AMDKFD GPUVM Support Updated For Radeon Discrete GPUs

[phoronix]

Phoronix: AMDKFD GPUVM Support Updated For Radeon Discrete GPUs

Many of you have been anxious to get ROCm/OpenCL compute working with the open-source Radeon Linux driver on modern GPUs while using a mainline kernel and that day continues inching closer...

http://www.phoronix.com/scan.php?page=news_item&px=AMDKFD-GPUVM-V2

[Azpegath]

Will it work with Blender? I was playing around with Blender around Christmas and it drove me crazy that I didn't have OpenCL acceleration for rendering. It took forever to render my simple scene, hopefully this will revolutionize the workflow.

[gsedej]

What will AMDKFD enable on dGPU? my rx480 already works fine with some opencl tasks.

[ernstp]

Will it work with Blender? I was playing around with Blender around Christmas and it drove me crazy that I didn't have OpenCL acceleration for rendering. It took forever to render my simple scene, hopefully this will revolutionize the workflow.

There are a couple methods to have very nice OpenCL acceleration available. For example running a vanilla Ubuntu 16.04.3 with rocm-dkms, just follow the instructions here: https://github.com/RadeonOpenCompute/ROCm

This news is about a fully upstream solution, which is something else..

[Brisse]

For example running a vanilla Ubuntu 16.04.3 with rocm-dkms

Also works perfectly fine on Ubuntu 17.10 for me even though it's not officially supported

Doesn't work on kernel 4.14 or 4.15 though, but works fine on the 4.13 kernel which 17.10 is running as default.

[Marc Driftmeyer]

Also works perfectly fine on Ubuntu 17.10 for me even though it's not officially supported

Doesn't work on kernel 4.14 or 4.15 though, but works fine on the 4.13 kernel which 17.10 is running as default.

I'm running Debian Sid 4-125-rc8 with AMDGPU PRO OpenCL Stack for Blender. I can tell you which drivers to install and to --force-install the dkms module and ignore its ensuing warning message which will result in it running, but one caveat: you have to be on Mesa 17.2.5 from your distro until they re-roll a new AMDGPU PRO revision for Mesa 18.

[Peter Fodrek]

What will AMDKFD enable on dGPU? my rx480 already works fine with some opencl tasks.

AMDKFD is not about openCL support. It is HSA

HSA in extreme simplification means, that there is no need of data transfer form CPU RAM into GPU RAM and vice versa.

The result is speedup as of

https://img.purch.com/w/600/aHR0cDovL21lZGlhLmJlc3RvZm1pY3JvLmNvbS9LL00vNDQ2NTY2L29yaWdpbmFsLzEwLUxpYnJlT2ZmaWNlLUhTQS5wbmc=

form

http://www.tomshardware.com/reviews/amd-a10-7800-kaveri-apu-efficiency,3899-5.html

where execution of same code on the CPU lasts 855.4% time of HSA code execution and pure openCL code runs 643.5% of execution time for HSA code
but it only runs on APUs at least for open source driver.

AMDKFD enables HSA (GPU's capability of read form CPU RAM) for discrete AMD GPUs

[Brisse]

Marc Driftmeyer Cool! Might give that a try later.

[bridgman]

What will AMDKFD enable on dGPU? my rx480 already works fine with some opencl tasks.

This is about taking functionality that is already available out-of-tree (via ROCm stack for several GPUs and AMDGPU-PRO stack for Vega) and getting closer to making it available in upstream kernels.

[Brisse]

Is there any way to get around this except downgrading the kernel?

$ sudo dkms --force install rock/1.7.60-ubuntu

Kernel preparation unnecessary for this kernel.  Skipping...

Running the pre_build script:

Building module:
cleaning build area...
make -j16 KERNELRELEASE=4.15.2-041502-generic -j16 -C /lib/modules/4.15.2-041502-generic/build M=/var/lib/dkms/rock/1.7.60-ubuntu/build...(bad exit status: 2)
ERROR (dkms apport): kernel package linux-headers-4.15.2-041502-generic is not supported
Error! Bad return status for module build on kernel: 4.15.2-041502-generic (x86_64)
Consult /var/lib/dkms/rock/1.7.60-ubuntu/build/make.log for more information.