Skip to content
KernelIndex
Search⌘K

submission 34190

KernelBot user 16 · 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.

submission.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-amd-fp8-mm-34190?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, 512]
AMD Instinct MI300X
214.7µs
#94 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 256]
AMD Instinct MI300X
226.0µs
#94 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 1536]
AMD Instinct MI300X
302.3µs
#94 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 7168] · n=512 · seed=6563
AMD Instinct MI300X
388.1µs
#92 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 7168] · n=576 · seed=12346
AMD Instinct MI300X
411.7µs
#92 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 256]
AMD Instinct MI300X
534.8µs
#94 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 512]
AMD Instinct MI300X
535.9µs
#94 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 2048]
AMD Instinct MI300X
719.6µs
#95 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 2304]
AMD Instinct MI300X
746.9µs
#96 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 7168] · n=1536 · seed=8135
AMD Instinct MI300X
792.6µs
#95 of 98
2025-08-22
Show all 18 measurements ›
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 1536]
AMD Instinct MI300X
1.03ms
#95 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 7168] · n=512 · seed=12341
AMD Instinct MI300X
1.53ms
#95 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 7168] · n=576 · seed=9863
AMD Instinct MI300X
1.69ms
#95 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 7168] · n=4608 · seed=7531
AMD Instinct MI300X
1.75ms
#95 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 7168] · n=1536 · seed=6543
AMD Instinct MI300X
2.73ms
#95 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 2048]
AMD Instinct MI300X
2.79ms
#93 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 2304]
AMD Instinct MI300X
3.12ms
#95 of 98
2025-08-22
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 7168] · n=4608 · seed=65436
AMD Instinct MI300X
6.42ms
#95 of 98
2025-08-22

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:5f4c15e6bbc17704f31a7ad0e720106657cdddab1066d88596bf4aee33dc2b5e
license declaredunknown
license concludedunknown
imported2026-08-15

Kernel source

submission.py1 lines
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

Source code from GPU Mode and the KernelBot dataset · June 9 Researcher Reciprocity License v1.0

Changes from previous submission

Against this author's previous submission submission 33458.

- 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
No newline at end of file
+ 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
No newline at end of file

Best evidence level for this revision: reported

JSON