summaryrefslogtreecommitdiff
path: root/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
blob: 622c392f59be32f2886c24ffe877736f66a929c3 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
[
    {
        "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)",
        "MetricExpr": "100 * (( BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) ) / TOPDOWN.SLOTS)",
        "MetricGroup": "Ret",
        "MetricName": "Branching_Overhead"
    },
    {
        "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
        "MetricExpr": "100 * (( 5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING ) / TOPDOWN.SLOTS) * ( (ICACHE_64B.IFTAG_STALL / CPU_CLK_UNHALTED.THREAD) + (ICACHE_16B.IFDATA_STALL / CPU_CLK_UNHALTED.THREAD) + (10 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) ) / #(( 5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING ) / TOPDOWN.SLOTS)",
        "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB",
        "MetricName": "Big_Code"
    },
    {
        "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
        "MetricGroup": "Ret;Summary",
        "MetricName": "IPC"
    },
    {
        "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
        "MetricExpr": "1 / (INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD)",
        "MetricGroup": "Pipeline;Mem",
        "MetricName": "CPI"
    },
    {
        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
        "MetricGroup": "Pipeline",
        "MetricName": "CLKS"
    },
    {
        "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
        "MetricExpr": "TOPDOWN.SLOTS",
        "MetricGroup": "TmaL1",
        "MetricName": "SLOTS"
    },
    {
        "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
        "MetricExpr": "TOPDOWN.SLOTS / ( TOPDOWN.SLOTS / 2 ) if #SMT_on else 1",
        "MetricGroup": "SMT",
        "MetricName": "Slots_Utilization"
    },
    {
        "BriefDescription": "The ratio of Executed- by Issued-Uops",
        "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
        "MetricGroup": "Cor;Pipeline",
        "MetricName": "Execute_per_Issue",
        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
    },
    {
        "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.DISTRIBUTED",
        "MetricGroup": "Ret;SMT;TmaL1",
        "MetricName": "CoreIPC"
    },
    {
        "BriefDescription": "Floating Point Operations Per Cycle",
        "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / CPU_CLK_UNHALTED.DISTRIBUTED",
        "MetricGroup": "Ret;Flops",
        "MetricName": "FLOPc"
    },
    {
        "BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width)",
        "MetricExpr": "( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) ) / ( 2 * CPU_CLK_UNHALTED.DISTRIBUTED )",
        "MetricGroup": "Cor;Flops;HPC",
        "MetricName": "FP_Arith_Utilization",
        "PublicDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). Values > 1 are possible due to Fused-Multiply Add (FMA) counting."
    },
    {
        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
        "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
        "MetricName": "ILP"
    },
    {
        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
        "MetricGroup": "Bad;BadSpec;BrMispredicts",
        "MetricName": "IpMispredict"
    },
    {
        "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
        "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED",
        "MetricGroup": "SMT",
        "MetricName": "CORE_CLKS"
    },
    {
        "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
        "MetricGroup": "InsType",
        "MetricName": "IpLoad"
    },
    {
        "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
        "MetricGroup": "InsType",
        "MetricName": "IpStore"
    },
    {
        "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
        "MetricGroup": "Branches;Fed;InsType",
        "MetricName": "IpBranch"
    },
    {
        "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": "IpCall"
    },
    {
        "BriefDescription": "Instruction per taken branch",
        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
        "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO",
        "MetricName": "IpTB"
    },
    {
        "BriefDescription": "Branch instructions per taken branch. ",
        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
        "MetricGroup": "Branches;Fed;PGO",
        "MetricName": "BpTkBranch"
    },
    {
        "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )",
        "MetricGroup": "Flops;InsType",
        "MetricName": "IpFLOP"
    },
    {
        "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / ( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) )",
        "MetricGroup": "Flops;InsType",
        "MetricName": "IpArith",
        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW."
    },
    {
        "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
        "MetricGroup": "Flops;FpScalar;InsType",
        "MetricName": "IpArith_Scalar_SP",
        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
    },
    {
        "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
        "MetricGroup": "Flops;FpScalar;InsType",
        "MetricName": "IpArith_Scalar_DP",
        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
    },
    {
        "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE )",
        "MetricGroup": "Flops;FpVector;InsType",
        "MetricName": "IpArith_AVX128",
        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
    },
    {
        "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )",
        "MetricGroup": "Flops;FpVector;InsType",
        "MetricName": "IpArith_AVX256",
        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
    },
    {
        "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )",
        "MetricGroup": "Flops;FpVector;InsType",
        "MetricName": "IpArith_AVX512",
        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
    },
    {
        "BriefDescription": "Total number of retired Instructions, Sample with: INST_RETIRED.PREC_DIST",
        "MetricExpr": "INST_RETIRED.ANY",
        "MetricGroup": "Summary;TmaL1",
        "MetricName": "Instructions"
    },
    {
        "BriefDescription": "Average number of Uops issued by front-end when it issued something",
        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
        "MetricGroup": "Fed;FetchBW",
        "MetricName": "Fetch_UpC"
    },
    {
        "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
        "MetricExpr": "LSD.UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
        "MetricGroup": "Fed;LSD",
        "MetricName": "LSD_Coverage"
    },
    {
        "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",
        "MetricName": "DSB_Coverage"
    },
    {
        "BriefDescription": "Number of Instructions per non-speculative DSB miss",
        "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
        "MetricGroup": "DSBmiss;Fed",
        "MetricName": "IpDSB_Miss_Ret"
    },
    {
        "BriefDescription": "Fraction of branches that are non-taken conditionals",
        "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES",
        "MetricGroup": "Bad;Branches;CodeGen;PGO",
        "MetricName": "Cond_NT"
    },
    {
        "BriefDescription": "Fraction of branches that are taken conditionals",
        "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES",
        "MetricGroup": "Bad;Branches;CodeGen;PGO",
        "MetricName": "Cond_TK"
    },
    {
        "BriefDescription": "Fraction of branches that are CALL or RET",
        "MetricExpr": "( BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN ) / BR_INST_RETIRED.ALL_BRANCHES",
        "MetricGroup": "Bad;Branches",
        "MetricName": "CallRet"
    },
    {
        "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps",
        "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES",
        "MetricGroup": "Bad;Branches",
        "MetricName": "Jump"
    },
    {
        "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)",
        "MetricExpr": "1 - ( (BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES) + (BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES) + (( BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN ) / BR_INST_RETIRED.ALL_BRANCHES) + ((BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES) )",
        "MetricGroup": "Bad;Branches",
        "MetricName": "Other_Branches"
    },
    {
        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles)",
        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
        "MetricGroup": "Mem;MemoryBound;MemoryLat",
        "MetricName": "Load_Miss_Real_Latency",
        "PublicDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles). Latency may be overestimated for multi-load instructions - e.g. repeat strings."
    },
    {
        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
        "MetricGroup": "Mem;MemoryBound;MemoryBW",
        "MetricName": "MLP"
    },
    {
        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
        "MetricGroup": "Mem;MemoryBW",
        "MetricName": "L1D_Cache_Fill_BW"
    },
    {
        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
        "MetricGroup": "Mem;MemoryBW",
        "MetricName": "L2_Cache_Fill_BW"
    },
    {
        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
        "MetricGroup": "Mem;MemoryBW",
        "MetricName": "L3_Cache_Fill_BW"
    },
    {
        "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
        "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
        "MetricGroup": "Mem;MemoryBW;Offcore",
        "MetricName": "L3_Cache_Access_BW"
    },
    {
        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
        "MetricGroup": "Mem;CacheMisses",
        "MetricName": "L1MPKI"
    },
    {
        "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)",
        "MetricExpr": "1000 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY",
        "MetricGroup": "Mem;CacheMisses",
        "MetricName": "L1MPKI_Load"
    },
    {
        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
        "MetricGroup": "Mem;Backend;CacheMisses",
        "MetricName": "L2MPKI"
    },
    {
        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
        "MetricExpr": "1000 * ( ( OFFCORE_REQUESTS.ALL_DATA_RD - OFFCORE_REQUESTS.DEMAND_DATA_RD ) + L2_RQSTS.ALL_DEMAND_MISS + L2_RQSTS.SWPF_MISS ) / INST_RETIRED.ANY",
        "MetricGroup": "Mem;CacheMisses;Offcore",
        "MetricName": "L2MPKI_All"
    },
    {
        "BriefDescription": "L2 cache misses per kilo instruction for all demand loads  (including speculative)",
        "MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY",
        "MetricGroup": "Mem;CacheMisses",
        "MetricName": "L2MPKI_Load"
    },
    {
        "BriefDescription": "L2 cache hits per kilo instruction for all demand loads  (including speculative)",
        "MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY",
        "MetricGroup": "Mem;CacheMisses",
        "MetricName": "L2HPKI_Load"
    },
    {
        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
        "MetricGroup": "Mem;CacheMisses",
        "MetricName": "L3MPKI"
    },
    {
        "BriefDescription": "Fill Buffer (FB) true hits per kilo instructions for retired demand loads",
        "MetricExpr": "1000 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY",
        "MetricGroup": "Mem;CacheMisses",
        "MetricName": "FB_HPKI"
    },
    {
        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
        "MetricConstraint": "NO_NMI_WATCHDOG",
        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING ) / ( 2 * CPU_CLK_UNHALTED.DISTRIBUTED )",
        "MetricGroup": "Mem;MemoryTLB",
        "MetricName": "Page_Walks_Utilization"
    },
    {
        "BriefDescription": "Average CPU Utilization",
        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
        "MetricGroup": "HPC;Summary",
        "MetricName": "CPU_Utilization"
    },
    {
        "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]",
        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time",
        "MetricGroup": "Summary;Power",
        "MetricName": "Average_Frequency"
    },
    {
        "BriefDescription": "Giga Floating Point Operations Per Second",
        "MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / 1000000000 ) / duration_time",
        "MetricGroup": "Cor;Flops;HPC",
        "MetricName": "GFLOPs"
    },
    {
        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
        "MetricGroup": "Power",
        "MetricName": "Turbo_Utilization"
    },
    {
        "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0",
        "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
        "MetricGroup": "Power",
        "MetricName": "Power_License0_Utilization",
        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes."
    },
    {
        "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1",
        "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
        "MetricGroup": "Power",
        "MetricName": "Power_License1_Utilization",
        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions."
    },
    {
        "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)",
        "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
        "MetricGroup": "Power",
        "MetricName": "Power_License2_Utilization",
        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions."
    },
    {
        "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
        "MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0",
        "MetricGroup": "SMT",
        "MetricName": "SMT_2T_Utilization"
    },
    {
        "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
        "MetricGroup": "OS",
        "MetricName": "Kernel_Utilization"
    },
    {
        "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
        "MetricGroup": "OS",
        "MetricName": "Kernel_CPI"
    },
    {
        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
        "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
        "MetricGroup": "HPC;Mem;MemoryBW;SoC",
        "MetricName": "DRAM_BW_Use"
    },
    {
        "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
        "MetricGroup": "Branches;OS",
        "MetricName": "IpFarBranch"
    },
    {
        "BriefDescription": "C6 residency percent per core",
        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
        "MetricGroup": "Power",
        "MetricName": "C6_Core_Residency"
    },
    {
        "BriefDescription": "C7 residency percent per core",
        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
        "MetricGroup": "Power",
        "MetricName": "C7_Core_Residency"
    },
    {
        "BriefDescription": "C2 residency percent per package",
        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
        "MetricGroup": "Power",
        "MetricName": "C2_Pkg_Residency"
    },
    {
        "BriefDescription": "C3 residency percent per package",
        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
        "MetricGroup": "Power",
        "MetricName": "C3_Pkg_Residency"
    },
    {
        "BriefDescription": "C6 residency percent per package",
        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
        "MetricGroup": "Power",
        "MetricName": "C6_Pkg_Residency"
    },
    {
        "BriefDescription": "C7 residency percent per package",
        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
        "MetricGroup": "Power",
        "MetricName": "C7_Pkg_Residency"
    },
    {
        "BriefDescription": "C8 residency percent per package",
        "MetricExpr": "(cstate_pkg@c8\\-residency@ / msr@tsc@) * 100",
        "MetricGroup": "Power",
        "MetricName": "C8_Pkg_Residency"
    },
    {
        "BriefDescription": "C9 residency percent per package",
        "MetricExpr": "(cstate_pkg@c9\\-residency@ / msr@tsc@) * 100",
        "MetricGroup": "Power",
        "MetricName": "C9_Pkg_Residency"
    },
    {
        "BriefDescription": "C10 residency percent per package",
        "MetricExpr": "(cstate_pkg@c10\\-residency@ / msr@tsc@) * 100",
        "MetricGroup": "Power",
        "MetricName": "C10_Pkg_Residency"
    }
]