CACHE_MISS",
"PublicDescription": "DTLB store misses with low part of linear-to-physical address translation missed.",
"SampleAfterValue": "100003",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x80"
},
{
"EventCode": "0x49",
"BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks",
"Counter": "0,1,2,3",
"UMask": "0x8",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "100003",
"UMask": "0x60"
},
{
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (2M)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_2M",
"PublicDescription": "This event counts store operations from a 2M page that miss the first DTLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (4K)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_4K",
"PublicDescription": "This event counts store operations from a 4K page that miss the first DTLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"PublicDescription": "Completed page walks due to store miss in any TLB levels of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks. (1G)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
"SampleAfterValue": "100003",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks. (1G)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x8"
},
{
"PublicDescription": "Completed page walks due to store miss in any TLB levels of any page size (4K/2M/4M/1G).",
"EventCode": "0x49",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)",
"Counter": "0,1,2,3",
"UMask": "0xe",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Completed page walks due to store misses in one or more TLB levels of 2M/4M page structure.",
"SampleAfterValue": "100003",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x4"
},
{
"PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB store misses.",
"EventCode": "0x49",
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "DTLB_STORE_MISSES.WALK_DURATION",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Completed page walks due to store misses in one or more TLB levels of 4K page structure.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts store operations from a 4K page that miss the first DTLB level but hit the second and do not cause page walks.",
"EventCode": "0x49",
"Counter": "0,1,2,3",
"UMask": "0x20",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_4K",
"SampleAfterValue": "100003",
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (4K)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "This event counts store operations from a 2M page that miss the first DTLB level but hit the second and do not cause page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"Counter": "0,1,2,3",
"UMask": "0x40",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_2M",
"EventName": "DTLB_STORE_MISSES.WALK_DURATION",
"PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB store misses.",
"SampleAfterValue": "100003",
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (2M)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x10"
},
{
"PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
"EventCode": "0x49",
"BriefDescription": "Cycle count for an Extended Page table walk.",
"Counter": "0,1,2,3",
"UMask": "0x60",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"SampleAfterValue": "100003",
"BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "DTLB store misses with low part of linear-to-physical address translation missed.",
"EventCode": "0x49",
"Counter": "0,1,2,3",
"UMask": "0x80",
"EventName": "DTLB_STORE_MISSES.PDE_CACHE_MISS",
"SampleAfterValue": "100003",
"BriefDescription": "DTLB store misses with low part of linear-to-physical address translation missed",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x4f",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "EPT.WALK_CYCLES",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycle count for an Extended Page table walk.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x10"
},
{
"PublicDescription": "Misses in ITLB that causes a page walk of any page size.",
"EventCode": "0x85",
"BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xae",
"EventName": "ITLB.ITLB_FLUSH",
"PublicDescription": "Counts the number of ITLB flushes, includes 4k/2M/4M pages.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Misses at all ITLB levels that cause page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Completed page walks due to misses in ITLB 4K page entries.",
"EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "Misses in ITLB that causes a page walk of any page size.",
"SampleAfterValue": "100003",
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"PublicDescription": "Completed page walks due to misses in ITLB 2M/4M page entries.",
"EventCode": "0x85",
"BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT",
"PublicDescription": "ITLB misses that hit STLB. No page walk.",
"SampleAfterValue": "100003",
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x60"
},
{
"EventCode": "0x85",
"BriefDescription": "Code misses that miss the DTLB and hit the STLB (2M)",
"Counter": "0,1,2,3",
"UMask": "0x8",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT_2M",
"PublicDescription": "ITLB misses that hit STLB (2M).",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Core misses that miss the DTLB and hit the STLB (4K)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT_4K",
"PublicDescription": "ITLB misses that hit STLB (4K).",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Misses in all ITLB levels that cause completed page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"PublicDescription": "Completed page walks in ITLB of any page size.",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
"SampleAfterValue": "100003",
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (1G)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x8"
},
{
"PublicDescription": "Completed page walks in ITLB of any page size.",
"EventCode": "0x85",
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"Counter": "0,1,2,3",
"UMask": "0xe",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Completed page walks due to misses in ITLB 2M/4M page entries.",
"SampleAfterValue": "100003",
"BriefDescription": "Misses in all ITLB levels that cause completed page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x4"
},
{
"PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by ITLB misses.",
"EventCode": "0x85",
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "ITLB_MISSES.WALK_DURATION",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Completed page walks due to misses in ITLB 4K page entries.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "ITLB misses that hit STLB (4K).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x20",
"EventName": "ITLB_MISSES.STLB_HIT_4K",
"EventName": "ITLB_MISSES.WALK_DURATION",
"PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by ITLB misses.",
"SampleAfterValue": "100003",
"BriefDescription": "Core misses that miss the DTLB and hit the STLB (4K)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x10"
},
{
"PublicDescription": "ITLB misses that hit STLB (2M).",
"EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x40",
"EventName": "ITLB_MISSES.STLB_HIT_2M",
"SampleAfterValue": "100003",
"BriefDescription": "Code misses that miss the DTLB and hit the STLB (2M)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "ITLB misses that hit STLB. No page walk.",
"EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x60",
"EventName": "ITLB_MISSES.STLB_HIT",
"SampleAfterValue": "100003",
"BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Counts the number of ITLB flushes, includes 4k/2M/4M pages.",
"EventCode": "0xae",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "ITLB.ITLB_FLUSH",
"SampleAfterValue": "100003",
"BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PublicDescription": "Number of DTLB page walker loads that hit in the L1+FB.",
"EventCode": "0xBC",
"Counter": "0,1,2,3",
"UMask": "0x11",
"EventName": "PAGE_WALKER_LOADS.DTLB_L1",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of DTLB page walker hits in the L1+FB",
"CounterHTOff": "0,1,2,3"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L1",
"PublicDescription": "Number of DTLB page walker loads that hit in the L1+FB.",
"SampleAfterValue": "2000003",
"UMask": "0x11"
},
{
"PublicDescription": "Number of DTLB page walker loads that hit in the L2.",
"EventCode": "0xBC",
"Counter": "0,1,2,3",
"UMask": "0x12",
"EventName": "PAGE_WALKER_LOADS.DTLB_L2",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of DTLB page walker hits in the L2",
"CounterHTOff": "0,1,2,3"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L2",
"PublicDescription": "Number of DTLB page walker loads that hit in the L2.",
"SampleAfterValue": "2000003",
"UMask": "0x12"
},
{
"PublicDescription": "Number of DTLB page walker loads that hit in the L3.",
"EventCode": "0xBC",
"Counter": "0,1,2,3",
"UMask": "0x14",
"Errata": "HSD25",
"EventName": "PAGE_WALKER_LOADS.DTLB_L3",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP",
"CounterHTOff": "0,1,2,3"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"Errata": "HSD25",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L3",
"PublicDescription": "Number of DTLB page walker loads that hit in the L3.",
"SampleAfterValue": "2000003",
"UMask": "0x14"
},
{
"PublicDescription": "Number of DTLB page walker loads from memory.",
"EventCode": "0xBC",
"Counter": "0,1,2,3",
"UMask": "0x18",
"Errata": "HSD25",
"EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of DTLB page walker hits in Memory",
"CounterHTOff": "0,1,2,3"
},
{
"PublicDescription": "Number of ITLB page walker loads that hit in the L1+FB.",
"EventCode": "0xBC",
"Counter": "0,1,2,3",
"UMask": "0x21",
"EventName": "PAGE_WALKER_LOADS.ITLB_L1",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of ITLB page walker hits in the L1+FB",
"CounterHTOff": "0,1,2,3"
},
{
"PublicDescription": "Number of ITLB page walker loads that hit in the L2.",
"EventCode": "0xBC",
"Counter": "0,1,2,3",
"UMask": "0x22",
"EventName": "PAGE_WALKER_LOADS.ITLB_L2",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of ITLB page walker hits in the L2",
"CounterHTOff": "0,1,2,3"
},
{
"PublicDescription": "Number of ITLB page walker loads that hit in the L3.",
"EventCode": "0xBC",
"Counter": "0,1,2,3",
"UMask": "0x24",
"CounterHTOff": "0,1,2,3",
"Errata": "HSD25",
"EventName": "PAGE_WALKER_LOADS.ITLB_L3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
"PublicDescription": "Number of DTLB page walker loads from memory.",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP",
"CounterHTOff": "0,1,2,3"
"UMask": "0x18"
},
{
"PublicDescription": "Number of ITLB page walker loads from memory.",
"EventCode": "0xBC",
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L1 and FB.",
"Counter": "0,1,2,3",
"UMask": "0x28",
"Errata": "HSD25",
"EventName": "PAGE_WALKER_LOADS.ITLB_MEMORY",
"SampleAfterValue": "2000003",
"BriefDescription": "Number of ITLB page walker hits in Memory",
"CounterHTOff": "0,1,2,3"
},
{
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"Counter": "0,1,2,3",
"UMask": "0x41",
"EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L1",
"SampleAfterValue": "2000003",
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L1 and FB.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x41"
},
{
"EventCode": "0xBC",
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L2.",
"Counter": "0,1,2,3",
"UMask": "0x42",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L2",
"SampleAfterValue": "2000003",
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L2.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x42"
},
{
"EventCode": "0xBC",
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L3.",
"Counter": "0,1,2,3",
"UMask": "0x44",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L3",
"SampleAfterValue": "2000003",
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L3.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x44"
},
{
"EventCode": "0xBC",
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in memory.",
"Counter": "0,1,2,3",
"UMask": "0x48",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.EPT_DTLB_MEMORY",
"SampleAfterValue": "2000003",
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in memory.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x48"
},
{
"EventCode": "0xBC",
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L1 and FB.",
"Counter": "0,1,2,3",
"UMask": "0x81",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L1",
"SampleAfterValue": "2000003",
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L1 and FB.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x81"
},
{
"EventCode": "0xBC",
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
"Counter": "0,1,2,3",
"UMask": "0x82",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L2",
"SampleAfterValue": "2000003",
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x82"
},
{
"EventCode": "0xBC",
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
"Counter": "0,1,2,3",
"UMask": "0x84",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L3",
"SampleAfterValue": "2000003",
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x84"
},
{
"EventCode": "0xBC",
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in memory.",
"Counter": "0,1,2,3",
"UMask": "0x88",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.EPT_ITLB_MEMORY",
"SampleAfterValue": "2000003",
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in memory.",
"CounterHTOff": "0,1,2,3"
"UMask": "0x88"
},
{
"PublicDescription": "DTLB flush attempts of the thread-specific entries.",
"EventCode": "0xBD",
"BriefDescription": "Number of ITLB page walker hits in the L1+FB",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "TLB_FLUSH.DTLB_THREAD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L1",
"PublicDescription": "Number of ITLB page walker loads that hit in the L1+FB.",
"SampleAfterValue": "2000003",
"UMask": "0x21"
},
{
"BriefDescription": "Number of ITLB page walker hits in the L2",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L2",
"PublicDescription": "Number of ITLB page walker loads that hit in the L2.",
"SampleAfterValue": "2000003",
"UMask": "0x22"
},
{
"BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"Errata": "HSD25",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L3",
"PublicDescription": "Number of ITLB page walker loads that hit in the L3.",
"SampleAfterValue": "2000003",
"UMask": "0x24"
},
{
"BriefDescription": "Number of ITLB page walker hits in Memory",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"Errata": "HSD25",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_MEMORY",
"PublicDescription": "Number of ITLB page walker loads from memory.",
"SampleAfterValue": "2000003",
"UMask": "0x28"
},
{
"BriefDescription": "DTLB flush attempts of the thread-specific entries",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.DTLB_THREAD",
"PublicDescription": "DTLB flush attempts of the thread-specific entries.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"PublicDescription": "Count number of STLB flush attempts.",
"EventCode": "0xBD",
"Counter": "0,1,2,3",
"UMask": "0x20",
"EventName": "TLB_FLUSH.STLB_ANY",
"SampleAfterValue": "100003",
"BriefDescription": "STLB flush attempts",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.STLB_ANY",
"PublicDescription": "Count number of STLB flush attempts.",
"SampleAfterValue": "100003",
"UMask": "0x20"
}
]

1928
lib/libpmc/pmu-events/arch/x86/haswellx/cache.json
View File

File diff suppressed because it is too large Load Diff

138
lib/libpmc/pmu-events/arch/x86/haswellx/floating-point.json
View File

@ -1,83 +1,103 @@
[
{
"EventCode": "0xC1",
"UMask": "0x8",
"BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
"Counter": "0,1,2,3",
"EventName": "OTHER_ASSISTS.AVX_TO_SSE",
"Errata": "HSD56, HSM57",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC1",
"UMask": "0x10",
"BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
"Counter": "0,1,2,3",
"EventName": "OTHER_ASSISTS.SSE_TO_AVX",
"Errata": "HSD56, HSM57",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC6",
"UMask": "0x7",
"BriefDescription": "Approximate counts of AVX & AVX2 256-bit instructions, including non-arithmetic instructions, loads, and stores. May count non-AVX instructions that employ 256-bit operations, including (but not necessarily limited to) rep string instructions that use 256-bit loads and stores for optimized performance, XSAVE* and XRSTOR*, and operations that transition the x87 FPU data registers between x87 and MMX.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xC6",
"EventName": "AVX_INSTS.ALL",
"PublicDescription": "Note that a whole rep string only counts AVX_INST.ALL once.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x7"
},
{
"EventCode": "0xCA",
"UMask": "0x2",
"BriefDescription": "Number of X87 assists due to output value.",
"BriefDescription": "Cycles with any input/output SSE or FP assist",
"Counter": "0,1,2,3",
"EventName": "FP_ASSIST.X87_OUTPUT",
"PublicDescription": "Number of X87 FP assists due to output values.",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.ANY",
"PublicDescription": "Cycles with any input/output SSE* or FP assists.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1e"
},
{
"EventCode": "0xCA",
"UMask": "0x4",
"BriefDescription": "Number of X87 assists due to input value.",
"Counter": "0,1,2,3",
"EventName": "FP_ASSIST.X87_INPUT",
"PublicDescription": "Number of X87 FP assists due to input values.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xCA",
"UMask": "0x8",
"BriefDescription": "Number of SIMD FP assists due to Output values",
"Counter": "0,1,2,3",
"EventName": "FP_ASSIST.SIMD_OUTPUT",
"PublicDescription": "Number of SIMD FP assists due to output values.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xCA",
"UMask": "0x10",
"BriefDescription": "Number of SIMD FP assists due to input values",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.SIMD_INPUT",
"PublicDescription": "Number of SIMD FP assists due to input values.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x10"
},
{
"EventCode": "0xCA",
"UMask": "0x1e",
"BriefDescription": "Cycles with any input/output SSE or FP assist",
"BriefDescription": "Number of SIMD FP assists due to Output values",
"Counter": "0,1,2,3",
"EventName": "FP_ASSIST.ANY",
"CounterMask": "1",
"PublicDescription": "Cycles with any input/output SSE* or FP assists.",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.SIMD_OUTPUT",
"PublicDescription": "Number of SIMD FP assists due to output values.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x8"
},
{
"BriefDescription": "Number of X87 assists due to input value.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.X87_INPUT",
"PublicDescription": "Number of X87 FP assists due to input values.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of X87 assists due to output value.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xCA",
"EventName": "FP_ASSIST.X87_OUTPUT",
"PublicDescription": "Number of X87 FP assists due to output values.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of SIMD Move Elimination candidate uops that were eliminated.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x58",
"EventName": "MOVE_ELIMINATION.SIMD_ELIMINATED",
"PublicDescription": "Number of SIMD move elimination candidate uops that were eliminated.",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of SIMD Move Elimination candidate uops that were not eliminated.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x58",
"EventName": "MOVE_ELIMINATION.SIMD_NOT_ELIMINATED",
"PublicDescription": "Number of SIMD move elimination candidate uops that were not eliminated.",
"SampleAfterValue": "1000003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "HSD56, HSM57",
"EventCode": "0xC1",
"EventName": "OTHER_ASSISTS.AVX_TO_SSE",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"Errata": "HSD56, HSM57",
"EventCode": "0xC1",
"EventName": "OTHER_ASSISTS.SSE_TO_AVX",
"SampleAfterValue": "100003",
"UMask": "0x10"
}
]

484
lib/libpmc/pmu-events/arch/x86/haswellx/frontend.json
View File

@ -1,294 +1,304 @@
[
{
"EventCode": "0x79",
"UMask": "0x2",
"BriefDescription": "Instruction Decode Queue (IDQ) empty cycles",
"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": "IDQ.EMPTY",
"Errata": "HSD135",
"PublicDescription": "Counts cycles the IDQ is empty.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xe6",
"EventName": "BACLEARS.ANY",
"PublicDescription": "Number of front end re-steers due to BPU misprediction.",
"SampleAfterValue": "100003",
"UMask": "0x1f"
},
{
"EventCode": "0x79",
"UMask": "0x4",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
"Counter": "0,1,2,3",
"EventName": "IDQ.MITE_UOPS",
"PublicDescription": "Increment each cycle # of uops delivered to IDQ from MITE path. Set Cmask = 1 to count cycles.",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xAB",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x2"
},
{
"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",
"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": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.",
"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",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x10",
"BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"EventName": "IDQ.MS_DSB_UOPS",
"PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.",
"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",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EdgeDetect": "1",
"EventCode": "0x79",
"UMask": "0x10",
"BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.",
"Counter": "0,1,2,3",
"EventName": "IDQ.MS_DSB_OCCUR",
"CounterMask": "1",
"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 cycles DSB is delivered four uops. Set Cmask = 4.",
"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 cycles DSB is delivered at least one uops. Set Cmask = 1.",
"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": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.",
"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 cycles MITE is delivered four uops. Set Cmask = 4.",
"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 cycles MITE is delivered at least one uop. Set Cmask = 1.",
"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": "This event counts uops delivered by the Front-end with the assistance of the microcode sequencer. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance.",
"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": "This event counts cycles during which the microcode sequencer assisted the Front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance.",
"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",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x3c",
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"EventName": "IDQ.MITE_ALL_UOPS",
"PublicDescription": "Number of uops delivered to IDQ from any path.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x80",
"UMask": "0x1",
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.HIT",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"UMask": "0x2",
"EventName": "ICACHE.IFDATA_STALL",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.IFETCH_STALL",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Misses. Includes Uncacheable accesses.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.MISSES",
"PublicDescription": "This event counts Instruction Cache (ICACHE) misses.",
"SampleAfterValue": "200003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x2"
},
{
"EventCode": "0x80",
"UMask": "0x4",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
"Counter": "0,1,2,3",
"EventName": "ICACHE.IFETCH_STALL",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
"PublicDescription": "Counts cycles DSB is delivered four uops. Set Cmask = 4.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x18"
},
{
"EventCode": "0x80",
"UMask": "0x4",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"Counter": "0,1,2,3",
"EventName": "ICACHE.IFDATA_STALL",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
"PublicDescription": "Counts cycles DSB is delivered at least one uops. Set Cmask = 1.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x18"
},
{
"BriefDescription": "Cycles MITE is delivering 4 Uops",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
"PublicDescription": "Counts cycles MITE is delivered four uops. Set Cmask = 4.",
"SampleAfterValue": "2000003",
"UMask": "0x24"
},
{
"BriefDescription": "Cycles MITE is delivering any Uop",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
"PublicDescription": "Counts cycles MITE is delivered at least one uop. Set Cmask = 1.",
"SampleAfterValue": "2000003",
"UMask": "0x24"
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
"PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Instruction Decode Queue (IDQ) empty cycles",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"Errata": "HSD135",
"EventCode": "0x79",
"EventName": "IDQ.EMPTY",
"PublicDescription": "Counts cycles the IDQ is empty.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MITE_ALL_UOPS",
"PublicDescription": "Number of uops delivered to IDQ from any path.",
"SampleAfterValue": "2000003",
"UMask": "0x3c"
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
"PublicDescription": "Increment each cycle # of uops delivered to IDQ from MITE path. Set Cmask = 1 to count cycles.",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_CYCLES",
"PublicDescription": "This event counts cycles during which the microcode sequencer assisted the Front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance.",
"SampleAfterValue": "2000003",
"UMask": "0x30"
},
{
"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",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_CYCLES",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_OCCUR",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_DSB_UOPS",
"PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_MITE_UOPS",
"PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.",
"SampleAfterValue": "2000003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_SWITCHES",
"SampleAfterValue": "2000003",
"UMask": "0x30"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x79",
"EventName": "IDQ.MS_UOPS",
"PublicDescription": "This event counts uops delivered by the Front-end with the assistance of the microcode sequencer. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance.",
"SampleAfterValue": "2000003",
"UMask": "0x30"
},
{
"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",
"CounterHTOff": "0,1,2,3",
"Errata": "HSD135",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
"PublicDescription": "This event count the number of undelivered (unallocated) uops from the Front-end to the Resource Allocation Table (RAT) while the Back-end of the processor is not stalled. The Front-end can allocate up to 4 uops per cycle so this event can increment 0-4 times per cycle depending on the number of unallocated uops. This event is counted on a per-core basis.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x1"
},
{
"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",
"CounterHTOff": "0,1,2,3",
"CounterMask": "4",
"Errata": "HSD135",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
"PublicDescription": "This event counts the number cycles during which the Front-end allocated exactly zero uops to the Resource Allocation Table (RAT) while the Back-end of the processor is not stalled. This event is counted on a per-core basis.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x1"
},
{
"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",
"Errata": "HSD135",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"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",
"Errata": "HSD135",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"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",
"Errata": "HSD135",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"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",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"Errata": "HSD135",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"Invert": "1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x1"
},
{
"EventCode": "0xAB",
"UMask": "0x2",
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
"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": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"CounterHTOff": "0,1,2,3",
"CounterMask": "3",
"Errata": "HSD135",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "2",
"Errata": "HSD135",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"CounterMask": "1",
"Errata": "HSD135",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
"SampleAfterValue": "2000003",
"UMask": "0x1"
}
]

265
lib/libpmc/pmu-events/arch/x86/haswellx/hsx-metrics.json
View File

@ -1,172 +1,125 @@
[
{
"BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Frontend_Bound",
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound."
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound."
},
{
"BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Frontend_Bound_SMT",
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
"PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Bad_Speculation",
"PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example."
},
{
"BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Bad_Speculation_SMT",
"PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * CPU_CLK_UNHALTED.THREAD)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)) )",
"MetricGroup": "TopdownL1",
"MetricName": "Backend_Bound",
"PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound."
},
{
"BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) )",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Backend_Bound_SMT",
"PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "TopdownL1",
"MetricName": "Retiring",
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. "
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. "
},
{
"BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopdownL1_SMT",
"MetricName": "Retiring_SMT",
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU."
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. SMT version; use when SMT is enabled and measuring per logical CPU."
},
{
"BriefDescription": "Instructions Per Cycle (per Logical Processor)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "TopDownL1",
"MetricGroup": "Ret;Summary",
"MetricName": "IPC"
},
{
"BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
"MetricGroup": "Pipeline;Retire",
"MetricGroup": "Pipeline;Ret;Retire",
"MetricName": "UPI"
},
{
"BriefDescription": "Instruction per taken branch",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fetch_BW;PGO",
"MetricName": "IpTB"
},
{
"BriefDescription": "Branch instructions per taken branch. ",
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;PGO",
"MetricName": "BpTB"
},
{
"BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
"MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
"MetricGroup": "PGO;IcMiss",
"MetricName": "IFetch_Line_Utilization"
},
{
"BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
"MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
"MetricGroup": "DSB;Fetch_BW",
"MetricName": "DSB_Coverage"
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW",
"MetricName": "UpTB"
},
{
"BriefDescription": "Cycles Per Instruction (per Logical Processor)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
"MetricGroup": "Pipeline;Summary",
"MetricExpr": "1 / (INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "Pipeline;Mem",
"MetricName": "CPI"
},
{
"BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Summary",
"MetricGroup": "Pipeline",
"MetricName": "CLKS"
},
{
"BriefDescription": "Total issue-pipeline slots (per-Physical Core)",
"MetricExpr": "4 * cycles",
"MetricGroup": "TopDownL1",
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
"MetricExpr": "4 * CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "TmaL1",
"MetricName": "SLOTS"
},
{
"BriefDescription": "Total issue-pipeline slots (per-Physical Core)",
"MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TopDownL1_SMT",
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
"MetricExpr": "4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "TmaL1_SMT",
"MetricName": "SLOTS_SMT"
},
{
"BriefDescription": "Instructions per Load (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
"MetricGroup": "Instruction_Type",
"MetricName": "IpL"
},
{
"BriefDescription": "Instructions per Store (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
"MetricGroup": "Instruction_Type",
"MetricName": "IpS"
},
{
"BriefDescription": "Instructions per Branch (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Branches;Instruction_Type",
"MetricName": "IpB"
},
{
"BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
"MetricGroup": "Branches",
"MetricName": "IpCall"
},
{
"BriefDescription": "Total number of retired Instructions",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
"BriefDescription": "Instructions Per Cycle (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / cycles",
"MetricGroup": "SMT",
"BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Ret;SMT;TmaL1",
"MetricName": "CoreIPC"
},
{
"BriefDescription": "Instructions Per Cycle (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "SMT",
"BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "Ret;SMT;TmaL1_SMT",
"MetricName": "CoreIPC_SMT"
},
{
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
"MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
"MetricGroup": "Pipeline",
"MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
"MetricName": "ILP"
},
{
"BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "BrMispredicts",
"MetricGroup": "Bad;BadSpec;BrMispredicts",
"MetricName": "IpMispredict"
},
{
@ -176,83 +129,127 @@
"MetricName": "CORE_CLKS"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
"MetricGroup": "InsType",
"MetricName": "IpLoad"
},
{
"BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
"MetricGroup": "InsType",
"MetricName": "IpStore"
},
{
"BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Branches;Fed;InsType",
"MetricName": "IpBranch"
},
{
"BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "IpCall"
},
{
"BriefDescription": "Instruction per taken branch",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO",
"MetricName": "IpTB"
},
{
"BriefDescription": "Branch instructions per taken branch. ",
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "BpTkBranch"
},
{
"BriefDescription": "Total number of retired Instructions, Sample with: INST_RETIRED.PREC_DIST",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary;TmaL1",
"MetricName": "Instructions"
},
{
"BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
"MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
"MetricGroup": "DSB;Fed;FetchBW",
"MetricName": "DSB_Coverage"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles)",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
"MetricGroup": "Mem;MemoryBound;MemoryLat",
"MetricName": "Load_Miss_Real_Latency",
"PublicDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles). Latency may be overestimated for multi-load instructions - e.g. repeat strings."
},
{
"BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
"MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
"MetricGroup": "Memory_Bound;Memory_BW",
"MetricGroup": "Mem;MemoryBound;MemoryBW",
"MetricName": "MLP"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles",
"MetricGroup": "TLB",
"MetricName": "Page_Walks_Utilization"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
"MetricGroup": "TLB_SMT",
"MetricName": "Page_Walks_Utilization_SMT"
},
{
"BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
"MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
"MetricGroup": "Memory_BW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L1D_Cache_Fill_BW"
},
{
"BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
"MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
"MetricGroup": "Memory_BW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L2_Cache_Fill_BW"
},
{
"BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
"MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
"MetricGroup": "Memory_BW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L3_Cache_Fill_BW"
},
{
"BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L1MPKI"
},
{
"BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;Backend;CacheMisses",
"MetricName": "L2MPKI"
},
{
"BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricName": "L2MPKI_All"
},
{
"BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricName": "L2HPKI_All"
},
{
"BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
"MetricGroup": "Cache_Misses",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L3MPKI"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Mem;MemoryTLB",
"MetricName": "Page_Walks_Utilization"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"MetricGroup": "Mem;MemoryTLB_SMT",
"MetricName": "Page_Walks_Utilization_SMT"
},
{
"BriefDescription": "Average CPU Utilization",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
"MetricGroup": "Summary",
"MetricGroup": "HPC;Summary",
"MetricName": "CPU_Utilization"
},
{
"BriefDescription": "Measured Average Frequency for unhalted processors [GHz]",
"MetricExpr": "(CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time",
"MetricGroup": "Summary;Power",
"MetricName": "Average_Frequency"
},
{
"BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
@ -261,40 +258,52 @@
},
{
"BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
"MetricGroup": "SMT;Summary",
"MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
"MetricGroup": "SMT",
"MetricName": "SMT_2T_Utilization"
},
{
"BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Summary",
"BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "OS",
"MetricName": "Kernel_Utilization"
},
{
"BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
"MetricGroup": "OS",
"MetricName": "Kernel_CPI"
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
"MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
"MetricGroup": "Memory_BW",
"MetricGroup": "HPC;Mem;MemoryBW;SoC",
"MetricName": "DRAM_BW_Use"
},
{
"BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
"MetricExpr": "1000000000 * ( cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x35\\,umask\\=0x3\\,filter_opc\\=0x182@ ) / ( cbox_0@event\\=0x0@ / duration_time )",
"MetricGroup": "Memory_Lat",
"MetricName": "DRAM_Read_Latency"
"MetricGroup": "Mem;MemoryLat;SoC",
"MetricName": "MEM_Read_Latency"
},
{
"BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
"MetricExpr": "cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182\\,thresh\\=1@",
"MetricGroup": "Memory_BW",
"MetricName": "DRAM_Parallel_Reads"
"MetricGroup": "Mem;MemoryBW;SoC",
"MetricName": "MEM_Parallel_Reads"
},
{
"BriefDescription": "Socket actual clocks when any core is active on that socket",
"MetricExpr": "cbox_0@event\\=0x0@",
"MetricGroup": "",
"MetricGroup": "SoC",
"MetricName": "Socket_CLKS"
},
{
"BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
"MetricGroup": "Branches;OS",
"MetricName": "IpFarBranch"
},
{
"BriefDescription": "C3 residency percent per core",
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",

1288
lib/libpmc/pmu-events/arch/x86/haswellx/memory.json
View File

File diff suppressed because it is too large Load Diff

28
lib/libpmc/pmu-events/arch/x86/haswellx/other.json
View File

@ -1,43 +1,43 @@
[
{
"EventCode": "0x5C",
"UMask": "0x1",
"BriefDescription": "Unhalted core cycles when the thread is in ring 0",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING0",
"PublicDescription": "Unhalted core cycles when the thread is in ring 0.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"EdgeDetect": "1",
"EventCode": "0x5C",
"UMask": "0x1",
"BriefDescription": "Number of intervals between processor halts while thread is in ring 0.",
"Counter": "0,1,2,3",
"EventName": "CPL_CYCLES.RING0_TRANS",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING0_TRANS",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"EventCode": "0x5C",
"UMask": "0x2",
"BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x5C",
"EventName": "CPL_CYCLES.RING123",
"PublicDescription": "Unhalted core cycles when the thread is not in ring 0.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x2"
},
{
"EventCode": "0x63",
"UMask": "0x1",
"BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x63",
"EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION",
"PublicDescription": "Cycles in which the L1D and L2 are locked, due to a UC lock or split lock.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
}
]

2431
lib/libpmc/pmu-events/arch/x86/haswellx/pipeline.json
View File

File diff suppressed because it is too large Load Diff

696
lib/libpmc/pmu-events/arch/x86/haswellx/virtual-memory.json
View File

@ -1,484 +1,484 @@
[
{
"EventCode": "0x08",
"UMask": "0x1",
"BriefDescription": "Load misses in all DTLB levels that cause page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "Misses in all TLB levels that cause a page walk of any page size.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"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": "Completed page walks due to demand load misses that caused 4K page walks in any TLB levels.",
"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": "Completed page walks due to demand load misses that caused 2M/4M page walks in any TLB levels.",
"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",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0xe",
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"PublicDescription": "Completed page walks in any TLB of any page size due to demand load misses.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x10",
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
"PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB load misses.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x20",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (4K)",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_4K",
"PublicDescription": "This event counts load operations from a 4K page that miss the first DTLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x40",
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (2M)",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_2M",
"PublicDescription": "This event counts load operations from a 2M page that miss the first DTLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x60",
"BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks",
"Counter": "0,1,2,3",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"PublicDescription": "Number of cache load STLB hits. No page walk.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x08",
"UMask": "0x80",
"BriefDescription": "DTLB demand load misses with low part of linear-to-physical address translation missed",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.PDE_CACHE_MISS",
"PublicDescription": "DTLB demand load misses with low part of linear-to-physical address translation missed.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x80"
},
{
"BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"PublicDescription": "Number of cache load STLB hits. No page walk.",
"SampleAfterValue": "2000003",
"UMask": "0x60"
},
{
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (2M)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_2M",
"PublicDescription": "This event counts load operations from a 2M page that miss the first DTLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "2000003",
"UMask": "0x40"
},
{
"BriefDescription": "Load misses that miss the DTLB and hit the STLB (4K)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT_4K",
"PublicDescription": "This event counts load operations from a 4K page that miss the first DTLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "2000003",
"UMask": "0x20"
},
{
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"PublicDescription": "Completed page walks in any TLB of any page size due to demand load misses.",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (2M/4M).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Completed page walks due to demand load misses that caused 2M/4M page walks in any TLB levels.",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Completed page walks due to demand load misses that caused 4K page walks in any TLB levels.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
"PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB load misses.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"EventCode": "0x49",
"UMask": "0x1",
"BriefDescription": "Store misses in all DTLB levels that cause page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "Miss in all TLB levels causes a page walk of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"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": "Completed page walks due to store misses in one or more TLB levels of 4K page structure.",
"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": "Completed page walks due to store misses in one or more TLB levels of 2M/4M page structure.",
"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",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0xe",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"PublicDescription": "Completed page walks due to store miss in any TLB levels of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0x10",
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.WALK_DURATION",
"PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB store misses.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0x20",
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (4K)",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_4K",
"PublicDescription": "This event counts store operations from a 4K page that miss the first DTLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0x40",
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (2M)",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_2M",
"PublicDescription": "This event counts store operations from a 2M page that miss the first DTLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0x60",
"BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks",
"Counter": "0,1,2,3",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x49",
"UMask": "0x80",
"BriefDescription": "DTLB store misses with low part of linear-to-physical address translation missed",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.PDE_CACHE_MISS",
"PublicDescription": "DTLB store misses with low part of linear-to-physical address translation missed.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x80"
},
{
"EventCode": "0x4f",
"UMask": "0x10",
"BriefDescription": "Cycle count for an Extended Page table walk.",
"BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks",
"Counter": "0,1,2,3",
"EventName": "EPT.WALK_CYCLES",
"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": "Misses in ITLB that causes a page walk of any page size.",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x60"
},
{
"EventCode": "0x85",
"UMask": "0x2",
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (2M)",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Completed page walks due to misses in ITLB 4K page entries.",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_2M",
"PublicDescription": "This event counts store operations from a 2M page that miss the first DTLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x40"
},
{
"EventCode": "0x85",
"UMask": "0x4",
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"BriefDescription": "Store misses that miss the DTLB and hit the STLB (4K)",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Completed page walks due to misses in ITLB 2M/4M page entries.",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT_4K",
"PublicDescription": "This event counts store operations from a 4K page that miss the first DTLB level but hit the second and do not cause page walks.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x20"
},
{
"EventCode": "0x85",
"UMask": "0x8",
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (1G)",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"PublicDescription": "Completed page walks due to store miss in any TLB levels of any page size (4K/2M/4M/1G).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0xe"
},
{
"EventCode": "0x85",
"UMask": "0xe",
"BriefDescription": "Misses in all ITLB levels that cause completed page walks",
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks. (1G)",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"PublicDescription": "Completed page walks in ITLB of any page size.",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x8"
},
{
"BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Completed page walks due to store misses in one or more TLB levels of 2M/4M page structure.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Completed page walks due to store misses in one or more TLB levels of 4K page structure.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"EventCode": "0x85",
"UMask": "0x10",
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.WALK_DURATION",
"PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by ITLB misses.",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_DURATION",
"PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB store misses.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x10"
},
{
"EventCode": "0x85",
"UMask": "0x20",
"BriefDescription": "Core misses that miss the DTLB and hit the STLB (4K)",
"BriefDescription": "Cycle count for an Extended Page table walk.",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.STLB_HIT_4K",
"PublicDescription": "ITLB misses that hit STLB (4K).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x4f",
"EventName": "EPT.WALK_CYCLES",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"EventCode": "0x85",
"UMask": "0x40",
"BriefDescription": "Code misses that miss the DTLB and hit the STLB (2M)",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.STLB_HIT_2M",
"PublicDescription": "ITLB misses that hit STLB (2M).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x85",
"UMask": "0x60",
"BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks",
"Counter": "0,1,2,3",
"EventName": "ITLB_MISSES.STLB_HIT",
"PublicDescription": "ITLB misses that hit STLB. No page walk.",
"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",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xae",
"EventName": "ITLB.ITLB_FLUSH",
"PublicDescription": "Counts the number of ITLB flushes, includes 4k/2M/4M pages.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"BriefDescription": "Misses at all ITLB levels that cause page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
"PublicDescription": "Misses in ITLB that causes a page walk of any page size.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT",
"PublicDescription": "ITLB misses that hit STLB. No page walk.",
"SampleAfterValue": "100003",
"UMask": "0x60"
},
{
"BriefDescription": "Code misses that miss the DTLB and hit the STLB (2M)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT_2M",
"PublicDescription": "ITLB misses that hit STLB (2M).",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Core misses that miss the DTLB and hit the STLB (4K)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT_4K",
"PublicDescription": "ITLB misses that hit STLB (4K).",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Misses in all ITLB levels that cause completed page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"PublicDescription": "Completed page walks in ITLB of any page size.",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (1G)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Completed page walks due to misses in ITLB 2M/4M page entries.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Completed page walks due to misses in ITLB 4K page entries.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when PMH is busy with page walks",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_DURATION",
"PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by ITLB misses.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"EventCode": "0xBC",
"UMask": "0x11",
"BriefDescription": "Number of DTLB page walker hits in the L1+FB",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L1",
"PublicDescription": "Number of DTLB page walker loads that hit in the L1+FB.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x11"
},
{
"EventCode": "0xBC",
"UMask": "0x12",
"BriefDescription": "Number of DTLB page walker hits in the L2",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L2",
"PublicDescription": "Number of DTLB page walker loads that hit in the L2.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x12"
},
{
"EventCode": "0xBC",
"UMask": "0x14",
"BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.DTLB_L3",
"CounterHTOff": "0,1,2,3",
"Errata": "HSD25",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_L3",
"PublicDescription": "Number of DTLB page walker loads that hit in the L3.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x14"
},
{
"EventCode": "0xBC",
"UMask": "0x18",
"BriefDescription": "Number of DTLB page walker hits in Memory",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
"CounterHTOff": "0,1,2,3",
"Errata": "HSD25",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
"PublicDescription": "Number of DTLB page walker loads from memory.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x18"
},
{
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L1 and FB.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"UMask": "0x21",
"EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L1",
"SampleAfterValue": "2000003",
"UMask": "0x41"
},
{
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L2.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L2",
"SampleAfterValue": "2000003",
"UMask": "0x42"
},
{
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L3.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L3",
"SampleAfterValue": "2000003",
"UMask": "0x44"
},
{
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in memory.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.EPT_DTLB_MEMORY",
"SampleAfterValue": "2000003",
"UMask": "0x48"
},
{
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L1 and FB.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L1",
"SampleAfterValue": "2000003",
"UMask": "0x81"
},
{
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L2",
"SampleAfterValue": "2000003",
"UMask": "0x82"
},
{
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L3",
"SampleAfterValue": "2000003",
"UMask": "0x84"
},
{
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in memory.",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.EPT_ITLB_MEMORY",
"SampleAfterValue": "2000003",
"UMask": "0x88"
},
{
"BriefDescription": "Number of ITLB page walker hits in the L1+FB",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L1",
"PublicDescription": "Number of ITLB page walker loads that hit in the L1+FB.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x21"
},
{
"EventCode": "0xBC",
"UMask": "0x22",
"BriefDescription": "Number of ITLB page walker hits in the L2",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L2",
"PublicDescription": "Number of ITLB page walker loads that hit in the L2.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x22"
},
{
"EventCode": "0xBC",
"UMask": "0x24",
"BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.ITLB_L3",
"CounterHTOff": "0,1,2,3",
"Errata": "HSD25",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_L3",
"PublicDescription": "Number of ITLB page walker loads that hit in the L3.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x24"
},
{
"EventCode": "0xBC",
"UMask": "0x28",
"BriefDescription": "Number of ITLB page walker hits in Memory",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.ITLB_MEMORY",
"CounterHTOff": "0,1,2,3",
"Errata": "HSD25",
"EventCode": "0xBC",
"EventName": "PAGE_WALKER_LOADS.ITLB_MEMORY",
"PublicDescription": "Number of ITLB page walker loads from memory.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
"UMask": "0x28"
},
{
"EventCode": "0xBC",
"UMask": "0x41",
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L1 and FB.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xBC",
"UMask": "0x42",
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L2.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L2",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xBC",
"UMask": "0x44",
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L3.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L3",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xBC",
"UMask": "0x48",
"BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in memory.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.EPT_DTLB_MEMORY",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xBC",
"UMask": "0x81",
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L1 and FB.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xBC",
"UMask": "0x82",
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L2",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xBC",
"UMask": "0x84",
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L3",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xBC",
"UMask": "0x88",
"BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in memory.",
"Counter": "0,1,2,3",
"EventName": "PAGE_WALKER_LOADS.EPT_ITLB_MEMORY",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xBD",
"UMask": "0x1",
"BriefDescription": "DTLB flush attempts of the thread-specific entries",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.DTLB_THREAD",
"PublicDescription": "DTLB flush attempts of the thread-specific entries.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x1"
},
{
"EventCode": "0xBD",
"UMask": "0x20",
"BriefDescription": "STLB flush attempts",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.STLB_ANY",
"PublicDescription": "Count number of STLB flush attempts.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"UMask": "0x20"
}
]

1662
lib/libpmc/pmu-events/arch/x86/icelake/cache.json
View File

File diff suppressed because it is too large Load Diff

169
lib/libpmc/pmu-events/arch/x86/icelake/floating-point.json
View File

@ -1,85 +1,4 @@
[
{
"BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. 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 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Counts all microcode FP assists.",
"CollectPEBSRecord": "2",
@ -91,5 +10,93 @@
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. 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 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. 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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x2"
}
]

745
lib/libpmc/pmu-events/arch/x86/icelake/frontend.json
View File

@ -11,214 +11,6 @@
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced DSB miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x11",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles MITE is delivering optimal number of Uops",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "5",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_OK",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Retired Instructions who experienced iTLB true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x14",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"CounterMask": "5",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "ICACHE_16B.IFDATA_STALL",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts 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": "500009",
"Speculative": "1",
"UMask": "0x4"
},
{
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
"MSRIndex": "0x3F7",
"MSRValue": "0x510006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_ANY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x8"
},
{
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x100206",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "DSB-to-MITE switch true penalty cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xab",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.STLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x15",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x4"
},
{
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
"MSRIndex": "0x3F7",
"MSRValue": "0x504006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
"MSRIndex": "0x3F7",
"MSRValue": "0x502006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles MITE is delivering any Uop",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_ANY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
"MSRIndex": "0x3F7",
"MSRValue": "0x500206",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE transitions count.",
"CollectPEBSRecord": "2",
@ -234,16 +26,76 @@
"UMask": "0x2"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"BriefDescription": "DSB-to-MITE switch true penalty cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
"EventCode": "0xab",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x8"
"UMask": "0x2"
},
{
"BriefDescription": "Retired Instructions who experienced DSB miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x1",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced a critical DSB miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x11",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced iTLB true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x14",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L1I_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x12",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
@ -260,92 +112,6 @@
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_HIT",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity. Accounts for both cacheable and uncacheable accesses.",
"SampleAfterValue": "200003",
"Speculative": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
"MSRIndex": "0x3F7",
"MSRValue": "0x520006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"Invert": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
"SampleAfterValue": "1000003",
"Speculative": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
"MSRIndex": "0x3F7",
"MSRValue": "0x501006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
"MSRIndex": "0x3F7",
"MSRValue": "0x508006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
"MSRIndex": "0x3F7",
"MSRValue": "0x500806",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle",
"CollectPEBSRecord": "2",
@ -361,6 +127,96 @@
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
"MSRIndex": "0x3F7",
"MSRValue": "0x508006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
"MSRIndex": "0x3F7",
"MSRValue": "0x501006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
"MSRIndex": "0x3F7",
"MSRValue": "0x500206",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
"MSRIndex": "0x3F7",
"MSRValue": "0x510006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x100206",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
"MSRIndex": "0x3F7",
"MSRValue": "0x502006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
@ -376,6 +232,203 @@
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
"MSRIndex": "0x3F7",
"MSRValue": "0x520006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
"MSRIndex": "0x3F7",
"MSRValue": "0x504006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
"MSRIndex": "0x3F7",
"MSRValue": "0x500806",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.STLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x15",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "ICACHE_16B.IFDATA_STALL",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts 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": "500009",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_HIT",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity. Accounts for both cacheable and uncacheable accesses.",
"SampleAfterValue": "200003",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_MISS",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity. Accounts for both cacheable and uncacheable accesses.",
"SampleAfterValue": "200003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_STALL",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"SampleAfterValue": "200003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_ANY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles DSB is delivering optimal number of Uops",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "5",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_OK",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x8"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles MITE is delivering any Uop",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_ANY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles MITE is delivering optimal number of Uops",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "5",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_OK",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_CYCLES_ANY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x30"
},
{
"BriefDescription": "Number of switches from DSB or MITE to the MS",
"CollectPEBSRecord": "2",
@ -390,18 +443,6 @@
"Speculative": "1",
"UMask": "0x30"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_STALL",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"SampleAfterValue": "200003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Uops delivered to IDQ while MS is busy",
"CollectPEBSRecord": "2",
@ -414,59 +455,6 @@
"Speculative": "1",
"UMask": "0x30"
},
{
"BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_MISS",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity. Accounts for both cacheable and uncacheable accesses.",
"SampleAfterValue": "200003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_CYCLES_ANY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x30"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L1I_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x12",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles DSB is delivering optimal number of Uops",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "5",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_OK",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x8"
},
{
"BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled",
"CollectPEBSRecord": "2",
@ -478,5 +466,32 @@
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"CounterMask": "5",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"Invert": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x1"
}
]

364
lib/libpmc/pmu-events/arch/x86/icelake/icl-metrics.json
View File

@ -1,273 +1,453 @@
[
{
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)",
"MetricExpr": "100 * (( BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) ) / TOPDOWN.SLOTS)",
"MetricGroup": "Ret",
"MetricName": "Branching_Overhead"
},
{
"BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
"MetricExpr": "100 * (( 5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING ) / TOPDOWN.SLOTS) * ( (ICACHE_64B.IFTAG_STALL / CPU_CLK_UNHALTED.THREAD) + (ICACHE_16B.IFDATA_STALL / CPU_CLK_UNHALTED.THREAD) + (10 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) ) / #(( 5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING ) / TOPDOWN.SLOTS)",
"MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB",
"MetricName": "Big_Code"
},
{
"BriefDescription": "Instructions Per Cycle (per Logical Processor)",
"MetricGroup": "Summary",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Ret;Summary",
"MetricName": "IPC"
},
{
"MetricExpr": "UOPS_RETIRED.SLOTS / INST_RETIRED.ANY",
"BriefDescription": "Uops Per Instruction",
"MetricGroup": "Pipeline;Retire",
"MetricName": "UPI"
},
{
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"BriefDescription": "Instruction per taken branch",
"MetricGroup": "Branches;FetchBW;PGO",
"MetricName": "IpTB"
},
{
"MetricExpr": "1 / (INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD)",
"BriefDescription": "Cycles Per Instruction (per Logical Processor)",
"MetricGroup": "Pipeline",
"MetricExpr": "1 / (INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "Pipeline;Mem",
"MetricName": "CPI"
},
{
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
"BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Pipeline",
"MetricName": "CLKS"
},
{
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
"MetricExpr": "TOPDOWN.SLOTS",
"MetricGroup": "TmaL1",
"MetricName": "SLOTS"
},
{
"BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
"MetricExpr": "TOPDOWN.SLOTS / ( TOPDOWN.SLOTS / 2 ) if #SMT_on else 1",
"MetricGroup": "SMT",
"MetricName": "Slots_Utilization"
},
{
"BriefDescription": "The ratio of Executed- by Issued-Uops",
"MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
"MetricGroup": "Cor;Pipeline",
"MetricName": "Execute_per_Issue",
"PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
},
{
"BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.DISTRIBUTED",
"BriefDescription": "Instructions Per Cycle (per physical core)",
"MetricGroup": "SMT;TmaL1",
"MetricGroup": "Ret;SMT;TmaL1",
"MetricName": "CoreIPC"
},
{
"MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / CPU_CLK_UNHALTED.DISTRIBUTED",
"BriefDescription": "Floating Point Operations Per Cycle",
"MetricGroup": "Flops",
"MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / CPU_CLK_UNHALTED.DISTRIBUTED",
"MetricGroup": "Ret;Flops",
"MetricName": "FLOPc"
},
{
"MetricExpr": "UOPS_EXECUTED.THREAD / ( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 )",
"BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width)",
"MetricExpr": "( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) ) / ( 2 * CPU_CLK_UNHALTED.DISTRIBUTED )",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "FP_Arith_Utilization",
"PublicDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). Values > 1 are possible due to Fused-Multiply Add (FMA) counting."
},
{
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
"MetricGroup": "Pipeline;PortsUtil",
"MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
"MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
"MetricName": "ILP"
},
{
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
"BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
"MetricGroup": "BrMispredicts",
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;BadSpec;BrMispredicts",
"MetricName": "IpMispredict"
},
{
"MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED",
"BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
"MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS"
},
{
"MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
"BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
"MetricGroup": "InsType",
"MetricName": "IpLoad"
},
{
"MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
"BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
"MetricGroup": "InsType",
"MetricName": "IpStore"
},
{
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
"MetricGroup": "Branches;InsType",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Branches;Fed;InsType",
"MetricName": "IpBranch"
},
{
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
"BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
"MetricGroup": "Branches",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "IpCall"
},
{
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"BriefDescription": "Instruction per taken branch",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO",
"MetricName": "IpTB"
},
{
"BriefDescription": "Branch instructions per taken branch. ",
"MetricGroup": "Branches;PGO",
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "BpTkBranch"
},
{
"MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )",
"BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
"MetricGroup": "Flops;FpArith;InsType",
"MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )",
"MetricGroup": "Flops;InsType",
"MetricName": "IpFLOP"
},
{
"BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) )",
"MetricGroup": "Flops;InsType",
"MetricName": "IpArith",
"PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW."
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "IpArith_Scalar_SP",
"PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "IpArith_Scalar_DP",
"PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "IpArith_AVX128",
"PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "IpArith_AVX256",
"PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "IpArith_AVX512",
"PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Total number of retired Instructions, Sample with: INST_RETIRED.PREC_DIST",
"MetricExpr": "INST_RETIRED.ANY",
"BriefDescription": "Total number of retired Instructions",
"MetricGroup": "Summary;TmaL1",
"MetricName": "Instructions"
},
{
"MetricExpr": "LSD.UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
"BriefDescription": "Average number of Uops issued by front-end when it issued something",
"MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
"MetricGroup": "Fed;FetchBW",
"MetricName": "Fetch_UpC"
},
{
"BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
"MetricGroup": "LSD",
"MetricExpr": "LSD.UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
"MetricGroup": "Fed;LSD",
"MetricName": "LSD_Coverage"
},
{
"MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
"BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
"MetricGroup": "DSB;FetchBW",
"MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
"MetricGroup": "DSB;Fed;FetchBW",
"MetricName": "DSB_Coverage"
},
{
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"MetricGroup": "MemoryBound;MemoryLat",
"MetricName": "Load_Miss_Real_Latency"
"BriefDescription": "Number of Instructions per non-speculative DSB miss",
"MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
"MetricGroup": "DSBmiss;Fed",
"MetricName": "IpDSB_Miss_Ret"
},
{
"BriefDescription": "Fraction of branches that are non-taken conditionals",
"MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;Branches;CodeGen;PGO",
"MetricName": "Cond_NT"
},
{
"BriefDescription": "Fraction of branches that are taken conditionals",
"MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;Branches;CodeGen;PGO",
"MetricName": "Cond_TK"
},
{
"BriefDescription": "Fraction of branches that are CALL or RET",
"MetricExpr": "( BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN ) / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;Branches",
"MetricName": "CallRet"
},
{
"BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps",
"MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;Branches",
"MetricName": "Jump"
},
{
"BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)",
"MetricExpr": "1 - ( (BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES) + (BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES) + (( BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN ) / BR_INST_RETIRED.ALL_BRANCHES) + ((BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES) )",
"MetricGroup": "Bad;Branches",
"MetricName": "Other_Branches"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles)",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
"MetricGroup": "Mem;MemoryBound;MemoryLat",
"MetricName": "Load_Miss_Real_Latency",
"PublicDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles). Latency may be overestimated for multi-load instructions - e.g. repeat strings."
},
{
"MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
"BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
"MetricGroup": "MemoryBound;MemoryBW",
"MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
"MetricGroup": "Mem;MemoryBound;MemoryBW",
"MetricName": "MLP"
},
{
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING ) / ( 2 * CPU_CLK_UNHALTED.DISTRIBUTED )",
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricGroup": "MemoryTLB",
"MetricName": "Page_Walks_Utilization"
},
{
"MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
"BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
"MetricGroup": "MemoryBW",
"MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L1D_Cache_Fill_BW"
},
{
"MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
"BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
"MetricGroup": "MemoryBW",
"MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L2_Cache_Fill_BW"
},
{
"MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
"BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
"MetricGroup": "MemoryBW",
"MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L3_Cache_Fill_BW"
},
{
"MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
"BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
"MetricGroup": "MemoryBW;Offcore",
"MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
"MetricGroup": "Mem;MemoryBW;Offcore",
"MetricName": "L3_Cache_Access_BW"
},
{
"MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
"BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
"MetricGroup": "CacheMisses",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L1MPKI"
},
{
"MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
"BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L1MPKI_Load"
},
{
"BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
"MetricGroup": "CacheMisses",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;Backend;CacheMisses",
"MetricName": "L2MPKI"
},
{
"MetricExpr": "1000 * ( ( OFFCORE_REQUESTS.ALL_DATA_RD - OFFCORE_REQUESTS.DEMAND_DATA_RD ) + L2_RQSTS.ALL_DEMAND_MISS + L2_RQSTS.SWPF_MISS ) / INST_RETIRED.ANY",
"BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
"MetricGroup": "CacheMisses;Offcore",
"MetricExpr": "1000 * ( ( OFFCORE_REQUESTS.ALL_DATA_RD - OFFCORE_REQUESTS.DEMAND_DATA_RD ) + L2_RQSTS.ALL_DEMAND_MISS + L2_RQSTS.SWPF_MISS ) / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses;Offcore",
"MetricName": "L2MPKI_All"
},
{
"MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
"BriefDescription": "L2 cache misses per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2MPKI_Load"
},
{
"BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2HPKI_Load"
},
{
"BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
"MetricGroup": "CacheMisses",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L3MPKI"
},
{
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
"BriefDescription": "Fill Buffer (FB) true hits per kilo instructions for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "FB_HPKI"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING ) / ( 2 * CPU_CLK_UNHALTED.DISTRIBUTED )",
"MetricGroup": "Mem;MemoryTLB",
"MetricName": "Page_Walks_Utilization"
},
{
"BriefDescription": "Average CPU Utilization",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
"MetricGroup": "HPC;Summary",
"MetricName": "CPU_Utilization"
},
{
"MetricExpr": "(CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time",
"BriefDescription": "Measured Average Frequency for unhalted processors [GHz]",
"MetricExpr": "(CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time",
"MetricGroup": "Summary;Power",
"MetricName": "Average_Frequency"
},
{
"MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / 1000000000 ) / duration_time",
"BriefDescription": "Giga Floating Point Operations Per Second",
"MetricGroup": "Flops;HPC",
"MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / 1000000000 ) / duration_time",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "GFLOPs"
},
{
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
"BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization"
},
{
"MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED",
"BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0",
"MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
"MetricGroup": "Power",
"MetricName": "Power_License0_Utilization",
"PublicDescription": "Fraction of 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."
},
{
"BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1",
"MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
"MetricGroup": "Power",
"MetricName": "Power_License1_Utilization",
"PublicDescription": "Fraction of 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."
},
{
"BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)",
"MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
"MetricGroup": "Power",
"MetricName": "Power_License2_Utilization",
"PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions."
},
{
"BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
"MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0",
"MetricGroup": "SMT",
"MetricName": "SMT_2T_Utilization"
},
{
"MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
"BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "OS",
"MetricName": "Kernel_Utilization"
},
{
"MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
"BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
"MetricGroup": "OS",
"MetricName": "Kernel_CPI"
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
"MetricGroup": "HPC;MemoryBW;SoC",
"MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
"MetricGroup": "HPC;Mem;MemoryBW;SoC",
"MetricName": "DRAM_BW_Use"
},
{
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
"BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
"MetricGroup": "Branches;OS",
"MetricName": "IpFarBranch"
},
{
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
"BriefDescription": "C3 residency percent per core",
"MetricGroup": "Power",
"MetricName": "C3_Core_Residency"
},
{
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"BriefDescription": "C6 residency percent per core",
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C6_Core_Residency"
},
{
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"BriefDescription": "C7 residency percent per core",
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C7_Core_Residency"
},
{
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"BriefDescription": "C2 residency percent per package",
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C2_Pkg_Residency"
},
{
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"BriefDescription": "C3 residency percent per package",
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C3_Pkg_Residency"
},
{
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"BriefDescription": "C6 residency percent per package",
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C6_Pkg_Residency"
},
{
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"BriefDescription": "C7 residency percent per package",
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C7_Pkg_Residency"
},
{
"BriefDescription": "C8 residency percent per package",
"MetricExpr": "(cstate_pkg@c8\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C8_Pkg_Residency"
},
{
"BriefDescription": "C9 residency percent per package",
"MetricExpr": "(cstate_pkg@c9\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C9_Pkg_Residency"
},
{
"BriefDescription": "C10 residency percent per package",
"MetricExpr": "(cstate_pkg@c10\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
"MetricName": "C10_Pkg_Residency"
}
]

797
lib/libpmc/pmu-events/arch/x86/icelake/memory.json
View File

@ -1,325 +1,4 @@
[
{
"BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CONFLICT",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times a TSX line had a cache conflict.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times HLE abort was triggered.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Counts demand data reads that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00001",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"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",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"MSRValue": "0x10",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "20011",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00010",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"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",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED_MEM",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x20"
},
{
"BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x8"
},
{
"BriefDescription": "Number of times an instruction execution caused the transactional nest count supported to be exceeded",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x5d",
"EventName": "TX_EXEC.MISC3",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts Unfriendly TSX abort triggered by a nest count that is too deep.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed inside a transactional region",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x5d",
"EventName": "TX_EXEC.MISC2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts Unfriendly TSX abort triggered by a vzeroupper instruction.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles where data return is pending for a Demand Data Read request who miss L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x60",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00002",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"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",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"MSRValue": "0x200",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "101",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Number of times an RTM execution successfully committed",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.COMMIT",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times RTM commit succeeded.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional writes.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_WRITE",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED_EVENTS",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an HLE execution aborted due to unfriendly events (such as interrupts).",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Number of times an HLE execution successfully committed",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.COMMIT",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times HLE commit succeeded.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MEMTYPE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Number of machine clears due to memory ordering conflicts.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times a TSX Abort was triggered due to release/commit but data and address mismatch.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "Counts streaming stores that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.STREAMING_WR.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00800",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"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",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional reads",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_READ",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x80"
},
{
"BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.OTHER.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC08000",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"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",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00020",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"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",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Demand Data Read requests who miss L3 cache",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xb0",
"EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Demand Data Read requests who miss L3 cache.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "Cycles while L3 cache miss demand load is outstanding.",
"CollectPEBSRecord": "2",
@ -333,26 +12,71 @@
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions",
"BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "6",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x6"
},
{
"BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.",
"PublicDescription": "Counts the number of times HLE abort was triggered.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED_EVENTS",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an HLE execution aborted due to unfriendly events (such as interrupts).",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED_MEM",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)",
"BriefDescription": "Number of times an HLE execution successfully committed",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_EVENTS",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.COMMIT",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).",
"PublicDescription": "Counts the number of times HLE commit succeeded.",
"SampleAfterValue": "100003",
"UMask": "0x80"
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an HLE execution started.",
@ -366,20 +90,16 @@
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
"BriefDescription": "Number of machine clears due to memory ordering conflicts.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"MSRValue": "0x4",
"PEBS": "2",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.",
"PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
"SampleAfterValue": "100003",
"TakenAlone": "1",
"UMask": "0x1"
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
@ -398,30 +118,18 @@
"UMask": "0x1"
},
{
"BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times we could not allocate Lock Buffer.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x40"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"MSRValue": "0x8",
"MSRValue": "0x10",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "50021",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "20011",
"TakenAlone": "1",
"UMask": "0x1"
},
@ -442,16 +150,52 @@
"UMask": "0x1"
},
{
"BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.",
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "6",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x6"
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"MSRValue": "0x20",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"MSRValue": "0x4",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "100003",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"MSRValue": "0x200",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "101",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
@ -470,47 +214,21 @@
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"MSRValue": "0x20",
"MSRValue": "0x8",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "100007",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "50021",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MEM",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L1D_AND_SWPF.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00400",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"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",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
@ -521,11 +239,132 @@
"MSRValue": "0x3FFFC00004",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"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",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00001",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00002",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L1D_AND_SWPF.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00400",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00010",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00020",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.OTHER.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC08000",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts streaming stores that was not supplied by the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.STREAMING_WR.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00800",
"Offcore": "1",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data read requests that miss the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xb0",
"EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "Cycles where at least one demand data read request known to have missed the L3 cache is pending.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x60",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Cycles where at least one demand data read request known to have missed the L3 cache is pending. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known to have missed the L3 cache.",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "Number of times an RTM execution aborted.",
"CollectPEBSRecord": "2",
@ -537,6 +376,61 @@
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_EVENTS",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MEM",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MEMTYPE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of times an RTM execution successfully committed",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.COMMIT",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times RTM commit succeeded.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an RTM execution started.",
"CollectPEBSRecord": "2",
@ -549,14 +443,99 @@
"UMask": "0x1"
},
{
"BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
"BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed inside a transactional region",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY",
"EventCode": "0x5d",
"EventName": "TX_EXEC.MISC2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
"PublicDescription": "Counts Unfriendly TSX abort triggered by a vzeroupper instruction.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an instruction execution caused the transactional nest count supported to be exceeded",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x5d",
"EventName": "TX_EXEC.MISC3",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts Unfriendly TSX abort triggered by a nest count that is too deep.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional reads",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_READ",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x80"
},
{
"BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional writes.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_WRITE",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CONFLICT",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times a TSX line had a cache conflict.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times a TSX Abort was triggered due to release/commit but data and address mismatch.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x8"
},
{
"BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x20"
},
{
@ -570,5 +549,17 @@
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times we could not allocate Lock Buffer.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x40"
}
]
]

1218
lib/libpmc/pmu-events/arch/x86/icelake/other.json
View File

File diff suppressed because it is too large Load Diff

1738
lib/libpmc/pmu-events/arch/x86/icelake/pipeline.json
View File

File diff suppressed because it is too large Load Diff

238
lib/libpmc/pmu-events/arch/x86/icelake/virtual-memory.json
View File

@ -1,38 +1,14 @@
[
{
"BriefDescription": "DTLB flush attempts of the thread-specific entries",
"BriefDescription": "Loads that miss the DTLB and hit the STLB.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.DTLB_THREAD",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.",
"SampleAfterValue": "100007",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
"PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0xe"
},
{
"BriefDescription": "STLB flush attempts",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.STLB_ANY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).",
"SampleAfterValue": "100007",
"Speculative": "1",
"UMask": "0x20"
},
{
@ -49,16 +25,28 @@
"UMask": "0x10"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
"PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x2"
"UMask": "0xe"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 4K page.",
@ -73,16 +61,28 @@
"UMask": "0x2"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
"PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x4"
"UMask": "0x10"
},
{
"BriefDescription": "Stores that miss the DTLB and hit the STLB.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x20"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.",
@ -97,30 +97,6 @@
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Stores that miss the DTLB and hit the STLB.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x20"
},
{
"BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)",
"CollectPEBSRecord": "2",
@ -134,16 +110,16 @@
"UMask": "0xe"
},
{
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
"BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0xe"
"UMask": "0x4"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 4K page.",
@ -157,6 +133,18 @@
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_PENDING",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
"CollectPEBSRecord": "2",
@ -169,30 +157,6 @@
"Speculative": "1",
"UMask": "0x20"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_PENDING",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.",
"CollectPEBSRecord": "2",
@ -207,39 +171,75 @@
"UMask": "0x10"
},
{
"BriefDescription": "Loads that miss the DTLB and hit the STLB.",
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
"PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0xe"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_PENDING",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "DTLB flush attempts of the thread-specific entries",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.DTLB_THREAD",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.",
"SampleAfterValue": "100007",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "STLB flush attempts",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.STLB_ANY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).",
"SampleAfterValue": "100007",
"Speculative": "1",
"UMask": "0x20"
},
{
"BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_PENDING",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x10"
}
]

1350
lib/libpmc/pmu-events/arch/x86/icelakex/cache.json
View File

File diff suppressed because it is too large Load Diff

51
lib/libpmc/pmu-events/arch/x86/icelakex/floating-point.json
View File

@ -11,26 +11,6 @@
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. 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 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
@ -38,6 +18,7 @@
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
@ -48,7 +29,7 @@
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
@ -59,6 +40,7 @@
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
@ -69,6 +51,7 @@
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
@ -79,17 +62,41 @@
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"BriefDescription": "Counts number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. 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 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. 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 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x2"
}
]

731
lib/libpmc/pmu-events/arch/x86/icelakex/frontend.json
View File

@ -1,105 +1,296 @@
[
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
"EventCode": "0xe6",
"EventName": "BACLEARS.ANY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"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",
"Speculative": "1",
"UMask": "0x4"
"UMask": "0x1"
},
{
"BriefDescription": "Cycles MITE is delivering optimal number of Uops",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "5",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_OK",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles MITE is delivering any Uop",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_ANY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles DSB is delivering optimal number of Uops",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "5",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_OK",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_ANY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x8"
},
{
"BriefDescription": "Number of switches from DSB or MITE to the MS",
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE transitions count.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_SWITCHES",
"EventCode": "0xab",
"EventName": "DSB2MITE_SWITCHES.COUNT",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"PublicDescription": "Counts the number of Decode Stream Buffer (DSB a.k.a. Uop Cache)-to-MITE speculative transitions.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x30"
"UMask": "0x2"
},
{
"BriefDescription": "Uops delivered to IDQ while MS is busy",
"BriefDescription": "DSB-to-MITE switch true penalty cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.MS_UOPS",
"EventCode": "0xab",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"PEBScounters": "0,1,2,3",
"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.",
"PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x30"
"UMask": "0x2"
},
{
"BriefDescription": "Retired Instructions who experienced DSB miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x1",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced a critical DSB miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x11",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced iTLB true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x14",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L1I_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x12",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L2_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x13",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x500106",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
"MSRIndex": "0x3F7",
"MSRValue": "0x508006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
"MSRIndex": "0x3F7",
"MSRValue": "0x501006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
"MSRIndex": "0x3F7",
"MSRValue": "0x500206",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
"MSRIndex": "0x3F7",
"MSRValue": "0x510006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x100206",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
"MSRIndex": "0x3F7",
"MSRValue": "0x502006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
"MSRIndex": "0x3F7",
"MSRValue": "0x500406",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
"MSRIndex": "0x3F7",
"MSRValue": "0x520006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
"MSRIndex": "0x3F7",
"MSRValue": "0x504006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
"MSRIndex": "0x3F7",
"MSRValue": "0x500806",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.STLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x15",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
@ -149,6 +340,108 @@
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_ANY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles DSB is delivering optimal number of Uops",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "5",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_OK",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x8"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles MITE is delivering any Uop",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_ANY",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles MITE is delivering optimal number of Uops",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "5",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_OK",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Number of switches from DSB or MITE to the MS",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_SWITCHES",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x30"
},
{
"BriefDescription": "Uops delivered to IDQ while MS is busy",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.MS_UOPS",
"PEBScounters": "0,1,2,3",
"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": "100003",
"Speculative": "1",
"UMask": "0x30"
},
{
"BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled",
"CollectPEBSRecord": "2",
@ -187,283 +480,5 @@
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x1"
},
{
"BriefDescription": "DSB-to-MITE switch true penalty cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xab",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE transitions count.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0xab",
"EventName": "DSB2MITE_SWITCHES.COUNT",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of Decode Stream Buffer (DSB a.k.a. Uop Cache)-to-MITE speculative transitions.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Retired Instructions who experienced DSB miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x11",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L1I_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x12",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L2_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x13",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced iTLB true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x14",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.STLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x15",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
"MSRIndex": "0x3F7",
"MSRValue": "0x500206",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
"MSRIndex": "0x3F7",
"MSRValue": "0x500406",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
"MSRIndex": "0x3F7",
"MSRValue": "0x500806",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
"MSRIndex": "0x3F7",
"MSRValue": "0x501006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
"MSRIndex": "0x3F7",
"MSRValue": "0x502006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
"MSRIndex": "0x3F7",
"MSRValue": "0x504006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
"MSRIndex": "0x3F7",
"MSRValue": "0x508006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
"MSRIndex": "0x3F7",
"MSRValue": "0x510006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
"MSRIndex": "0x3F7",
"MSRValue": "0x520006",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts 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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x100206",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"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.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x500106",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"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.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xe6",
"EventName": "BACLEARS.ANY",
"PEBScounters": "0,1,2,3",
"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",
"Speculative": "1",
"UMask": "0x1"
}
]

280
lib/libpmc/pmu-events/arch/x86/icelakex/icx-metrics.json
View File

@ -1,26 +1,38 @@
[
{
"BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)",
"MetricExpr": "100 * (( BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) ) / TOPDOWN.SLOTS)",
"MetricGroup": "Ret",
"MetricName": "Branching_Overhead"
},
{
"BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
"MetricExpr": "100 * (( 5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING ) / TOPDOWN.SLOTS) * ( (ICACHE_64B.IFTAG_STALL / CPU_CLK_UNHALTED.THREAD) + (ICACHE_16B.IFDATA_STALL / CPU_CLK_UNHALTED.THREAD) + (10 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) ) / #(( 5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING ) / TOPDOWN.SLOTS)",
"MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB",
"MetricName": "Big_Code"
},
{
"BriefDescription": "Instructions Per Cycle (per Logical Processor)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Summary",
"MetricGroup": "Ret;Summary",
"MetricName": "IPC"
},
{
"BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.SLOTS / INST_RETIRED.ANY",
"MetricGroup": "Pipeline;Retire",
"MetricGroup": "Pipeline;Ret;Retire",
"MetricName": "UPI"
},
{
"BriefDescription": "Instruction per taken branch",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;FetchBW;PGO",
"MetricName": "IpTB"
"MetricExpr": "UOPS_RETIRED.SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW",
"MetricName": "UpTB"
},
{
"BriefDescription": "Cycles Per Instruction (per Logical Processor)",
"MetricExpr": "1 / (INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD)",
"MetricGroup": "Pipeline",
"MetricGroup": "Pipeline;Mem",
"MetricName": "CPI"
},
{
@ -30,27 +42,53 @@
"MetricName": "CLKS"
},
{
"BriefDescription": "Instructions Per Cycle (per physical core)",
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
"MetricExpr": "TOPDOWN.SLOTS",
"MetricGroup": "TmaL1",
"MetricName": "SLOTS"
},
{
"BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
"MetricExpr": "TOPDOWN.SLOTS / ( TOPDOWN.SLOTS / 2 ) if #SMT_on else 1",
"MetricGroup": "SMT",
"MetricName": "Slots_Utilization"
},
{
"BriefDescription": "The ratio of Executed- by Issued-Uops",
"MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
"MetricGroup": "Cor;Pipeline",
"MetricName": "Execute_per_Issue",
"PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
},
{
"BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.DISTRIBUTED",
"MetricGroup": "SMT;TmaL1",
"MetricGroup": "Ret;SMT;TmaL1",
"MetricName": "CoreIPC"
},
{
"BriefDescription": "Floating Point Operations Per Cycle",
"MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / CPU_CLK_UNHALTED.DISTRIBUTED",
"MetricGroup": "Flops",
"MetricGroup": "Ret;Flops",
"MetricName": "FLOPc"
},
{
"BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width)",
"MetricExpr": "( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) ) / ( 2 * CPU_CLK_UNHALTED.DISTRIBUTED )",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "FP_Arith_Utilization",
"PublicDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). Values > 1 are possible due to Fused-Multiply Add (FMA) counting."
},
{
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
"MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
"MetricGroup": "Pipeline;PortsUtil",
"MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
"MetricName": "ILP"
},
{
"BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "BrMispredicts",
"MetricGroup": "Bad;BadSpec;BrMispredicts",
"MetricName": "IpMispredict"
},
{
@ -74,122 +112,237 @@
{
"BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Branches;InsType",
"MetricGroup": "Branches;Fed;InsType",
"MetricName": "IpBranch"
},
{
"BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
"MetricGroup": "Branches",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "IpCall"
},
{
"BriefDescription": "Instruction per taken branch",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO",
"MetricName": "IpTB"
},
{
"BriefDescription": "Branch instructions per taken branch. ",
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;PGO",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "BpTkBranch"
},
{
"BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpArith;InsType",
"MetricGroup": "Flops;InsType",
"MetricName": "IpFLOP"
},
{
"BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) )",
"MetricGroup": "Flops;InsType",
"MetricName": "IpArith",
"PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW."
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "IpArith_Scalar_SP",
"PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "IpArith_Scalar_DP",
"PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "IpArith_AVX128",
"PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "IpArith_AVX256",
"PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )",
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "IpArith_AVX512",
"PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
},
{
"BriefDescription": "Total number of retired Instructions, Sample with: INST_RETIRED.PREC_DIST",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary;TmaL1",
"MetricName": "Instructions"
},
{
"BriefDescription": "Average number of Uops issued by front-end when it issued something",
"MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
"MetricGroup": "Fed;FetchBW",
"MetricName": "Fetch_UpC"
},
{
"BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
"MetricExpr": "LSD.UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
"MetricGroup": "LSD",
"MetricGroup": "Fed;LSD",
"MetricName": "LSD_Coverage"
},
{
"BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
"MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
"MetricGroup": "DSB;FetchBW",
"MetricGroup": "DSB;Fed;FetchBW",
"MetricName": "DSB_Coverage"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"BriefDescription": "Number of Instructions per non-speculative DSB miss",
"MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
"MetricGroup": "DSBmiss;Fed",
"MetricName": "IpDSB_Miss_Ret"
},
{
"BriefDescription": "Fraction of branches that are non-taken conditionals",
"MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;Branches;CodeGen;PGO",
"MetricName": "Cond_NT"
},
{
"BriefDescription": "Fraction of branches that are taken conditionals",
"MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;Branches;CodeGen;PGO",
"MetricName": "Cond_TK"
},
{
"BriefDescription": "Fraction of branches that are CALL or RET",
"MetricExpr": "( BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN ) / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;Branches",
"MetricName": "CallRet"
},
{
"BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps",
"MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;Branches",
"MetricName": "Jump"
},
{
"BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)",
"MetricExpr": "1 - ( (BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES) + (BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES) + (( BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN ) / BR_INST_RETIRED.ALL_BRANCHES) + ((BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES) )",
"MetricGroup": "Bad;Branches",
"MetricName": "Other_Branches"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles)",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
"MetricGroup": "MemoryBound;MemoryLat",
"MetricName": "Load_Miss_Real_Latency"
"MetricGroup": "Mem;MemoryBound;MemoryLat",
"MetricName": "Load_Miss_Real_Latency",
"PublicDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles). Latency may be overestimated for multi-load instructions - e.g. repeat strings."
},
{
"BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
"MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
"MetricGroup": "MemoryBound;MemoryBW",
"MetricGroup": "Mem;MemoryBound;MemoryBW",
"MetricName": "MLP"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING ) / ( 2 * CPU_CLK_UNHALTED.DISTRIBUTED )",
"MetricGroup": "MemoryTLB",
"MetricName": "Page_Walks_Utilization"
},
{
"BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
"MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
"MetricGroup": "MemoryBW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L1D_Cache_Fill_BW"
},
{
"BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
"MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
"MetricGroup": "MemoryBW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L2_Cache_Fill_BW"
},
{
"BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
"MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
"MetricGroup": "MemoryBW",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "L3_Cache_Fill_BW"
},
{
"BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
"MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
"MetricGroup": "MemoryBW;Offcore",
"MetricGroup": "Mem;MemoryBW;Offcore",
"MetricName": "L3_Cache_Access_BW"
},
{
"BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
"MetricGroup": "CacheMisses",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L1MPKI"
},
{
"BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L1MPKI_Load"
},
{
"BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
"MetricGroup": "CacheMisses",
"MetricGroup": "Mem;Backend;CacheMisses",
"MetricName": "L2MPKI"
},
{
"BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
"MetricExpr": "1000 * ( ( OFFCORE_REQUESTS.ALL_DATA_RD - OFFCORE_REQUESTS.DEMAND_DATA_RD ) + L2_RQSTS.ALL_DEMAND_MISS + L2_RQSTS.SWPF_MISS ) / INST_RETIRED.ANY",
"MetricGroup": "CacheMisses;Offcore",
"MetricGroup": "Mem;CacheMisses;Offcore",
"MetricName": "L2MPKI_All"
},
{
"BriefDescription": "L2 cache misses per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2MPKI_Load"
},
{
"BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)",
"MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L2HPKI_Load"
},
{
"BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
"MetricGroup": "CacheMisses",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "L3MPKI"
},
{
"BriefDescription": "Fill Buffer (FB) true hits per kilo instructions for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "FB_HPKI"
},
{
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
"MetricConstraint": "NO_NMI_WATCHDOG",
"MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING ) / ( 2 * CPU_CLK_UNHALTED.DISTRIBUTED )",
"MetricGroup": "Mem;MemoryTLB",
"MetricName": "Page_Walks_Utilization"
},
{
"BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)",
"MetricExpr": "1000 * L2_LINES_OUT.SILENT / INST_RETIRED.ANY",
"MetricGroup": "L2Evicts;Server",
"MetricGroup": "L2Evicts;Mem;Server",
"MetricName": "L2_Evictions_Silent_PKI"
},
{
"BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction",
"MetricExpr": "1000 * L2_LINES_OUT.NON_SILENT / INST_RETIRED.ANY",
"MetricGroup": "L2Evicts;Server",
"MetricGroup": "L2Evicts;Mem;Server",
"MetricName": "L2_Evictions_NonSilent_PKI"
},
{
@ -207,7 +360,7 @@
{
"BriefDescription": "Giga Floating Point Operations Per Second",
"MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / 1000000000 ) / duration_time",
"MetricGroup": "Flops;HPC",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "GFLOPs"
},
{
@ -216,6 +369,27 @@
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization"
},
{
"BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0",
"MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
"MetricGroup": "Power",
"MetricName": "Power_License0_Utilization",
"PublicDescription": "Fraction of 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."
},
{
"BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1",
"MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
"MetricGroup": "Power",
"MetricName": "Power_License1_Utilization",
"PublicDescription": "Fraction of 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."
},
{
"BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)",
"MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
"MetricGroup": "Power",
"MetricName": "Power_License2_Utilization",
"PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions."
},
{
"BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
"MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0",
@ -228,52 +402,64 @@
"MetricGroup": "OS",
"MetricName": "Kernel_Utilization"
},
{
"BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
"MetricGroup": "OS",
"MetricName": "Kernel_CPI"
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
"MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
"MetricGroup": "HPC;MemoryBW;SoC",
"MetricGroup": "HPC;Mem;MemoryBW;SoC",
"MetricName": "DRAM_BW_Use"
},
{
"BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
"MetricExpr": "1000000000 * ( UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD ) / ( cha_0@event\\=0x0@ / duration_time )",
"MetricGroup": "MemoryLat;SoC",
"MetricGroup": "Mem;MemoryLat;SoC",
"MetricName": "MEM_Read_Latency"
},
{
"BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
"MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@event\\=0x36\\,umask\\=0xC817FE01\\,thresh\\=1@",
"MetricGroup": "MemoryBW;SoC",
"MetricGroup": "Mem;MemoryBW;SoC",
"MetricName": "MEM_Parallel_Reads"
},
{
"BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches",
"MetricExpr": "( 1000000000 * ( UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM ) / cha_0@event\\=0x0@ )",
"MetricGroup": "MemoryLat;SoC;Server",
"MetricGroup": "Mem;MemoryLat;SoC;Server",
"MetricName": "MEM_PMM_Read_Latency"
},
{
"BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches",
"MetricExpr": " 1000000000 * ( UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR ) / cha_0@event\\=0x0@",
"MetricGroup": "Mem;MemoryLat;SoC;Server",
"MetricName": "MEM_DRAM_Read_Latency"
},
{
"BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]",
"MetricExpr": "( ( 64 * imc@event\\=0xe3@ / 1000000000 ) / duration_time )",
"MetricGroup": "MemoryBW;SoC;Server",
"MetricGroup": "Mem;MemoryBW;SoC;Server",
"MetricName": "PMM_Read_BW"
},
{
"BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]",
"MetricExpr": "( ( 64 * imc@event\\=0xe7@ / 1000000000 ) / duration_time )",
"MetricGroup": "MemoryBW;SoC;Server",
"MetricGroup": "Mem;MemoryBW;SoC;Server",
"MetricName": "PMM_Write_BW"
},
{
"BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]",
"MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1000000000 / duration_time",
"MetricGroup": "IoBW;SoC;Server",
"MetricGroup": "IoBW;Mem;SoC;Server",
"MetricName": "IO_Write_BW"
},
{
"BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]",
"MetricExpr": "( UNC_CHA_TOR_INSERTS.IO_HIT_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR ) * 64 / 1000000000 / duration_time",
"MetricGroup": "IoBW;SoC;Server",
"MetricGroup": "IoBW;Mem;SoC;Server",
"MetricName": "IO_Read_BW"
},
{

718
lib/libpmc/pmu-events/arch/x86/icelakex/memory.json
View File

@ -1,40 +1,491 @@
[
{
"BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address",
"BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CONFLICT",
"CounterMask": "6",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times a TSX line had a cache conflict.",
"SampleAfterValue": "100003",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x1"
"UMask": "0x6"
},
{
"BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional writes.",
"BriefDescription": "Number of machine clears due to memory ordering conflicts.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_WRITE",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional reads",
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"MSRValue": "0x80",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "1009",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"MSRValue": "0x10",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "20011",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"MSRValue": "0x100",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "503",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"MSRValue": "0x20",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"MSRValue": "0x4",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "100003",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"MSRValue": "0x200",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "101",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"MSRValue": "0x40",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "2003",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"MSRValue": "0x8",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "50021",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC00004",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_CODE_RD.L3_MISS_LOCAL",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F84400004",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC00001",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F84400001",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F3FC00002",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by the local socket.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F04400002",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L1D_AND_SWPF.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC00400",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L1D_AND_SWPF.L3_MISS_LOCAL",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F84400400",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetches to the L3 only that missed the local socket's L1, L2, and L3 caches.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L3.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x94002380",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L3.L3_MISS_LOCAL",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x84002380",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts full cacheline writes (ItoM) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.ITOM.L3_MISS_LOCAL",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x84000002",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that were not supplied by the local socket's L1, L2, or L3 caches.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.OTHER.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC08000",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.OTHER.L3_MISS_LOCAL",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F84408000",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware and software prefetches to all cache levels that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.PREFETCHES.L3_MISS_LOCAL",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F844027F0",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.READS_TO_CORE.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F3FC00477",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by the local socket.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F04400477",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that missed the L3 Cache and were supplied by the local socket (DRAM or PMM), whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM or DRAM accesses that are controlled by the close or distant SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL_SOCKET",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x70CC00477",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts streaming stores that missed the local socket's L1, L2, and L3 caches.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.STREAMING_WR.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x94000800",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts streaming stores that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.STREAMING_WR.L3_MISS_LOCAL",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x84000800",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data read requests that miss the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_READ",
"EventCode": "0xb0",
"EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "Cycles where at least one demand data read request known to have missed the L3 cache is pending.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x60",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Cycles where at least one demand data read request known to have missed the L3 cache is pending. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known to have missed the L3 cache.",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x60",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
"PEBScounters": "0,1,2,3",
"PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known to have missed the L3 cache.",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "Cycles where the core is waiting on at least 6 outstanding demand data read requests known to have missed the L3 cache.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "6",
"EventCode": "0x60",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Cycles where the core is waiting on at least 6 outstanding demand data read requests known to have missed the L3 cache. Note that this event does not capture all elapsed cycles while the requests are outstanding - only cycles from when the requests were known to have missed the L3 cache.",
"SampleAfterValue": "2000003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "Number of times an RTM execution aborted.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times RTM abort was triggered.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_EVENTS",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MEM",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MEMTYPE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of times an RTM execution successfully committed",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.COMMIT",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times RTM commit succeeded.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an RTM execution started.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.START",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed inside a transactional region",
"CollectPEBSRecord": "2",
@ -60,232 +511,39 @@
"UMask": "0x4"
},
{
"BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.",
"BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional reads",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"CounterMask": "6",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_READ",
"PEBScounters": "0,1,2,3",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x6"
},
{
"BriefDescription": "Number of machine clears due to memory ordering conflicts.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
"PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an RTM execution started.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.START",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of times an RTM execution successfully committed",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.COMMIT",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times RTM commit succeeded.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an RTM execution aborted.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times RTM abort was triggered.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MEM",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MEMTYPE",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_EVENTS",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
"BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional writes.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"MSRValue": "0x4",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_WRITE",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.",
"SampleAfterValue": "100003",
"TakenAlone": "1",
"UMask": "0x1"
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
"BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"MSRValue": "0x8",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "50021",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"MSRValue": "0x10",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "20011",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"MSRValue": "0x20",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"MSRValue": "0x40",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "2003",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"MSRValue": "0x80",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "1009",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"MSRValue": "0x100",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "503",
"TakenAlone": "1",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"MSRValue": "0x200",
"PEBS": "2",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "101",
"TakenAlone": "1",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CONFLICT",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of times a TSX line had a cache conflict.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x1"
}
]
]

539
lib/libpmc/pmu-events/arch/x86/icelakex/other.json
View File

@ -1,15 +1,4 @@
[
{
"BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event",
"CollectPEBSRecord": "2",
"Counter": "35",
"EventName": "TOPDOWN.SLOTS",
"PEBScounters": "35",
"PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).",
"SampleAfterValue": "10000003",
"Speculative": "1",
"UMask": "0x4"
},
{
"BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the Non-AVX turbo schedule.",
"CollectPEBSRecord": "2",
@ -47,122 +36,515 @@
"UMask": "0x20"
},
{
"BriefDescription": "Number of PREFETCHNTA instructions executed.",
"BriefDescription": "Hit snoop reply with data, line invalidated.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x32",
"EventName": "SW_PREFETCH_ACCESS.NTA",
"EventCode": "0xef",
"EventName": "CORE_SNOOP_RESPONSE.I_FWD_FE",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
"SampleAfterValue": "100003",
"PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated: removed from this core's cache, after the data is forwarded back to the requestor and indicating the data was found unmodified in the (FE) Forward or Exclusive State in this cores caches cache. A single snoop response from the core counts on all hyperthreads of the core.",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x1"
"UMask": "0x20"
},
{
"BriefDescription": "Number of PREFETCHT0 instructions executed.",
"BriefDescription": "HitM snoop reply with data, line invalidated.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x32",
"EventName": "SW_PREFETCH_ACCESS.T0",
"EventCode": "0xef",
"EventName": "CORE_SNOOP_RESPONSE.I_FWD_M",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
"SampleAfterValue": "100003",
"PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated: removed from this core's caches, after the data is forwarded back to the requestor, and indicating the data was found modified(M) in this cores caches cache (aka HitM response). A single snoop response from the core counts on all hyperthreads of the core.",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x10"
},
{
"BriefDescription": "Hit snoop reply without sending the data, line invalidated.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xef",
"EventName": "CORE_SNOOP_RESPONSE.I_HIT_FSE",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated in this core's caches without being forwarded back to the requestor. The line was in Forward, Shared or Exclusive (FSE) state in this cores caches. A single snoop response from the core counts on all hyperthreads of the core.",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.",
"BriefDescription": "Line not found snoop reply",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x32",
"EventName": "SW_PREFETCH_ACCESS.T1_T2",
"EventCode": "0xef",
"EventName": "CORE_SNOOP_RESPONSE.MISS",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
"SampleAfterValue": "100003",
"PublicDescription": "Counts responses to snoops indicating that the data was not found (IHitI) in this core's caches. A single snoop response from the core counts on all hyperthreads of the Core.",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x4"
"UMask": "0x1"
},
{
"BriefDescription": "Number of PREFETCHW instructions executed.",
"BriefDescription": "Hit snoop reply with data, line kept in Shared state.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0x32",
"EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
"EventCode": "0xef",
"EventName": "CORE_SNOOP_RESPONSE.S_FWD_FE",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts the number of PREFETCHW instructions executed.",
"SampleAfterValue": "100003",
"PublicDescription": "Counts responses to snoops indicating the line may be kept on this core in the (S)hared state, after the data is forwarded back to the requestor, initially the data was found in the cache in the (FS) Forward or Shared state. A single snoop response from the core counts on all hyperthreads of the core.",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x40"
},
{
"BriefDescription": "HitM snoop reply with data, line kept in Shared state",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"EventCode": "0xef",
"EventName": "CORE_SNOOP_RESPONSE.S_FWD_M",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts responses to snoops indicating the line may be kept on this core in the (S)hared state, after the data is forwarded back to the requestor, initially the data was found in the cache in the (M)odified state. A single snoop response from the core counts on all hyperthreads of the core.",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x8"
},
{
"BriefDescription": "TMA slots available for an unhalted logical processor. General counter - architectural event",
"BriefDescription": "Hit snoop reply without sending the data, line kept in Shared state.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa4",
"EventName": "TOPDOWN.SLOTS_P",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.",
"SampleAfterValue": "10000003",
"Counter": "0,1,2,3",
"EventCode": "0xef",
"EventName": "CORE_SNOOP_RESPONSE.S_HIT_FSE",
"PEBScounters": "0,1,2,3",
"PublicDescription": "Counts responses to snoops indicating the line was kept on this core in the (S)hared state, and that the data was found unmodified but not forwarded back to the requestor, initially the data was found in the cache in the (FSE) Forward, Shared state or Exclusive state. A single snoop response from the core counts on all hyperthreads of the core.",
"SampleAfterValue": "1000003",
"Speculative": "1",
"UMask": "0x1"
"UMask": "0x4"
},
{
"BriefDescription": "TMA slots where no uops were being issued due to lack of back-end resources.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa4",
"EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of Top-down Microarchitecture Analysis (TMA) method's slots where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.",
"SampleAfterValue": "10000003",
"Speculative": "1",
"UMask": "0x2"
},
{
"BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.ANY",
"PEBScounters": "0,1,2,3,4,5,6,7",
"PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware Examples include AD (page Access Dirty), FP and AVX related assists.",
"SampleAfterValue": "100003",
"Speculative": "1",
"UMask": "0x7"
},
{
"BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
"EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0001",
"MSRValue": "0x10004",
"Offcore": "1",
"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",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop hit in another cores caches which forwarded the unmodified data to the requesting core.",
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
"EventName": "OCR.DEMAND_CODE_RD.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x8003C0001",
"MSRValue": "0x73C000004",
"Offcore": "1",
"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",
"UMask": "0x1"
},
{
"BriefDescription": "Counts writes that generate a demand reads for ownership (RFO) request and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
"EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0002",
"MSRValue": "0x104000004",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x708000004",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10001",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were supplied by DRAM.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x73C000001",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x104000001",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.LOCAL_PMM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x100400001",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were supplied by PMM.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.PMM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x703C00001",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x730000001",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were supplied by PMM attached to another socket.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.REMOTE_PMM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x703000001",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x708000001",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.SNC_PMM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x700800001",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F3FFC0002",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x73C000002",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x104000002",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.LOCAL_PMM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x100400002",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.PMM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x703C00002",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM attached to another socket.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.REMOTE_PMM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x703000002",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.SNC_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x708000002",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.SNC_PMM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x700800002",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that were supplied by DRAM.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x73C000400",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x104000400",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch (which bring data to L2) that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10070",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L3.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x12380",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L3.REMOTE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x90002380",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts full cacheline writes (ItoM) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.ITOM.REMOTE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x90000002",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.OTHER.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x18000",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F3FFC0477",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.READS_TO_CORE.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x73C000477",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x104000477",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.READS_TO_CORE.LOCAL_PMM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x100400477",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x70C000477",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_PMM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x700C00477",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.READS_TO_CORE.REMOTE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F33000477",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.READS_TO_CORE.REMOTE_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x730000477",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to another socket.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.READS_TO_CORE.REMOTE_PMM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x703000477",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.READS_TO_CORE.SNC_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x708000477",
"Offcore": "1",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
"Counter": "0,1,2,3",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.READS_TO_CORE.SNC_PMM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x700800477",
"Offcore": "1",
"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",
"UMask": "0x1"
},
@ -174,8 +556,7 @@
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10800",
"Offcore": "1",
"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",
"UMask": "0x1"
}
]
]

1451
lib/libpmc/pmu-events/arch/x86/icelakex/pipeline.json
View File

File diff suppressed because it is too large Load Diff

61
lib/libpmc/pmu-events/arch/x86/icelakex/uncore-other.json
View File

@ -60,7 +60,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Clockticks of the uncore caching &amp;amp; home agent (CHA)",
"BriefDescription": "Clockticks of the uncore caching and home agent (CHA)",
"Counter": "0,1,2,3",
"CounterType": "PGMABLE",
"EventName": "UNC_CHA_CLOCKTICKS",
@ -2472,5 +2472,64 @@
"PerPkg": "1",
"UMask": "0x27",
"Unit": "UPI LL"
},
{
"BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices to locally HOMed memory",
"Counter": "0,1,2,3",
"CounterType": "PGMABLE",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL",
"PerPkg": "1",
"PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices : Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.",
"UMask": "0xCD42FF04",
"UMaskExt": "0xCD42FF",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices to remotely HOMed memory",
"Counter": "0,1,2,3",
"CounterType": "PGMABLE",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE",
"PerPkg": "1",
"PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices : Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.",
"UMask": "0xCD437F04",
"UMaskExt": "0xCD437F",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Inserts : ItoMs issued by IO Devices to locally HOMed memory",
"Counter": "0,1,2,3",
"CounterType": "PGMABLE",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL",
"PerPkg": "1",
"PublicDescription": "TOR Inserts : ItoMs issued by IO Devices : Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.",
"UMask": "0xCC42FF04",
"UMaskExt": "0xCC42FF",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Inserts : ItoMs issued by IO Devices to remotely HOMed memory",
"Counter": "0,1,2,3",
"CounterType": "PGMABLE",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE",
"PerPkg": "1",
"PublicDescription": "TOR Inserts : ItoMs issued by IO Devices : Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.",
"UMask": "0xCC437F04",
"UMaskExt": "0xCC437F",
"Unit": "CHA"
},
{
"BriefDescription": "Multi-socket cacheline Directory Updates : From/to any state. Note: event counts are incorrect in 2LM mode.",
"Counter": "0,1,2,3",
"CounterType": "PGMABLE",
"EventCode": "0x2e",
"EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY",
"PerPkg": "1",
"PublicDescription": "Multi-socket cacheline Directory Updates : From/to any state. Note: event counts are incorrect in 2LM mode.",
"UMask": "0x01",
"Unit": "M2M"
}
]

Some files were not shown because too many files have changed in this diff Show More