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

1.0 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 CUs90Cus12075.0
10SALU UtilPct100
11VALU UtilPct100
12MFMA UtilPct100
13VALU Active Threads/WaveThreads64
14IPC - IssueInstr/cycle5
15LDS BWGb/sec23070.72
16LDS Bank ConflictConflicts/access32
17Instr Cache Hit Rate99.99340225613768Pct10099.99340225613768
18Instr Cache BW1411.1691618570987Gb/s4614.14430.583552699202684
19Scalar L1D Cache Hit Rate99.35620448529848Pct10099.35620448529848
20Scalar L1D Cache BW43.035436533707404Gb/s4614.1440.932685164002411
21Vector L1D Cache Hit RatePct100
22Vector L1D Cache BWGb/s11535.36
23L2 Cache Hit RatePct100
24L2-Fabric Read BWGb/s1228.8
25L2-Fabric Write BWGb/s1228.8
26L2-Fabric Read LatencyCycles
27L2-Fabric Write LatencyCycles
28Wave OccupancyWavefronts4800
29Instr Fetch BWGb/s2307.072
30Instr Fetch LatencyCycles