Lines Matching +full:power +full:- +full:sample +full:- +full:average
4 "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC",
5 "MetricGroup": "Power",
11 "MetricExpr": "cstate_core@c1\\-residency@ / TSC",
12 "MetricGroup": "Power",
18 "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC",
19 "MetricGroup": "Power",
25 "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC",
26 "MetricGroup": "Power",
32 "MetricExpr": "cstate_core@c6\\-residency@ / TSC",
33 "MetricGroup": "Power",
39 "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC",
40 "MetricGroup": "Power",
46 "MetricExpr": "cstate_core@c7\\-residency@ / TSC",
47 "MetricGroup": "Power",
53 "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC",
54 "MetricGroup": "Power",
60 "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC",
61 "MetricGroup": "Power",
67 "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC",
68 "MetricGroup": "Power",
74 "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)",
89 "MetricExpr": "(max(cycles\\-t - cycles\\-ct, 0) / cycles if has_event(cycles\\-t) else 0)",
96 "MetricExpr": "(cycles\\-t / el\\-start if has_event(el\\-start) else 0)",
103 "MetricExpr": "(cycles\\-t / tx\\-start if has_event(cycles\\-t) else 0)",
110 "MetricExpr": "(cycles\\-t / cycles if has_event(cycles\\-t) else 0)",
139 …"MetricExpr": "(5 * cpu_atom@CPU_CLK_UNHALTED.CORE@ - (cpu_atom@TOPDOWN_FE_BOUND.ALL@ + cpu_atom@T…
304 …"MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RET…
471 …umber of machine clears relative to thousands of instructions retired, due to self-modifying code",
477 … "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block",
483 …"BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown sto…
531 … "BriefDescription": "Percentage of total non-speculative loads that perform one or more locks",
537 "BriefDescription": "Percentage of total non-speculative loads that are splits",
555 "BriefDescription": "Average CPU Utilization",
568 "BriefDescription": "Average Frequency Utilization relative nominal frequency",
570 "MetricGroup": "Power",
682 "MetricExpr": "tma_backend_bound - tma_core_bound",
732 …-cases for operations that cannot be handled natively by the execution pipeline. For example; when…
748 …opdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core…
753 …-of-order scheduler dispatches ready uops into their respective execution units; and once complete…
760 "MetricExpr": "max(1 - (tma_frontend_bound + tma_backend_bound + tma_retiring), 0)",
765 …s for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For…
771 …own\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_co…
776 …ram path; or stalls when the out-of-order part of the machine needs to recover its state from a sp…
786 …-predicted branches. For example; branchy code with lots of miss-predictions might get categorized…
791 …s the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; S…
800 …es the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; …
810 "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
814 …ead-modify-write as an example. Since these instructions require multiple uops they may or may not…
820 …"MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEE…
824 …he CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLE…
834 … true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_…
839 …"BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of…
840 "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)",
845 …-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in s…
850 …n of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
851 …_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_…
855 …-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause in…
860 …"BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active…
861 …"MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cma…
865 …"PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only activ…
875 …than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDE…
885 … loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RET…
891 …"MetricExpr": "(cpu_core@IDQ.DSB_CYCLES_ANY@ - cpu_core@IDQ.DSB_CYCLES_OK@) / tma_info_core_core_c…
905 …-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heav…
911 …@DTLB_LOAD_MISSES.WALK_ACTIVE@, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTI…
915 …-aside Buffers) are processor caches for recently used entries out of the Page Tables that are use…
920 …: "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store …
925 …-level data TLB store misses. As with ordinary data caching; focus on improving data locality and…
935 …ultiple Logical Processors contend on different data-elements mapped into the same cache line. Sam…
951 "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)",
956 …he Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RET…
962 …n\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@top…
967 …-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Fron…
973 "MetricExpr": "max(0, tma_heavy_operations - tma_microcode_sequencer)",
977 …t are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the n…
982 …"BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations frac…
987 …-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may excee…
997 …ts. FP Assist may apply when working with very small floating point values (so-called Denormals).",
1002 …"BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction …
1007 …"PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction…
1012 …"BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction …
1017 …"PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction…
1022 …tric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors",
1027 … approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May…
1032 …tric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors",
1037 … approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May…
1044 …n\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topd…
1049 …-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into mi…
1054 …represents fraction of slots where the CPU was retiring fused instructions -- where one uop can re…
1059 …represents fraction of slots where the CPU was retiring fused instructions -- where one uop can re…
1064 … slots where the CPU was retiring heavy-weight operations -- instructions that require two or more…
1065 …pdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core…
1070 …-weight operations -- instructions that require two or more uops or micro-coded sequences. This hi…
1080 … fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RET…
1085 …"BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative b…
1089 …"PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative …
1093 …"BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lowe…
1125 …"BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lo…
1140 … "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
1141 …"MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_ut…
1148 …"BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch…
1153 …"PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetc…
1157 …"BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fet…
1162 …"PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fe…
1166 …"BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bott…
1171 …"PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bot…
1175 …of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and B…
1183 …"BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset …
1188 …"PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset…
1192 …"BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottleneck…
1197 …"PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenec…
1201 …"BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
1206 …"PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks…
1210 … "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
1215 …ine cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as w…
1219 …tch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the…
1220 …- (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_…
1228 …"MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask…
1232 …"PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait tim…
1236 …ription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
1241 …"Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related m…
1246 …t_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (…
1255 …"MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispre…
1263 "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end",
1264 …"MetricExpr": "100 - (tma_info_bottleneck_big_code + tma_info_bottleneck_instruction_fetch_bw + tm…
1268 …aining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) a…
1272 …"BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring catego…
1273 …tiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_c…
1287 "BriefDescription": "Fraction of branches that are non-taken conditionals",
1302 …"MetricExpr": "(cpu_core@BR_INST_RETIRED.NEAR_TAKEN@ - cpu_core@BR_INST_RETIRED.COND_TAKEN@ - 2 * …
1309 …"MetricExpr": "1 - (tma_info_branches_cond_nt + tma_info_branches_cond_tk + tma_info_branches_call…
1322 "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
1331 "MetricGroup": "Power",
1343 …BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardles…
1347 …-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width…
1351 …efDescription": "Instruction-Level-Parallelism (average number of uops executed when there is exec…
1367 …"BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch un…
1374 "BriefDescription": "Average number of Uops issued by front-end when it issued something",
1381 "BriefDescription": "Average Latency for L1 instruction cache misses",
1388 …"BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurren…
1424 …"BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch d…
1428 …"PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch …
1443 … "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST",
1456 …"BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number mean…
1461 …"PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number mea…
1465 …"BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means h…
1470 …"PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means …
1474 …"BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower num…
1479 …"PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower nu…
1483 …"BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower num…
1488 …"PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower nu…
1556 "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
1563 "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
1570 "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
1577 "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
1584 … instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)",
1591 … "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
1612 "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
1620 …"MetricExpr": "1e3 * (cpu_core@L2_RQSTS.REFERENCES@ - cpu_core@L2_RQSTS.MISS@) / cpu_core@INST_RET…
1661 "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]",
1668 "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
1682 "BriefDescription": "Average Parallel L2 cache miss data reads",
1689 "BriefDescription": "Average Latency for L2 cache miss demand Loads",
1696 "BriefDescription": "Average Parallel L2 cache miss demand Loads",
1703 "BriefDescription": "Average Latency for L3 cache miss demand Loads",
1710 …"BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core…
1724 "BriefDescription": "Un-cacheable retired load per kilo instruction",
1731 …"BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is…
1735 …ublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is …
1739 … level TLB) code speculative misses per kilo instruction (misses of any page-size that complete th…
1746 …l TLB) data load speculative misses per kilo instruction (misses of any page-size that complete th…
1761 … TLB) data store speculative misses per kilo instruction (misses of any page-size that complete th…
1768 …"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is …
1775 "BriefDescription": "Average number of uops fetched from DSB per cycle",
1782 "BriefDescription": "Average number of uops fetched from LSD per cycle",
1789 "BriefDescription": "Average number of uops fetched from MITE per cycle",
1805 …"BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
1812 … "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
1820 … yet unhalted; covering legacy PAUSE instruction, as well as C0.1 / C0.2 power-performance optimiz…
1828 "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]",
1830 "MetricGroup": "Power;Summary",
1835 "BriefDescription": "Average CPU Utilization (percentage)",
1842 "BriefDescription": "Average number of utilized CPUs",
1849 "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
1853 …"PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Relat…
1861 …gate across all supported options of: FP precisions, scalar and vector instructions, vector-width",
1888 "BriefDescription": "Average number of parallel data read requests to external memory",
1892 …"PublicDescription": "Average number of parallel data read requests to external memory. Accounts f…
1896 … "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
1901 …tion": "Average latency of data read request to external memory (in nanoseconds). Accounts for dem…
1906 …"MetricExpr": "(1 - cpu_core@CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE@ / cpu_core@CPU_CLK_UNHALTED.REF_D…
1919 "BriefDescription": "Average Frequency Utilization relative nominal frequency",
1921 "MetricGroup": "Power",
1926 … "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
1940 "BriefDescription": "The ratio of Executed- by Issued-Uops",
1944 …"PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop m…
1955 …"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor…
1962 … "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
1995 …"BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neu…
2000 …"PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Ne…
2005 …"BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector…
2010 …"PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vecto…
2020 …tion of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RET…
2026 …"MetricExpr": "max((cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MI…
2030 …t stalls; while some non-completed demand load lives in the machine without having that demand loa…
2036 …ALL_LOADS@ - cpu_core@MEM_LOAD_RETIRED.FB_HIT@ - cpu_core@MEM_LOAD_RETIRED.L1_MISS@) * 20 / 100, m…
2040 …ncy of the L1 data cache may be exposed in pointer-chasing memory access patterns as an example. S…
2046 …"MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MIS…
2050 ….e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RET…
2056 …"MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS…
2060 ….e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RET…
2070 …performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RET…
2085 …slots where the CPU was retiring light-weight operations -- instructions that require no more than…
2086 "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
2091 …-weight operations -- instructions that require no more than one uop (micro-operation). This corre…
2101 …ion of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATC…
2106 … the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)",
2107 "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
2115 …"BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB…
2125 …"MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + …
2129 … classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RET…
2135 …"MetricExpr": "(cpu_core@LSD.CYCLES_ACTIVE@ - cpu_core@LSD.CYCLES_OK@) / tma_info_core_core_clks /…
2139 …ly does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be…
2145 "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)",
2150 …-of-order portion of the machine needs to recover its state after the clear. For example; this can…
2155 …as likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM…
2160 …- DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic i…
2165 …e the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM…
2166 …ore@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth",
2170 …e the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM…
2176 …pdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core…
2181 …o demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory d…
2196 … represents fraction of slots where the CPU was retiring memory operations -- uops for memory load…
2210 …odes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED…
2220 … Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLE…
2226 …"MetricExpr": "(cpu_core@IDQ.MITE_CYCLES_ANY@ - cpu_core@IDQ.MITE_CYCLES_OK@) / tma_info_core_core…
2230 …-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long imm…
2235 …n terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [A…
2240 …n terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [A…
2250 …-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled native…
2256 …"MetricExpr": "tma_light_operations * (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ - cpu_core@INST_RETI…
2260 …lots where the CPU was retiring branch instructions that were not fused. Non-conditional branches …
2270 …rs often use NOPs for certain address alignments - e.g. start address of a function or loop body. …
2275 …is metric represents the remaining light uops fraction the CPU has executed - remaining means not …
2276 …"MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_opera…
2280 …is metric represents the remaining light uops fraction the CPU has executed - remaining means not …
2285 …action of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches …
2286 …pr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MIS…
2295 …"MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@M…
2318 …atched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATC…
2328 …s Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATC…
2338 …patched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATC…
2343 … the CPU performance was potentially limited due to Core computation issues (non divider-related)",
2344 …_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVIT…
2348 …-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency …
2354 …RS.EMPTY\\,umask\\=1@ - cpu_core@RESOURCE_STALLS.SCOREBOARD@, 0)) / tma_info_thread_clks * (cpu_co…
2358 …t (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions …
2368 …-dependency among software instructions; or over oversubscribing a particular hardware resource. I…
2379 …-most compilers feature auto-Vectorization options today- reduces pressure on the execution ports …
2390 …ts (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTE…
2397 …topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@…
2402 …-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no r…
2407 …"BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled …
2412 …-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE seri…
2417 …sents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP o…
2422 …sents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP o…
2433 …esents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHA…
2438 … estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache …
2443 …ion of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. S…
2453 …lit store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample wit…
2458 …f cycles where the Super Queue (SQ) was full taking into account all request-types and both hardwa…
2463 …f cycles where the Super Queue (SQ) was full taking into account all request-types and both hardwa…
2468 … CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request b…
2473 …-for-ownership request before the write. Even though store accesses do not typically stall out-of-…
2483 …perations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writi…
2489 …_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIR…
2493 …-of-order core performance; however; holding resources for longer time can lead into undesired imp…
2503 …on of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATC…
2508 …tion of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)",
2509 "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
2531 …t-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be f…
2541 …is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RET…