Skip to content
KernelIndex
Search⌘K

submission 780585

Samuel Nordmann · python · License unknown

Use it

Vendorable · source mirrored · license unknownView source →

No package. Vendor the mirrored source: 11 lines, June 9 Researcher Reciprocity License v1.0.

submission_torch_out_clean.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-matmul-v2-780585?include=source"
interfacepython
Compatibility
measured onNVIDIA B200
declared hardwareNVIDIA B200
architecturessm_100
dtypesfp16

Benchmark evidence

1 measurement across 1 GPU, fastest first.

Operation / workload
Hardware
Latency
Rank
Observed
FP16 matmulsuite of 8 cases
NVIDIA B200
114.7µs
#16 of 53
2026-05-04

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:2c57f6aeb94d4ab37beb0f8f40f479c814bac38fd2cbc2e2c2e5727c5e9aa59c
license declaredunknown
license concludedunknown
authorsSamuel Nordmann
imported2026-08-15

Kernel source

submission_torch_out_clean.py11 lines
#!POPCORN leaderboard matmul_v2
#!POPCORN gpu B200
import torch
from task import input_t, output_t


def custom_kernel(data: input_t) -> output_t:
    a, b, c = data
    torch.mm(a, b, out=c)
    return c

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

Changes from previous submission

Against this author's previous submission submission 780584.

Best evidence level for this revision: reported

JSON