submission 18889
AMD FP8 blockwise GEMM · k = 512 · m = 1024 · n = 4096 · seed = 17512 · fp32/fp8_e4m3fnuz · run 01a006cb-ee92…
●passedReported evidence
Not re-observed recently.
Primary measurement
35.6µsmean of 100
Rank 8 in its comparison group · source-native comparison · observed 2025-05-09
best ns 33911 · mean ns 35562.4 · leaderboard score s 0.000132468550674019
Identity
implementationsubmission 18889
projectKernelBot user 376
revisionsubmission-18889
workloadk = 512 · m = 1024 · n = 4096 · seed = 17512 · fp32/fp8_e4m3fnuz
comparison keysha256:5f0bfdcbea922b8b…
sourceGPU MODE KernelBot
external idsubmission/18889/benchmark/8
sha256:a73be5acbcbb6edc9336d48…
Correctness
Marked passed by the source; the correctness policy was not published.
Workload
k512
m1024
n4096
seed17512
afp8_e4m3fnuz [1024, 512]
bfp8_e4m3fnuz [4096, 512]
a_scalefp32 [1024, 4]
b_scalefp32 [32, 4]
definition comparatorkernelbot_eval
Measurements
latency · max40.0 µs · n=100
latency · mean35.6 µs · n=100
latency · min33.9 µs · n=100
latency · std1.01 µs · n=100
Protocol
harnessreference-kernels eval.py
timerwall_clock
primaryStatisticmean
correctnessReferenceproblem reference implementation
comparabilityFamilygpumode_kernelbot
Environment
gpuAMD Instinct MI300X (gfx942)
Artifacts
No artifacts published with this run.
Replications and notes
No attestations yet.
Community attestations. They never change the evidence level; only a KernelIndex-controlled rerun does.
Add a reproduction or note
Canonical manifest
Show manifestHide manifest
{
"run": {
"kind": "BenchmarkRun",
"spec": {
"status": "passed",
"timing": {
"samples": 100,
"latencyNs": {
"mean": 35562,
"maximum": 40026,
"minimum": 33911
},
"primaryStatistic": "mean"
},
"observedAt": "2025-05-09T15:42:12.095Z",
"measurements": [
{
"unit": "ns",
"value": 1008.5036820793846,
"metric": "latency",
"statistic": "std",
"sampleCount": 100
}
],
"sourceNative": {
"source": "gpumode-kernelbot",
"metrics": {
"best_ns": 33911,
"mean_ns": 35562.4,
"leaderboard_score_s": 0.000132468550674019
},
"benchmark": "amd-fp8-mm/8",
"externalId": "submission/18889"
},
"protocolDigest": "sha256:7c66da4b5866502eb10444a7ba013d0f6bdf1620c55847945008cad2fbf98aec",
"workloadDigest": "sha256:5270e235caa52c12fe63d38ad431224f0c2cfaaae73a9f48152370cc89a144da",
"environmentDigest": "sha256:f722892449ed976f3e21b12df8b92b34573fc232883fec6a2f3da399a00abdd5",
"implementationDigest": "sha256:418dce6a873bca1ee14a0ea998553e2e00e8e6afac1b55a7183a5811c1fb84c8"
},
"metadata": {
"name": "kernelbot-18889-k512-m1024-n4096-seed17512",
"title": "amd-fp8-mm · submission 18889 · case 8",
"labels": {
"torch": "2.8.0.dev20250502+rocm6.3",
"platform": "Linux-5.15.0-136-generic-x86_64-with-glibc2.35"
}
},
"apiVersion": "kernelindex.dev/v1alpha1"
},
"protocol": {
"kind": "BenchmarkProtocol",
"spec": {
"harness": {
"name": "reference-kernels eval.py",
"repository": "https://github.com/gpu-mode/reference-kernels"
},
"correctness": {
"reference": "problem reference implementation",
"comparator": "kernelbot_eval"
},
"measurement": {
"timer": "wall_clock",
"primaryStatistic": "mean"
},
"comparability": {
"notes": "Per-case wall-clock statistics as published in the KernelBot dataset. Comparable only within one leaderboard problem and GPU type; runner software versions ride each run's labels.",
"family": "gpumode_kernelbot"
}
},
"metadata": {
"name": "gpumode-kernelbot-eval",
"title": "GPU MODE KernelBot evaluation harness"
},
"apiVersion": "kernelindex.dev/v1alpha1"
},
"environment": {
"kind": "ExecutionEnvironment",
"spec": {
"hardware": {
"vendor": "amd",
"product": "AMD Instinct MI300X",
"architecture": "gfx942"
},
"software": {}
},
"metadata": {
"name": "gpumode-kernelbot-amd-instinct-mi300x",
"title": "KernelBot runner · AMD Instinct MI300X"
},
"apiVersion": "kernelindex.dev/v1alpha1"
}
}Cite this record (permalink, digest, access date)
Report an issue with this run
Published 2026-08-15 · GPU MODE KernelBot · June 9 Researcher Reciprocity License v1.0All results for AMD FP8 blockwise GEMM →JSON