search

exaloop / codon

A high-performance, zero-overhead, extensible Python compiler using LLVM
https://docs.exaloop.io/codon
Other
14.31k stars 502 forks source link

Codon vs OpenAI Triton? #197

Open tlemo opened 1 year ago

tlemo commented 1 year ago

Both Codon and Triton can generate CUDA kernels. What are the differences between the two when it comes to GPU programming?

Thanks!

PS. This may be something worth adding to Codon's FAQ

xanderdunn commented 1 year ago

It would be interesting to see a matrix multiplication kernel implemented in codon and compared for performance against the triton benchmarks at the bottom of this page.