Hugging Face's logo

Kernels:
AethronPhantom
/
matrix_mult

Kernel card Files
xet
 Community
matrix_mult / README.md
Allanatrix's picture
Allanatrix
Publish matrix_mult kernel and performance card
c3ac9d5 verified
preview code
|
Raw History Blame Contribute Delete
1.12 kB
metadata 
license: apache-2.0
tags:
  - cuda
  - kernel
  - gpu-optimization
  - hpc

matrix_mult

CUDA matrix multiplication kernel (compile-only baseline).

This repository contains the standalone CUDA source for the matrix_mult lane from the PyC kernel lab. It is a source artifact for inspection and benchmarking; it is not a precompiled binary and the result below is not a universal ranking.

Performance

Kernel GPU / architecture Shape Best recorded result Evidence
matrix_mult not recorded not recorded Not measured in the published campaign No published performance receipt was found for this lane.

Performance plot

The result is reported with the original campaign's timing and correctness context. Compare kernels only when GPU, CUDA version, matrix shape, warmup, repeats, and reference/correctness mode match.

Source

  • kernel.cu — copied from kernels/prototypes/baseline/matmul/kernel.cu.
  • Original lane tags: cuda, matmul.

Build/run contract 

{nvcc} -O3 -c {source} -o {build_dir}/{name}.o
(compile-only)