Skip to content
KernelIndex
Search⌘K

submission 512298

burtenshaw · python · License unknown

Use it

Vendorable · source mirrored · license unknownView source →

No package. Vendor the mirrored source: 19 lines, June 9 Researcher Reciprocity License v1.0.

submission_ref.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-prefixsum-v2-512298?include=source"
interfacepython
Compatibility
measured onNVIDIA A100
declared hardwareNVIDIA A100
architecturessm_80
dtypesfp32

Benchmark evidence

1 measurement across 1 GPU, fastest first.

Operation / workload
Hardware
Latency
Rank
Observed
Inclusive prefix sumsuite of 11 cases
NVIDIA A100
2.74ms
#16 of 25
2026-03-02

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:4ef006bce7caed7e2ea15d673e8ccd698fdc0fa678677274e638f4d3b87f4e70
license declaredunknown
license concludedunknown
authorsburtenshaw
imported2026-08-15

Kernel source

submission_ref.py19 lines
#!POPCORN leaderboard prefixsum_v2
#!POPCORN gpu A100

import torch
from task import input_t, output_t


def custom_kernel(data: input_t) -> output_t:
    """
    Reference implementation of inclusive prefix sum using PyTorch.
    Args:
        data: Input tensor to compute prefix sum on
    Returns:
        Tensor containing the inclusive prefix sum
    """
    data, output = data
    output[...] = torch.cumsum(data, dim=0)
    return output

Source code from GPU Mode and the KernelBot dataset · June 9 Researcher Reciprocity License v1.0

Best evidence level for this revision: reported

JSON