pytorch VS HIP

For anyone interested in getting this to run, here are the steps I needed to follow for a 6900XT:

Clone this pytorch fork (git clone --recursive https://github.com/micmelesse/pytorch)

Is it perhaps because they want people to use HIP?

> HIP is very thin and has little or no performance impact over coding directly in CUDA mode.

> The HIPIFY tools automatically convert source from CUDA to HIP.

1. https://github.com/ROCm/HIP

AMD has released HIP and a tool called HIPIFY which kind of behaves like this but at the source level¹. Rather than try and just translate CUDA to work on AMD compute they are more focused on higher level tooling.

Currently they seem to have a particular focus on AI frameworks and tools like PyTorch/Tensorflow/ONNX. They have sponsored and helped with a lot of PyTorch development for example, so PyTorch support for AMD is much better than it was this time last year².

¹(https://github.com/ROCm/HIP)

²(https://pytorch.org/blog/experience-power-pytorch-2.0/)

> what would be the point for someone to add ROCm support to various pieces of software which currently require CUDA

It isn't just old cards though, CUDA is a point of centralization on a single provider during a time when access to that providers higher end cards isn't even available and that is causing people to look elsewhere.

ROCm supports CUDA through the included HIP projects...

https://github.com/ROCm/HIP

https://github.com/ROCm/HIPCC

https://github.com/ROCm/HIPIFY

The later will regex replace your CUDA methods with HIP methods. If it is as easy as running hipify on your codebase (or just coding to HIP apis), it certainly makes sense to do so.

AMD's equivalent is HIP [1], for sufficiently flexible definitions of "equivalent". I can't speak to how complete/correct/performant it is (I'm just a guy running tutorial/toy-level ML stuff on an RDNA1 card), but part of AMD's problem is that it might not practically matter how well they do this because the broader ecosystem support specifically for the CUDA stack is so entrenched.

[1] https://github.com/ROCm-Developer-Tools/HIP

From what I know, modern GPUs are still programmed with C++ exclusively. See CUDA [0] for Nvidia and ROCm [1] for AMD.

Why is this? Why Rust is not loved there?

[0] https://docs.nvidia.com/cuda/

[1] https://github.com/ROCm-Developer-Tools/HIP

Go ahead and try to ship ROCm code that works on multiple consumer graphics cards on Linux, MacOS, and Windows. As an example of how much AMD cares about it, the installation notes linked to in the readme returns a 404.

The big whoop for ROCm is that AMD invested a considerable amount of engineering time and talent into a tool they call hip. Basically, it's an analysis tool that does its best to port proprietary Nvidia CUDA-style code - which due to various smelly reasons rules the roost - to code that can happily run on AMD graphics cards, and presumably others. Intel has a similar thing going with OneAPI. They've done this whilst working on porting a lot of their code base to the linux AMGPU open source kernel driver, as well.