Announcement

Collapse
No announcement yet.

AMDGPU-PRO 18.50 vs. ROCm 2.0 OpenCL Performance

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • Etherman
    replied
    This thread describes the reasoning.

    Leave a comment:


  • utrrrongeeb
    replied
    Probably referring to
    Code:
    CYCLES_OPENCL_SPLIT_KERNEL_TEST=1
    , via https://blender.stackexchange.com/a/7486
    Last edited by utrrrongeeb; 20 January 2019, 02:55 PM. Reason: removed incorrect at-username

    Leave a comment:


  • Michael
    replied
    Originally posted by Etherman View Post
    There's an env variable for enabling support for unsupported opencl implementations for
    Blenders cycles renderer.
    Maybe that is needed for rocm.
    Happen to have any documentation on that env var?

    Leave a comment:


  • Etherman
    replied
    Originally posted by Michael View Post

    Had tried but currently was falling back to CPU rendering for some reason, didn't have time to explore to see if it was bug in ROCm or a Blender issue.
    There's an env variable for enabling support for unsupported opencl implementations for
    Blenders cycles renderer.
    Maybe that is needed for rocm.

    Leave a comment:


  • bridgman
    replied
    Originally posted by khnazile View Post
    Is there a guide how to get ROCm working with mainline kernel without installing whole amdgpu-pro graphics stack? Some people claim it's possible, but I didn't manage to get it working. I tried installing pre-built binaries as https://rocm.github.io/ROCmInstall.html suggests, but it didn't work for me. Also, those binaries come unsigned for some reason...
    You need 4.18 or newer upstream kernel; 4.19 if you have a Vega. Also need ROCm 1.9 or newer.

    What hardware do you have ?

    Leave a comment:


  • Marc Driftmeyer
    replied
    Since AMD wrote the vast majority of the OpenCL stack in Blender one would think their ``tests'' at conferences would work with ROCm, but my guess is this HSA designed stack for HPC has no future on Blender.

    If you'll notice Blender is only testing Pro Renderer on the new Vega VII test slides, not Cycles, never mind Evee.

    Leave a comment:


  • Michael
    replied
    Originally posted by Azpegath View Post
    Michael, could you please add the Blender tests to this run? That's the only actual use I have for ROCm, and the reason I waited patiently and longingly for it.
    Had tried but currently was falling back to CPU rendering for some reason, didn't have time to explore to see if it was bug in ROCm or a Blender issue.

    Leave a comment:


  • Azpegath
    replied
    Michael, could you please add the Blender tests to this run? That's the only actual use I have for ROCm, and the reason I waited patiently and longingly for it.

    Leave a comment:


  • cb88
    replied
    Originally posted by khnazile View Post
    Is there a guide how to get ROCm working with mainline kernel without installing whole amdgpu-pro graphics stack? Some people claim it's possible, but I didn't manage to get it working. I tried installing pre-built binaries as https://rocm.github.io/ROCmInstall.html suggests, but it didn't work for me. Also, those binaries come unsigned for some reason...
    This is the wrong place to ask... Also ROCm has nothing to do with amdgpu-pro they are separate things. The easiest route is probably thier recommended rock-dkms if on Debian.

    If you want to get ROCm working with an upstream kernel... then you'll just have to try several ones to see which one works probably 4.18 and 4.19 would be a good place to start. Note there are caveats to using an upstream kernel.

    Leave a comment:


  • khnazile
    replied
    Is there a guide how to get ROCm working with mainline kernel without installing whole amdgpu-pro graphics stack? Some people claim it's possible, but I didn't manage to get it working. I tried installing pre-built binaries as https://rocm.github.io/ROCmInstall.html suggests, but it didn't work for me. Also, those binaries come unsigned for some reason...

    Leave a comment:

Working...
X