Ross ROSS = Recommend OSS · open-source software intelligence for agents

Liu-xiandong/How_to_optimize_in_GPU resource

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit. observed · 2026-08-28

github.com/Liu-xiandong/How_to_optimize_in_GPU · Cuda · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

32/100

  • Activity 0
  • Release rhythm 35
  • Longevity 100

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 1781
  • days_rel: n/a
  • days_push: 1131
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1350 stars · 187 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A tutorial series repository teaching CUDA kernel optimization with detailed walkthroughs of elementwise, reduce, sgemv, and sgemm kernels. The kernels achieve near-theoretical-limit performance on V100 GPUs, benchmarked with Nsight against cuBLAS.

Use cases

  • learn how to optimize CUDA kernels
  • understand vectorized memory access in CUDA
  • write a high-performance sgemm kernel
  • optimize reduce operations on GPU
  • compare my kernel performance against cuBLAS
  • learn SASS-level tuning with register remapping

When to choose

  • you want to learn GPU kernel optimization from worked examples
  • you need reference implementations of near-peak elementwise, reduce, sgemv, or sgemm kernels
  • you are studying HPC or preparing for GPU performance engineering work

When to avoid

  • you need a production linear algebra library - use cuBLAS or CUTLASS instead
  • you want a maintained framework rather than educational code
  • you target GPUs other than NVIDIA V100-class hardware without adapting the tuning

Facets

learning-resource · maturity stable

gpu-computing benchmarking developer-tools gpu-computing performance tutorials developer-tools cuda-kernels high-performance-computing sgemm sgemv kernel-optimization nsight v100 gpu cuda linux

1 source

Member repositories

RepositoryRoleHealth v2
Liu-xiandong/How_to_optimize_in_GPUmain32

For agents

markdown · JSON · MCP: product_card(name="Liu-xiandong/How_to_optimize_in_GPU")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem