Ben Skeggs at Red Hat has long been the primary Nouveau DRM kernel driver maintainer for keeping this open-source NVIDIA GPU kernel driver within the mainline kernel going… Throughout all the battles, particularly after the GTX 900 series and later has required signed firmware images for enabling any accelerated GPU support, he’s now resigning from maintaining the driver. Ben Skeggs has contributed to the Nouveau project for more than one dedace – he’s earned references on Phoronix since 2008.

  • cbarrick@lemmy.world
    link
    fedilink
    English
    arrow-up
    60
    arrow-down
    1
    ·
    1 year ago

    The state of GPUs on Linux:

    • Want to game: choose AMD,
    • Want to do ML/scientific computing: choose NVIDIA,
    • Want to do both: fuck you!
    • oats@110010.win
      link
      fedilink
      English
      arrow-up
      22
      ·
      1 year ago

      AMD is getting better for ML/scientific computing very fast for the regular consumer GPUs. I have seen the pytorch performance more than double on my 6700xt in 6 months to the point that it has better performance than a 3060(not ti).

      • Carlos Solís@communities.azkware.net
        link
        fedilink
        English
        arrow-up
        9
        arrow-down
        1
        ·
        1 year ago

        Great to know, but unfortunately CUDA is still too entrenched in comparison to OpenCL - hopefully there’s some way to convert from one to the other.

        • cbarrick@lemmy.world
          link
          fedilink
          English
          arrow-up
          10
          ·
          1 year ago

          OpenCL is dead. Vulkan is the future.

          We still need core libraries to be written as Vulkan compute shaders, similar to cuFFT and cuDNN.

          There is VkFFT, but I don’t know how good it is. I don’t think anyone has written a VkDNN library.

          NVIDIA has signaled that they will fully support Vulkan.

    • woodgen@lemm.ee
      link
      fedilink
      English
      arrow-up
      3
      ·
      1 year ago

      I’m doing both on AMD, while I contribute to a bunch of ROCm packages. Stable Diffusion XL and training runs great.