Lines Matching +full:- +full:100
7 …-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into mi…
8 "ScaleUnit": "100%"
15 …he CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB mi…
16 "ScaleUnit": "100%"
20 "MetricExpr": "ICACHE.IFETCH_STALL / CLKS - tma_itlb_misses",
23 "ScaleUnit": "100%"
31 "ScaleUnit": "100%"
38 … corrected path; following all sorts of miss-predicted branches. For example; branchy code with lo…
39 "ScaleUnit": "100%"
46 …o switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-en…
47 "ScaleUnit": "100%"
55 "ScaleUnit": "100%"
62 … Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legac…
63 "ScaleUnit": "100%"
67 "MetricExpr": "tma_frontend_bound - tma_fetch_latency",
71 "ScaleUnit": "100%"
75 "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / CORE_CLKS / 2",
78 …the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or …
79 "ScaleUnit": "100%"
83 "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / CORE_CLKS / 2",
87 "ScaleUnit": "100%"
91 …"MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ((INT_MISC.RECOVERY_CYCLES_ANY /…
94 …s for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For…
95 "ScaleUnit": "100%"
102 …etched from an incorrectly speculated program path; or stalls when the out-of-order part of the ma…
103 "ScaleUnit": "100%"
107 "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts",
110 …-of-order portion of the machine needs to recover its state after the clear. For example; this can…
111 "ScaleUnit": "100%"
115 "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)",
118 …-of-order scheduler dispatches ready uops into their respective execution units; and once complete…
119 "ScaleUnit": "100%"
123 …XECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if (IPC > 1.8) else UOPS_EXECUT…
126 …o demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory d…
127 "ScaleUnit": "100%"
131 …"MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVI…
134 … TLB. These cases are characterized by execution unit stalls; while some non-completed demand load…
135 "ScaleUnit": "100%"
142 …-aside Buffers) are processor caches for recently used entries out of the Page Tables that are use…
143 "ScaleUnit": "100%"
150 …perations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writi…
151 "ScaleUnit": "100%"
159 "ScaleUnit": "100%"
162 … estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache …
166 … estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache …
167 "ScaleUnit": "100%"
174 …sible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidde…
175 "ScaleUnit": "100%"
183 "ScaleUnit": "100%"
187 … "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / CLKS",
191 "ScaleUnit": "100%"
199 "ScaleUnit": "100%"
207 "ScaleUnit": "100%"
210 …n of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
214 … cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Dat…
215 "ScaleUnit": "100%"
223 "ScaleUnit": "100%"
226 …f cycles where the Super Queue (SQ) was full taking into account all request-types and both hardwa…
230 …f cycles where the Super Queue (SQ) was full taking into account all request-types and both hardwa…
231 "ScaleUnit": "100%"
235 …"MetricExpr": "(1 - (MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD…
239 "ScaleUnit": "100%"
246 …-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests …
247 "ScaleUnit": "100%"
251 …CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CLKS - tma_mem_bandwidth",
255 "ScaleUnit": "100%"
258 … CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request b…
262 …ses; RFO store issue a read-for-ownership request before the write. Even though store accesses do …
263 "ScaleUnit": "100%"
267 …etricExpr": "((L2_RQSTS.RFO_HIT * 9 * (1 - (MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STO…
270 …-of-order core performance; however; holding resources for longer time can lead into undesired imp…
271 "ScaleUnit": "100%"
278 …hreading hiccup; where multiple Logical Processors contend on different data-elements mapped into …
279 "ScaleUnit": "100%"
286 …resents rate of split store accesses. Consider aligning your data to the 64-byte cache line granu…
287 "ScaleUnit": "100%"
290 …: "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store …
294 …-level data TLB store misses. As with ordinary data caching; focus on improving data locality and…
295 "ScaleUnit": "100%"
298 …"BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of…
299 "MetricExpr": "tma_backend_bound - tma_memory_bound",
302 …-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in s…
303 "ScaleUnit": "100%"
311 "ScaleUnit": "100%"
314 … the CPU performance was potentially limited due to Core computation issues (non divider-related)",
315 …- UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if (IPC > 1.8) else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS…
318 …-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency …
319 "ScaleUnit": "100%"
323 …SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - RS_EVENTS.EMPTY_CYCL…
326 …t (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions …
327 "ScaleUnit": "100%"
331 …_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECU…
334 …-dependency among software instructions; or over oversubscribing a particular hardware resource. I…
335 "ScaleUnit": "100%"
339 …_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECU…
342 …cal Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options…
343 "ScaleUnit": "100%"
350 "ScaleUnit": "100%"
357 "ScaleUnit": "100%"
364 "ScaleUnit": "100%"
371 "ScaleUnit": "100%"
378 "ScaleUnit": "100%"
382 …"MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 - UOPS_DISPATCHED_PORT.P…
385 "ScaleUnit": "100%"
388 …ion of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads…
392 "ScaleUnit": "100%"
395 …ion of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads…
399 "ScaleUnit": "100%"
406 "ScaleUnit": "100%"
409 …sents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data) Sample with: UO…
413 "ScaleUnit": "100%"
420 …100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typic…
421 "ScaleUnit": "100%"
424 …slots where the CPU was retiring light-weight operations -- instructions that require no more than…
425 "MetricExpr": "tma_retiring - tma_heavy_operations",
428 …-weight operations -- instructions that require no more than one uop (micro-operation). This corre…
429 "ScaleUnit": "100%"
432 …"BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations frac…
436 …-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may excee…
437 "ScaleUnit": "100%"
445 "ScaleUnit": "100%"
448 …"BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction …
452 …"PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction…
453 "ScaleUnit": "100%"
456 …"BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction …
460 …"PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction…
461 "ScaleUnit": "100%"
464 …tric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructio…
468 …he CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro…
469 "ScaleUnit": "100%"
477 "ScaleUnit": "100%"
481 "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / SLOTS",
484 …er-cases for operations that cannot be handled natively by the execution pipeline. For example; wh…
485 "ScaleUnit": "100%"
489 "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
492 … as in the case of read-modify-write as an example. Since these instructions require multiple uops…
493 "ScaleUnit": "100%"
520 … "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
526 …"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor…
532 "BriefDescription": "The ratio of Executed- by Issued-Uops",
536 …"PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop m…
539 "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
551 …"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is …
630 …"BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lo…
636 …"BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core…
642 …BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is …
673 "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
679 "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
685 "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
691 … "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
697 "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
703 "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
709 "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]",
731 … supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine."
741 …"MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SM…
783 "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
789 "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
795 "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
801 "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
807 "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
813 "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
819 "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",