Skip to content
KernelIndex
Search⌘K

submission 512327

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_deterministic.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-matmul-v2-512327?include=source"
interfacepython
Compatibility
measured onNVIDIA H100
declared hardwareNVIDIA H100
architecturessm_90
dtypesfp16

Benchmark evidence

1 measurement across 1 GPU, fastest first.

Operation / workload
Hardware
Latency
Rank
Observed
FP16 matmulsuite of 8 cases
NVIDIA H100
248.6µs
#12 of 28
2026-03-02

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:58f9b271d60cf7370621089f7cd5275353111ecde974eac4562366c45521ed67
license declaredunknown
license concludedunknown
authorsburtenshaw
imported2026-08-15

Kernel source

submission_deterministic.py19 lines
#!POPCORN leaderboard matmul_v2
#!POPCORN gpu A100

import os
# Needed for deterministic matmul path used by the evaluator's reference check.
os.environ.setdefault("CUBLAS_WORKSPACE_CONFIG", ":4096:8")

import torch

from task import input_t, output_t
from utils import DeterministicContext


def custom_kernel(data: input_t) -> output_t:
    a, b, c = data
    with DeterministicContext():
        c[...] = a @ b
    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 512299.

Best evidence level for this revision: reported

JSON