Live data from Hacker News

FastGPT: Faster than PyTorch in 300 lines of Fortran

ondrejcertik.com

11–14 of 14 posts

Re: FastGPT: Faster than PyTorch in 300 lines of Fortran

#11
post #2

The author here. I am happy to answer any questions.

What happened to the theoretical physics reference book ?

It's here: https://github.com/certik/theoretical-physics/, I was hoping more people would contribute to the effort, but so far I didn't manage to spark enough interest. It's open source, it's out there and if I find at least a single person willing to contribute to get it polished, the development will pick up.

In the absence of it, I would have to drive it hard as my main effort, but right now my main effort is LFortran/LPython, we are making excellent progress there, so I am not spreading too thin until the compilers are delivered.

If anyone is interested in the theoretical physics book, please let me know!

Re: FastGPT: Faster than PyTorch in 300 lines of Fortran

#12
post #5
post #2

The author here. I am happy to answer any questions.

The article mentions requiring help to use the GPU for compute: how easy is using the GPU for compute in Fortran? (Total newbie in Fortran)

I don't have much GPU experience myself. As the sibling comment said, there are Fortran compilers that can offload to GPU, there is also Cuda Fortran. There is OpenMP offloading. I think LLVM can also target it somehow, and I would like to support it in LFortran, a compiler that we are developing. In general I am hoping people more experienced with GPU would be interested in helping out.
Post reply on HN