Announcement

Collapse
No announcement yet.

AMD Squeezes In Additional GPU Enablement Code For Linux 6.9

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

  • George99
    replied
    As darkbasic said there is only iGPU support for SR-IOV

    Leave a comment:


  • darkbasic
    replied
    Originally posted by flower View Post

    Intel Arc already has it?
    It works on my A380 which i use in my nas.
    Nope it doesn't.

    Leave a comment:


  • mathieu.cossette
    replied
    AMD+Kernel news always makes my day

    Leave a comment:


  • pong
    replied

    Originally posted by flower View Post

    Intel Arc already has it?
    It works on my A380 which i use in my nas.

    i wait for battlemage to evaluate it for my gaming desktop though
    That's interesting news to me. I have read that several intel IGPUs had SR-IOV or something like it
    called something like GVT-g, but I have not heard of any ARC DGPU having SR-IOV enabled and besides that working usefully
    in the way the IGPUs could.
    How (driver / OS support & configuration etc.) do you configure to make use of it and how did you learn of its capacity?
    What does the host / guest "see" wrt. capabilities / resources and SW support for whatever (video codecs, sycl, opencl, ...)?
    Last edited by pong; 09 March 2024, 03:42 PM.

    Leave a comment:


  • pong
    replied
    Originally posted by Danny3 View Post
    How about enabling SR-IOV on consumer GPUs so we can use VirtualBox with that SR-IOV back-end for near native gaming performance?
    I agree 100%, though speaking only of gaming is really underselling the need.
    Even just running a 1-3 VMs of any kind e.g. linux guest / linux host, linux / windows, whatever is a use case.
    Even the most ordinary GUI based desktop / productivity applications these days depend heavily on GPU use
    and multiple high resolution (4k+ etc.) monitors are very normal configurations for personal / productivity desktops.

    And then lots of applications depend to some extent on GPU compute either alone or mixed with graphics operations
    e.g. ordinary basic ML models, OCR, photo / image editing filters, video encode / decode / conversion, noise / background
    removal for audio / webcam, basic personal language translation, ML based grammar / language / composition analysis / assistance, etc. etc.

    Pretty much every single consumer oriented CPU and system chipset supports MMU, virtualization, per-process / user isolation,
    CPU integrated abilities to efficiently share the computer resources between many different programs / tasks / users.
    So clearly AMD, Intel, ARM CPU / system chipset makers already see the need for HW backed virtualization & multi-tasking isolation
    security even in the low end of consumer compute HW.

    Yet for GPUs? NOTHING USEFUL FOR VIRTUALIZATION AT ALL. AFAICT the core support needed for SR-IOV is only to start exposing
    some dozens of registers for the functions in PCIE capabilities structures and handling them in very ordinary ways at the driver level.
    Simpler even than the MMU and virtualization support already in the main processor which apparently you've already long ago decided to agree is
    necessary for mass consumer market use cases, so what possible cognitive dissonance could result in integrating a boat load of complex virtualization supporting
    HW into every part of the consumer computing architecture EXCEPT the GPU where arguably it's extremely critically needed and is the biggest
    sore spot for consumer computing today to have no commensurate multi-tasking / multi-VM support for it at all.

    On the one hand GPU makers evidently seem to encourage them as the solution for graphics, video, image processing, inferencing ML / NPUs,
    and yet they offer basically crippled and defective-by-design architectures when they already routinely support sane virtualization support
    for all of their other GPU / CPU / chipset product lines.

    AFAICT the HW level capability already EXISTS and is DISABLED so it isn't even a question of adding ASIC design capabilities, it's a question
    of not punishing and abusing your users for no sane reason.



    Leave a comment:


  • Kjell
    replied
    Originally posted by NeoMorpheus View Post

    Aah, gaming gpu, which none do for obvious reasons.
    💩💩💩💩💩

    Leave a comment:


  • NeoMorpheus
    replied
    Originally posted by Kjell View Post

    Sure but to be realistic, would it even work with QEMU+KVM? Seems like Xen is preferred in DCs where professional GPUs are used. Also, is there even one which can compete with latest gaming GPUs in terms of FPS in games?
    Aah, gaming gpu, which none do for obvious reasons.

    Leave a comment:


  • Kjell
    replied
    Originally posted by NeoMorpheus View Post

    They do, its called professional gpus and they would love your wallet.
    Sure but to be realistic, would it even work with QEMU+KVM? Seems like Xen is preferred in DCs where professional GPUs are used. Also, is there even one which can compete with latest gaming GPUs in terms of FPS in games?
    Last edited by Kjell; 09 March 2024, 10:57 AM.

    Leave a comment:


  • Kjell
    replied
    Originally posted by flower View Post

    Intel Arc already has it?
    It works on my A380 which i use in my nas.

    i wait for battlemage to evaluate it for my gaming desktop though
    None of Intel's dGPUs can match the performance of my current setup

    Intel still has some work left but I'm glad they're making progress
    Last edited by Kjell; 09 March 2024, 10:57 AM.

    Leave a comment:


  • NeoMorpheus
    replied
    Originally posted by Kjell View Post
    GPU Passthrough is cumbersome for gaming if you want to quickly switch between Linux Desktop & Windows VM.. SR-IOV would make it seamless.

    Whoever brings this technology first to modern gaming GPUs can have my wallet.
    They do, its called professional gpus and they would love your wallet.

    Leave a comment:

Working...
X