6

If I'm using my GPU for CUDA computations and I want to use my CPU to manage the display, is there a way to get Xorg to use the CPU and the motherboard's HDMI slot instead of the GPU and its HDMI slot? Right now I'm maxing out the computational power of my GPU and Unity is really slow but my CPU is idling.

7
  • you can let xrandr show you a list of outputs availible with xrandr --current if you then identify the HDMI output of your mainboard you could set that as primary if you use a APU with dedicated GPU you would need a switching method most likely try looking up hybrid solutions like bumblebee
    – WooJoo
    Jan 8 '17 at 16:22
  • I think prime-select intel should do the trick. After that you have to logout/login.
    – Thomas
    Jan 8 '17 at 16:58
  • 1
    I do not think this is a laptop so not sure bumblebee is relevent is sounds like @john standford is describing a desktop. Does your cpu and motherboard support pcie passthrough to a vm and run unity on the host with the integrated.
    – ianorlin
    Jan 8 '17 at 20:54
  • 2
    I'm looking for an answer to this question as well. In my case this is a server where GPUs are dedicated to computation, graphics is irrelevant (only necessary for the console). I don't want the Xorg processes taking GPU memory, they should just run on the CPU. Jul 10 '18 at 0:03
  • 1
    I need the Nvidia GPU drivers installed. The server I have has 2x 1080 GPUs that we use for applications. Currently, Xorg is using ~1GB of memory on one of the two GPUs. There is no integrated graphics card on the server. Jul 16 '18 at 20:29
3
+50

This answer: Use integrated graphics for display and NVIDIA GPU for CUDA on Ubuntu 14.04 appears relevant for you.

In summary setting up /etc/X11/xorg.conf as follows:

Section "ServerLayout"
    Identifier "layout"
    Screen 0 "intel"
    Screen 1 "nvidia"
EndSection

Section "Device"
    Identifier "intel"
    Driver "intel"
    BusID "PCI:0@0:2:0"
    Option "AccelMethod" "SNA"
EndSection

Section "Screen"
    Identifier "intel"
    Device "intel"
EndSection

Section "Device"
    Identifier "nvidia"
    Driver "nvidia"
    BusID "PCI:1@0:0:0"
    Option "ConstrainCursor" "off"
EndSection

Section "Screen"
    Identifier "nvidia"
    Device "nvidia"
    Option "AllowEmptyInitialConfiguration" "on"
    Option "IgnoreDisplayDevices" "CRT"
EndSection

Read the entire post for more details.


Reply to comments

According Asus Canada specs:

Integrated Graphics Processor- Intel® HD Graphics support Multi-VGA output support : HDMI/DVI-D/RGB/DisplayPort ports - Supports HDMI with max. resolution 4096 x 2160 @ 24 Hz / 2560 x 1600 @ 60 Hz - Supports DVI-D with max. resolution 1920 x 1200 @ 60 Hz - Supports RGB with max. resolution 1920 x 1200 @ 60 Hz - Supports DisplayPort with max. resolution 4096 x 2304 @ 60 Hz Maximum shared memory of 512 MB Supports Intel® InTru™ 3D, Quick Sync Video, Clear Video HD Technology, Insider™ Supports up to 3 displays simultaneously DP 1.2 Multi-Stream Transport compliant, supports DP 1.2 monitor daisy chain up to 3 displays

I suggest temporarily taking out your two nVidia cards, plugging a monitor into the on-board HDMI port and booting with a Live USB to runs tests with Ubuntu.

It is important to know your CPU. Discover this using:

cat /proc/cpuinfo | grep 'model name'

and report back.

7
  • We're looking for CPU though, no graphics card, there is no integrated graphics card in my case. Unfortunately, the link isn't loading at the moment. I'll try looking later. The GPU in my case should be dedicated entirely to distributed scientific compute purposes. Jul 16 '18 at 17:41
  • 1
    Most CPUs have integrated GPUs. What CPU do you have? Jul 16 '18 at 19:52
  • Reading other comments I see you have a build it yourself motherboard and you can through a Skylake inside. I have an i7-6700HQ and the HD 530 graphics are so fast I leave the nVidia GTX 970M turned off. Jul 16 '18 at 20:01
  • This server doesn't have an integrated GPU (lspci | grep VGA only shows 2 Nvidia 1080's). It's a (typically) headless server that shouldn't have the ~1GB memory allocated for X windows (we do use the full 10GB of GPU memory for applications). Jul 16 '18 at 20:10
  • 1
    @DavidParks I did some more research and updated my answer. It's important to know your CPU model though. Jul 17 '18 at 2:22

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.