Files
rocm-systems/tests/workloads/HBM/mi100/prev_analysis/201.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

1.5 KiB

1MetricValueUnitPeakPoP
2VALU FLOPsGflops23070.72
3VALU IOPsGops23070.72
4MFMA FLOPs (BF16)Gflops92282.88
5MFMA FLOPs (F16)Gflops184565.76
6MFMA FLOPs (F32)Gflops46141.44
7MFMA FLOPs (F64)Gflops46141.44
8MFMA IOPs (Int8)Gops184565.76
9Active CUs95Cus12079.16666666666667
10SALU Util2.1217752494263187Pct1002.1217752494263187
11VALU Util59.676879482999304Pct10059.676879482999304
12MFMA UtilPct100
13VALU Active Threads/Wave63.96798227036171Threads6499.94997229744017
14IPC - Issue0.8437278321487935Instr/cycle516.874556642975868
15LDS BW0.0Gb/sec23070.720.0
16LDS Bank ConflictConflicts/access32
17Instr Cache Hit Rate99.9934121023554Pct10099.9934121023554
18Instr Cache BW1411.7911427566892Gb/s4614.14430.59703257541787
19Scalar L1D Cache Hit Rate99.35620448524938Pct10099.35620448524938
20Scalar L1D Cache BW43.089402129263Gb/s4614.1440.933854732952916
21Vector L1D Cache Hit Rate20.508982035928145Pct10020.508982035928145
22Vector L1D Cache BW1222.5815912030869Gb/s11535.3610.598556015617083
23L2 Cache Hit Rate0.3929622399050042Pct1000.3929622399050042
24L2-Fabric Read BW839.7916983529678Gb/s1228.868.34242336856835
25L2-Fabric Write BW4.94904750128308Gb/s1228.80.40275451670597984
26L2-Fabric Read Latency459.0660446714204Cycles
27L2-Fabric Write Latency145.5355038332391Cycles
28Wave Occupancy3233.6892061731164Wavefronts480067.3685251286066
29Instr Fetch BW687.7298508082541Gb/s2307.07229.809639699508907
30Instr Fetch Latency18.577400163935433Cycles