Hacker News new | past | comments | ask | show | jobs | submit login
Micrograd-CUDA: adapting Karpathy's tiny autodiff engine for GPU acceleration (github.com/mlecauchois)
178 points by cataPhil 8 months ago | hide | past | favorite | 13 comments



I recently decided to turbo-teach myself basic cuda with a proper project. I really enjoyed Karpathy’s micrograd (https://github.com/karpathy/micrograd), so I extended it with cuda kernels and 2D tensor logic. It’s a bit longer than the original project, but it’s still very readable for anyone wanting to quickly learn about gpu acceleration in practice.


If you ever feel like improving your matmul kernel you can check this blog https://siboehm.com/articles/22/CUDA-MMM


Thanks! I will probably do that this weekend


Lovely project, what did you find as the beat place to learn about cuda?


Thanks! I highly recommend the book Programming Massively Parallel Processors


This is the second time this week that people have recommended this boot while I was searching for information about CUDA. Thanks!


Awesome, thank you for publishing it. I was planning the same, but didn't find the time yet.


Is your work publicly available anywhere? I'd love to have a look if possible.


Hi :) Yes it's in the post url or here: https://github.com/mlecauchois/micrograd-cuda


Oh sorry, I didn't realise you were OP :) Thanks!


Awesome. Thanks


Very cool!!


Cool




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: