Talk:AMDGPU

Moving "Enable GPU display scaling" to xrandr

I thought about it to put this under xrandr directly, but for example for my integrated Intel 6th gen GPU I don't have the "scaling mode" option, and I don't know about NVIDIA. And even if the "scaling mode" option exists for other vendors and or cards, I don't know if the possible values for "scaling mode" are the same everywhere, as far as I remember there are not. That was the reason I did put it here. Bertl (talk) 16:01, 18 February 2018 (UTC)

Ok, looks like Intel uses the same settings, but it's only available for internal (LVDS, eDP) ports, but at least according to https://bugs.freedesktop.org/show_bug.cgi?id=90989 it also uses "None, Full, Center, Full aspect".

I know that radeonsi uses the same commands, but still don't know about NVIDIA.

But yea, now I also think that it should be moved and the Intel section should be merged into it. Bertl (talk) 18:37, 18 February 2018 (UTC)

OpenCL implementation?

I've just spent the past day finding out how to get OpenCL to work with AMDGPU and I just found the answer on the Blender page by using opencl-amd^AUR. I don't really know if it would fit in with the page (as I could of solved this much sooner by searching up OpenCL and just looking at GPGPU) but I was still confused by people saying that only AMDGPU-PRO has OpenCL 2 support, so if it was mentioned somehow on the page I think it would be very helpful. Polygonerror (talk) 15:45, 20 December 2019 (UTC)

Navi power consumption addition: Idle power consumption & memory clocks with Navi 10 and multiple monitors

Using a Gigabyte 5700 XT Gaming OC and 2 Monitors (LG OLED 55" and Dell 25") connected, the GPU won't throttle down and uses around 30W in idle. Xorg.conf and xrandr etc. don't help. A workaround is to suspend and resume, using the following as an systemd user job.

.config/systemd/user/xrandr.service

[Unit]
Description=xrandr
After=suspend.target

[Service]
Type=oneshot
Environment=DISPLAY=:0
ExecStart=/usr/bin/xrandr -s 2560x1440 --dpi 117 --output DisplayPort-2 --mode 2560x1440 --primary --output HDMI-A-0 --same-as DisplayPort-2  --scale-from 2560x1440 --mode 1920x1080 --rate 60 --dpi 96
ExecStart=/usr/bin/xrandr --output HDMI-A-0 --off


[Install]
WantedBy=suspend.target

Change ports and resolutions and enable with

systemctl --user enable xrandr

Setting --rate of the LG OLED to 120 will not reduce power consumption as much, because the GPU needs to clock the memory higher.

Everything works as expected after resuming. Power1 from amdgpu is around 9-10W in idle.

Is there anything official to fix this that I didn't find?

The problem is still present in 5.5.15-1-ck and 5.6rc7-1.

Is it OK to include this in the troubleshooting section ?

Strikemybread (talk) 11:29, 7 April 2020 (UTC)

still present in 5.7-mainline Strikemybread (talk)

OK, using a modeline _without_ reduced blanking gives proper power usage right after boot (cvt 2560 1440 60). More than the max. reported pixel clock of the monitor(connection). Power reading is now ~10 W, with workaround above ~ 8 W. And, workaround doesn't work anymore with > 5.9.14. Strikemybread (talk)

Section about Colour Spaces and how to change them

I recently read about the issues around colour spaces with AMDGPU via HDMI. Apparently? AMDGPU uses YCbCr color format. There should be a section explaining how to change this behavior, as it is a common issue among users, causing weird colors with monitors in some cases. This blog post shows a possible workaround, by editing the monitor's EDID and passing that to KMS with a kernel parameter. Though it might not be the desired workaround for many people. The section should also mention possible settings on the monitor itself (changing colour space there).

Scrumplex (talk) 08:47, 7 April 2021 (UTC)

Section about Wrong GPU clocks

After I added this block, I found that the problem was enabled overclocking. After disabling overclocking, the frequencies became the same as specified by the manufacturer, but the problem did not go away. Sometimes when changing the parameters (frequencies, undervolting, board consumption) the situation gets better, but in some games it does not go away (e.g. "The Finals" crashes my PC with 50% chance). Also, user reports are confusing and it is not clear what exactly the problem is. I am not sure that the problem is due to the frequencies, but the problem exists. Maybe there is something with lack of VRAM, but I'm not sure. Losted (talk) 09:40, 13 August 2025 (UTC)