$ | >

OpenCL & CUDA GPU support

It would be nice to have (relatively) easy access to the dedicated GPU's on our Win10 PC's, and OpenCL support for the AMD Drivers & CUDA for NVidia drivers etc.

What I am thinking on specifically (although there are many many uses for it and CUDA support) is hashing functions that are lackluster within windows itself, but benefit immensely within Linux and Unix.

Cryptocurrency mining for example, is known to be much faster on Linux systems than Windows. Do you see any support for OpenCL and/or CUDA in the future?

1,194 votes
Sign in
Check!
(thinking…)
Reset
or sign in with
  • facebook
  • google
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Zachary BoltZachary Bolt shared this idea  ·   ·  Flag idea as inappropriate…  ·  Admin →
    on the backlog  ·  richturnAdminrichturn (Admin, Windows Developer) responded  · 

    It’s on the backlog, but not currently planned.

    We know many of you would like to be able to accelerate your numerical analysis code via CUDA/OpenCL, etc.

    One thing to explore in the meantime is to try running your code in Windows. Windows actually has very powerful GPU-acceleration capabilities and you may well find that much of your existing code may well work already or require trivial effort to port to Windows itself.

    in the meantime, bear with us, and UPVOTE THIS ISSUE if you care (please don’t create another duplicate ask – that doesn’t help us prioritize asks).

    Thanks.

    111 comments

    Sign in
    Check!
    (thinking…)
    Reset
    or sign in with
    • facebook
    • google
      Password icon
      Signed in as (Sign out)
      Submitting...
      • OwenOwen commented  ·   ·  Flag as inappropriate

        Ok nobody do that. I patched the kernel with just ldconfig it allowed clinfo to run and get a full profile but as VRAMFS didn't work tried make config :( Reinstalling right now.

      • OwenOwen commented  ·   ·  Flag as inappropriate

        And admin said, Windows does just fine with OpenCL and CUDA. we def need block device support and opencl for stuff like vramfs and bcachefs

      • OwenOwen commented  ·   ·  Flag as inappropriate

        wait has anybody tried patching the kernel? Like as in unzipping the device specific opencl drivers and then ldconfig and downloading the 4.7 kernel and repatching?? Doing this right now. Would be nice though. VRAMFS!!!! We need this for VRAMFS people.

      • George HatzopoulosGeorge Hatzopoulos commented  ·   ·  Flag as inappropriate

        the only reason i am switching to Linux is because of machine learning on GPUs. If this is added, I will probably remove the ubuntu installation altogether.

      • Samim EkramSamim Ekram commented  ·   ·  Flag as inappropriate

        what the **** are the developers sleeping for 6 months or wtf are they doings clearly the GPU support is of utmost importance then why no response ,,,, I guess even this will be ignored

      • Kevin van ZonneveldKevin van Zonneveld commented  ·   ·  Flag as inappropriate

        This is currently the only reason why we're booting into Ubuntu because we need to train AI models in a linux env. If you add this it would save us a lot of hassle and reboots : )

      • WilliamWilliam commented  ·   ·  Flag as inappropriate

        I love WSL its great, please ad CUDA support

        or give us hints to work around the problem and get deep learning frameworks working on WSL.

      • Stephen PegoraroStephen Pegoraro commented  ·   ·  Flag as inappropriate

        Could we please get an update from the team on this? Last response was Oct 2016, this is really the main blocker for many people to migrate from a dual-boot setup.

      • Michael-Rainabba RichardsonMichael-Rainabba Richardson commented  ·   ·  Flag as inappropriate

        How many votes does it take to get this off the backlog? MUST have OpenCL and/or CUDA for virtually anything gaming, AI, or video (ffmpeg NVENC). Those aren't exactly irrelevant technologies as of 2017.

      ← Previous 1 3 4 5 6

      Feedback and Knowledge Base