Skip to content
KernelIndex
Search⌘K

submission 20350

AMD FP8 blockwise GEMM · k = 7168 · m = 6144 · n = 1536 · seed = 6543 · fp32/fp8_e4m3fnuz · run 01a006cb-856f…
●passedReported evidence

Not re-observed recently.

Primary measurement
528.0µsmean of 100

Rank 60 in its comparison group · source-native comparison · observed 2025-05-11

Compare with #1 →

best ns 496246 · mean ns 528014.08 · leaderboard score s 0.00020830547804429205

Identity
implementationsubmission 20350
projectKernelBot user 267
revisionsubmission-20350
workloadk = 7168 · m = 6144 · n = 1536 · seed = 6543 · fp32/fp8_e4m3fnuz
comparison keysha256:94c7135ff76c3088…
sourceGPU MODE KernelBot
external idsubmission/20350/benchmark/9
sha256:0f0cd9eacb3d667619d8207…

Correctness

Marked passed by the source; the correctness policy was not published.

Workload

k7168
m6144
n1536
seed6543
afp8_e4m3fnuz [6144, 7168]
bfp8_e4m3fnuz [1536, 7168]
a_scalefp32 [6144, 56]
b_scalefp32 [12, 56]
definition comparatorkernelbot_eval

Measurements

latency · max576.7 µs · n=100
latency · mean528.0 µs · n=100
latency · min496.2 µs · n=100
latency · std16.0 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
I

Published under your account name. Community attestations never change the evidence level; a maintainer can hide abuse.

Canonical manifest

Show manifest
{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "samples": 100,
        "latencyNs": {
          "mean": 528014,
          "maximum": 576677,
          "minimum": 496246
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2025-05-11T13:24:19.951Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 15967.18839957351,
          "metric": "latency",
          "statistic": "std",
          "sampleCount": 100
        }
      ],
      "sourceNative": {
        "source": "gpumode-kernelbot",
        "metrics": {
          "best_ns": 496246,
          "mean_ns": 528014.08,
          "leaderboard_score_s": 0.00020830547804429205
        },
        "benchmark": "amd-fp8-mm/9",
        "externalId": "submission/20350"
      },
      "protocolDigest": "sha256:7c66da4b5866502eb10444a7ba013d0f6bdf1620c55847945008cad2fbf98aec",
      "workloadDigest": "sha256:006e0bcabaff048b9ca009169446189ecbfdedceeb04267df8ddd7978f4999fe",
      "environmentDigest": "sha256:f722892449ed976f3e21b12df8b92b34573fc232883fec6a2f3da399a00abdd5",
      "implementationDigest": "sha256:3a637191fb4ce78900a78d6af9fb7a0585df94a44f844cbd4d16d792ed2095cc"
    },
    "metadata": {
      "name": "kernelbot-20350-k7168-m6144-n1536-seed6543",
      "title": "amd-fp8-mm · submission 20350 · case 9",
      "labels": {
        "torch": "2.8.0.dev20250510+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

A maintainer reviews every report. If accepted, the record is retracted or superseded; its history stays visible.

Published 2026-08-15 · GPU MODE KernelBot · June 9 Researcher Reciprocity License v1.0All results for AMD FP8 blockwise GEMM →JSON