Skip to content
KernelIndex
Search⌘K

submission 516991

navneet098 · python · License unknown

Use it

Vendorable · source mirrored · license unknownView source →

No package. Vendor the mirrored source: 22 lines, June 9 Researcher Reciprocity License v1.0.

submission.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-sort-v2-516991?include=source"
interfacepython
Compatibility
measured onNVIDIA H100
declared hardwareNVIDIA H100
architecturessm_90
dtypesfp32

Benchmark evidence

1 measurement across 1 GPU, fastest first.

Operation / workload
Hardware
Latency
Rank
Observed
Sortsuite of 5 cases
NVIDIA H100
6.77ms
#18 of 26
2026-03-08

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:9d940e83660bc82ac4027509ce8909a79c9f1a845f283ce82380f82c7a9831c0
license declaredunknown
license concludedunknown
authorsnavneet098
imported2026-08-15

Kernel source

submission.py22 lines
#!POPCORN leaderboard sort_v2
#!POPCORN gpu H100

import torch
from task import input_t, output_t


def _custom_kernel(data: input_t) -> output_t:
    """
    Implements sort using PyTorch.
    Args:
        data: Input tensor to be sorted
    Returns:
        Sorted tensor
    """
    data, output = data
    output[...] = torch.sort(data)[0]
    return output


custom_kernel = torch.compile(_custom_kernel, mode="reduce-overhead")

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

Best evidence level for this revision: reported

JSON