Simon Boehm personal blog
How to Optimize a CUDA Matmul Kernel for CuBLAS-Like Performance: A Worklog
In this post, I’ll iteratively optimize an implementation of matrix multiplication written in CUDA.My goal is not to build a cuBLAS replacement, but to deepl...
- Points
- 130
- HN comments
- 49
- Submissions
- 2
- Cited by
- 10 commenters
Software EngineeringAI & Machine Learning2023
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Jan 5, 2023 | How to Optimize a CUDA Matmul Kernel for CuBLAS-Like Performance: A Worklog by todsacerdoti | 130 | 16 |
| Jul 26, 2024 | How to optimize a CUDA matmul kernel for cuBLAS-like performance (2022) by mpweiher | 103 | 33 |
Cited in comments
Linked from 11 Hacker News comments by 10 different people, from Nov 2023 to May 2026.
Most recent:
