perf-eh_elf/pmu-events/arch/x86/broadwell/bdw-metrics.json

[
    {
        "BriefDescription": "Instructions Per Cycle (per logical thread)",
        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
        "MetricGroup": "TopDownL1",
        "MetricName": "IPC"
    },
    {
        "BriefDescription": "Uops Per Instruction",
        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
        "MetricGroup": "Pipeline",
        "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": "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",
        "MetricName": "CPI"
    },
    {
        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
        "MetricGroup": "Summary",
        "MetricName": "CLKS"
    },
    {
        "BriefDescription": "Total issue-pipeline slots",
        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
        "MetricGroup": "TopDownL1",
        "MetricName": "SLOTS"
    },
    {
        "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 / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
        "MetricGroup": "SMT",
        "MetricName": "CoreIPC"
    },
    {
        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
        "MetricGroup": "Pipeline;Ports_Utilization",
        "MetricName": "ILP"
    },
    {
        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)",
        "MetricGroup": "Unknown_Branches",
        "MetricName": "BAClear_Cost"
    },
    {
        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
        "MetricGroup": "SMT",
        "MetricName": "CORE_CLKS"
    },
    {
        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
        "MetricGroup": "Memory_Bound;Memory_Lat",
        "MetricName": "Load_Miss_Real_Latency"
    },
    {
        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
        "MetricGroup": "Memory_Bound;Memory_BW",
        "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)) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
        "MetricGroup": "TLB",
        "MetricName": "Page_Walks_Utilization"
    },
    {
        "BriefDescription": "Average CPU Utilization",
        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
        "MetricGroup": "Summary",
        "MetricName": "CPU_Utilization"
    },
    {
        "BriefDescription": "Giga Floating Point Operations Per Second",
        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
        "MetricGroup": "FLOPS;Summary",
        "MetricName": "GFLOPs"
    },
    {
        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
        "MetricGroup": "Power",
        "MetricName": "Turbo_Utilization"
    },
    {
        "BriefDescription": "Fraction of cycles where both hardware threads were active",
        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
        "MetricGroup": "SMT;Summary",
        "MetricName": "SMT_2T_Utilization"
    },
    {
        "BriefDescription": "Fraction of cycles spent in Kernel mode",
        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
        "MetricGroup": "Summary",
        "MetricName": "Kernel_Utilization"
    },
    {
        "BriefDescription": "C3 residency percent per core",
        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
        "MetricGroup": "Power",
        "MetricName": "C3_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"
    }
]