blob: 5bb546882ae70e0a3d7e3c5b689584ea601ac595 (
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
|
---------- Begin Simulation Statistics ----------
sim_seconds 0.090508 # Number of seconds simulated
sim_ticks 90508462500 # Number of ticks simulated
sim_freq 1000000000000 # Frequency of simulated ticks
host_inst_rate 100669 # Simulator instruction rate (inst/s)
host_tick_rate 24259753 # Simulator tick rate (ticks/s)
host_mem_usage 252880 # Number of bytes of host memory used
host_seconds 3730.81 # Real time elapsed on the host
sim_insts 375574794 # Number of instructions simulated
system.cpu.dtb.fetch_hits 0 # ITB hits
system.cpu.dtb.fetch_misses 0 # ITB misses
system.cpu.dtb.fetch_acv 0 # ITB acv
system.cpu.dtb.fetch_accesses 0 # ITB accesses
system.cpu.dtb.read_hits 105325909 # DTB read hits
system.cpu.dtb.read_misses 93344 # DTB read misses
system.cpu.dtb.read_acv 48634 # DTB read access violations
system.cpu.dtb.read_accesses 105419253 # DTB read accesses
system.cpu.dtb.write_hits 79718162 # DTB write hits
system.cpu.dtb.write_misses 1558 # DTB write misses
system.cpu.dtb.write_acv 0 # DTB write access violations
system.cpu.dtb.write_accesses 79719720 # DTB write accesses
system.cpu.dtb.data_hits 185044071 # DTB hits
system.cpu.dtb.data_misses 94902 # DTB misses
system.cpu.dtb.data_acv 48634 # DTB access violations
system.cpu.dtb.data_accesses 185138973 # DTB accesses
system.cpu.itb.fetch_hits 58032693 # ITB hits
system.cpu.itb.fetch_misses 351 # ITB misses
system.cpu.itb.fetch_acv 0 # ITB acv
system.cpu.itb.fetch_accesses 58033044 # ITB accesses
system.cpu.itb.read_hits 0 # DTB read hits
system.cpu.itb.read_misses 0 # DTB read misses
system.cpu.itb.read_acv 0 # DTB read access violations
system.cpu.itb.read_accesses 0 # DTB read accesses
system.cpu.itb.write_hits 0 # DTB write hits
system.cpu.itb.write_misses 0 # DTB write misses
system.cpu.itb.write_acv 0 # DTB write access violations
system.cpu.itb.write_accesses 0 # DTB write accesses
system.cpu.itb.data_hits 0 # DTB hits
system.cpu.itb.data_misses 0 # DTB misses
system.cpu.itb.data_acv 0 # DTB access violations
system.cpu.itb.data_accesses 0 # DTB accesses
system.cpu.workload.num_syscalls 215 # Number of system calls
system.cpu.numCycles 181016927 # number of cpu cycles simulated
system.cpu.numWorkItemsStarted 0 # number of work items this cpu started
system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed
system.cpu.BPredUnit.lookups 56908652 # Number of BP lookups
system.cpu.BPredUnit.condPredicted 33128839 # Number of conditional branches predicted
system.cpu.BPredUnit.condIncorrect 3549307 # Number of conditional branches incorrect
system.cpu.BPredUnit.BTBLookups 40569971 # Number of BTB lookups
system.cpu.BPredUnit.BTBHits 32137344 # Number of BTB hits
system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly.
system.cpu.BPredUnit.usedRAS 10736279 # Number of times the RAS was used to get a target.
system.cpu.BPredUnit.RASInCorrect 1343 # Number of incorrect RAS predictions.
system.cpu.fetch.icacheStallCycles 59988242 # Number of cycles fetch is stalled on an Icache miss
system.cpu.fetch.Insts 503999677 # Number of instructions fetch has processed
system.cpu.fetch.Branches 56908652 # Number of branches that fetch encountered
system.cpu.fetch.predictedBranches 42873623 # Number of branches that fetch has predicted taken
system.cpu.fetch.Cycles 93805949 # Number of cycles fetch has run and was not squashing or blocked
system.cpu.fetch.SquashCycles 12846494 # Number of cycles fetch has spent squashing
system.cpu.fetch.BlockedCycles 17811682 # Number of cycles fetch has spent blocked
system.cpu.fetch.MiscStallCycles 180 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
system.cpu.fetch.PendingTrapStallCycles 7687 # Number of stall cycles due to pending traps
system.cpu.fetch.CacheLines 58032693 # Number of cache lines fetched
system.cpu.fetch.IcacheSquashes 1098562 # Number of outstanding Icache misses that were squashed
system.cpu.fetch.rateDist::samples 180895317 # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::mean 2.786140 # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::stdev 3.241759 # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::underflows 0 0.00% 0.00% # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::0 87089368 48.14% 48.14% # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::1 8126413 4.49% 52.64% # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::2 9953250 5.50% 58.14% # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::3 6311167 3.49% 61.63% # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::4 13618559 7.53% 69.16% # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::5 9505792 5.25% 74.41% # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::6 5896466 3.26% 77.67% # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::7 3503145 1.94% 79.61% # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::8 36891157 20.39% 100.00% # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::overflows 0 0.00% 100.00% # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::min_value 0 # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::max_value 8 # Number of instructions fetched each cycle (Total)
system.cpu.fetch.rateDist::total 180895317 # Number of instructions fetched each cycle (Total)
system.cpu.fetch.branchRate 0.314383 # Number of branch fetches per cycle
system.cpu.fetch.rate 2.784268 # Number of inst fetches per cycle
system.cpu.decode.IdleCycles 66262768 # Number of cycles decode is idle
system.cpu.decode.BlockedCycles 13721794 # Number of cycles decode is blocked
system.cpu.decode.RunCycles 87804231 # Number of cycles decode is running
system.cpu.decode.UnblockCycles 3829220 # Number of cycles decode is unblocking
system.cpu.decode.SquashCycles 9277304 # Number of cycles decode is squashing
system.cpu.decode.BranchResolved 10346731 # Number of times decode resolved a branch
system.cpu.decode.BranchMispred 4343 # Number of times decode detected a branch misprediction
system.cpu.decode.DecodedInsts 492360513 # Number of instructions handled by decode
system.cpu.decode.SquashedInsts 11994 # Number of squashed instructions handled by decode
system.cpu.rename.SquashCycles 9277304 # Number of cycles rename is squashing
system.cpu.rename.IdleCycles 70771279 # Number of cycles rename is idle
system.cpu.rename.BlockCycles 4688791 # Number of cycles rename is blocking
system.cpu.rename.serializeStallCycles 402464 # count of cycles rename stalled for serializing inst
system.cpu.rename.RunCycles 87101855 # Number of cycles rename is running
system.cpu.rename.UnblockCycles 8653624 # Number of cycles rename is unblocking
system.cpu.rename.RenamedInsts 479416177 # Number of instructions processed by rename
system.cpu.rename.ROBFullEvents 6 # Number of times rename has blocked due to ROB full
system.cpu.rename.IQFullEvents 50185 # Number of times rename has blocked due to IQ full
system.cpu.rename.LSQFullEvents 7149377 # Number of times rename has blocked due to LSQ full
system.cpu.rename.RenamedOperands 311562327 # Number of destination operands rename has renamed
system.cpu.rename.RenameLookups 628686073 # Number of register rename lookups that rename has made
system.cpu.rename.int_rename_lookups 332583088 # Number of integer rename lookups
system.cpu.rename.fp_rename_lookups 296102985 # Number of floating rename lookups
system.cpu.rename.CommittedMaps 259532319 # Number of HB maps that are committed
system.cpu.rename.UndoneMaps 52030008 # Number of HB maps that are undone due to squashing
system.cpu.rename.serializingInsts 38365 # count of serializing insts renamed
system.cpu.rename.tempSerializingInsts 280 # count of temporary serializing insts renamed
system.cpu.rename.skidInsts 23740235 # count of insts added to the skid buffer
system.cpu.memDep0.insertedLoads 110658167 # Number of loads inserted to the mem dependence unit.
system.cpu.memDep0.insertedStores 85526614 # Number of stores inserted to the mem dependence unit.
system.cpu.memDep0.conflictingLoads 15465988 # Number of conflicting loads.
system.cpu.memDep0.conflictingStores 10430696 # Number of conflicting stores.
system.cpu.iq.iqInstsAdded 434355597 # Number of instructions added to the IQ (excludes non-spec)
system.cpu.iq.iqNonSpecInstsAdded 252 # Number of non-speculative instructions added to the IQ
system.cpu.iq.iqInstsIssued 419519707 # Number of instructions issued
system.cpu.iq.iqSquashedInstsIssued 1756806 # Number of squashed instructions issued
system.cpu.iq.iqSquashedInstsExamined 57360180 # Number of squashed instructions iterated over during squash; mainly for profiling
system.cpu.iq.iqSquashedOperandsExamined 32293778 # Number of squashed operands that are examined and possibly removed from graph
system.cpu.iq.iqSquashedNonSpecRemoved 37 # Number of squashed non-spec instructions that were removed
system.cpu.iq.issued_per_cycle::samples 180895317 # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::mean 2.319130 # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::stdev 1.993104 # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::0 44820498 24.78% 24.78% # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::1 29979430 16.57% 41.35% # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::2 28846817 15.95% 57.30% # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::3 25627519 14.17% 71.46% # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::4 22480714 12.43% 83.89% # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::5 15907163 8.79% 92.68% # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::6 8306052 4.59% 97.28% # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::7 3747889 2.07% 99.35% # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::8 1179235 0.65% 100.00% # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::min_value 0 # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::max_value 8 # Number of insts issued each cycle
system.cpu.iq.issued_per_cycle::total 180895317 # Number of insts issued each cycle
system.cpu.iq.fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available
system.cpu.iq.fu_full::IntAlu 69354 0.60% 0.60% # attempts to use FU when none available
system.cpu.iq.fu_full::IntMult 0 0.00% 0.60% # attempts to use FU when none available
system.cpu.iq.fu_full::IntDiv 0 0.00% 0.60% # attempts to use FU when none available
system.cpu.iq.fu_full::FloatAdd 38404 0.33% 0.93% # attempts to use FU when none available
system.cpu.iq.fu_full::FloatCmp 5709 0.05% 0.98% # attempts to use FU when none available
system.cpu.iq.fu_full::FloatCvt 19332 0.17% 1.15% # attempts to use FU when none available
system.cpu.iq.fu_full::FloatMult 2037444 17.66% 18.81% # attempts to use FU when none available
system.cpu.iq.fu_full::FloatDiv 875919 7.59% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::FloatSqrt 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdAdd 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdAlu 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdCmp 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdCvt 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdMisc 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdMult 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdShift 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdSqrt 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 26.40% # attempts to use FU when none available
system.cpu.iq.fu_full::MemRead 5719458 49.56% 75.96% # attempts to use FU when none available
system.cpu.iq.fu_full::MemWrite 2774394 24.04% 100.00% # attempts to use FU when none available
system.cpu.iq.fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available
system.cpu.iq.fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available
system.cpu.iq.FU_type_0::No_OpClass 33581 0.01% 0.01% # Type of FU issued
system.cpu.iq.FU_type_0::IntAlu 164900286 39.31% 39.31% # Type of FU issued
system.cpu.iq.FU_type_0::IntMult 2243051 0.53% 39.85% # Type of FU issued
system.cpu.iq.FU_type_0::IntDiv 0 0.00% 39.85% # Type of FU issued
system.cpu.iq.FU_type_0::FloatAdd 33844550 8.07% 47.92% # Type of FU issued
system.cpu.iq.FU_type_0::FloatCmp 7897710 1.88% 49.80% # Type of FU issued
system.cpu.iq.FU_type_0::FloatCvt 2993735 0.71% 50.51% # Type of FU issued
system.cpu.iq.FU_type_0::FloatMult 16825521 4.01% 54.52% # Type of FU issued
system.cpu.iq.FU_type_0::FloatDiv 1580906 0.38% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::FloatSqrt 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdAdd 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdAddAcc 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdAlu 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdCmp 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdCvt 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdMisc 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdMult 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdMultAcc 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdShift 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdShiftAcc 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdSqrt 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdFloatAdd 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdFloatAlu 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdFloatCmp 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdFloatCvt 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdFloatDiv 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdFloatMisc 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 54.90% # Type of FU issued
system.cpu.iq.FU_type_0::MemRead 107841565 25.71% 80.61% # Type of FU issued
system.cpu.iq.FU_type_0::MemWrite 81358802 19.39% 100.00% # Type of FU issued
system.cpu.iq.FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued
system.cpu.iq.FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued
system.cpu.iq.FU_type_0::total 419519707 # Type of FU issued
system.cpu.iq.rate 2.317572 # Inst issue rate
system.cpu.iq.fu_busy_cnt 11540014 # FU busy when requested
system.cpu.iq.fu_busy_rate 0.027508 # FU busy rate (busy events/executed inst)
system.cpu.iq.int_inst_queue_reads 685462958 # Number of integer instruction queue reads
system.cpu.iq.int_inst_queue_writes 291219348 # Number of integer instruction queue writes
system.cpu.iq.int_inst_queue_wakeup_accesses 242560611 # Number of integer instruction queue wakeup accesses
system.cpu.iq.fp_inst_queue_reads 347768593 # Number of floating instruction queue reads
system.cpu.iq.fp_inst_queue_writes 200512633 # Number of floating instruction queue writes
system.cpu.iq.fp_inst_queue_wakeup_accesses 164917620 # Number of floating instruction queue wakeup accesses
system.cpu.iq.int_alu_accesses 253759021 # Number of integer alu accesses
system.cpu.iq.fp_alu_accesses 177267119 # Number of floating point alu accesses
system.cpu.iew.lsq.thread0.forwLoads 14283738 # Number of loads that had data forwarded from stores
system.cpu.iew.lsq.thread0.invAddrLoads 0 # Number of loads ignored due to an invalid address
system.cpu.iew.lsq.thread0.squashedLoads 15903681 # Number of loads squashed
system.cpu.iew.lsq.thread0.ignoredResponses 169313 # Number of memory responses ignored because the instruction is squashed
system.cpu.iew.lsq.thread0.memOrderViolation 15968 # Number of memory ordering violations
system.cpu.iew.lsq.thread0.squashedStores 12005886 # Number of stores squashed
system.cpu.iew.lsq.thread0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address
system.cpu.iew.lsq.thread0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding
system.cpu.iew.lsq.thread0.rescheduledLoads 213972 # Number of loads that were rescheduled
system.cpu.iew.lsq.thread0.cacheBlocked 3 # Number of times an access to memory failed due to the cache being blocked
system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle
system.cpu.iew.iewSquashCycles 9277304 # Number of cycles IEW is squashing
system.cpu.iew.iewBlockCycles 2317535 # Number of cycles IEW is blocking
system.cpu.iew.iewUnblockCycles 350843 # Number of cycles IEW is unblocking
system.cpu.iew.iewDispatchedInsts 460018539 # Number of instructions dispatched to IQ
system.cpu.iew.iewDispSquashedInsts 2425230 # Number of squashed instructions skipped by dispatch
system.cpu.iew.iewDispLoadInsts 110658167 # Number of dispatched load instructions
system.cpu.iew.iewDispStoreInsts 85526614 # Number of dispatched store instructions
system.cpu.iew.iewDispNonSpecInsts 252 # Number of dispatched non-speculative instructions
system.cpu.iew.iewIQFullEvents 132 # Number of times the IQ has become full, causing a stall
system.cpu.iew.iewLSQFullEvents 14 # Number of times the LSQ has become full, causing a stall
system.cpu.iew.memOrderViolationEvents 15968 # Number of memory order violations
system.cpu.iew.predictedTakenIncorrect 3438704 # Number of branches that were predicted taken incorrectly
system.cpu.iew.predictedNotTakenIncorrect 545017 # Number of branches that were predicted not taken incorrectly
system.cpu.iew.branchMispredicts 3983721 # Number of branch mispredicts detected at execute
system.cpu.iew.iewExecutedInsts 411016170 # Number of executed instructions
system.cpu.iew.iewExecLoadInsts 105467950 # Number of load instructions executed
system.cpu.iew.iewExecSquashedInsts 8503537 # Number of squashed instructions skipped in execute
system.cpu.iew.exec_swp 0 # number of swp insts executed
system.cpu.iew.exec_nop 25662690 # number of nop insts executed
system.cpu.iew.exec_refs 185187689 # number of memory reference insts executed
system.cpu.iew.exec_branches 48286737 # Number of branches executed
system.cpu.iew.exec_stores 79719739 # Number of stores executed
system.cpu.iew.exec_rate 2.270595 # Inst execution rate
system.cpu.iew.wb_sent 408658291 # cumulative count of insts sent to commit
system.cpu.iew.wb_count 407478231 # cumulative count of insts written-back
system.cpu.iew.wb_producers 198809248 # num instructions producing a value
system.cpu.iew.wb_consumers 280006771 # num instructions consuming a value
system.cpu.iew.wb_penalized 0 # number of instrctions required to write to 'other' IQ
system.cpu.iew.wb_rate 2.251050 # insts written-back per cycle
system.cpu.iew.wb_fanout 0.710016 # average fanout of values written-back
system.cpu.iew.wb_penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ
system.cpu.commit.commitCommittedInsts 398664569 # The number of committed instructions
system.cpu.commit.commitSquashedInsts 61360500 # The number of squashed insts skipped by commit
system.cpu.commit.commitNonSpecStalls 215 # The number of times commit has been forced to stall to communicate backwards
system.cpu.commit.branchMispredicts 3545034 # The number of times a branch was mispredicted
system.cpu.commit.committed_per_cycle::samples 171618013 # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::mean 2.322976 # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::stdev 2.832511 # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::0 70646303 41.16% 41.16% # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::1 26006834 15.15% 56.32% # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::2 15503557 9.03% 65.35% # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::3 13282401 7.74% 73.09% # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::4 8794833 5.12% 78.22% # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::5 6427011 3.74% 81.96% # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::6 5152706 3.00% 84.96% # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::7 2862149 1.67% 86.63% # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::8 22942219 13.37% 100.00% # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::overflows 0 0.00% 100.00% # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::min_value 0 # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::max_value 8 # Number of insts commited each cycle
system.cpu.commit.committed_per_cycle::total 171618013 # Number of insts commited each cycle
system.cpu.commit.count 398664569 # Number of instructions committed
system.cpu.commit.swp_count 0 # Number of s/w prefetches committed
system.cpu.commit.refs 168275214 # Number of memory references committed
system.cpu.commit.loads 94754486 # Number of loads committed
system.cpu.commit.membars 0 # Number of memory barriers committed
system.cpu.commit.branches 44587530 # Number of branches committed
system.cpu.commit.fp_insts 155295106 # Number of committed floating point instructions.
system.cpu.commit.int_insts 316365825 # Number of committed integer instructions.
system.cpu.commit.function_calls 8007752 # Number of function calls committed.
system.cpu.commit.bw_lim_events 22942219 # number cycles where commit BW limit reached
system.cpu.commit.bw_limited 0 # number of insts not committed due to BW limits
system.cpu.rob.rob_reads 608697886 # The number of ROB reads
system.cpu.rob.rob_writes 929339596 # The number of ROB writes
system.cpu.timesIdled 2701 # Number of times that the entire CPU went into an idle state and unscheduled itself
system.cpu.idleCycles 121610 # Total number of cycles that the CPU has spent unscheduled due to idling
system.cpu.committedInsts 375574794 # Number of Instructions Simulated
system.cpu.committedInsts_total 375574794 # Number of Instructions Simulated
system.cpu.cpi 0.481973 # CPI: Cycles Per Instruction
system.cpu.cpi_total 0.481973 # CPI: Total CPI of All Threads
system.cpu.ipc 2.074805 # IPC: Instructions Per Cycle
system.cpu.ipc_total 2.074805 # IPC: Total IPC of All Threads
system.cpu.int_regfile_reads 410790761 # number of integer regfile reads
system.cpu.int_regfile_writes 176550359 # number of integer regfile writes
system.cpu.fp_regfile_reads 159677516 # number of floating regfile reads
system.cpu.fp_regfile_writes 106247961 # number of floating regfile writes
system.cpu.misc_regfile_reads 350572 # number of misc regfile reads
system.cpu.misc_regfile_writes 1 # number of misc regfile writes
system.cpu.icache.replacements 2105 # number of replacements
system.cpu.icache.tagsinuse 1832.667923 # Cycle average of tags in use
system.cpu.icache.total_refs 58027410 # Total number of references to valid blocks.
system.cpu.icache.sampled_refs 4031 # Sample count of references to valid blocks.
system.cpu.icache.avg_refs 14395.289010 # Average number of references to valid blocks.
system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit.
system.cpu.icache.occ_blocks::0 1832.667923 # Average occupied blocks per context
system.cpu.icache.occ_percent::0 0.894857 # Average percentage of cache occupancy
system.cpu.icache.ReadReq_hits 58027410 # number of ReadReq hits
system.cpu.icache.demand_hits 58027410 # number of demand (read+write) hits
system.cpu.icache.overall_hits 58027410 # number of overall hits
system.cpu.icache.ReadReq_misses 5283 # number of ReadReq misses
system.cpu.icache.demand_misses 5283 # number of demand (read+write) misses
system.cpu.icache.overall_misses 5283 # number of overall misses
system.cpu.icache.ReadReq_miss_latency 167989000 # number of ReadReq miss cycles
system.cpu.icache.demand_miss_latency 167989000 # number of demand (read+write) miss cycles
system.cpu.icache.overall_miss_latency 167989000 # number of overall miss cycles
system.cpu.icache.ReadReq_accesses 58032693 # number of ReadReq accesses(hits+misses)
system.cpu.icache.demand_accesses 58032693 # number of demand (read+write) accesses
system.cpu.icache.overall_accesses 58032693 # number of overall (read+write) accesses
system.cpu.icache.ReadReq_miss_rate 0.000091 # miss rate for ReadReq accesses
system.cpu.icache.demand_miss_rate 0.000091 # miss rate for demand accesses
system.cpu.icache.overall_miss_rate 0.000091 # miss rate for overall accesses
system.cpu.icache.ReadReq_avg_miss_latency 31798.031422 # average ReadReq miss latency
system.cpu.icache.demand_avg_miss_latency 31798.031422 # average overall miss latency
system.cpu.icache.overall_avg_miss_latency 31798.031422 # average overall miss latency
system.cpu.icache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked
system.cpu.icache.blocked_cycles::no_targets 0 # number of cycles access was blocked
system.cpu.icache.blocked::no_mshrs 0 # number of cycles access was blocked
system.cpu.icache.blocked::no_targets 0 # number of cycles access was blocked
system.cpu.icache.avg_blocked_cycles::no_mshrs no_value # average number of cycles each access was blocked
system.cpu.icache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked
system.cpu.icache.fast_writes 0 # number of fast writes performed
system.cpu.icache.cache_copies 0 # number of cache copies performed
system.cpu.icache.writebacks 0 # number of writebacks
system.cpu.icache.ReadReq_mshr_hits 1252 # number of ReadReq MSHR hits
system.cpu.icache.demand_mshr_hits 1252 # number of demand (read+write) MSHR hits
system.cpu.icache.overall_mshr_hits 1252 # number of overall MSHR hits
system.cpu.icache.ReadReq_mshr_misses 4031 # number of ReadReq MSHR misses
system.cpu.icache.demand_mshr_misses 4031 # number of demand (read+write) MSHR misses
system.cpu.icache.overall_mshr_misses 4031 # number of overall MSHR misses
system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses
system.cpu.icache.ReadReq_mshr_miss_latency 123392000 # number of ReadReq MSHR miss cycles
system.cpu.icache.demand_mshr_miss_latency 123392000 # number of demand (read+write) MSHR miss cycles
system.cpu.icache.overall_mshr_miss_latency 123392000 # number of overall MSHR miss cycles
system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles
system.cpu.icache.ReadReq_mshr_miss_rate 0.000069 # mshr miss rate for ReadReq accesses
system.cpu.icache.demand_mshr_miss_rate 0.000069 # mshr miss rate for demand accesses
system.cpu.icache.overall_mshr_miss_rate 0.000069 # mshr miss rate for overall accesses
system.cpu.icache.ReadReq_avg_mshr_miss_latency 30610.766559 # average ReadReq mshr miss latency
system.cpu.icache.demand_avg_mshr_miss_latency 30610.766559 # average overall mshr miss latency
system.cpu.icache.overall_avg_mshr_miss_latency 30610.766559 # average overall mshr miss latency
system.cpu.icache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency
system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated
system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions
system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate
system.cpu.dcache.replacements 787 # number of replacements
system.cpu.dcache.tagsinuse 3295.378268 # Cycle average of tags in use
system.cpu.dcache.total_refs 164327794 # Total number of references to valid blocks.
system.cpu.dcache.sampled_refs 4186 # Sample count of references to valid blocks.
system.cpu.dcache.avg_refs 39256.520306 # Average number of references to valid blocks.
system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit.
system.cpu.dcache.occ_blocks::0 3295.378268 # Average occupied blocks per context
system.cpu.dcache.occ_percent::0 0.804536 # Average percentage of cache occupancy
system.cpu.dcache.ReadReq_hits 90826520 # number of ReadReq hits
system.cpu.dcache.WriteReq_hits 73501267 # number of WriteReq hits
system.cpu.dcache.LoadLockedReq_hits 7 # number of LoadLockedReq hits
system.cpu.dcache.demand_hits 164327787 # number of demand (read+write) hits
system.cpu.dcache.overall_hits 164327787 # number of overall hits
system.cpu.dcache.ReadReq_misses 1669 # number of ReadReq misses
system.cpu.dcache.WriteReq_misses 19461 # number of WriteReq misses
system.cpu.dcache.demand_misses 21130 # number of demand (read+write) misses
system.cpu.dcache.overall_misses 21130 # number of overall misses
system.cpu.dcache.ReadReq_miss_latency 56052000 # number of ReadReq miss cycles
system.cpu.dcache.WriteReq_miss_latency 568707000 # number of WriteReq miss cycles
system.cpu.dcache.demand_miss_latency 624759000 # number of demand (read+write) miss cycles
system.cpu.dcache.overall_miss_latency 624759000 # number of overall miss cycles
system.cpu.dcache.ReadReq_accesses 90828189 # number of ReadReq accesses(hits+misses)
system.cpu.dcache.WriteReq_accesses 73520728 # number of WriteReq accesses(hits+misses)
system.cpu.dcache.LoadLockedReq_accesses 7 # number of LoadLockedReq accesses(hits+misses)
system.cpu.dcache.demand_accesses 164348917 # number of demand (read+write) accesses
system.cpu.dcache.overall_accesses 164348917 # number of overall (read+write) accesses
system.cpu.dcache.ReadReq_miss_rate 0.000018 # miss rate for ReadReq accesses
system.cpu.dcache.WriteReq_miss_rate 0.000265 # miss rate for WriteReq accesses
system.cpu.dcache.demand_miss_rate 0.000129 # miss rate for demand accesses
system.cpu.dcache.overall_miss_rate 0.000129 # miss rate for overall accesses
system.cpu.dcache.ReadReq_avg_miss_latency 33584.182145 # average ReadReq miss latency
system.cpu.dcache.WriteReq_avg_miss_latency 29222.907353 # average WriteReq miss latency
system.cpu.dcache.demand_avg_miss_latency 29567.392333 # average overall miss latency
system.cpu.dcache.overall_avg_miss_latency 29567.392333 # average overall miss latency
system.cpu.dcache.blocked_cycles::no_mshrs 7500 # number of cycles access was blocked
system.cpu.dcache.blocked_cycles::no_targets 0 # number of cycles access was blocked
system.cpu.dcache.blocked::no_mshrs 3 # number of cycles access was blocked
system.cpu.dcache.blocked::no_targets 0 # number of cycles access was blocked
system.cpu.dcache.avg_blocked_cycles::no_mshrs 2500 # average number of cycles each access was blocked
system.cpu.dcache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked
system.cpu.dcache.fast_writes 0 # number of fast writes performed
system.cpu.dcache.cache_copies 0 # number of cache copies performed
system.cpu.dcache.writebacks 662 # number of writebacks
system.cpu.dcache.ReadReq_mshr_hits 676 # number of ReadReq MSHR hits
system.cpu.dcache.WriteReq_mshr_hits 16268 # number of WriteReq MSHR hits
system.cpu.dcache.demand_mshr_hits 16944 # number of demand (read+write) MSHR hits
system.cpu.dcache.overall_mshr_hits 16944 # number of overall MSHR hits
system.cpu.dcache.ReadReq_mshr_misses 993 # number of ReadReq MSHR misses
system.cpu.dcache.WriteReq_mshr_misses 3193 # number of WriteReq MSHR misses
system.cpu.dcache.demand_mshr_misses 4186 # number of demand (read+write) MSHR misses
system.cpu.dcache.overall_mshr_misses 4186 # number of overall MSHR misses
system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses
system.cpu.dcache.ReadReq_mshr_miss_latency 31737500 # number of ReadReq MSHR miss cycles
system.cpu.dcache.WriteReq_mshr_miss_latency 113123500 # number of WriteReq MSHR miss cycles
system.cpu.dcache.demand_mshr_miss_latency 144861000 # number of demand (read+write) MSHR miss cycles
system.cpu.dcache.overall_mshr_miss_latency 144861000 # number of overall MSHR miss cycles
system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles
system.cpu.dcache.ReadReq_mshr_miss_rate 0.000011 # mshr miss rate for ReadReq accesses
system.cpu.dcache.WriteReq_mshr_miss_rate 0.000043 # mshr miss rate for WriteReq accesses
system.cpu.dcache.demand_mshr_miss_rate 0.000025 # mshr miss rate for demand accesses
system.cpu.dcache.overall_mshr_miss_rate 0.000025 # mshr miss rate for overall accesses
system.cpu.dcache.ReadReq_avg_mshr_miss_latency 31961.228600 # average ReadReq mshr miss latency
system.cpu.dcache.WriteReq_avg_mshr_miss_latency 35428.593799 # average WriteReq mshr miss latency
system.cpu.dcache.demand_avg_mshr_miss_latency 34606.067845 # average overall mshr miss latency
system.cpu.dcache.overall_avg_mshr_miss_latency 34606.067845 # average overall mshr miss latency
system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency
system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated
system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions
system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate
system.cpu.l2cache.replacements 11 # number of replacements
system.cpu.l2cache.tagsinuse 4003.203107 # Cycle average of tags in use
system.cpu.l2cache.total_refs 792 # Total number of references to valid blocks.
system.cpu.l2cache.sampled_refs 4846 # Sample count of references to valid blocks.
system.cpu.l2cache.avg_refs 0.163434 # Average number of references to valid blocks.
system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit.
system.cpu.l2cache.occ_blocks::0 3625.567893 # Average occupied blocks per context
system.cpu.l2cache.occ_blocks::1 377.635214 # Average occupied blocks per context
system.cpu.l2cache.occ_percent::0 0.110644 # Average percentage of cache occupancy
system.cpu.l2cache.occ_percent::1 0.011525 # Average percentage of cache occupancy
system.cpu.l2cache.ReadReq_hits 719 # number of ReadReq hits
system.cpu.l2cache.Writeback_hits 662 # number of Writeback hits
system.cpu.l2cache.ReadExReq_hits 62 # number of ReadExReq hits
system.cpu.l2cache.demand_hits 781 # number of demand (read+write) hits
system.cpu.l2cache.overall_hits 781 # number of overall hits
system.cpu.l2cache.ReadReq_misses 4305 # number of ReadReq misses
system.cpu.l2cache.ReadExReq_misses 3131 # number of ReadExReq misses
system.cpu.l2cache.demand_misses 7436 # number of demand (read+write) misses
system.cpu.l2cache.overall_misses 7436 # number of overall misses
system.cpu.l2cache.ReadReq_miss_latency 148172000 # number of ReadReq miss cycles
system.cpu.l2cache.ReadExReq_miss_latency 108394500 # number of ReadExReq miss cycles
system.cpu.l2cache.demand_miss_latency 256566500 # number of demand (read+write) miss cycles
system.cpu.l2cache.overall_miss_latency 256566500 # number of overall miss cycles
system.cpu.l2cache.ReadReq_accesses 5024 # number of ReadReq accesses(hits+misses)
system.cpu.l2cache.Writeback_accesses 662 # number of Writeback accesses(hits+misses)
system.cpu.l2cache.ReadExReq_accesses 3193 # number of ReadExReq accesses(hits+misses)
system.cpu.l2cache.demand_accesses 8217 # number of demand (read+write) accesses
system.cpu.l2cache.overall_accesses 8217 # number of overall (read+write) accesses
system.cpu.l2cache.ReadReq_miss_rate 0.856887 # miss rate for ReadReq accesses
system.cpu.l2cache.ReadExReq_miss_rate 0.980583 # miss rate for ReadExReq accesses
system.cpu.l2cache.demand_miss_rate 0.904953 # miss rate for demand accesses
system.cpu.l2cache.overall_miss_rate 0.904953 # miss rate for overall accesses
system.cpu.l2cache.ReadReq_avg_miss_latency 34418.583043 # average ReadReq miss latency
system.cpu.l2cache.ReadExReq_avg_miss_latency 34619.770042 # average ReadExReq miss latency
system.cpu.l2cache.demand_avg_miss_latency 34503.294782 # average overall miss latency
system.cpu.l2cache.overall_avg_miss_latency 34503.294782 # average overall miss latency
system.cpu.l2cache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked
system.cpu.l2cache.blocked_cycles::no_targets 0 # number of cycles access was blocked
system.cpu.l2cache.blocked::no_mshrs 0 # number of cycles access was blocked
system.cpu.l2cache.blocked::no_targets 0 # number of cycles access was blocked
system.cpu.l2cache.avg_blocked_cycles::no_mshrs no_value # average number of cycles each access was blocked
system.cpu.l2cache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked
system.cpu.l2cache.fast_writes 0 # number of fast writes performed
system.cpu.l2cache.cache_copies 0 # number of cache copies performed
system.cpu.l2cache.writebacks 0 # number of writebacks
system.cpu.l2cache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits
system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits
system.cpu.l2cache.ReadReq_mshr_misses 4305 # number of ReadReq MSHR misses
system.cpu.l2cache.ReadExReq_mshr_misses 3131 # number of ReadExReq MSHR misses
system.cpu.l2cache.demand_mshr_misses 7436 # number of demand (read+write) MSHR misses
system.cpu.l2cache.overall_mshr_misses 7436 # number of overall MSHR misses
system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses
system.cpu.l2cache.ReadReq_mshr_miss_latency 134317500 # number of ReadReq MSHR miss cycles
system.cpu.l2cache.ReadExReq_mshr_miss_latency 98537000 # number of ReadExReq MSHR miss cycles
system.cpu.l2cache.demand_mshr_miss_latency 232854500 # number of demand (read+write) MSHR miss cycles
system.cpu.l2cache.overall_mshr_miss_latency 232854500 # number of overall MSHR miss cycles
system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles
system.cpu.l2cache.ReadReq_mshr_miss_rate 0.856887 # mshr miss rate for ReadReq accesses
system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.980583 # mshr miss rate for ReadExReq accesses
system.cpu.l2cache.demand_mshr_miss_rate 0.904953 # mshr miss rate for demand accesses
system.cpu.l2cache.overall_mshr_miss_rate 0.904953 # mshr miss rate for overall accesses
system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31200.348432 # average ReadReq mshr miss latency
system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31471.414883 # average ReadExReq mshr miss latency
system.cpu.l2cache.demand_avg_mshr_miss_latency 31314.483593 # average overall mshr miss latency
system.cpu.l2cache.overall_avg_mshr_miss_latency 31314.483593 # average overall mshr miss latency
system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency
system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated
system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions
system.cpu.l2cache.no_allocate_misses 0 # Number of misses that were no-allocate
---------- End Simulation Statistics ----------
|