Skip to content
KernelIndex
Search⌘K

submission 68816

v0i0 · python · License unknown

Use it

Vendorable · source mirrored · license unknownView source →

No package. Vendor the mirrored source: 14 lines, June 9 Researcher Reciprocity License v1.0.

first_submission.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-vectoradd-v2-68816?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 vector additionsuite of 5 cases
NVIDIA B200
252.1µs
#54 of 66
2025-11-10

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:4e8c3589035d59fbcac3c64c2f228683123ae40574f5e7428cf6616b11efc47d
license declaredunknown
license concludedunknown
authorsv0i0
imported2026-08-15

Kernel source

first_submission.py14 lines
#!POPCORN leaderboard vectoradd_v2

from task import input_t, output_t
import torch

@torch.compile
def fn(A, B, C):
    C.copy_(A + B)

def custom_kernel(data: input_t) -> output_t:
    A, B, C = data
    fn(A, B, C)
    return C

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

Best evidence level for this revision: reported

JSON