Untersuchungsergebnis.json Download desUnknown {[0] [0] [0]}zum Wurzelverzeichnis wechseln
[
{
"BriefDescription": "C1 residency percent per core",
"MetricExpr": "cstate_core@c1\\-residency@ / TSC",
"MetricGroup": "Power",
"MetricName": "C1_Core_Residency",
"ScaleUnit": "100%"
},
{
"BriefDescription": "C2 residency percent per package",
"MetricExpr": "cstate_pkg@c2\\-residency@ / TSC",
"MetricGroup": "Power",
"MetricName": "C2_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": "Uncore frequency per die [GHZ]",
"MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9",
"MetricGroup": "SoC",
"MetricName": "UNCORE_FREQ"
},
{
"BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY",
"MetricName": "cpi",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "CPU operating frequency (in GHz)",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9",
"MetricName": "cpu_operating_frequency",
"ScaleUnit": "1GHz"
},
{
"BriefDescription": "Percentage of time spent in the active CPU power state C0",
"MetricExpr": "tma_info_system_cpus_utilized",
"MetricName": "cpu_utilization",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions",
"MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY",
"MetricName": "dtlb_2nd_level_2mb_large_page_load_mpi",
"PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions",
"MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
"MetricName": "dtlb_2nd_level_load_mpi",
"PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions",
"MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
"MetricName": "dtlb_2nd_level_store_mpi",
"PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU",
"MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_HIT_PCIRDCUR + UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR) * 64 / 1e6 / duration_time",
"MetricName": "io_bandwidth_read",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket",
"MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL * 64 / 1e6 / duration_time",
"MetricName": "io_bandwidth_read_local",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from a remote CPU socket",
"MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE * 64 / 1e6 / duration_time",
"MetricName": "io_bandwidth_read_remote",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU",
"MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_HIT_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR) * 64 / 1e6 / duration_time",
"MetricName": "io_bandwidth_write",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket",
"MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL) * 64 / 1e6 / duration_time",
"MetricName": "io_bandwidth_write_local",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to a remote CPU socket",
"MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE) * 64 / 1e6 / duration_time",
"MetricName": "io_bandwidth_write_remote",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions",
"MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY",
"MetricName": "itlb_2nd_level_large_page_mpi",
"PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions",
"MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
"MetricName": "itlb_2nd_level_mpi",
"PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions",
"MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY",
"MetricName": "l1_i_code_read_misses_with_prefetches_per_instr",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions",
"MetricExpr": "MEM_LOAD_RETIRED.L1_HIT / INST_RETIRED.ANY",
"MetricName": "l1d_demand_data_read_hits_per_instr",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions",
"MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY",
"MetricName": "l1d_mpi",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions",
"MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY",
"MetricName": "l2_demand_code_mpi",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions",
"MetricExpr": "MEM_LOAD_RETIRED.L2_HIT / INST_RETIRED.ANY",
"MetricName": "l2_demand_data_read_hits_per_instr",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions",
"MetricExpr": "MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
"MetricName": "l2_demand_data_read_mpi",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions",
"MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY",
"MetricName": "l2_mpi",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions",
"MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_CRD + UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF) / INST_RETIRED.ANY",
"MetricName": "llc_code_read_mpi_demand_plus_prefetch",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions",
"MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA + UNC_CHA_TOR_INSERTS.IA_MISS_DRD + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF) / INST_RETIRED.ANY",
"MetricName": "llc_data_read_mpi_demand_plus_prefetch",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) in nano seconds",
"MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD) * #num_packages)) * duration_time",
"MetricName": "llc_demand_data_read_miss_latency",
"ScaleUnit": "1ns"
},
{
"BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to local memory in nano seconds",
"MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL) * #num_packages)) * duration_time",
"MetricName": "llc_demand_data_read_miss_latency_for_local_requests",
"ScaleUnit": "1ns"
},
{
"BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to remote memory in nano seconds",
"MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE) * #num_packages)) * duration_time",
"MetricName": "llc_demand_data_read_miss_latency_for_remote_requests",
"ScaleUnit": "1ns"
},
{
"BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to DRAM in nano seconds",
"MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR) * #num_packages)) * duration_time",
"MetricName": "llc_demand_data_read_miss_to_dram_latency",
"ScaleUnit": "1ns"
},
{
"BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to Intel(R) Optane(TM) Persistent Memory(PMEM) in nano seconds",
"MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM) * #num_packages)) * duration_time",
"MetricName": "llc_demand_data_read_miss_to_pmem_latency",
"ScaleUnit": "1ns"
},
{
"BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory",
"MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time",
"MetricName": "llc_miss_local_memory_bandwidth_read",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory",
"MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time",
"MetricName": "llc_miss_local_memory_bandwidth_write",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory",
"MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time",
"MetricName": "llc_miss_remote_memory_bandwidth_read",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory",
"MetricExpr": "UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1e6 / duration_time",
"MetricName": "llc_miss_remote_memory_bandwidth_write",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions",
"MetricExpr": "MEM_INST_RETIRED.ALL_LOADS / INST_RETIRED.ANY",
"MetricName": "loads_per_instr",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "DDR memory read bandwidth (MB/sec)",
"MetricExpr": "UNC_M_CAS_COUNT.RD * 64 / 1e6 / duration_time",
"MetricName": "memory_bandwidth_read",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "DDR memory bandwidth (MB/sec)",
"MetricExpr": "(UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) * 64 / 1e6 / duration_time",
"MetricName": "memory_bandwidth_total",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "DDR memory write bandwidth (MB/sec)",
"MetricExpr": "UNC_M_CAS_COUNT.WR * 64 / 1e6 / duration_time",
"MetricName": "memory_bandwidth_write",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "Memory write bandwidth (MB/sec) caused by directory updates; includes DDR and Intel(R) Optane(TM) Persistent Memory(PMEM)",
"MetricExpr": "(UNC_CHA_DIR_UPDATE.HA + UNC_CHA_DIR_UPDATE.TOR + UNC_M2M_DIRECTORY_UPDATE.ANY) * 64 / 1e6 / duration_time",
"MetricName": "memory_extra_write_bw_due_to_directory_updates",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches",
"MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)",
"MetricName": "numa_reads_addressed_to_local_dram",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches",
"MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)",
"MetricName": "numa_reads_addressed_to_remote_dram",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue",
"MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)",
"MetricName": "percent_uops_delivered_from_decoded_icache",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue",
"MetricExpr": "IDQ.MITE_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)",
"MetricName": "percent_uops_delivered_from_legacy_decode_pipeline",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue",
"MetricExpr": "IDQ.MS_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)",
"MetricName": "percent_uops_delivered_from_microcode_sequencer",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory read bandwidth (MB/sec)",
"MetricExpr": "UNC_M_PMM_RPQ_INSERTS * 64 / 1e6 / duration_time",
"MetricName": "pmem_memory_bandwidth_read",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory bandwidth (MB/sec)",
"MetricExpr": "(UNC_M_PMM_RPQ_INSERTS + UNC_M_PMM_WPQ_INSERTS) * 64 / 1e6 / duration_time",
"MetricName": "pmem_memory_bandwidth_total",
"ScaleUnit": "1MB/s"
},
{
"BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory write bandwidth (MB/sec)",
"MetricExpr": "UNC_M_PMM_WPQ_INSERTS * 64 / 1e6 / duration_time",
"MetricName": "pmem_memory_bandwidth_write",
"ScaleUnit": "1MB/s"
},
{
"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": "The ratio of number of completed memory store instructions to the total number completed instructions",
"MetricExpr": "MEM_INST_RETIRED.ALL_STORES / INST_RETIRED.ANY",
"MetricName": "stores_per_instr",
"ScaleUnit": "1per_instr"
},
{
"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_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_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_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_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + 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))",