summaryrefslogtreecommitdiffstats
path: root/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
blob: 21e2cb5e31783d8172a9f80c29a3002fcb655feb (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
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
[
    {
        "BriefDescription": "C2 residency percent per package",
        "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC",
        "MetricGroup": "Power",
        "MetricName": "C2_Pkg_Residency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "C3 residency percent per core",
        "MetricExpr": "cstate_core@c3\\-residency@ / TSC",
        "MetricGroup": "Power",
        "MetricName": "C3_Core_Residency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "C3 residency percent per package",
        "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC",
        "MetricGroup": "Power",
        "MetricName": "C3_Pkg_Residency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "C6 residency percent per core",
        "MetricExpr": "cstate_core@c6\\-residency@ / TSC",
        "MetricGroup": "Power",
        "MetricName": "C6_Core_Residency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "C6 residency percent per package",
        "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC",
        "MetricGroup": "Power",
        "MetricName": "C6_Pkg_Residency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "C7 residency percent per core",
        "MetricExpr": "cstate_core@c7\\-residency@ / TSC",
        "MetricGroup": "Power",
        "MetricName": "C7_Core_Residency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "C7 residency percent per package",
        "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC",
        "MetricGroup": "Power",
        "MetricName": "C7_Pkg_Residency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "Uncore frequency per die [GHZ]",
        "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9",
        "MetricGroup": "SoC",
        "MetricName": "UNCORE_FREQ"
    },
    {
        "BriefDescription": "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_cpu_utilization",
        "MetricName": "cpu_utilization",
        "ScaleUnit": "100%"
    },
    {
        "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_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_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": "cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x19e@ * 64 / 1e6 / duration_time",
        "MetricName": "io_bandwidth_read",
        "ScaleUnit": "1MB/s"
    },
    {
        "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.",
        "MetricExpr": "cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x1c8\\,filter_tid\\=0x3e@ * 64 / 1e6 / duration_time",
        "MetricName": "io_bandwidth_write",
        "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_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_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_UOPS_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_UOPS_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_UOPS_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": "(cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x181@ + cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x191@) / INST_RETIRED.ANY",
        "MetricName": "llc_code_read_mpi_demand_plus_prefetch",
        "ScaleUnit": "1per_instr"
    },
    {
        "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) in nano seconds",
        "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time",
        "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency",
        "ScaleUnit": "1ns"
    },
    {
        "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to local memory in nano seconds",
        "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time",
        "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_local_requests",
        "ScaleUnit": "1ns"
    },
    {
        "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to remote memory in nano seconds",
        "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time",
        "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_remote_requests",
        "ScaleUnit": "1ns"
    },
    {
        "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": "(cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x192@) / INST_RETIRED.ANY",
        "MetricName": "llc_data_read_mpi_demand_plus_prefetch",
        "ScaleUnit": "1per_instr"
    },
    {
        "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions",
        "MetricExpr": "MEM_UOPS_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 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": "cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)",
        "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": "cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)",
        "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 / UOPS_ISSUED.ANY",
        "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 / UOPS_ISSUED.ANY",
        "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "Uops delivered from loop stream detector(LSD) as a percent of total uops delivered to Instruction Decode Queue",
        "MetricExpr": "(UOPS_ISSUED.ANY - IDQ.MITE_UOPS - IDQ.MS_UOPS - IDQ.DSB_UOPS) / UOPS_ISSUED.ANY",
        "MetricName": "percent_uops_delivered_from_loop_stream_detector",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue",
        "MetricExpr": "IDQ.MS_UOPS / UOPS_ISSUED.ANY",
        "MetricName": "percent_uops_delivered_from_microcode_sequencer",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "Intel(R) Quick Path Interconnect (QPI) data transmit bandwidth (MB/sec)",
        "MetricExpr": "UNC_Q_TxL_FLITS_G0.DATA * 8 / 1e6 / duration_time",
        "MetricName": "qpi_data_transmit_bw",
        "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_UOPS_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",
        "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
        "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
        "MetricName": "tma_4k_aliasing",
        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
        "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots",
        "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
        "MetricName": "tma_alu_op_utilization",
        "MetricThreshold": "tma_alu_op_utilization > 0.4",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists",
        "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots",
        "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
        "MetricName": "tma_assists",
        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
        "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)",
        "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
        "MetricName": "tma_backend_bound",
        "MetricThreshold": "tma_backend_bound > 0.2",
        "MetricgroupNoGroup": "TopdownL1",
        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
        "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots",
        "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
        "MetricName": "tma_bad_speculation",
        "MetricThreshold": "tma_bad_speculation > 0.15",
        "MetricgroupNoGroup": "TopdownL1",
        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation",
        "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
        "MetricName": "tma_branch_mispredicts",
        "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
        "MetricgroupNoGroup": "TopdownL2",
        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers",
        "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks",
        "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
        "MetricName": "tma_branch_resteers",
        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction",
        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
        "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
        "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
        "MetricName": "tma_cisc",
        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks",
        "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
        "MetricName": "tma_contested_accesses",
        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "tma_backend_bound - tma_memory_bound",
        "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
        "MetricName": "tma_core_bound",
        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
        "MetricgroupNoGroup": "TopdownL2",
        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
        "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
        "MetricName": "tma_data_sharing",
        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active",
        "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_core_clks",
        "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
        "MetricName": "tma_divider",
        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
        "MetricConstraint": "NO_GROUP_EVENTS_SMT",
        "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks",
        "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
        "MetricName": "tma_dram_bound",
        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline",
        "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2",
        "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
        "MetricName": "tma_dsb",
        "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines",
        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
        "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
        "MetricName": "tma_dsb_switches",
        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
        "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks",
        "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
        "MetricName": "tma_dtlb_load",
        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
        "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks",
        "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
        "MetricName": "tma_dtlb_store",
        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
        "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks",
        "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
        "MetricName": "tma_false_sharing",
        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
        "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
        "MetricName": "tma_fb_full",
        "MetricThreshold": "tma_fb_full > 0.3",
        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues",
        "MetricExpr": "tma_frontend_bound - tma_fetch_latency",
        "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
        "MetricName": "tma_fetch_bandwidth",
        "MetricThreshold": "tma_fetch_bandwidth > 0.2",
        "MetricgroupNoGroup": "TopdownL2",
        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
        "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_thread_slots",
        "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
        "MetricName": "tma_fetch_latency",
        "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
        "MetricgroupNoGroup": "TopdownL2",
        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots",
        "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
        "MetricName": "tma_frontend_bound",
        "MetricThreshold": "tma_frontend_bound > 0.15",
        "MetricgroupNoGroup": "TopdownL1",
        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
        "MetricExpr": "tma_microcode_sequencer",
        "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
        "MetricName": "tma_heavy_operations",
        "MetricThreshold": "tma_heavy_operations > 0.1",
        "MetricgroupNoGroup": "TopdownL2",
        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.",
        "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks",
        "MetricGroup": "BigFootprint;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
        "MetricName": "tma_icache_misses",
        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
        "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
        "MetricGroup": "Bad;BrMispredicts",
        "MetricName": "tma_info_bad_spec_ipmisp_indirect",
        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
    },
    {
        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
        "MetricGroup": "Bad;BadSpec;BrMispredicts",
        "MetricName": "tma_info_bad_spec_ipmispredict",
        "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200"
    },
    {
        "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
        "MetricGroup": "SMT",
        "MetricName": "tma_info_core_core_clks"
    },
    {
        "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
        "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks",
        "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group",
        "MetricName": "tma_info_core_coreipc"
    },
    {
        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
        "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))",
        "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
        "MetricName": "tma_info_core_ilp"
    },
    {
        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
        "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
        "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
        "MetricName": "tma_info_frontend_dsb_coverage",
        "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35",
        "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_inst_mix_iptb, tma_lcp"
    },
    {
        "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)",
        "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY",
        "MetricGroup": "Fed",
        "MetricName": "tma_info_frontend_ipunknown_branch"
    },
    {
        "BriefDescription": "Branch instructions per taken branch.",
        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
        "MetricGroup": "Branches;Fed;PGO",
        "MetricName": "tma_info_inst_mix_bptkbranch"
    },
    {
        "BriefDescription": "Total number of retired Instructions",
        "MetricExpr": "INST_RETIRED.ANY",
        "MetricGroup": "Summary;TmaL1;tma_L1_group",
        "MetricName": "tma_info_inst_mix_instructions",
        "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST"
    },
    {
        "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
        "MetricGroup": "Branches;Fed;InsType",
        "MetricName": "tma_info_inst_mix_ipbranch",
        "MetricThreshold": "tma_info_inst_mix_ipbranch < 8"
    },
    {
        "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
        "MetricGroup": "Branches;Fed;PGO",
        "MetricName": "tma_info_inst_mix_ipcall",
        "MetricThreshold": "tma_info_inst_mix_ipcall < 200"
    },
    {
        "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
        "MetricGroup": "InsType",
        "MetricName": "tma_info_inst_mix_ipload",
        "MetricThreshold": "tma_info_inst_mix_ipload < 3"
    },
    {
        "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
        "MetricGroup": "InsType",
        "MetricName": "tma_info_inst_mix_ipstore",
        "MetricThreshold": "tma_info_inst_mix_ipstore < 8"
    },
    {
        "BriefDescription": "Instruction per taken branch",
        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
        "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
        "MetricName": "tma_info_inst_mix_iptb",
        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
        "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp"
    },
    {
        "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
        "MetricExpr": "tma_info_memory_l1d_cache_fill_bw",
        "MetricGroup": "Mem;MemoryBW",
        "MetricName": "tma_info_memory_core_l1d_cache_fill_bw_2t"
    },
    {
        "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
        "MetricExpr": "tma_info_memory_l2_cache_fill_bw",
        "MetricGroup": "Mem;MemoryBW",
        "MetricName": "tma_info_memory_core_l2_cache_fill_bw_2t"
    },
    {
        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
        "MetricExpr": "tma_info_memory_l3_cache_fill_bw",
        "MetricGroup": "Mem;MemoryBW",
        "MetricName": "tma_info_memory_core_l3_cache_fill_bw_2t"
    },
    {
        "BriefDescription": "Average Parallel L2 cache miss data reads",
        "MetricExpr": "tma_info_memory_latency_data_l2_mlp",
        "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group",
        "MetricName": "tma_info_memory_data_l2_mlp",
        "MetricgroupNoGroup": "TopdownL1"
    },
    {
        "BriefDescription": "",
        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time",
        "MetricGroup": "Mem;MemoryBW",
        "MetricName": "tma_info_memory_l1d_cache_fill_bw"
    },
    {
        "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / (duration_time * 1e3 / 1e3)",
        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
        "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t",
        "MetricgroupNoGroup": "TopdownL1"
    },
    {
        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
        "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
        "MetricGroup": "CacheHits;Mem",
        "MetricName": "tma_info_memory_l1mpki"
    },
    {
        "BriefDescription": "",
        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time",
        "MetricGroup": "Mem;MemoryBW",
        "MetricName": "tma_info_memory_l2_cache_fill_bw"
    },
    {
        "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / (duration_time * 1e3 / 1e3)",
        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
        "MetricName": "tma_info_memory_l2_cache_fill_bw_2t",
        "MetricgroupNoGroup": "TopdownL1"
    },
    {
        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
        "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
        "MetricGroup": "Backend;CacheHits;Mem",
        "MetricName": "tma_info_memory_l2mpki"
    },
    {
        "BriefDescription": "",
        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time",
        "MetricGroup": "Mem;MemoryBW",
        "MetricName": "tma_info_memory_l3_cache_fill_bw"
    },
    {
        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / (duration_time * 1e3 / 1e3)",
        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
        "MetricName": "tma_info_memory_l3_cache_fill_bw_2t",
        "MetricgroupNoGroup": "TopdownL1"
    },
    {
        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
        "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
        "MetricGroup": "Mem",
        "MetricName": "tma_info_memory_l3mpki"
    },
    {
        "BriefDescription": "Average Parallel L2 cache miss data reads",
        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
        "MetricGroup": "Memory_BW;Offcore",
        "MetricName": "tma_info_memory_latency_data_l2_mlp"
    },
    {
        "BriefDescription": "Average Latency for L2 cache miss demand Loads",
        "MetricExpr": "tma_info_memory_load_l2_miss_latency",
        "MetricGroup": "Memory_Lat;Offcore",
        "MetricName": "tma_info_memory_latency_load_l2_miss_latency"
    },
    {
        "BriefDescription": "Average Parallel L2 cache miss demand Loads",
        "MetricExpr": "tma_info_memory_load_l2_mlp",
        "MetricGroup": "Memory_BW;Offcore",
        "MetricName": "tma_info_memory_latency_load_l2_mlp"
    },
    {
        "BriefDescription": "Average Latency for L2 cache miss demand Loads",
        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
        "MetricGroup": "Memory_Lat;Offcore;TopdownL1;tma_L1_group",
        "MetricName": "tma_info_memory_load_l2_miss_latency",
        "MetricgroupNoGroup": "TopdownL1"
    },
    {
        "BriefDescription": "Average Parallel L2 cache miss demand Loads",
        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
        "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group",
        "MetricName": "tma_info_memory_load_l2_mlp",
        "MetricgroupNoGroup": "TopdownL1"
    },
    {
        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)",
        "MetricGroup": "Mem;MemoryBound;MemoryLat",
        "MetricName": "tma_info_memory_load_miss_real_latency"
    },
    {
        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
        "MetricGroup": "Mem;MemoryBW;MemoryBound",
        "MetricName": "tma_info_memory_mlp",
        "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)"
    },
    {
        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
        "MetricExpr": "tma_info_memory_tlb_page_walks_utilization",
        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
        "MetricName": "tma_info_memory_page_walks_utilization",
        "MetricgroupNoGroup": "TopdownL1"
    },
    {
        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
        "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_core_core_clks",
        "MetricGroup": "Mem;MemoryTLB",
        "MetricName": "tma_info_memory_tlb_page_walks_utilization",
        "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
    },
    {
        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
        "MetricGroup": "Pipeline;Ret",
        "MetricName": "tma_info_pipeline_retire"
    },
    {
        "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]",
        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time",
        "MetricGroup": "Power;Summary",
        "MetricName": "tma_info_system_core_frequency"
    },
    {
        "BriefDescription": "Average CPU Utilization (percentage)",
        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
        "MetricGroup": "HPC;Summary",
        "MetricName": "tma_info_system_cpu_utilization"
    },
    {
        "BriefDescription": "Average number of utilized CPUs",
        "MetricExpr": "#num_cpus_online * tma_info_system_cpu_utilization",
        "MetricGroup": "Summary",
        "MetricName": "tma_info_system_cpus_utilized"
    },
    {
        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
        "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time",
        "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW",
        "MetricName": "tma_info_system_dram_bw_use",
        "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full"
    },
    {
        "BriefDescription": "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": "tma_info_system_ipfarbranch",
        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
    },
    {
        "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": "tma_info_system_kernel_cpi"
    },
    {
        "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": "tma_info_system_kernel_utilization",
        "MetricThreshold": "tma_info_system_kernel_utilization > 0.05"
    },
    {
        "BriefDescription": "Average number of parallel data read requests to external memory",
        "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@",
        "MetricGroup": "Mem;MemoryBW;SoC",
        "MetricName": "tma_info_system_mem_parallel_reads",
        "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
    },
    {
        "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
        "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / duration_time)",
        "MetricGroup": "Mem;MemoryLat;SoC",
        "MetricName": "tma_info_system_mem_read_latency",
        "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)"
    },
    {
        "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
        "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)",
        "MetricGroup": "SMT",
        "MetricName": "tma_info_system_smt_2t_utilization"
    },
    {
        "BriefDescription": "Socket actual clocks when any core is active on that socket",
        "MetricExpr": "cbox_0@event\\=0x0@",
        "MetricGroup": "SoC",
        "MetricName": "tma_info_system_socket_clks"
    },
    {
        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
        "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC",
        "MetricGroup": "Power",
        "MetricName": "tma_info_system_turbo_utilization"
    },
    {
        "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]",
        "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time",
        "MetricGroup": "SoC",
        "MetricName": "tma_info_system_uncore_frequency"
    },
    {
        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
        "MetricGroup": "Pipeline",
        "MetricName": "tma_info_thread_clks"
    },
    {
        "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
        "MetricExpr": "1 / tma_info_thread_ipc",
        "MetricGroup": "Mem;Pipeline",
        "MetricName": "tma_info_thread_cpi"
    },
    {
        "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
        "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks",
        "MetricGroup": "Ret;Summary",
        "MetricName": "tma_info_thread_ipc"
    },
    {
        "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
        "MetricExpr": "4 * tma_info_core_core_clks",
        "MetricGroup": "TmaL1;tma_L1_group",
        "MetricName": "tma_info_thread_slots"
    },
    {
        "BriefDescription": "Uops Per Instruction",
        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
        "MetricGroup": "Pipeline;Ret;Retire",
        "MetricName": "tma_info_thread_uoppi",
        "MetricThreshold": "tma_info_thread_uoppi > 1.05"
    },
    {
        "BriefDescription": "Instruction per taken branch",
        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
        "MetricGroup": "Branches;Fed;FetchBW",
        "MetricName": "tma_info_thread_uptb",
        "MetricThreshold": "tma_info_thread_uptb < 6"
    },
    {
        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
        "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks",
        "MetricGroup": "BigFootprint;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
        "MetricName": "tma_itlb_misses",
        "MetricThreshold": "tma_itlb_misses > 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 Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache",
        "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)",
        "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
        "MetricName": "tma_l1_bound",
        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache.  The L1 data cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
        "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_thread_clks",
        "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
        "MetricName": "tma_l2_bound",
        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
        "MetricConstraint": "NO_GROUP_EVENTS_SMT",
        "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks",
        "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
        "MetricName": "tma_l3_bound",
        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
        "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
        "MetricName": "tma_l3_hit_latency",
        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)",
        "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks",
        "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
        "MetricName": "tma_lcp",
        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
        "MetricExpr": "tma_retiring - tma_heavy_operations",
        "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
        "MetricName": "tma_light_operations",
        "MetricThreshold": "tma_light_operations > 0.6",
        "MetricgroupNoGroup": "TopdownL2",
        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations",
        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
        "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)",
        "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
        "MetricName": "tma_load_op_utilization",
        "MetricThreshold": "tma_load_op_utilization > 0.6",
        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory",
        "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
        "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
        "MetricName": "tma_local_mem",
        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks",
        "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
        "MetricName": "tma_lock_latency",
        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts",
        "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
        "MetricName": "tma_machine_clears",
        "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
        "MetricgroupNoGroup": "TopdownL2",
        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks",
        "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
        "MetricName": "tma_mem_bandwidth",
        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM)",
        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
        "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
        "MetricName": "tma_mem_latency",
        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound",
        "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
        "MetricName": "tma_memory_bound",
        "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
        "MetricgroupNoGroup": "TopdownL2",
        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit",
        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots",
        "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
        "MetricName": "tma_microcode_sequencer",
        "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
        "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit.  The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)",
        "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2",
        "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
        "MetricName": "tma_mite",
        "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)",
        "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
        "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
        "MetricName": "tma_ms_switches",
        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)",
        "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks",
        "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
        "MetricName": "tma_port_0",
        "MetricThreshold": "tma_port_0 > 0.6",
        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)",
        "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks",
        "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
        "MetricName": "tma_port_1",
        "MetricThreshold": "tma_port_1 > 0.6",
        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)",
        "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks",
        "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group",
        "MetricName": "tma_port_2",
        "MetricThreshold": "tma_port_2 > 0.6",
        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_2",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)",
        "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks",
        "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group",
        "MetricName": "tma_port_3",
        "MetricThreshold": "tma_port_3 > 0.6",
        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_3",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data)",
        "MetricExpr": "tma_store_op_utilization",
        "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group",
        "MetricName": "tma_port_4",
        "MetricThreshold": "tma_port_4 > 0.6",
        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Sample with: UOPS_DISPATCHED_PORT.PORT_4. Related metrics: tma_split_stores",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)",
        "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks",
        "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
        "MetricName": "tma_port_5",
        "MetricThreshold": "tma_port_5 > 0.6",
        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU)",
        "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_core_clks",
        "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
        "MetricName": "tma_port_6",
        "MetricThreshold": "tma_port_6 > 0.6",
        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)",
        "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_core_clks",
        "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group",
        "MetricName": "tma_port_7",
        "MetricThreshold": "tma_port_7 > 0.6",
        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address). Sample with: UOPS_DISPATCHED_PORT.PORT_7",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks",
        "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
        "MetricName": "tma_ports_utilization",
        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)",
        "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
        "MetricName": "tma_ports_utilized_0",
        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks)",
        "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
        "MetricName": "tma_ports_utilized_1",
        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks)",
        "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
        "MetricName": "tma_ports_utilized_2",
        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks",
        "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
        "MetricName": "tma_ports_utilized_3m",
        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks",
        "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
        "MetricName": "tma_remote_cache",
        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory",
        "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
        "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
        "MetricName": "tma_remote_mem",
        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots",
        "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
        "MetricName": "tma_retiring",
        "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
        "MetricgroupNoGroup": "TopdownL1",
        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks",
        "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
        "MetricName": "tma_split_loads",
        "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents rate of split store accesses",
        "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
        "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
        "MetricName": "tma_split_stores",
        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)",
        "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
        "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
        "MetricName": "tma_sq_full",
        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write",
        "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks",
        "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
        "MetricName": "tma_store_bound",
        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
        "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
        "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
        "MetricName": "tma_store_fwd_blk",
        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses",
        "MetricConstraint": "NO_GROUP_EVENTS",
        "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
        "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
        "MetricName": "tma_store_latency",
        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations",
        "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks",
        "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
        "MetricName": "tma_store_op_utilization",
        "MetricThreshold": "tma_store_op_utilization > 0.6",
        "ScaleUnit": "100%"
    },
    {
        "BriefDescription": "Uncore operating frequency in GHz",
        "MetricExpr": "UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages) / 1e9 / duration_time",
        "MetricName": "uncore_frequency",
        "ScaleUnit": "1GHz"
    }
]