Quelle icl-metrics.json
Sprache: unbekannt
|
|
[
{
"BriefDescription": "C10 residency percent per package",
"MetricExpr": "cstate_pkg@c10\\-residency@ / TSC",
"MetricGroup": "Power",
"MetricName": "C10_Pkg_Residency",
"ScaleUnit": "100%"
},
{
"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 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": "C8 residency percent per package",
"MetricExpr": "cstate_pkg@c8\\-residency@ / TSC",
"MetricGroup": "Power",
"MetricName": "C8_Pkg_Residency",
"ScaleUnit": "100%"
},
{
"BriefDescription": "C9 residency percent per package",
"MetricExpr": "cstate_pkg@c9\\-residency@ / TSC",
"MetricGroup": "Power",
"MetricName": "C9_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 metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset",
"MetricConstraint": "NO_GROUP_EVENTS_NMI",
"MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
"MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
"MetricName": "tma_4k_aliasing",
"MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
"PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
"MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)",
"MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
"MetricName": "tma_alu_op_utilization",
"MetricThreshold": "tma_alu_op_utilization > 0.4",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists",
"MetricExpr": "34 * ASSISTS.ANY / tma_info_thread_slots",
"MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
"MetricName": "tma_assists",
"MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
"PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
"ScaleUnit": "100%"
},
{
"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",
"DefaultMetricgroupName": "TopdownL1",
"MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / tma_info_thread_slots",
"MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group",
"MetricName": "tma_backend_bound",
"MetricThreshold": "tma_backend_bound > 0.2",
"MetricgroupNoGroup": "TopdownL1;Default",
"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. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
"DefaultMetricgroupName": "TopdownL1",
"MetricExpr": "max(1 - (tma_frontend_bound + tma_backend_bound + tma_retiring), 0)",
"MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group",
"MetricName": "tma_bad_speculation",
"MetricThreshold": "tma_bad_speculation > 0.15",
"MetricgroupNoGroup": "TopdownL1;Default",
"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": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
"MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
"MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
"MetricName": "tma_bottleneck_big_code",
"MetricThreshold": "tma_bottleneck_big_code > 20"
},
{
"BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA",
"MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)",
"MetricGroup": "BvBO;Ret",
"MetricName": "tma_bottleneck_branching_overhead",
"MetricThreshold": "tma_bottleneck_branching_overhead > 5",
"PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)"
},
{
"BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
"MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
"MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
"MetricName": "tma_bottleneck_cache_memory_bandwidth",
"MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
"PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full"
},
{
"BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
"MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
"MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
"MetricName": "tma_bottleneck_cache_memory_latency",
"MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
"PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency"
},
{
"BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
"MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
"MetricGroup": "BvCB;Cor;tma_issueComp",
"MetricName": "tma_bottleneck_compute_bound_est",
"MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
"PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
},
{
"BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
"MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code",
"MetricGroup": "BvFB;Fed;FetchBW;Frontend",
"MetricName": "tma_bottleneck_instruction_fetch_bw",
"MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
},
{
"BriefDescription": "Total pipeline cost of irregular execution (e.g",
"MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
"MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
"MetricName": "tma_bottleneck_irregular_overhead",
"MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
"PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches"
},
{
"BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
"MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
"MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
"MetricName": "tma_bottleneck_memory_data_tlbs",
"MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
"PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store"
},
{
"BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
"MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
"MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
"MetricName": "tma_bottleneck_memory_synchronization",
"MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
"PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache"
},
{
"BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
"MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
"MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
"MetricName": "tma_bottleneck_mispredictions",
"MetricThreshold": "tma_bottleneck_mispredictions > 20",
"PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers"
},
{
"BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end",
"MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)",
"MetricGroup": "BvOB;Cor;Offcore",
"MetricName": "tma_bottleneck_other_bottlenecks",
"MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
"PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
},
{
"BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
"MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
"MetricGroup": "BvUW;Ret",
"MetricName": "tma_bottleneck_useful_work",
"MetricThreshold": "tma_bottleneck_useful_work > 20"
},
{
"BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.",
"MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
"MetricName": "tma_branch_instructions",
"MetricThreshold": "tma_branch_instructions > 0.1 & tma_light_operations > 0.6",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
"MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation",
"MetricGroup": "BadSpec;BrMispredicts;BvMP;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_bottleneck_mispredictions, 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": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
"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 estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction",
"MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
"MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
"MetricName": "tma_cisc",
"MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
"PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears",
"MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
"MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
"MetricName": "tma_clears_resteers",
"MetricThreshold": "tma_clears_resteers > 0.05 & (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 as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
"MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)",
"MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
"MetricName": "tma_code_l2_hit",
"MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
"MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks",
"MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
"MetricName": "tma_code_l2_miss",
"MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)",
"MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
"MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
"MetricName": "tma_code_stlb_hit",
"MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk",
"MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
"MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
"MetricName": "tma_code_stlb_miss",
"MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
"MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
"MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
"MetricName": "tma_code_stlb_miss_2m",
"MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
"MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
"MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
"MetricName": "tma_code_stlb_miss_4k",
"MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
"MetricConstraint": "NO_GROUP_EVENTS",
"MetricExpr": "(29 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 23.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
"MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
"MetricName": "tma_contested_accesses",
"MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
"PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck",
"MetricExpr": "max(0, 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 estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
"MetricConstraint": "NO_GROUP_EVENTS",
"MetricExpr": "23.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
"MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
"MetricName": "tma_data_sharing",
"MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
"PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
"MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
"MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
"MetricName": "tma_decoder0_alone",
"MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
"PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of cycles where the Divider unit was active",
"MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks",
"MetricGroup": "BvCB;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_ACTIVE",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
"MetricConstraint": "NO_GROUP_EVENTS",
"MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound",
"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_RETIRED.L3_MISS",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline",
"MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_core_clks / 2",
"MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
"MetricName": "tma_dsb",
"MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
"PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
"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. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
"MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
"MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", | |
