submission 20620
KernelBot user 395 · python · License unknown
Use it
Vendorable · source mirrored · license unknownView source →
No package. Vendor the mirrored source: 1 lines, June 9 Researcher Reciprocity License v1.0.
v8.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-amd-fp8-mm-20620?include=source"interfacepython
Compatibility
measured onAMD Instinct MI300X
declared hardwareAMD Instinct MI300X
architecturesgfx942
dtypesfp32, fp8_e4m3fnuz
Benchmark evidence
18 measurements across 1 GPU, fastest first.
Operation / workload
Hardware
Latency
Rank
Observed
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 7168] · n=576 · seed=12346
AMD Instinct MI300X
106.2µs
#47 of 98
2025-05-12
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 7168] · n=512 · seed=6563
AMD Instinct MI300X
106.7µs
#47 of 98
2025-05-12
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 7168] · n=1536 · seed=8135
AMD Instinct MI300X
171.2µs
#52 of 98
2025-05-12
Show all 18 measurements ›Showing all 18 measurements ⌄
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 7168] · n=4608 · seed=7531
AMD Instinct MI300X
360.6µs
#71 of 98
2025-05-12
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 7168] · n=512 · seed=12341
AMD Instinct MI300X
494.3µs
#77 of 98
2025-05-12
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 7168] · n=576 · seed=9863
AMD Instinct MI300X
500.3µs
#75 of 98
2025-05-12
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 7168] · n=1536 · seed=6543
AMD Instinct MI300X
696.0µs
#70 of 98
2025-05-12
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 7168] · n=4608 · seed=65436
AMD Instinct MI300X
1.28ms
#62 of 98
2025-05-12
Reported · How evidence levels are derived →
Source and license
sourceavailable
revision digestsha256:1128d81aaabc3f85a74514c85166ac42a3e7fef5a10ddc4aba106dead419dc19
license declaredunknown
license concludedunknown
imported2026-08-15
Kernel source
v8.py1 lines
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 code from GPU Mode and the KernelBot dataset · June 9 Researcher Reciprocity License v1.0
Best evidence level for this revision: reported
JSON