Alternative(s) to run CUDA on non-Nvidia hardware

(hpcwire.com)

34 points | by alok-g 1 hour ago

7 comments

  • woctordho 17 minutes ago
    There's nothing wrong to run CUDA on non-Nvidia hardware. CUDA has an interface that is reasonably well-designed, well-documented/reverse-engineered, and battle-tested for decades. What we need is not to invent another interface just under the name of 'open standard', but to implement the same interface. ROCm is exactly doing this, and so are other hardware SDKs such as MooreThread and Alibaba T-Head.
  • luciana1u 18 minutes ago
    every CUDA alternative follows the same arc: bold launch, works for 3 operations, then a Discord server where the last message is 'any updates?' from 2024
  • pjmlp 1 hour ago
    Most of these "alternatives" focus on CUDA C++, and overlook what actually makes CUDA interesting.

    Already in 2020,

    https://developer.nvidia.com/blog/cuda-refresher-the-gpu-com...

    • msond 1 hour ago
      We're actually targeting all of it, and not just CUDA C++.
      • pjmlp 59 minutes ago
        Including stuff like Fortran, Haskell, Java, .NET via PTX, Python JIT, IDE tooling integration with major IDEs, graphical GPU debugging and profiling, libraries and co?

        Then I guess all the best.

        • zorked 23 minutes ago
          This post has some serious peanut-gallery vibes.
          • pjmlp 3 minutes ago
            Peanut-gallery is happily using CUDA, and needs actual sound reasons to move.
      • embedding-shape 51 minutes ago
        Ambitions but neat, good luck if nothing else :)

        If you were to guess, when do you think your Nsight Compute alternative might be ready with your own toolchain?

  • maxloh 35 minutes ago
    There is also ZLUDA, which is open source and works on pre-compiled binaries.

    https://github.com/vosen/ZLUDA

  • DiabloD3 24 minutes ago
    Its easier to just get rid of your legacy code entirely and use Vulkan for compute, or have your compiler emit SPIR-V directly.

    No reason to tie yourself to Nvidia's moat.

    • swerner 18 minutes ago
      Unfortunately, Vulkan Compute doesn’t to all the things that OpenCL, SYCL, HIP or CUDA do.
    • dannecodez 18 minutes ago
      [dead]
  • lulzx 23 minutes ago
    I have been trying for cuda -> metal, to run it on mac, https://github.com/lulzx/cuda-metal
  • z0ltan 5 minutes ago
    [dead]