Skip to content
KernelIndex
Search⌘K

submission 15295

KernelBot user 115 · 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_1.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-amd-fp8-mm-15295?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
62.6µs
#78 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 256]
AMD Instinct MI300X
63.3µs
#77 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 1536]
AMD Instinct MI300X
85.4µs
#61 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 7168] · n=512 · seed=6563
AMD Instinct MI300X
106.3µs
#46 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 7168] · n=576 · seed=12346
AMD Instinct MI300X
107.3µs
#48 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 256]
AMD Instinct MI300X
117.6µs
#52 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 512]
AMD Instinct MI300X
119.7µs
#42 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 2048]
AMD Instinct MI300X
163.2µs
#67 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 7168] · n=1536 · seed=8135
AMD Instinct MI300X
171.8µs
#53 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 2304]
AMD Instinct MI300X
188.1µs
#69 of 98
2025-05-03
Show all 18 measurements ›
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 1536]
AMD Instinct MI300X
220.1µs
#65 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [1024, 7168] · n=4608 · seed=7531
AMD Instinct MI300X
353.2µs
#67 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 7168] · n=512 · seed=12341
AMD Instinct MI300X
483.5µs
#76 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 2048]
AMD Instinct MI300X
488.5µs
#46 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 7168] · n=576 · seed=9863
AMD Instinct MI300X
489.6µs
#74 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 2304]
AMD Instinct MI300X
583.5µs
#52 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 7168] · n=1536 · seed=6543
AMD Instinct MI300X
682.1µs
#69 of 98
2025-05-03
AMD FP8 blockwise GEMMfp32/fp8_e4m3fnuz · [6144, 7168] · n=4608 · seed=65436
AMD Instinct MI300X
1.26ms
#61 of 98
2025-05-03

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:d91b65fe8813c857cb54fc20da19d6261405c970f84da77bdbffd2c2f4703ca6
license declaredunknown
license concludedunknown
imported2026-08-15

Kernel source

submission_1.py1 lines
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

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

Best evidence level for this revision: reported

JSON