Run 01a03f0e · KernelIndex

Primary measurement

5.54ms±0.01 · mean of 100

Rank 1 in its comparison group · source-native comparison · observed 2026-03-05

max ms 5.76 · min ms 5.5 · std ms 0.0282 · mean ms 5.54

Identity

implementationtorch.compile (inductor)

projectPyTorch

revisionunknown

workloadwidth = 512 · height = 512 · batch_size = 16 · in_channels = 64 · fp32

comparison keysha256:686910cd32c3dbbb…

sourceKernelBench baseline timings

external idH100_Modal/torch-compile-inductor/level2/42_ConvTranspose2d_GlobalAvgPool_BiasAdd_LogSumExp_Sum_Multiply.py

sha256:f7fc4bf3c13107761d2d5d9…

Correctness

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

Workload

width512

height512

batch_size16

in_channels64

input_1fp32 [16, 64, 512, 512]

definition comparatornot_asserted

Measurements

latency · max5.76 ms · n=100

latency · mean5.54 ms · n=100

latency · min5.50 ms · n=100

latency · std28.2 µs

Protocol

harnessKernelBench timing scripts

timercuda_events

primaryStatisticmean

comparabilityFamilykernelbench_baseline_timing

Environment

gpuNVIDIA H100 (sm_90)

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 manifest

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "samples": 100,
        "latencyNs": {
          "mean": 5540000,
          "maximum": 5760000,
          "minimum": 5500000,
          "confidence95": [
            5534473,
            5545527
          ]
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2026-03-05T08:38:15.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 28200,
          "metric": "latency",
          "statistic": "std"
        }
      ],
      "sourceNative": {
        "source": "kernelbench",
        "metrics": {
          "max_ms": 5.76,
          "min_ms": 5.5,
          "std_ms": 0.0282,
          "mean_ms": 5.54
        },
        "benchmark": "H100_Modal/baseline_time_torch_compile_inductor_default.json",
        "externalId": "H100_Modal/torch-compile-inductor/level2/42_ConvTranspose2d_GlobalAvgPool_BiasAdd_LogSumExp_Sum_Multiply.py"
      },
      "protocolDigest": "sha256:547725b033a9911eae0c5ac362344a85aed824894ed4ab476af945b9bb491ea6",
      "workloadDigest": "sha256:e70803eba625323e50e6bd32bd50996fbdfe5b3a964f2bc4d568207cc6fba9e9",
      "environmentDigest": "sha256:2750ae381d6de582f1eb6b9008e0987463d19ede8af127d97d76c5ae09121393",
      "implementationDigest": "sha256:1166854a95bf9ed5ae642152dcafd14dad46f44eb1e56e5c5267f2b2568252a2"
    },
    "metadata": {
      "name": "kernelbench-h100-modal-torch-compile-inductor-l2-42-convtranspose2d-globalavgpool-biasadd-logsumexp-",
      "title": "ConvTranspose2d GlobalAvgPool BiasAdd LogSumExp Sum Multiply · torch.compile (inductor) · Modal"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  },
  "protocol": {
    "kind": "BenchmarkProtocol",
    "spec": {
      "harness": {
        "name": "KernelBench timing scripts",
        "repository": "https://github.com/ScalingIntelligence/KernelBench"
      },
      "measurement": {
        "timer": "cuda_events",
        "primaryStatistic": "mean"
      },
      "comparability": {
        "notes": "Mean of 100 timed forward passes (CUDA events, warm-up excluded) of the reference module on fixed inputs; the 95% interval is the mean's, from the reported standard deviation. The upstream JSON records no torch or CUDA version. Comparable only within one problem and one timing host.",
        "family": "kernelbench_baseline_timing"
      }
    },
    "metadata": {
      "name": "kernelbench-timing-v1",
      "title": "KernelBench baseline timing"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  },
  "environment": {
    "kind": "ExecutionEnvironment",
    "spec": {
      "hardware": {
        "vendor": "nvidia",
        "product": "NVIDIA H100",
        "formFactor": "80GB HBM3",
        "architecture": "sm_90"
      },
      "software": {}
    },
    "metadata": {
      "name": "kernelbench-h100-modal",
      "title": "KernelBench host · H100 80GB HBM3 (Modal)"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  }
}

Cite this record (permalink, digest, access date)

Report an issue with this run

Published 2026-08-26 · KernelBench baseline timings · MITAll results for ConvTranspose2d GlobalAvgPool BiasAdd LogSumExp Sum Multiply →JSON