Re: Planned Vega support in Linux

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Tue, Aug 8, 2017 at 11:46 PM, David Niklas <doark@xxxxxxxx> wrote:
> BTW: I'm on list, no need to CC.
>
> On Wed, 9 Aug 2017 10:38:23 +0900
> Michel Dänzer <michel@xxxxxxxxxxx> wrote:
>
>> On 09/08/17 05:12 AM, David Niklas wrote:
>> > I know that currently some form of headless support already exists,
>> > but then I'd have to use crossfire (which does not work with the
>> > opensource driver AFAIK).
>>
>> You don't need CrossFire to make use of a GPU in a headless fashion.
>
> No, but you do if you intend to use your primary desktop machine and Vega
> supports only headless, or as Harry pointed out, a display driver (which,
> I am assuming means 2D only).

Full asic functionality is available for vega10 including displays in
the branch Harry pointed out.

> Besides, and as a side thought, I have had the temptation of using two
> GPUs for compute tasks since it's just silly to toss/sell a GPU that
> could be useful and is worth more to me than it's online value in dollars
> (I have to choose the only GPU that actually goes *down* in price....)
>
>> OpenCL should support that out of the box, and in X the GPU can be used
>> for OpenGL apps via RandR 1.4 render offloading (obviously, you'll need
>> another GPU in the system that X can use for output).
>>
>
> You've lost me.
> Let my try to understand, and you correct me as I go astray.
> 1. X can send the OpenGL requests to another GPU while Vega does other
> things or idles mindlessly in headless mode.
> 2. X can send the OpenGL requests to the Vega GPU while the other GPU
> sends frames to the display from Vega.
>
> Also, do I need to configure X using RandR, or will it "just work" ...
> Stupid question, let me rephrase:
> What do I need to do to tell RandR to get X to work?

If you use the kernel branch mentioned above, X will detect all
relevant GPUs and you can use xrandr to dynamically configure what
GPU(s) you want to display with or render with at runtime.  You only
need X for display.  If you just want to use a GPU for offscreen
graphics rendering or compute work, you don't need to be running X.

Alex
_______________________________________________
dri-devel mailing list
dri-devel@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/dri-devel




[Index of Archives]     [Linux DRI Users]     [Linux Intel Graphics]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [XFree86]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Linux Kernel]     [Linux SCSI]     [XFree86]
  Powered by Linux