Radeon ROCm 5.0 Released With Some RDNA2 GPU Support

[vein]

I've updated it now for Arch, it should be working with ROCm 5.0 I think - Any feedback is welcome
p.s You also need `opencl-amd-dev` package if you want ML libraries and OpenCL / HIP SDK.

Great! I will update during the weekend and see how good it works. And thanks for the other package too. Will install that one too...

[ernstp]

Thanks! Finally I installed all packages without problem. Amazing.

Do you have
grep rocm /etc/ld.so.conf.d/ -r
/etc/ld.so.conf.d/10-rocm-opencl.conf:/opt/rocm-5.0.0/opencl/lib
?
It's from rocm-ocl-icd I think.

clinfo
Number of platforms 1
Platform Name AMD Accelerated Parallel Processing
Platform Vendor Advanced Micro Devices, Inc.
Platform Version OpenCL 2.2 AMD-APP (3406.0)
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_icd cl_amd_event_callback
Platform Extensions function suffix AMD
Platform Host timer resolution 1ns

Platform Name AMD Accelerated Parallel Processing
Number of devices 1
Device Name gfx1030
Device Vendor Advanced Micro Devices, Inc.
Device Vendor ID 0x1002
Device Version OpenCL 2.0
Driver Version 3406.0 (HSA1.1,LC)
Device OpenCL C Version OpenCL C 2.0

[piorunz]

Do you have
grep rocm /etc/ld.so.conf.d/ -r
/etc/ld.so.conf.d/10-rocm-opencl.conf:/opt/rocm-5.0.0/opencl/lib
?
It's from rocm-ocl-icd I think.

clinfo
Number of platforms 1
Platform Name AMD Accelerated Parallel Processing
Platform Vendor Advanced Micro Devices, Inc.
Platform Version OpenCL 2.2 AMD-APP (3406.0)
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_icd cl_amd_event_callback
Platform Extensions function suffix AMD
Platform Host timer resolution 1ns

Platform Name AMD Accelerated Parallel Processing
Number of devices 1
Device Name gfx1030
Device Vendor Advanced Micro Devices, Inc.
Device Vendor ID 0x1002
Device Version OpenCL 2.0
Driver Version 3406.0 (HSA1.1,LC)
Device OpenCL C Version OpenCL C 2.0

Yes, I have this package installed, and this file reads:

[FONT=monospace][COLOR=#000000]$ cat /etc/ld.so.conf.d/10-rocm-opencl.conf [/COLOR]
/opt/rocm-5.0.0/opencl/lib[/FONT]

ls says:

[FONT=monospace][COLOR=#000000]$ ls /opt/rocm-5.0.0/opencl/lib [/COLOR]
libamdocl64.so  [COLOR=#54ffff][B]libOpenCL.so[/B][/COLOR][COLOR=#000000]  [/COLOR][COLOR=#54ffff][B]libOpenCL.so.1[/B][/COLOR][COLOR=#000000]  libOpenCL.so.1.2[/COLOR][/FONT]

But still Platform Name AMD Accelerated Parallel Processing
Number of devices 0
.

[ernstp]

Did you setup the udev rule for using upstream kernel?

https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html#using-debian-based-rocm-with-upstream-kernel-drivers

Guess you need to reboot after that also.

[Spacefish]

5700XT (RDNA1) with tensorflow-rocm build from source (for rocm 5.0)

Python 3.9.10 (main, Jan 16 2022, 17:12:18)
[GCC 11.2.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import tensorflow as tf
>>> tf.add(1, 2).numpy()
"hipErrorNoBinaryForGpu: Unable to find code object for all current devices!"
Aborted (core dumped)

could probably work if i build rocm from source with the gfx1010 backend enabled.. But building rocm from source is a pain in the b**** IMHO (at least it was for older versions where i did it once).

Edit: HIP examples work fine / HIP works out of the box for gfx1010

[gobenji]

In my experience on Debian Sid, an easy way to get going with rocm is to use the rocm/tensorflow-autobuilds docker image:

docker run --rm -it --name rocm --device=/dev/kfd --device=/dev/dri --security-opt seccomp=unconfined rocm/tensorflow-autobuilds

With a 6700xt I've found that opencl works but not tensorflow.

[boboviz]

Oh, I don't know . . . . . how about 4 Million users and 205K hosts according to today's BoincStats BOINC combined stats. That is a not small number.

Wait, wait, i'm boinc volunteers since...i don't remember.
In the boinc's world i don't think rocm can change the situation:
- projects with gpu support (Milkyway, Einstein, ecc) have Cuda and OpenCl.
- projects without gpu support continue not to have it.

[boboviz]

Mobile phone makers advertise their new chips contain neural co-processors. 99.999% of phone users don't write neural software either.
"Consumers" by definition don't "make" stuff. They consume GPGPU applications if they are widely supported and available.

Rocm is NOT for smartphone. AMD is very clear about the use of Rocm.
First: data center
Second: high-end gpu

[billyswong]

Rocm is NOT for smartphone. AMD is very clear about the use of Rocm.
First: data center
Second: high-end gpu

If "General Purpose GPU" is only supposed to be used for data centers and the selected premium high-end workstations (a moving narrow range of not too old and not too new), then it is not "General Purpose".

CUDA is far more "General Purpose" than ROCm in this aspect. Don't wonder why many GPU computation frameworks are written for CUDA only. It is about market share and entry barrier.

I took smartphone as example because it shows there are applications of GPU-style computations outside data centers and selected high-end workstations. ROCm being restrictive and high barrier to enter is an issue to be solved, not an explanation to its defect.

[davide445]

https://rocmdocs.amd.com/en/latest/FAQ/FAQ_HIP.html

Didn't understand if this it's up to date with 5.0 release, in therm of supported and unsupported features.
Interested in graphics interop.