https://bugs.freedesktop.org/show_bug.cgi?id=107266
Bug ID: 107266
Summary: Radeon Pro Duo (Polaris) - ring sdma0 timeout
Product: DRI
Version: unspecified
Hardware: x86-64 (AMD64)
OS: Linux (All)
Status: NEW
Severity: normal
Priority: medium
Component: DRM/AMDgpu-pro
Assignee: dri-devel@lists.freedesktop.org
Reporter: rh...@hotmail.com
Running a polaris Pro Duo on Ubuntu 18.04, Kernel from ROCm branch
4.17.0-rc2-180424-fkxamd and everything works great.
In testing latest drm-next-4.19-wip kernel, I get the following errors on boot,
and have no working opencl (ie clinfo hangs indefinitely)
[ 58.913281] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring sdma0 timeout,
signaled seq=573, emitted seq=574
[ 58.913284] [drm] GPU recovery disabled.
[ 58.914276] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring sdma1 timeout,
signaled seq=331, emitted seq=333
[ 58.914280] [drm] GPU recovery disabled.
[ 58.914312] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring sdma1 timeout,
signaled seq=331, emitted seq=333
[ 58.914313] [drm] GPU recovery disabled.
Please let me know if you need any specifics.
--
You are receiving this mail because:
You are the assignee for the bug.
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel