Planned Vega support in Linux

Planned Vega support in Linux

[David Niklas]

[-- Attachment #1.1: Type: text/plain, Size: 1005 bytes --]

Hello,
I'm not seeking any secret info.
I'm a Gentoo Linux user who wants to run some massively parallel
experiments.
I'm unwilling to wait and see what kind of support Linux gets because
the annoying bitcoin miners tend to cause the price to go through the roof
quickly.
My current card is an AMD SI HD7780 by MSI.
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).
I filed a ticket at AMD on 05/07/17 but AMD has not gotten back to me on
this matter and like I said, if I wait then I risk having to buy
something way out of my price range.
--And I really have tried to wait till the last minute--
Anything official or unofficial will do.
I am planning to use the OpenCL language to do my MP experiments.

Thanks,
David

BTW: I got the emails to CC from the discussion:
[RFC] Using DC in amdgpu for upcoming GPU
so don't worry that I have an email harvester or something.

[-- Attachment #1.2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[-- Attachment #2: Type: text/plain, Size: 160 bytes --]

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

Re: Planned Vega support in Linux

[Harry Wentland]

Hi David,

upstream kernels currently have only headless support. We're still
working on getting our display driver accepted upstream but in the
meantime you can compile it yourself from
https://cgit.freedesktop.org/~agd5f/linux/?h=amd-staging-4.12. With this
you should have no issues booting to desktop with whatever displays you got.

As for the rest of our driver Alex can probably give you a better
picture but I imagine pretty much everything should be working on Vega
on that tree.

Harry


On 2017-08-08 04:12 PM, David Niklas wrote:
> Hello,
> I'm not seeking any secret info.
> I'm a Gentoo Linux user who wants to run some massively parallel
> experiments.
> I'm unwilling to wait and see what kind of support Linux gets because
> the annoying bitcoin miners tend to cause the price to go through the roof
> quickly.
> My current card is an AMD SI HD7780 by MSI.
> 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).
> I filed a ticket at AMD on 05/07/17 but AMD has not gotten back to me on
> this matter and like I said, if I wait then I risk having to buy
> something way out of my price range.
> --And I really have tried to wait till the last minute--
> Anything official or unofficial will do.
> I am planning to use the OpenCL language to do my MP experiments.
> 
> Thanks,
> David
> 
> BTW: I got the emails to CC from the discussion:
> [RFC] Using DC in amdgpu for upcoming GPU
> so don't worry that I have an email harvester or something.
> 
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

RE: Planned Vega support in Linux

[Deucher, Alexander]

> -----Original Message-----
> From: David Niklas [mailto:doark@mail.com]
> Sent: Tuesday, August 08, 2017 4:13 PM
> To: dri-devel@lists.freedesktop.org
> Cc: Deucher, Alexander; Bridgman, John; Deucher, Alexander; Cheng, Tony;
> Koenig, Christian; Wentland, Harry
> Subject: Planned Vega support in Linux
> 
> Hello,
> I'm not seeking any secret info.
> I'm a Gentoo Linux user who wants to run some massively parallel
> experiments.
> I'm unwilling to wait and see what kind of support Linux gets because
> the annoying bitcoin miners tend to cause the price to go through the roof
> quickly.
> My current card is an AMD SI HD7780 by MSI.
> 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).
> I filed a ticket at AMD on 05/07/17 but AMD has not gotten back to me on
> this matter and like I said, if I wait then I risk having to buy
> something way out of my price range.
> --And I really have tried to wait till the last minute--
> Anything official or unofficial will do.
> I am planning to use the OpenCL language to do my MP experiments.

I'm not quite sure what you are asking.  We released initial open source support for vega10 months ago and it continues to evolve as new SKUs are launched.  It is expected that you can get a complete working stack in open source at launch time for whatever sku you are interested in.  Not all of the patches are upstream, but they are all public.  OpenCL support is provided by the ROCm stack which you can get from the gpuopen site.  Headless boards are supported just fine and have been for years.  If you prefer packaged drivers, you can download the ROCm stack from gpuopen or the pro stack from amd.com.  All stacks build on the same open source kernel driver and other components.

Alex

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

Re: Planned Vega support in Linux

[Kai Wasserbäch]

[-- Attachment #1.1.1: Type: text/plain, Size: 787 bytes --]

Hey Harry,
Harry Wentland wrote on 08.08.2017 22:25:
> upstream kernels currently have only headless support. We're still
> working on getting our display driver accepted upstream but in the
> meantime you can compile it yourself from
> https://cgit.freedesktop.org/~agd5f/linux/?h=amd-staging-4.12. With this
> you should have no issues booting to desktop with whatever displays you got.

can you or somebody else from AMD expand on what is – from your point of view –
missing before you can start upstreaming DAL/DC/display? If possible with a
rough time-frame.
Is there a page with a list of outstanding tasks? Maybe even low-hanging fruit
for new contributors (particularly tasks you haven't started internally so
there's no unnecessary overlap)?

Cheers,
Kai


[-- Attachment #1.2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 659 bytes --]

[-- Attachment #2: Type: text/plain, Size: 160 bytes --]

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

Re: Planned Vega support in Linux

[Michel Dänzer]

[-- Attachment #1.1.1: Type: text/plain, Size: 644 bytes --]

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.
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).


-- 
Earthling Michel Dänzer               |               http://www.amd.com
Libre software enthusiast             |             Mesa and X developer


[-- Attachment #1.2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 224 bytes --]

[-- Attachment #2: Type: text/plain, Size: 160 bytes --]

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

Re: Planned Vega support in Linux

[David Niklas]

[-- Attachment #1.1: Type: text/plain, Size: 1590 bytes --]

BTW: I'm on list, no need to CC.

On Wed, 9 Aug 2017 10:38:23 +0900
Michel Dänzer <michel@daenzer.net> 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).
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?

Thanks,
David

[-- Attachment #1.2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[-- Attachment #2: Type: text/plain, Size: 160 bytes --]

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

Re: Planned Vega support in Linux

[David Niklas]

[-- Attachment #1.1: Type: text/plain, Size: 3124 bytes --]

BTW: I'm on list, no need to CC.

On Tue, 8 Aug 2017 20:30:02 +0000
"Deucher, Alexander" <Alexander.Deucher@amd.com> wrote:
> > From: David Niklas [mailto:doark@mail.com]
> > Hello,
> > I'm not seeking any secret info.
> > I'm a Gentoo Linux user who wants to run some massively parallel
> > experiments.
> > I'm unwilling to wait and see what kind of support Linux gets because
> > the annoying bitcoin miners tend to cause the price to go through the
> > roof quickly.
> > My current card is an AMD SI HD7780 by MSI.
> > 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).
> > I filed a ticket at AMD on 05/07/17 but AMD has not gotten back to me
> > on this matter and like I said, if I wait then I risk having to buy
> > something way out of my price range.
> > --And I really have tried to wait till the last minute--
> > Anything official or unofficial will do.
> > I am planning to use the OpenCL language to do my MP experiments.  
> 
> I'm not quite sure what you are asking.  We released initial open
> source support for vega10 months ago and it continues to evolve as new
> SKUs are launched. 

I used AMD pro stack for sometime before the AMDGPU driver evolved to
something useful. Believe me, I do well to ask[1].

> It is expected that you can get a complete working
> stack in open source at launch time for whatever sku you are interested
> in.  Not all of the patches are upstream, but they are all public.

Is the opensource driver you're thinking of at the url that harry gave
me?
What it the state? (beta, alpha, etc.).
About how complete is it with respect to the other opensource GCN drivers?

> OpenCL support is provided by the ROCm stack which you can get from the
> gpuopen site.

"We do not support ROCm with PCIe Gen 2 enabled CPUs such as the AMD
Opteron, Phenom, Phenom II, Athlon, Athlon X2, Athlon II and Older Intel
Xeon and Intel Core Architecture and Pentium CPUs."

Ouch!
Mine is a Phenom II 6 core 1090T.
I can't go spending a ton on a new CPU, MB, RAM, and GPU (and I'd need a
less hacked case too :)
Granted I could get an i3, cheap the MB and RAM, but I've worked so hard
for a great platform... 32GB RAM, 6 core Phenom II, HD 7780 GPU, RAID 5
on 2TB HDs, Bluray drive, Mechanical keyboard, HP laser printer,
4800x4800dpi HP scanner...
AMD is normally so good at compatibility too.
Ok, I'm over it, what is doable at this point?

> Headless boards are supported just fine and have been
> for years.  If you prefer packaged drivers, you can download the ROCm
> stack from gpuopen or the pro stack from amd.com.  All stacks build on
> the same open source kernel driver and other components.
> 
> Alex
> 

Good to know!



[1] No offence, but AMD's gpu-pro would not allow the system to suspend
(sleep), also I'd often get a black and white set of vertical lines
through my display and the kernel would totally freeze (no sysreq). The
worst part is that it would happen totally randomly (really).

[-- Attachment #1.2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[-- Attachment #2: Type: text/plain, Size: 160 bytes --]

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

Re: Planned Vega support in Linux

[Alex Deucher]

On Tue, Aug 8, 2017 at 11:46 PM, David Niklas <doark@mail.com> wrote:
> BTW: I'm on list, no need to CC.
>
> On Tue, 8 Aug 2017 20:30:02 +0000
> "Deucher, Alexander" <Alexander.Deucher@amd.com> wrote:
>> > From: David Niklas [mailto:doark@mail.com]
>> > Hello,
>> > I'm not seeking any secret info.
>> > I'm a Gentoo Linux user who wants to run some massively parallel
>> > experiments.
>> > I'm unwilling to wait and see what kind of support Linux gets because
>> > the annoying bitcoin miners tend to cause the price to go through the
>> > roof quickly.
>> > My current card is an AMD SI HD7780 by MSI.
>> > 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).
>> > I filed a ticket at AMD on 05/07/17 but AMD has not gotten back to me
>> > on this matter and like I said, if I wait then I risk having to buy
>> > something way out of my price range.
>> > --And I really have tried to wait till the last minute--
>> > Anything official or unofficial will do.
>> > I am planning to use the OpenCL language to do my MP experiments.
>>
>> I'm not quite sure what you are asking.  We released initial open
>> source support for vega10 months ago and it continues to evolve as new
>> SKUs are launched.
>
> I used AMD pro stack for sometime before the AMDGPU driver evolved to
> something useful. Believe me, I do well to ask[1].
>
>> It is expected that you can get a complete working
>> stack in open source at launch time for whatever sku you are interested
>> in.  Not all of the patches are upstream, but they are all public.
>
> Is the opensource driver you're thinking of at the url that harry gave
> me?
> What it the state? (beta, alpha, etc.).
> About how complete is it with respect to the other opensource GCN drivers?

It's the same driver.  However, kernel and other open source
components do not always align to product cycles so support may not be
upstream in the various open source projects yet.  The vega10 code
that is upstream doesn't not have full functionality for all vega10
skus or features because older kernels were released before all the
products were finalized.  The amd-staging-4.12 branch Harry pointed
out has the latest code which provides full functionality for the
asic.

>
>> OpenCL support is provided by the ROCm stack which you can get from the
>> gpuopen site.
>
> "We do not support ROCm with PCIe Gen 2 enabled CPUs such as the AMD
> Opteron, Phenom, Phenom II, Athlon, Athlon X2, Athlon II and Older Intel
> Xeon and Intel Core Architecture and Pentium CPUs."
>
> Ouch!
> Mine is a Phenom II 6 core 1090T.
> I can't go spending a ton on a new CPU, MB, RAM, and GPU (and I'd need a
> less hacked case too :)
> Granted I could get an i3, cheap the MB and RAM, but I've worked so hard
> for a great platform... 32GB RAM, 6 core Phenom II, HD 7780 GPU, RAID 5
> on 2TB HDs, Bluray drive, Mechanical keyboard, HP laser printer,
> 4800x4800dpi HP scanner...
> AMD is normally so good at compatibility too.
> Ok, I'm over it, what is doable at this point?

PCIe gen 3 is required for pcie atomics.  I'm not a ROCm expert so I'm
not sure if that is a hard requirement or only if you need platform
atomics.

Alex

>
>> Headless boards are supported just fine and have been
>> for years.  If you prefer packaged drivers, you can download the ROCm
>> stack from gpuopen or the pro stack from amd.com.  All stacks build on
>> the same open source kernel driver and other components.
>>
>> Alex
>>
>
> Good to know!
>
>
>
> [1] No offence, but AMD's gpu-pro would not allow the system to suspend
> (sleep), also I'd often get a black and white set of vertical lines
> through my display and the kernel would totally freeze (no sysreq). The
> worst part is that it would happen totally randomly (really).
>
> _______________________________________________
> dri-devel mailing list
> dri-devel@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/dri-devel
>
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: Planned Vega support in Linux

[Alex Deucher]

On Tue, Aug 8, 2017 at 11:46 PM, David Niklas <doark@mail.com> wrote:
> BTW: I'm on list, no need to CC.
>
> On Wed, 9 Aug 2017 10:38:23 +0900
> Michel Dänzer <michel@daenzer.net> 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@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel