PyTorch eager
Mean reduction over a dimension · dim1 = 4096 · dim2 = 4095 · batch_size = 128 · fp32 · run 01a03f0e-f6cd…
●passedReported evidence
Not re-observed recently.
Primary measurement
2.88ms±0.00 · mean of 100
Rank 1 in its comparison group · source-native comparison · observed 2026-03-05
max ms 2.93 · min ms 2.85 · std ms 0.0128 · mean ms 2.88
Identity
implementationPyTorch eager
projectPyTorch
revisionunknown
workloaddim1 = 4096 · dim2 = 4095 · batch_size = 128 · fp32
comparison keysha256:1ffb2444eeb8e5ef…
sourceKernelBench baseline timings
external idH100_Modal/torch/level1/48_Mean_reduction_over_a_dimension.py
sha256:9faceb07c8c4064e8a7a5b0…
Correctness
Marked passed by the source; the correctness policy was not published.
Workload
dim14096
dim24095
batch_size128
xfp32 [128, 4096, 4095]
definition comparatornot_asserted
Measurements
latency · max2.93 ms · n=100
latency · mean2.88 ms · n=100
latency · min2.85 ms · n=100
latency · std12.8 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": 2880000,
"maximum": 2930000,
"minimum": 2850000,
"confidence95": [
2877491,
2882509
]
},
"primaryStatistic": "mean"
},
"observedAt": "2026-03-05T08:38:15.000Z",
"measurements": [
{
"unit": "ns",
"value": 12800,
"metric": "latency",
"statistic": "std"
}
],
"sourceNative": {
"source": "kernelbench",
"metrics": {
"max_ms": 2.93,
"min_ms": 2.85,
"std_ms": 0.0128,
"mean_ms": 2.88
},
"benchmark": "H100_Modal/baseline_time_torch.json",
"externalId": "H100_Modal/torch/level1/48_Mean_reduction_over_a_dimension.py"
},
"protocolDigest": "sha256:547725b033a9911eae0c5ac362344a85aed824894ed4ab476af945b9bb491ea6",
"workloadDigest": "sha256:ee296ce58cab9b5d181bc9271842d4124f6cd331e730934426b51b0a8a444448",
"environmentDigest": "sha256:2750ae381d6de582f1eb6b9008e0987463d19ede8af127d97d76c5ae09121393",
"implementationDigest": "sha256:bc690e07c1de6812d9b7912a61ffa40e4df64e6ee3acdb14ccd7e3b027c033ce"
},
"metadata": {
"name": "kernelbench-h100-modal-torch-l1-48-mean-reduction-over-a-dimension",
"title": "Mean reduction over a dimension · PyTorch eager · 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 Mean reduction over a dimension →JSON