Jump to content

Welcome to ExtremeHW

Welcome to ExtremeHW, register to take part in our community, don't worry this is a simple FREE process that requires minimal information for you to signup.


Registered users can: 

  • Start new topics and reply to others.
  • Show off your PC using our Rig Creator feature.
  • Subscribe to topics and forums to get updates.
  • Get your own profile page to customize.
  • Send personal messages to other members.
  • Take advantage of site exclusive features.
  • Upgrade to Premium to unlock additional sites features.

AMDGPU Gets A Big Batch Of Fixes For Its New Driver Code Coming In Linux 5.10


Recommended Posts

Folding@Home Staff
726 370

In addition to the last minute AMDGPU fixes for Linux 5.9 that include work on the RDNA2 new GPU support and promoting Navi 12 out of the experimental status, an initial batch of fixes for AMDGPU were also sent in to DRM-Next on Wednesday in addressing early fallout from the new feature code slated for Linux 5.10.


With the window for merging new feature code to DRM-Next to make it in Linux 5.10 closed, the AMDGPU pull request issued on Wednesday is for the initial batch of fixes after landing various features in recent weeks.


The fixes for the AMDGPU (and AMDKFD/Radeon) driver code for DRM-Next/Linux 5.10 include correcting problems with AMDKFD compute initialization failures, backlight problems, eDP issues, memory clock handling fixes for Navi 1x, SR-IOV fixes, power fixes for Raven and Renoir APUs, and other fixes throughout.




Lots of great new work for AMD GPU's happening still.

Link to comment
Share on other sites

They need to work on OpenCL.  ROCm, the open source OpenCL driver, doesn't support all their GPU's and doesn't work with all applications.  The proprietary OpenCL driver that does work on all AMD GPU's and with all applications isn't installable on all distros.


It's one of the reasons why I removed my Radeon VII and reinstalled my 1070ti FTW.  I gave up some gaming performance, but gained functionality.

Edited by Diffident
Link to comment
Share on other sites

ROCm is a bit of a mess.  I am actually running it on an upstream kernel, but the OpenCL implementation in ROCm is incomplete at best.  


Right now I'm not sure what AMD wants developers to do.  AMD is pushing their HIP/HCC stack, OpenCL 3.0 rolls back the clock about a decade on the standard, and Intel is pushing OneAPI.  All the while CUDA is remains the dominant platform.  Hopefully their is a future for OpenCL, but right it doesn't look great.  

Link to comment
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

  • Create New...

Important Information

This Website may place and access certain Cookies on your computer. ExtremeHW uses Cookies to improve your experience of using the Website and to improve our range of products and services. ExtremeHW has carefully chosen these Cookies and has taken steps to ensure that your privacy is protected and respected at all times. All Cookies used by this Website are used in accordance with current UK and EU Cookie Law. For more information please see our Privacy Policy