Quelle ivb-metrics.json
Sprache: unbekannt
|
|
[
{
"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 metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset",
"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.",
"MetricConstraint": "NO_GROUP_EVENTS_NMI",
"MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5) / (3 * 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": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / 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: OTHER_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",
"MetricConstraint": "NO_GROUP_EVENTS_NMI",
"MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)",
"MetricGroup": "BvOB;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;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_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 estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction",
"MetricConstraint": "NO_GROUP_EVENTS_NMI",
"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 estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
"MetricConstraint": "NO_GROUP_EVENTS",
"MetricExpr": "(60 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) + 43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS)))) / 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_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",
"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 estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
"MetricConstraint": "NO_GROUP_EVENTS",
"MetricExpr": "43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) / 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_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
"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": "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_SMT",
"MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_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 Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline",
"MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / 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. Related metrics: tma_fetch_bandwidth, 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": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks",
"MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
"MetricName": "tma_dtlb_load",
"MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
"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 roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
"MetricExpr": "(7 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks",
"MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
"MetricName": "tma_dtlb_store",
"MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
"PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
"MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE / tma_info_thread_clks",
"MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
"MetricName": "tma_false_sharing",
"MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
"PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
"MetricConstraint": "NO_GROUP_EVENTS",
"MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
"MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
"MetricName": "tma_fb_full",
"MetricThreshold": "tma_fb_full > 0.3",
"PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
"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_info_inst_mix_iptb, 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_EXECUTED.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_0, tma_port_1, tma_port_5, 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_EXECUTED.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_0, tma_port_1, tma_port_5, 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_EXECUTED.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 prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, 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_EXECUTED.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 prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
"MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots",
"MetricGroup": "BvFB;BvIO;PGO;TmaL1;TopdownL1;tma_L1_group",
"MetricName": "tma_frontend_bound",
"MetricThreshold": "tma_frontend_bound > 0.15",
"MetricgroupNoGroup": "TopdownL1",
"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 Pipeline_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.",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
"MetricExpr": "tma_microcode_sequencer",
"MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
"MetricName": "tma_heavy_operations",
"MetricThreshold": "tma_heavy_operations > 0.1",
"MetricgroupNoGroup": "TopdownL2",
"PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.",
"MetricExpr": "ICACHE.IFETCH_STALL / tma_info_thread_clks - tma_itlb_misses",
"MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
"MetricName": "tma_icache_misses",
"MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
"MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
"MetricGroup": "Bad;BrMispredicts",
"MetricName": "tma_info_bad_spec_ipmisp_indirect",
"MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
},
{
"BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
"MetricGroup": "Bad;BadSpec;BrMispredicts",
"MetricName": "tma_info_bad_spec_ipmispredict",
"MetricThreshold": "tma_info_bad_spec_ipmispredict < 200"
},
{
"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) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
"MetricGroup": "SMT",
"MetricName": "tma_info_core_core_clks"
},
{
"BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
"MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks",
"MetricGroup": "Ret;SMT;TmaL1;tma_L1_group",
"MetricName": "tma_info_core_coreipc"
},
{
"BriefDescription": "Floating Point Operations Per Cycle",
"MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / tma_info_core_core_clks",
"MetricGroup": "Flops;Ret",
"MetricName": "tma_info_core_flopc"
},
{
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
"MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
"MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
"MetricName": "tma_info_core_ilp"
},
{
"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;tma_issueFB",
"MetricName": "tma_info_frontend_dsb_coverage",
"MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35",
"PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_inst_mix_iptb, tma_lcp"
},
{
"BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)",
"MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY",
"MetricGroup": "Fed",
"MetricName": "tma_info_frontend_ipunknown_branch"
},
{
"BriefDescription": "Taken Branches retired Per Cycle",
"MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks",
"MetricGroup": "Branches;FetchBW",
"MetricName": "tma_info_frontend_tbpc"
},
{
"BriefDescription": "Branch instructions per taken branch.",
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "tma_info_inst_mix_bptkbranch"
},
{
"BriefDescription": "Total number of retired Instructions",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary;TmaL1;tma_L1_group",
"MetricName": "tma_info_inst_mix_instructions",
"PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST"
},
{
"BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
"MetricExpr": "1 / (tma_fp_scalar + tma_fp_vector)",
"MetricGroup": "Flops;InsType",
"MetricName": "tma_info_inst_mix_iparith",
"MetricThreshold": "tma_info_inst_mix_iparith < 10",
"PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
},
{
"BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
"MetricGroup": "Branches;Fed;InsType",
"MetricName": "tma_info_inst_mix_ipbranch",
"MetricThreshold": "tma_info_inst_mix_ipbranch < 8"
},
{
"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": "tma_info_inst_mix_ipcall",
"MetricThreshold": "tma_info_inst_mix_ipcall < 200"
},
{
"BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
"MetricGroup": "InsType",
"MetricName": "tma_info_inst_mix_ipload",
"MetricThreshold": "tma_info_inst_mix_ipload < 3"
},
{
"BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
"MetricGroup": "InsType",
"MetricName": "tma_info_inst_mix_ipstore",
"MetricThreshold": "tma_info_inst_mix_ipstore < 8"
},
{
"BriefDescription": "Instructions per taken branch",
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
"MetricName": "tma_info_inst_mix_iptb",
"MetricThreshold": "tma_info_inst_mix_iptb < 9",
"PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp"
},
{
"BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
"MetricExpr": "tma_info_memory_l1d_cache_fill_bw",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "tma_info_memory_core_l1d_cache_fill_bw_2t"
},
{
"BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
"MetricExpr": "tma_info_memory_l2_cache_fill_bw",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "tma_info_memory_core_l2_cache_fill_bw_2t"
},
{
"BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
"MetricExpr": "tma_info_memory_l3_cache_fill_bw",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "tma_info_memory_core_l3_cache_fill_bw_2t"
},
{
"BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
"MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "tma_info_memory_l1d_cache_fill_bw"
},
{
"BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
"MetricGroup": "CacheHits;Mem",
"MetricName": "tma_info_memory_l1mpki"
},
{
"BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
"MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "tma_info_memory_l2_cache_fill_bw"
},
{
"BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
"MetricGroup": "Backend;CacheHits;Mem",
"MetricName": "tma_info_memory_l2mpki"
},
{
"BriefDescription": "Offcore requests (L2 cache miss) per kilo instruction for demand RFOs",
"MetricExpr": "1e3 * OFFCORE_REQUESTS.DEMAND_RFO / INST_RETIRED.ANY",
"MetricGroup": "CacheMisses;Offcore",
"MetricName": "tma_info_memory_l2mpki_rfo"
},
{
"BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
"MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "tma_info_memory_l3_cache_fill_bw"
},
{
"BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY",
"MetricGroup": "Mem",
"MetricName": "tma_info_memory_l3mpki"
},
{
"BriefDescription": "Average Parallel L2 cache miss data reads",
"MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
"MetricGroup": "Memory_BW;Offcore",
"MetricName": "tma_info_memory_latency_data_l2_mlp"
},
{
"BriefDescription": "Average Latency for L2 cache miss demand Loads",
"MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
"MetricGroup": "LockCont;Memory_Lat;Offcore",
"MetricName": "tma_info_memory_latency_load_l2_miss_latency"
},
{
"BriefDescription": "Average Parallel L2 cache miss demand Loads",
"MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
"MetricGroup": "Memory_BW;Offcore",
"MetricName": "tma_info_memory_latency_load_l2_mlp"
},
{
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
"MetricConstraint": "NO_GROUP_EVENTS",
"MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)",
"MetricGroup": "Mem;MemoryBound;MemoryLat",
"MetricName": "tma_info_memory_load_miss_real_latency"
},
{
"BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss",
"MetricConstraint": "NO_GROUP_EVENTS",
"MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
"MetricGroup": "Mem;MemoryBW;MemoryBound",
"MetricName": "tma_info_memory_mlp",
"PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)"
},
{
"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) / tma_info_core_core_clks",
"MetricGroup": "Mem;MemoryTLB",
"MetricName": "tma_info_memory_tlb_page_walks_utilization",
"MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
},
{
"BriefDescription": "",
"MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
"MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
"MetricName": "tma_info_pipeline_execute"
},
{
"BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
"MetricGroup": "Pipeline;Ret",
"MetricName": "tma_info_pipeline_retire"
},
{
"BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]",
"MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time",
"MetricGroup": "Power;Summary",
"MetricName": "tma_info_system_core_frequency"
},
{
"BriefDescription": "Average CPU Utilization (percentage)",
"MetricExpr": "tma_info_system_cpus_utilized / #num_cpus_online",
"MetricGroup": "HPC;Summary",
"MetricName": "tma_info_system_cpu_utilization"
},
{
"BriefDescription": "Average number of utilized CPUs",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
"MetricGroup": "Summary",
"MetricName": "tma_info_system_cpus_utilized"
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
"MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3",
"MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW",
"MetricName": "tma_info_system_dram_bw_use",
"PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full"
},
{
"BriefDescription": "Giga Floating Point Operations Per Second",
"MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / tma_info_system_time", | |