torch.compile (inductor)
conv depthwise 2D asymmetric input square kernel · width_in = 512 · height_in = 256 · batch_size = 64 · in_channels = 128 · fp32 · run 01a03f0e-f6e3…
●passedReported evidence
Not re-observed recently.
Primary measurement
9.83ms±0.04 · mean of 100
Rank 1 in its comparison group · source-native comparison · observed 2026-03-05
max ms 11.8 · min ms 9.78 · std ms 0.21 · mean ms 9.83
Identity
implementationtorch.compile (inductor)
projectPyTorch
revisionunknown
workloadwidth_in = 512 · height_in = 256 · batch_size = 64 · in_channels = 128 · fp32
comparison keysha256:9440c5908461cc5b…
sourceKernelBench baseline timings
external idH100_Modal/torch-compile-inductor/level1/84_conv_depthwise_2D_asymmetric_input_square_kernel.py
sha256:8ed63ce55357cd7ede083a1…
Correctness
Marked passed by the source; the correctness policy was not published.
Workload
width_in512
height_in256
batch_size64
in_channels128
xfp32 [64, 128, 256, 512]
definition comparatornot_asserted
Measurements
latency · max11.8 ms · n=100
latency · mean9.83 ms · n=100
latency · min9.78 ms · n=100
latency · std210.0 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 manifestHide manifest
{
"run": {
"kind": "BenchmarkRun",
"spec": {
"status": "passed",
"timing": {
"samples": 100,
"latencyNs": {
"mean": 9830000,
"maximum": 11800000,
"minimum": 9780000,
"confidence95": [
9788840,
9871160
]
},
"primaryStatistic": "mean"
},
"observedAt": "2026-03-05T08:38:15.000Z",
"measurements": [
{
"unit": "ns",
"value": 210000,
"metric": "latency",
"statistic": "std"
}
],
"sourceNative": {
"source": "kernelbench",
"metrics": {
"max_ms": 11.8,
"min_ms": 9.78,
"std_ms": 0.21,
"mean_ms": 9.83
},
"benchmark": "H100_Modal/baseline_time_torch_compile_inductor_default.json",
"externalId": "H100_Modal/torch-compile-inductor/level1/84_conv_depthwise_2D_asymmetric_input_square_kernel.py"
},
"protocolDigest": "sha256:547725b033a9911eae0c5ac362344a85aed824894ed4ab476af945b9bb491ea6",
"workloadDigest": "sha256:02bfc0b3df48acf8f95c3cc6e28bd6376c36e0d052a4b226f8f300aa890a2a6e",
"environmentDigest": "sha256:2750ae381d6de582f1eb6b9008e0987463d19ede8af127d97d76c5ae09121393",
"implementationDigest": "sha256:a5ad43e57541e44efd6eb02b96bca73451bf527b8471d6932580810baee7c8b4"
},
"metadata": {
"name": "kernelbench-h100-modal-torch-compile-inductor-l1-84-conv-depthwise-2d-asymmetric-input-square-kernel",
"title": "conv depthwise 2D asymmetric input square kernel · 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 conv depthwise 2D asymmetric input square kernel →JSON