Skip to content
KernelIndex
Search⌘K
Sign in

submission 68216

koshibat · python · License unknown
Kernel source · 7 lines ↓

Use it

Vendorable · source mirrored · license unknownView source →

No package. Vendor the mirrored source: 7 lines, June 9 Researcher Reciprocity License v1.0.

test.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-vectorsum-v2-68216?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
Vector sum reductionsuite of 6 cases
NVIDIA A100
666.7µs
#76 of 96
2025-11-08
Run →

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:1aea06a2dd4266c7a214996132933052f2a08d7b8fafb34aab9d63ef0c10c802
license declaredunknown
license concludedunknown
authorskoshibat
imported2026-08-15

Kernel source

test.py7 lines
import torch

def custom_kernel(data):
    input_tensor, output_tensor = data
    # 単純にrefと同じことをする
    result = input_tensor.to(torch.float64).sum().to(torch.float32)
    return result  # output_tensorではなく、計算結果を直接返す

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

Best evidence level for this revision: reported

JSON