Announcement

Collapse
No announcement yet.

AMD Posts Open-Source Linux Driver Support For "NAVI 14" GPU

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • ernstp
    replied
    Originally posted by QuImUfu View Post

    Oh, what does it do and how can it be used?
    https://lists.freedesktop.org/archiv...st/001058.html :
    The Virtual Display feature is to fake a display engine in amdgpu kernel driver, which allows any other kernel modules or user mode components to work as expected even without real display HW. User can get the desktop/primary surface through remote desktop tools instead of displaying HW associated with the GPU. The virtual display feature is designed for following cases: 1)Headless GPU, which has no display engine, while for some reason the X server is required to initialize in this GPU; 2)GPU with head (display engine) but Video BIOS disables display capability for some reason. For example, SR-IOV virtualization enabled Video BIOS often disables display connector. Some S-series Pro-Graphics designed for headless computer also disable display capability in Video BIOS; 3)For whatever reason, end user wants to enable a virtual display (don’t need HW display capability).

    Leave a comment:


  • QuImUfu
    replied
    Originally posted by ernstp View Post
    This is just a standard software feature that's supported by all other families already and nothing special.
    Oh, what does it do and how can it be used?

    Leave a comment:


  • entropy
    replied
    Originally posted by asdfgh View Post
    <sarcasm>Will this driver be as stable as vega's one?</sarcasm>
    Can you be a bit more specific please.

    What instabilities are you talking about?

    Currently, I still run a Radeon HD 7950 and it's completely stable.
    I want to upgrade to Navi in the foreseeable future.
    Should I expect issues with stability?

    Leave a comment:


  • ernstp
    replied
    modinfo amdgpu says:
    parm: virtual_display:Enable virtual display feature (the virtual_display will be set like xxxx:xx:xx.x,x;xxxx:xx:xx.x,x) (charp)

    This is just a standard software feature that's supported by all other families already and nothing special.

    Leave a comment:


  • QuImUfu
    replied
    Originally posted by boxie View Post
    and yes, I had forgotten about VSR on the windows driver, it could be that feature making its way into the product line.
    VSR is in all Linux graphics drivers that support xrandr for **ages**. xrandr --output DVI-1 --scale 1.5x1.5 --auto --panning 1920x1536 --fb 1920x1536 gives me 1920x1536 resolution downscaled to 1280x1024 (my monitors resolution) in games.
    I hope virtual display would enable me to e.g. put another GPU in my pc, start a Xorg instance on that "virtual display" and then stream it over kmsgrab and vaapi to another device, so i could have full, virtually latency-free access to my desktop pc anywhere in my house, without having to buy another (expensive) monitor that is not used. Or put my PC in the cellar and have only a raspberry pi(or similar) in my room, preventing heat production and noise.

    If it can do multiple displays i could even stream each one to a different location.
    For that to be useful one would need proper multi seat support in Xorg. if that would be a thing, i could replace all PC's/Static Laptops's in my house with a Raspberry pi(or similar), reducing costs (they are only used for browsing anyway, so them getting a display should not hinder my performance significantly) and power consumption. Additionally bursty workloads (because that one PC would be much better than any of the current ones) would profit on all of these replaced PC's and because everyone is often accessing similar programs caching would work even better. Because there is no VM the usual drawbacks of additional memory usage(duplicated services) and fixed resource distribution (e.g. VM1 has 3gb ram and 4 cores, VM2 13gb and 12 cores) do not exist. IMO VM's are only useful if you do not trust the other users.

    Leave a comment:


  • asdfgh
    replied
    <sarcasm>Will this driver be as stable as vega's one?</sarcasm>

    Leave a comment:


  • starshipeleven
    replied
    Originally posted by DebianLinuxero View Post
    What's the difference between AMDGPU and AMDGPU PRO?

    What hides the closed source implementation?
    The "PRO" contains:
    a more updated kernel driver, but that part is upstreamed regularly into AMDGPU
    the proprietary userspace blob that provides OpenGL/CL/Vulkan/whatever and replaces Mesa (which is what AMDGPU uses)

    Leave a comment:


  • DebianLinuxero
    replied
    What's the difference between AMDGPU and AMDGPU PRO?

    What hides the closed source implementation?

    Leave a comment:


  • boxie
    replied
    Originally posted by cb88 View Post

    Maybe, I was thinking custom more as in how can we cram as many of these into a box as possible and get low latency video encoding in there.... so I'd think a custom Vega or Navi die + custom video hardware + network uplink straight off the card.
    that certainly all makes sense. Output video directly into video encoder -> pcie transit directly out of the hosts NIC would certainly be an interesting custom solution.

    Leave a comment:


  • cb88
    replied
    Originally posted by boxie View Post

    Just re-read the announcement doc, they do not specifically call out a uArch - they do say "SR-IOV, 56 CU's and HBM2" Custom GPU.

    Currently a vega56 DC GPU fits that - but being that AMD does a lot of custom stuff, I wouldn't be surprised if it is a custom Navi (given launch timelines) for power saving.

    and yes, I had forgotten about VSR on the windows driver, it could be that feature making its way into the product line.
    Maybe, I was thinking custom more as in how can we cram as many of these into a box as possible and get low latency video encoding in there.... so I'd think a custom Vega or Navi die + custom video hardware + network uplink straight off the card.

    Leave a comment:

Working...
X