From mboxrd@z Thu Jan 1 00:00:00 1970
From: bugzilla-daemon@freedesktop.org
Subject: [Bug 110781] Radeon: heavy r300 performance drop regression between
11.x and 19.x
Date: Fri, 07 Jun 2019 15:20:31 +0000
Message-ID:
References:
Mime-Version: 1.0
Content-Type: multipart/mixed; boundary="===============0783805278=="
Return-path:
Received: from culpepper.freedesktop.org (culpepper.freedesktop.org
[IPv6:2610:10:20:722:a800:ff:fe98:4b55])
by gabe.freedesktop.org (Postfix) with ESMTP id 25F2989D7D
for ; Fri, 7 Jun 2019 15:20:31 +0000 (UTC)
In-Reply-To:
List-Unsubscribe: ,
List-Archive:
List-Post:
List-Help:
List-Subscribe: ,
Errors-To: dri-devel-bounces@lists.freedesktop.org
Sender: "dri-devel"
To: dri-devel@lists.freedesktop.org
List-Id: dri-devel@lists.freedesktop.org
--===============0783805278==
Content-Type: multipart/alternative; boundary="15599208310.5EEedbeB8.22781"
Content-Transfer-Encoding: 7bit
--15599208310.5EEedbeB8.22781
Date: Fri, 7 Jun 2019 15:20:31 +0000
MIME-Version: 1.0
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Bugzilla-URL: http://bugs.freedesktop.org/
Auto-Submitted: auto-generated
https://bugs.freedesktop.org/show_bug.cgi?id=3D110781
--- Comment #54 from Richard Thier ---
> The GPU has a scaler that can scale a smaller image to the native timing.=
Many > LCD monitors also have a scaler built in to provide the same funct=
ionality.
I see, but still I see a big performance rise when I change the resolution
smaller and let this scaler do its work in the last phase.
I have no idea if there is a real speed difference between this two:
- having 640x480 on a 4:3 aspect screen without a scaler
- Having hardware pixels of 1024x768, but using the scaler in the end as
640x480 software.
- Z tests run for smaller amount of pixels
- Stencil and Z buffers are smaller just like the backbuffer
- etc.
Memory usage on the GPU should be still smaller, pixel shaders still run ra=
rer
times, post processing things still run on smaller amount of pixels etc... =
The
only reason it can be slower if for some reason the scaler circuit would be=
so
slow while doing its job that it cannot keep its FPS, but I think this is a
highly specialized hardware not doing anything else so I hoped it is just
"fast" and even if there is some loss I guess it is barely measurable - but
tell me if I am wrong as that would be new to me if this has a really
measurable overhead.
In any ways I think it is better to use a same aspect ratio, but smaller
resolution than using the biggest possible native size. Actually on my mach=
ine
I get faster frame rate even if I run a game in 640x480 window on the top l=
eft
corner the same way as if I turn the screen into 640x480 itself and even th=
en I
barely see a difference despite this case I feel there should be some overh=
ead
against using directly a video mode for that..
--=20
You are receiving this mail because:
You are the assignee for the bug.=
--15599208310.5EEedbeB8.22781
Date: Fri, 7 Jun 2019 15:20:31 +0000
MIME-Version: 1.0
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Bugzilla-URL: http://bugs.freedesktop.org/
Auto-Submitted: auto-generated
Comme=
nt # 54
on bug 11078=
1
from =
Richard Thier
> The GPU has a scaler that can scale=
a smaller image to the native timing. Many > LCD monitors also have a =
scaler built in to provide the same functionality.
I see, but still I see a big performance rise when I change the resolution
smaller and let this scaler do its work in the last phase.
I have no idea if there is a real speed difference between this two:
- having 640x480 on a 4:3 aspect screen without a scaler
- Having hardware pixels of 1024x768, but using the scaler in the end as
640x480 software.
- Z tests run for smaller amount of pixels
- Stencil and Z buffers are smaller just like the backbuffer
- etc.
Memory usage on the GPU should be still smaller, pixel shaders still run ra=
rer
times, post processing things still run on smaller amount of pixels etc... =
The
only reason it can be slower if for some reason the scaler circuit would be=
so
slow while doing its job that it cannot keep its FPS, but I think this is a
highly specialized hardware not doing anything else so I hoped it is just
"fast" and even if there is some loss I guess it is barely measur=
able - but
tell me if I am wrong as that would be new to me if this has a really
measurable overhead.
In any ways I think it is better to use a same aspect ratio, but smaller
resolution than using the biggest possible native size. Actually on my mach=
ine
I get faster frame rate even if I run a game in 640x480 window on the top l=
eft
corner the same way as if I turn the screen into 640x480 itself and even th=
en I
barely see a difference despite this case I feel there should be some overh=
ead
against using directly a video mode for that..
You are receiving this mail because:
- You are the assignee for the bug.
=
--15599208310.5EEedbeB8.22781--
--===============0783805278==
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: base64
Content-Disposition: inline
X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KZHJpLWRldmVs
IG1haWxpbmcgbGlzdApkcmktZGV2ZWxAbGlzdHMuZnJlZWRlc2t0b3Aub3JnCmh0dHBzOi8vbGlz
dHMuZnJlZWRlc2t0b3Aub3JnL21haWxtYW4vbGlzdGluZm8vZHJpLWRldmVs
--===============0783805278==--