hip

> 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 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/)

ROCm has HIP (1) which is a compatibility layer to run CUDA code on AMD GPUs. In theory, you only have to adjust #includes, and everything should just work, but as usual, reality is different. Newer backends for AI frameworks like OpenXLA and OpenAI Triton directly generate GPU native code using MLIR and LLVM, they do not use CUDA apart from some glue code to actually load the code onto the GPU and get the data there. Both already support ROCm, but from what I've read the support is not as mature yet compared to NVIDIA. 1: https://github.com/ROCm-Developer-Tools/HIP

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

> does not run on the GPU both Cuda and the Metal shader language are C++, so is OpenCL since 2.0 (https://www.khronos.org/opencl/), so is AMD ROCm's HIP (https://github.com/ROCm-Developer-Tools/HIP), so is SYCL (https://www.khronos.org/sycl/)? C++ is pretty much the language that runs most on GPUs. > no vector instructions, There's a thousand different possibilities for SIMD in C++, from #pragma omp simd, to libs such as std::experimental::simd (https://en.cppreference.com/w/cpp/experimental/simd/simd), Eve (https://github.com/jfalcou/eve), Highway (https://github.com/google/highway), Vc (https://github.com/VcDevel/Vc)...

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