Am 21.03.2018 um 19:23 schrieb Marek Olšák:
On Wed, Mar 21, 2018 at 2:15 PM, Christian König
> wrote:
Am 21.03.2018 um 19:04 schrieb Marek Olšák:
On Wed, Mar 21, 2018 at 10:07 AM, Christian König
On Wed, Mar 21, 2018 at 2:15 PM, Christian König
wrote:
> Am 21.03.2018 um 19:04 schrieb Marek Olšák:
>
> On Wed, Mar 21, 2018 at 10:07 AM, Christian König <
> christian.koe...@amd.com> wrote:
>
>> Am 21.03.2018 um 14:57 schrieb Marek Olšák:
>>
>> On Wed, Mar 21, 2018
Am 21.03.2018 um 19:04 schrieb Marek Olšák:
On Wed, Mar 21, 2018 at 10:07 AM, Christian König
> wrote:
Am 21.03.2018 um 14:57 schrieb Marek Olšák:
On Wed, Mar 21, 2018 at 4:13 AM, Christian König
On Wed, Mar 21, 2018 at 10:07 AM, Christian König
wrote:
> Am 21.03.2018 um 14:57 schrieb Marek Olšák:
>
> On Wed, Mar 21, 2018 at 4:13 AM, Christian König <
> ckoenig.leichtzumer...@gmail.com> wrote:
>
>> Am 21.03.2018 um 06:08 schrieb Marek Olšák:
>>
>> On Tue, Mar
eucher, Alexander <alexander.deuc...@amd.com>; Alex Deucher
<alexdeuc...@gmail.com>; Michel Dänzer <mic...@daenzer.net>; amd-gfx list
<amd-gfx@lists.freedesktop.org>; Li, Samuel <samuel...@amd.com>
Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display sup
Am 21.03.2018 um 14:57 schrieb Marek Olšák:
On Wed, Mar 21, 2018 at 4:13 AM, Christian König
> wrote:
Am 21.03.2018 um 06:08 schrieb Marek Olšák:
On Tue, Mar 20, 2018 at 4:16 PM, Christian König
On Wed, Mar 21, 2018 at 4:13 AM, Christian König <
ckoenig.leichtzumer...@gmail.com> wrote:
> Am 21.03.2018 um 06:08 schrieb Marek Olšák:
>
> On Tue, Mar 20, 2018 at 4:16 PM, Christian König > wrote:
>
>> That's what I meant with use up the otherwise unused VRAM. I
Am 21.03.2018 um 06:08 schrieb Marek Olšák:
On Tue, Mar 20, 2018 at 4:16 PM, Christian König
> wrote:
That's what I meant with use up the otherwise unused VRAM. I don't
see any disadvantage of always setting GTT as second
samuel...@amd.com>; amd-gfx list
<amd-gfx@lists.freedesktop.org>
*Subject:* Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display
support
That's what I meant with use up the otherwise unused VRAM. I don't see
any disadvantage of always setting GTT as second domain on APUs.
mic...@daenzer.net>;
amd-gfx list <amd-gfx@lists.freedesktop.org>; Marek Olšák <mar...@gmail.com>;
Koenig, Christian <christian.koe...@amd.com>
Subject: RE: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
O I think we can also have the case of systems with simi
com>; Marek Olšák
<mar...@gmail.com>
Cc: Alex Deucher <alexdeuc...@gmail.com>; Michel Dänzer <mic...@daenzer.net>;
Li, Samuel <samuel...@amd.com>; amd-gfx list <amd-gfx@lists.freedesktop.org>
Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display supp
<ckoenig.leichtzumer...@gmail.com>
*Sent:* Tuesday, March 20, 2018 2:32:49 PM
*To:* Marek Olšák; Koenig, Christian
*Cc:* Alex Deucher; Deucher, Alexander; Michel Dänzer; Li, Samuel;
amd-gfx list
*Subject:* Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display
support
I don't think that is
From: Christian König <ckoenig.leichtzumer...@gmail.com>
Sent: Tuesday, March 20, 2018 2:32:49 PM
To: Marek Olšák; Koenig, Christian
Cc: Alex Deucher; Deucher, Alexander; Michel Dänzer; Li, Samuel; amd-gfx list
Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display supp
I don't think that is a good idea.
Ideally GTT should now have the same performance as VRAM on APUs and we
should use VRAM only for things where we absolutely have to and to
actually use up the otherwise unused VRAM.
Can you run some tests with all BOs forced to GTT and see if there is
any
On Tue, Mar 20, 2018 at 9:55 AM, Christian König <
ckoenig.leichtzumer...@gmail.com> wrote:
> Yes, exactly. And if I remember correctly Mesa used to always set GTT as
> fallback on APUs, correct?
>
"used to" is the key part. Mesa doesn't force GTT on APUs anymore. It
expects that the combination
Yes, exactly. And if I remember correctly Mesa used to always set GTT as
fallback on APUs, correct?
The problem seems to be that this fallback isn't set for displayable BOs.
So what needs to be done is to just enable this fallback for displayable
BOs as well if the kernel can handle it.
In theory, Mesa doesn't have to do anything. It can continue setting VRAM
and if the kernel has to put a display buffer into GTT, it doesn't matter
(for Mesa). Whether the VRAM placement is really used is largely determined
by BO priorities.
The way I understand scather/gather is that it only
hristian.koe...@amd.com>; Alex Deucher <alexdeuc...@gmail.com>; Michel
> Dänzer <mic...@daenzer.net>; amd-gfx list <amd-gfx@lists.freedesktop.org>
>
>
> Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
>
>
>
> When Mesa wants a buf
On Mon, Mar 19, 2018 at 4:53 PM, Alex Deucher wrote:
> On Mon, Mar 19, 2018 at 4:26 PM, Marek Olšák wrote:
> > When Mesa wants a buffer in VRAM, it always sets VRAM. It relies on BO
> move
> > throttling to prevent unnecessary BO moves.
> >
> > My
e, it would make sense to put the buffer in vram because otherwise you
>> are wasting a comparatively scarce resource.
>>
>>
>>
>> Alex
>>
>>
>>
>> From: Li, Samuel
>> Sent: Monday, March 19, 2018 3:58:52 PM
>
Samuel
Sent: Monday, March 19, 2018 3:58:52 PM
To: Deucher, Alexander; Koenig, Christian; Marek Olšák
Cc: Alex Deucher; Michel Dänzer; amd-gfx list
Subject: RE: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
Alex,
I assume you are talking the three scenarios here, 1)VRAM, 2)G
..@gmail.com>; Michel Dänzer <
> mic...@daenzer.net>; amd-gfx list <amd-gfx@lists.freedesktop.org>
> *Subject:* Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display
> support
>
>
>
> I'm not sure what you mean by the 3 scenarios. Generally userspace
> selects
el <samuel...@amd.com>; Koenig, Christian
<christian.koe...@amd.com>; Marek Olšák <mar...@gmail.com>
Cc: Alex Deucher <alexdeuc...@gmail.com>; Michel Dänzer <mic...@daenzer.net>;
amd-gfx list <amd-gfx@lists.freedesktop.org>
Subject: Re: [PATCH 1/2] drm/amdgpu: Enable
<amd-gfx@lists.freedesktop.org>
Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
My personal preference is still to plumb this through to mesa rather than
forcing it in the kernel.
Alex
From: amd-gfx
<amd-gfx-
stian.koe...@amd.com>; Marek Olšák <mar...@gmail.com>
*Cc:* Alex Deucher <alexdeuc...@gmail.com>; Michel Dänzer
<mic...@daenzer.net>; amd-gfx list <amd-gfx@lists.freedesktop.org>
*Subject:* Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display
support
My personal prefe
.@lists.freedesktop.org>>
on behalf of Li, Samuel <samuel...@amd.com<mailto:samuel...@amd.com>>
Sent: Monday, March 19, 2018 3:50:34 PM
To: Koenig, Christian; Marek Olšák
Cc: Alex Deucher; Michel Dänzer; amd-gfx list
Subject: RE: [PATCH 1/2] drm/amdgpu: Enable scatter gather displ
M
To: Koenig, Christian; Marek Olšák
Cc: Alex Deucher; Michel Dänzer; amd-gfx list
Subject: RE: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
Christian,
You misunderstood Alex’s comments,
>Regardless of which scenarios we need to support, I think we also need
>to really
..@daenzer.net>;
amd-gfx list <amd-gfx@lists.freedesktop.org>
Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
Quoting Alex:
Regardless of which scenarios we need to support, I think we also need
to really plumb this through to mesa however since use
<samuel...@amd.com <mailto:samuel...@amd.com>>; Alex
Deucher <alexdeuc...@gmail.com <mailto:alexdeuc...@gmail.com>>
Cc: amd-gfx list <amd-gfx@lists.freedesktop.org
<mailto:amd-gfx@lists.freedesktop.org>>
Subject:
lto:alexdeuc...@gmail.com>>
Cc: amd-gfx list <amd-gfx@lists.freedesktop.org
<mailto:amd-gfx@lists.freedesktop.org>>
Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather
display support
Am 08.03.2018 um 09:35 sc
istian <christian.koe...@amd.com>
Cc: Li, Samuel <samuel...@amd.com>; Michel Dänzer <mic...@daenzer.net>; Alex
Deucher <alexdeuc...@gmail.com>; amd-gfx list <amd-gfx@lists.freedesktop.org>
Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
On Mon
-Original Message-
>>> From: Koenig, Christian
>>> Sent: Thursday, March 08, 2018 4:07 AM
>>> To: Michel Dänzer <mic...@daenzer.net>; Li, Samuel
>>> <samuel...@amd.com>; Alex Deucher <alexdeuc...@gmail.com>
>>> Cc: amd-gfx list <amd-gfx
om>; Alex Deucher <alexdeuc...@gmail.com>
Cc: amd-gfx list <amd-gfx@lists.freedesktop.org>
Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
Am 08.03.2018 um 09:35 schrieb Michel Dänzer:
On 2018-03-07 10:47 AM, Christian König wrote:
Am 07.03.2018 um 09:
et>; Li, Samuel
> <samuel...@amd.com>; Alex Deucher <alexdeuc...@gmail.com>
> Cc: amd-gfx list <amd-gfx@lists.freedesktop.org>
> Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
>
> Am 08.03.2018 um 09:35 schrieb Michel Dänzer:
> &g
Am 08.03.2018 um 09:35 schrieb Michel Dänzer:
On 2018-03-07 10:47 AM, Christian König wrote:
Am 07.03.2018 um 09:42 schrieb Michel Dänzer:
On 2018-03-06 07:23 PM, Christian König wrote:
E.g. the last time I tested it placing things into GTT still resulted
in quite a performance penalty for
On 2018-03-07 10:47 AM, Christian König wrote:
> Am 07.03.2018 um 09:42 schrieb Michel Dänzer:
>> On 2018-03-06 07:23 PM, Christian König wrote:
>>
>>> E.g. the last time I tested it placing things into GTT still resulted
>>> in quite a performance penalty for rendering.
>> FWIW, I think the
;> -Original Message-
>> From: Samuel Li [mailto:samuel...@amd.com]
>> Sent: Wednesday, March 07, 2018 1:54 PM
>> To: Alex Deucher <alexdeuc...@gmail.com>
>> Cc: Michel Dänzer <mic...@daenzer.net>; Koenig, Christian
>> <christian.koe...@amd.com>;
Christian
> <christian.koe...@amd.com>; amd-gfx list <amd-gfx@lists.freedesktop.org>
> Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
>
> > You might also want to prefer VRAM, but also allow buffers to fall
> > back to GTT if necessary.
>
> You might also want to prefer VRAM, but also allow buffers to fall back to
> GTT if
> necessary.
For display buffer, this case seems not really attractive. When display buffer
changes between GTT and VRAM dynamically, our driver needs to adpat too, which
is hard to see the benefits and not
On Wed, Mar 7, 2018 at 1:18 PM, Samuel Li wrote:
> I think it's not useful though. Think about that, SG display feature is
> intended to use as less VRAM as possible. Will someone want a display buffer
> sometimes VRAM, sometimes GTT?
> Hardly a case to me, and I think it's a
I think it's not useful though. Think about that, SG display feature is
intended to use as less VRAM as possible. Will someone want a display buffer
sometimes VRAM, sometimes GTT?
Hardly a case to me, and I think it's a waste of effort. That also might
explain no driver does that now.
Sam
On 2018-03-07 06:38 PM, Alex Deucher wrote:
> On Wed, Mar 7, 2018 at 12:29 PM, Samuel Li wrote:
>>
>> Why so complicated? If old user space compatibility is required, just use
>> sg_display=0.
>
> It will always just work in that case and we can adjust for the
> optimal
On Wed, Mar 7, 2018 at 12:29 PM, Samuel Li wrote:
>
> Why so complicated? If old user space compatibility is required, just use
> sg_display=0.
It will always just work in that case and we can adjust for the
optimal scenario by default in all cases without requiring the user
Why so complicated? If old user space compatibility is required, just use
sg_display=0.
Sam
On 2018-03-07 05:12 AM, Michel Dänzer wrote:
> On 2018-03-07 11:04 AM, Christian König wrote:
>> Am 07.03.2018 um 10:53 schrieb Michel Dänzer:
>>> On 2018-03-07 10:47 AM, Christian König wrote:
On 2018-03-07 11:04 AM, Christian König wrote:
> Am 07.03.2018 um 10:53 schrieb Michel Dänzer:
>> On 2018-03-07 10:47 AM, Christian König wrote:
>>> See when I tested this the DDX and Mesa where unmodified, so both still
>>> assumed VRAM as placement for scanout BOs, but the kernel forced scanout
Am 07.03.2018 um 10:53 schrieb Michel Dänzer:
On 2018-03-07 10:47 AM, Christian König wrote:
See when I tested this the DDX and Mesa where unmodified, so both still
assumed VRAM as placement for scanout BOs, but the kernel forced scanout
BOs into GTT for testing.
So what happened was that on
On 2018-03-07 10:47 AM, Christian König wrote:
>
> See when I tested this the DDX and Mesa where unmodified, so both still
> assumed VRAM as placement for scanout BOs, but the kernel forced scanout
> BOs into GTT for testing.
>
> So what happened was that on scanout we moved the VRAM BO to GTT
Am 07.03.2018 um 09:42 schrieb Michel Dänzer:
On 2018-03-06 07:23 PM, Christian König wrote:
Am 06.03.2018 um 19:15 schrieb Michel Dänzer:
On 2018-03-06 07:02 PM, Christian König wrote:
Am 06.03.2018 um 18:51 schrieb Michel Dänzer:
On 2018-03-06 06:44 PM, Christian König wrote:
Am
On 2018-03-06 07:23 PM, Christian König wrote:
> Am 06.03.2018 um 19:15 schrieb Michel Dänzer:
>> On 2018-03-06 07:02 PM, Christian König wrote:
>>> Am 06.03.2018 um 18:51 schrieb Michel Dänzer:
On 2018-03-06 06:44 PM, Christian König wrote:
> Am 06.03.2018 um 18:22 schrieb Li, Samuel:
Am 06.03.2018 um 19:15 schrieb Michel Dänzer:
On 2018-03-06 07:02 PM, Christian König wrote:
Am 06.03.2018 um 18:51 schrieb Michel Dänzer:
On 2018-03-06 06:44 PM, Christian König wrote:
Am 06.03.2018 um 18:22 schrieb Li, Samuel:
addition to that I agree with Michel that the module parameter
On 2018-03-06 07:02 PM, Christian König wrote:
> Am 06.03.2018 um 18:51 schrieb Michel Dänzer:
>> On 2018-03-06 06:44 PM, Christian König wrote:
>>> Am 06.03.2018 um 18:22 schrieb Li, Samuel:
> addition to that I agree with Michel that the module parameter is
> overkill.
That I
gt; Cc: amd-gfx list <amd-gfx@lists.freedesktop.org>
> Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
>
> Am 06.03.2018 um 18:51 schrieb Michel Dänzer:
> > On 2018-03-06 06:44 PM, Christian König wrote:
> >> Am 06.03.2018 um 18:22 schrieb
Am 06.03.2018 um 18:51 schrieb Michel Dänzer:
On 2018-03-06 06:44 PM, Christian König wrote:
Am 06.03.2018 um 18:22 schrieb Li, Samuel:
addition to that I agree with Michel that the module parameter is
overkill.
That I already explained. Currently SG display feature needs to
provide options
On 2018-03-06 06:44 PM, Christian König wrote:
> Am 06.03.2018 um 18:22 schrieb Li, Samuel:
>>
>>> addition to that I agree with Michel that the module parameter is
>>> overkill.
>> That I already explained. Currently SG display feature needs to
>> provide options for all kinds of use cases. All
: Koenig, Christian
Sent: Tuesday, March 06, 2018 12:12 PM
To: Li, Samuel <samuel...@amd.com>; Alex Deucher
<alexdeuc...@gmail.com>
Cc: amd-gfx list <amd-gfx@lists.freedesktop.org>
Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
And exactly that's the proble
gt; To: Li, Samuel <samuel...@amd.com>; Alex Deucher
> <alexdeuc...@gmail.com>
> Cc: amd-gfx list <amd-gfx@lists.freedesktop.org>
> Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
>
> And exactly that's the problematical assumption.
>
]
Sent: Tuesday, March 06, 2018 12:04 PM
To: Li, Samuel <samuel...@amd.com>
Cc: Koenig, Christian <christian.koe...@amd.com>; amd-gfx list
Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
On Tue, Mar 6, 2018 at 11:49 AM, Samuel Li <samuel...@amd.com> wro
m>
> Cc: Koenig, Christian <christian.koe...@amd.com>; amd-gfx list g...@lists.freedesktop.org>
> Subject: Re: [PATCH 1/2] drm/amdgpu: Enable scatter gather display support
>
> On Tue, Mar 6, 2018 at 11:49 AM, Samuel Li <samuel...@amd.com> wrote:
> >>&g
On Tue, Mar 6, 2018 at 11:49 AM, Samuel Li wrote:
>>> domain = amdgpu_display_framebuffer_domains(adev);
>>> +if (domain == AMDGPU_GEM_DOMAIN_GTT) {
>>> +DRM_INFO("Scatter gather display: enabled\n");
>>> +} else if (domain & AMDGPU_GEM_DOMAIN_GTT) {
>>> +
>> domain = amdgpu_display_framebuffer_domains(adev);
>> +if (domain == AMDGPU_GEM_DOMAIN_GTT) {
>> +DRM_INFO("Scatter gather display: enabled\n");
>> +} else if (domain & AMDGPU_GEM_DOMAIN_GTT) {
>> +DRM_INFO("Scatter gather display: auto\n");
>> +}
>
> Dito and
There are three major options when SG capability is enabled,
1) Allocate everything when possible from GTT memory
2) Allocate everything when possible from VRAM
3) Allow both VRAM/GTT to be available
Each has its own pros/cons, and it has not been decided which direction is
going to be used for
On 2018-03-03 12:25 AM, Samuel Li wrote:
> It's enabled by default. -1 is auto, to allow both vram and gtt
> memory be available, for testing purpose only.
Do we really need a module parameter for this? There's already too many
of them. The driver should know which to use in which cases, and
Am 03.03.2018 um 00:25 schrieb Samuel Li:
It's enabled by default. -1 is auto, to allow both vram and gtt
memory be available, for testing purpose only.
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 9 +++--
63 matches
Mail list logo