path: root/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json

[
    {
        "BriefDescription": "C2 residency percent per package",
        "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC",
        "MetricGroup": "Power",
        "MetricName": "C2_Pkg_Residency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "C3 residency percent per core",
        "MetricExpr": "cstate_core@c3\\-residency@ / TSC",
        "MetricGroup": "Power",
        "MetricName": "C3_Core_Residency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "C3 residency percent per package",
        "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC",
        "MetricGroup": "Power",
        "MetricName": "C3_Pkg_Residency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "C6 residency percent per core",
        "MetricExpr": "cstate_core@c6\\-residency@ / TSC",
        "MetricGroup": "Power",
        "MetricName": "C6_Core_Residency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "C6 residency percent per package",
        "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC",
        "MetricGroup": "Power",
        "MetricName": "C6_Pkg_Residency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "C7 residency percent per core",
        "MetricExpr": "cstate_core@c7\\-residency@ / TSC",
        "MetricGroup": "Power",
        "MetricName": "C7_Core_Residency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "C7 residency percent per package",
        "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC",
        "MetricGroup": "Power",
        "MetricName": "C7_Pkg_Residency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "Uncore frequency per die [GHZ]",
        "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9",
        "MetricGroup": "SoC",
        "MetricName": "UNCORE_FREQ"
    },
    {
        "BriefDescription": "Percentage of cycles spent in System Management Interrupts.",
        "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)",
        "MetricGroup": "smi",
        "MetricName": "smi_cycles",
        "MetricThreshold": "smi_cycles > 0.1",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "Number of SMI interrupts.",
        "MetricExpr": "msr@smi@",
        "MetricGroup": "smi",
        "MetricName": "smi_num",
        "ScaleUnit": "1SMI#"
    },
    {
        "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_GROUP_EVENTS_NMI",
        "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)",
        "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
        "MetricName": "tma_backend_bound",
        "MetricThreshold": "tma_backend_bound > 0.2",
        "MetricgroupNoGroup": "TopdownL1",
        "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.",
        "ScaleUnit": "100%"
    },
    {
        "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_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots",
        "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
        "MetricName": "tma_bad_speculation",
        "MetricThreshold": "tma_bad_speculation > 0.15",
        "MetricgroupNoGroup": "TopdownL1",
        "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.",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation",
        "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
        "MetricName": "tma_branch_mispredicts",
        "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
        "MetricgroupNoGroup": "TopdownL2",
        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers",
        "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks",
        "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
        "MetricName": "tma_branch_resteers",
        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "tma_backend_bound - tma_memory_bound",
        "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
        "MetricName": "tma_core_bound",
        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
        "MetricgroupNoGroup": "TopdownL2",
        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active",
        "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks",
        "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
        "MetricName": "tma_divider",
        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
        "MetricConstraint": "NO_GROUP_EVENTS_SMT",
        "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks",
        "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
        "MetricName": "tma_dram_bound",
        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines",
        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
        "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
        "MetricName": "tma_dsb_switches",
        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
        "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks",
        "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
        "MetricName": "tma_dtlb_load",
        "MetricThreshold": "tma_dtlb_load > 0.1",
        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues",
        "MetricExpr": "tma_frontend_bound - tma_fetch_latency",
        "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
        "MetricName": "tma_fetch_bandwidth",
        "MetricThreshold": "tma_fetch_bandwidth > 0.2",
        "MetricgroupNoGroup": "TopdownL2",
        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_lcp",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
        "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_thread_slots",
        "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
        "MetricName": "tma_fetch_latency",
        "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
        "MetricgroupNoGroup": "TopdownL2",
        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)",
        "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector",
        "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
        "MetricName": "tma_fp_arith",
        "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired",
        "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE) / UOPS_DISPATCHED.THREAD",
        "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
        "MetricName": "tma_fp_scalar",
        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths",
        "MetricExpr": "(FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) / UOPS_DISPATCHED.THREAD",
        "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
        "MetricName": "tma_fp_vector",
        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors",
        "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE) / UOPS_DISPATCHED.THREAD",
        "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
        "MetricName": "tma_fp_vector_128b",
        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors",
        "MetricExpr": "(SIMD_FP_256.PACKED_DOUBLE + SIMD_FP_256.PACKED_SINGLE) / UOPS_DISPATCHED.THREAD",
        "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
        "MetricName": "tma_fp_vector_256b",
        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This category represent