Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
Hasso Tepper ha...@linux.ee (26/06/2007): Yes, greedy fixes the EXA issue for me, thanks. smart introduces different slowdown, seems (I don't have numbers, but it feels so) - rendering process itself is fast, but reacting to various events (keypress, clicking with mouse etc) takes some time. I hope it's better in squeeze or even sid? KiBi. signature.asc Description: Digital signature
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
On Mon, 2007-06-25 at 11:17 +0300, Hasso Tepper wrote: About a year ago, you reported a bug to the Debian BTS regarding RGBA image rendering being very slow on a ATI board. Did you reproduce this problem recently? With Xorg/Etch? With latest xserver-xorg-core and drivers? If not, I will close this bug in the next weeks. Problem is still there and is even worse with xorg 7.2 - EXA is broken [...] Define 'broken', and which version of xserver-xorg-core are you referring to? -- Earthling Michel Dänzer | http://tungstengraphics.com Libre software enthusiast | Debian, X and DRI developer
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
Michel Dänzer wrote: On Mon, 2007-06-25 at 11:17 +0300, Hasso Tepper wrote: Problem is still there and is even worse with xorg 7.2 - EXA is broken [...] Define 'broken', and which version of xserver-xorg-core are you referring to? It's so slow, it's almost unusable and it _was_ OK with Xorg 7.1. Mails render several seconds here is KMail. Slow machine (600MHz) helps as well probably. It's probably freedesktop.org bug #10070. regards, -- Hasso Tepper
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
On Tue, 2007-06-26 at 12:02 +0300, Hasso Tepper wrote: Michel Dänzer wrote: On Mon, 2007-06-25 at 11:17 +0300, Hasso Tepper wrote: Problem is still there and is even worse with xorg 7.2 - EXA is broken [...] Define 'broken', and which version of xserver-xorg-core are you referring to? I'll assume 1.3. Does Option MigrationHeuristic greedy (or smart) make a difference? It's so slow, it's almost unusable and it _was_ OK with Xorg 7.1. Mails render several seconds here is KMail. Slow machine (600MHz) helps as well probably. It's probably freedesktop.org bug #10070. Possibly, though I'm not sure the operation reported as regressed there will be used if text rendering is done using the RENDER extension. -- Earthling Michel Dänzer | http://tungstengraphics.com Libre software enthusiast | Debian, X and DRI developer
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
Michel Dänzer wrote: I'll assume 1.3. Does Option MigrationHeuristic greedy (or smart) make a difference? Yes, greedy fixes the EXA issue for me, thanks. smart introduces different slowdown, seems (I don't have numbers, but it feels so) - rendering process itself is fast, but reacting to various events (keypress, clicking with mouse etc) takes some time. regards, -- Hasso Tepper
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
About a year ago, you reported a bug to the Debian BTS regarding RGBA image rendering being very slow on a ATI board. Did you reproduce this problem recently? With Xorg/Etch? With latest xserver-xorg-core and drivers? If not, I will close this bug in the next weeks. Problem is still there and is even worse with xorg 7.2 - EXA is broken there and there is no other alternative as running binary nvidia/ati modules. In platforms/OSes where there is no binary modules, there is no option at all. Note, that problem is not really bound to ati and Debian/Linux, but seems to present on every platform using Xorg drivers with XAA. I also opened bug in Freedesktop.org bugzilla: http://bugs.freedesktop.org/show_bug.cgi?id=11167 regards, -- Hasso Tepper -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Processed: Re: Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
Processing commands for [EMAIL PROTECTED]: reassign 376132 xserver-xorg-core Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images Bug reassigned from package `xserver-xorg-video-ati' to `xserver-xorg-core'. retitle 376132 Very slow rendering of RGBA images Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images Changed Bug title to `Very slow rendering of RGBA images' from `xserver-xorg-video-ati: Very slow rendering of RGBA images'. forwarded 376132 http://bugs.freedesktop.org/show_bug.cgi?id=11167 Bug#376132: Very slow rendering of RGBA images Noted your statement that Bug has been forwarded to http://bugs.freedesktop.org/show_bug.cgi?id=11167. thank you Stopping processing here. Please contact me if you need assistance. Debian bug tracking system administrator (administrator, Debian Bugs database) -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
reassign 376132 xserver-xorg-core retitle 376132 Very slow rendering of RGBA images forwarded 376132 http://bugs.freedesktop.org/show_bug.cgi?id=11167 thank you Hasso Tepper wrote: Problem is still there and is even worse with xorg 7.2 - EXA is broken there and there is no other alternative as running binary nvidia/ati modules. In platforms/OSes where there is no binary modules, there is no option at all. EXA should be slow under some condition, but better under some others (for instance with compositing managers such as compiz). I don't think it is actually broken. Note, that problem is not really bound to ati and Debian/Linux, but seems to present on every platform using Xorg drivers with XAA. Ok, reassigning to the server core, then. I also opened bug in Freedesktop.org bugzilla: http://bugs.freedesktop.org/show_bug.cgi?id=11167 Thanks, marking the bug as forwarded then. If you have any non-trivial option in your xorg.conf, you might want to post it there too. Brice -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
Hi, About a year ago, you reported a bug to the Debian BTS regarding RGBA image rendering being very slow on a ATI board. Did you reproduce this problem recently? With Xorg/Etch? With latest xserver-xorg-core and drivers? If not, I will close this bug in the next weeks. Thanks, Brice -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
Michel Dänzer wrote: With the mga driver, it may be because it hasn't adapted to changes in the XAA RENDER acceleration interface, so RENDER isn't currently accelerated with it. I'm 100% sure that there was no problem with 6.8 with mga. It appeared with 6.9. The radeon driver has adapted to this though, but you may still want to check in the log file that RENDER acceleration is enabled (and/or just send the full log to this report :). RENDER seems to be enabled. Full log attached. regards, -- Hasso X Window System Version 7.0.0 Release Date: 21 December 2005 X Protocol Version 11, Revision 0, Release 7.0 Build Operating System:Linux 2.6.12-1-686 i686 Current Operating System: Linux arena 2.6.17-ck1 #1 PREEMPT Thu Jun 22 10:36:51 EEST 2006 i686 Build Date: 16 March 2006 Before reporting problems, check http://wiki.x.org to make sure that you have the latest version. Module Loader present Markers: (--) probed, (**) from config file, (==) default setting, (++) from command line, (!!) notice, (II) informational, (WW) warning, (EE) error, (NI) not implemented, (??) unknown. (==) Log file: /var/log/Xorg.0.log, Time: Wed Aug 9 19:52:06 2006 (==) Using config file: /etc/X11/xorg.conf (==) ServerLayout Default Layout (**) |--Screen Default Screen (0) (**) | |--Monitor Generic Monitor (**) | |--Device ATI Technologies, Inc. RV350 [Mobility Radeon 9600 M10] (**) |--Input Device Generic Keyboard (**) Option XkbRules xfree86 (**) XKB: rules: xfree86 (**) Option XkbModel pc105 (**) XKB: model: pc105 (**) Option XkbLayout ee (**) XKB: layout: ee (==) Keyboard: CustomKeycode disabled (**) |--Input Device Configured Mouse (WW) The directory /usr/share/fonts/X11/cyrillic does not exist. Entry deleted from font path. (WW) The directory /usr/lib/X11/fonts/cyrillic does not exist. Entry deleted from font path. (WW) The directory /usr/share/fonts/X11/CID does not exist. Entry deleted from font path. (WW) The directory /usr/lib/X11/fonts/CID does not exist. Entry deleted from font path. (**) FontPath set to unix/:7100,/usr/share/fonts/X11/misc,/usr/lib/X11/fonts/misc,/usr/lib/X11/fonts/100dpi/:unscaled,/usr/lib/X11/fonts/75dpi/:unscaled,/usr/share/fonts/X11/Type1,/usr/lib/X11/fonts/Type1,/usr/lib/X11/fonts/Speedo,/usr/share/fonts/X11/100dpi,/usr/lib/X11/fonts/100dpi,/usr/share/fonts/X11/75dpi,/usr/lib/X11/fonts/75dpi,/usr/share/fonts/X11/misc/,/usr/share/fonts/X11/TTF/,/usr/share/fonts/X11/OTF,/usr/share/fonts/X11/Type1/,/usr/share/fonts/X11/CID/,/usr/share/fonts/X11/100dpi/,/usr/share/fonts/X11/75dpi/ (==) RgbPath set to /usr/share/X11/rgb (==) ModulePath set to /usr/lib/xorg/modules (**) Extension RENDER is enabled (II) Module ABI versions: X.Org ANSI C Emulation: 0.2 X.Org Video Driver: 0.8 X.Org XInput driver : 0.5 X.Org Server Extension : 0.2 X.Org Font Renderer : 0.4 (II) Loader running on linux (II) LoadModule: bitmap (II) Loading /usr/lib/xorg/modules/fonts/libbitmap.so (II) Module bitmap: vendor=X.Org Foundation compiled for 7.0.0, module version = 1.0.0 Module class: X.Org Font Renderer ABI class: X.Org Font Renderer, version 0.4 (II) Loading font Bitmap (II) LoadModule: pcidata (II) Loading /usr/lib/xorg/modules/libpcidata.so (II) Module pcidata: vendor=X.Org Foundation compiled for 7.0.0, module version = 1.0.0 ABI class: X.Org Video Driver, version 0.8 (++) using VT number 7 (II) PCI: PCI scan (all values are in hex) (II) PCI: 00:00:0: chip 8086,3340 card 1014,0529 rev 03 class 06,00,00 hdr 00 (II) PCI: 00:01:0: chip 8086,3341 card , rev 03 class 06,04,00 hdr 01 (II) PCI: 00:1d:0: chip 8086,24c2 card 1014,052d rev 01 class 0c,03,00 hdr 80 (II) PCI: 00:1d:1: chip 8086,24c4 card 1014,052d rev 01 class 0c,03,00 hdr 00 (II) PCI: 00:1d:2: chip 8086,24c7 card 1014,052d rev 01 class 0c,03,00 hdr 00 (II) PCI: 00:1d:7: chip 8086,24cd card 1014,052e rev 01 class 0c,03,20 hdr 00 (II) PCI: 00:1e:0: chip 8086,2448 card , rev 81 class 06,04,00 hdr 01 (II) PCI: 00:1f:0: chip 8086,24cc card , rev 01 class 06,01,00 hdr 80 (II) PCI: 00:1f:1: chip 8086,24ca card 1014,052d rev 01 class 01,01,8a hdr 00 (II) PCI: 00:1f:3: chip 8086,24c3 card 1014,052d rev 01 class 0c,05,00 hdr 00 (II) PCI: 00:1f:5: chip 8086,24c5 card 1014,0554 rev 01 class 04,01,00 hdr 00 (II) PCI: 00:1f:6: chip 8086,24c6 card 1014,055a rev 01 class 07,03,00 hdr 00 (II) PCI: 01:00:0: chip 1002,4e50 card 1014,0550 rev 00 class 03,00,00 hdr 00 (II) PCI: 02:00:0: chip 104c,ac46 card 4000, rev 01 class 06,07,00 hdr 82 (II) PCI: 02:00:1: chip 104c,ac46 card 4800, rev 01 class 06,07,00 hdr 82 (II) PCI: 02:01:0: chip 8086,101e card 1014,0549 rev 03 class 02,00,00 hdr 00 (II) PCI: 02:02:0: chip 8086,4220 card 8086,2712 rev 05 class 02,80,00 hdr 00 (II) PCI: End of PCI scan (II) Host-to-PCI bridge: (II) Bus 0: bridge is at (0:0:0), (0,0,7), BCTRL: 0x0008 (VGA_EN is set) (II) Bus 0 I/O range: [0] -1 0 0x - 0x (0x1) IX[B] (II) Bus 0 non-prefetchable memory range: [0] -1 0 0x -
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
On Wed, 2006-08-09 at 20:28 +0300, Hasso Tepper wrote: Michel Dänzer wrote: With the mga driver, it may be because it hasn't adapted to changes in the XAA RENDER acceleration interface, so RENDER isn't currently accelerated with it. I'm 100% sure that there was no problem with 6.8 with mga. It appeared with 6.9. That's probably when the XAA RENDER acceleration interface changed then. The radeon driver has adapted to this though, but you may still want to check in the log file that RENDER acceleration is enabled (and/or just send the full log to this report :). RENDER seems to be enabled. Full log attached. (II) RADEON(0): Render acceleration unsupported on Radeon 9500/9700 and newer. -- Earthling Michel Dänzer | http://tungstengraphics.com Libre software enthusiast | Debian, X and DRI developer
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
On Fri, 2006-06-30 at 20:25 +0300, Hasso Tepper wrote:
Michel Dänzer wrote:
Does this also occur without Option BackingStore or with Option
AccelMethod EXA?
Removing BackingStore doesn't have any effect to the issue.
Okay, it's generally a bad idea to enable it though.
But EXA makes rendering RGBA images significantly faster - although not as
fast I'd expect to, there is no noticeable impact to scrolling these images
in
Konqueror.
Okay, do the attached patches extracted from the upstream git history
make a difference? They're the only substantial changes to the XAA code
since X.Org 7.0...
EXA seems to have another performance problems though.
It definitely did in xserver 1.0. Should be better with 1.1, and we're
still making significant improvements upstream since then.
--
Earthling Michel Dänzer | http://tungstengraphics.com
Libre software enthusiast | Debian, X and DRI developer
From 9db5d2dfc33e384ea4db1b7cbc377e0b05cfb3ff Mon Sep 17 00:00:00 2001
From: Matthias Hopf [EMAIL PROTECTED]
Date: Thu, 11 May 2006 10:18:08 +
Subject: [PATCH] Bug #4320: Improved XAA Composite fastpath.
---
ChangeLog|5 +
hw/xfree86/xaa/xaaPict.c | 19 +--
2 files changed, 18 insertions(+), 6 deletions(-)
diff --git a/ChangeLog b/ChangeLog
index 9e131e7..9af4ff4 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+2006-05-11 Matthias Hopf [EMAIL PROTECTED]
+
+ * hw/xfree86/xaa/xaaPict.c: (XAAComposite):
+ Bug #4320: Improved XAA Composite fastpath.
+
2006-05-10 Adam Jackson [EMAIL PROTECTED]
* record/record.c:
diff --git a/hw/xfree86/xaa/xaaPict.c b/hw/xfree86/xaa/xaaPict.c
index 847ccb2..f7c1f3d 100644
--- a/hw/xfree86/xaa/xaaPict.c
+++ b/hw/xfree86/xaa/xaaPict.c
@@ -507,12 +507,19 @@ XAAComposite (CARD8 op,
XAAInfoRecPtr infoRec = GET_XAAINFORECPTR_FROM_SCREEN(pScreen);
XAA_RENDER_PROLOGUE(pScreen, Composite);
-if((op == PictOpSrc) !pMask infoRec-pScrn-vtSema
- infoRec-ScreenToScreenBitBlt
-pSrc-pDrawable
- DRAWABLE_IS_ON_CARD(pSrc-pDrawable)
- DRAWABLE_IS_ON_CARD(pDst-pDrawable)
- !pSrc-transform !pSrc-repeat (pSrc-format == pDst-format))
+if(!pMask infoRec-pScrn-vtSema
+ infoRec-ScreenToScreenBitBlt
+ pSrc-pDrawable
+ DRAWABLE_IS_ON_CARD(pSrc-pDrawable)
+ DRAWABLE_IS_ON_CARD(pDst-pDrawable)
+ !pSrc-transform
+ (!pSrc-repeat || (xSrc = 0 ySrc = 0
+ xSrc+width=pSrc-pDrawable-width
+ ySrc+height=pSrc-pDrawable-height))
+ ((op == PictOpSrc pSrc-format == pDst-format) ||
+ (op == PictOpOver !pSrc-alphaMap !pDst-alphaMap
+pSrc-format==pDst-format
+(pSrc-format==PICT_x8r8g8b8 || pSrc-format==PICT_x8b8g8r8
{
XAACompositeSrcCopy(pSrc, pDst, xSrc, ySrc, xDst, yDst, width, height);
} else if(!pSrc-pDrawable || (pMask !pMask-pDrawable) ||
--
1.4.0
From ea5e0eabd1303a55d8fc10f44d21a3d371ce8919 Mon Sep 17 00:00:00 2001
From: Matthias Hopf [EMAIL PROTECTED]
Date: Wed, 21 Jun 2006 17:08:51 +0200
Subject: [PATCH] Bug 4320: Fastpath corner case improvement for Composite.
---
hw/xfree86/xaa/xaaPict.c |5 -
1 files changed, 4 insertions(+), 1 deletions(-)
diff --git a/hw/xfree86/xaa/xaaPict.c b/hw/xfree86/xaa/xaaPict.c
index f7c1f3d..a1ff510 100644
--- a/hw/xfree86/xaa/xaaPict.c
+++ b/hw/xfree86/xaa/xaaPict.c
@@ -516,7 +516,10 @@ XAAComposite (CARD8 op,
(!pSrc-repeat || (xSrc = 0 ySrc = 0
xSrc+width=pSrc-pDrawable-width
ySrc+height=pSrc-pDrawable-height))
- ((op == PictOpSrc pSrc-format == pDst-format) ||
+ ((op == PictOpSrc
+((pSrc-format==pDst-format) ||
+ (pSrc-format==PICT_a8r8g8b8 pDst-format==PICT_x8r8g8b8) ||
+ (pSrc-format==PICT_a8b8g8r8 pDst-format==PICT_x8b8g8r8))) ||
(op == PictOpOver !pSrc-alphaMap !pDst-alphaMap
pSrc-format==pDst-format
(pSrc-format==PICT_x8r8g8b8 || pSrc-format==PICT_x8b8g8r8
--
1.4.0
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
Michel Dänzer wrote: Okay, do the attached patches extracted from the upstream git history make a difference? They're the only substantial changes to the XAA code since X.Org 7.0... No any difference. And I just discovered that my old machine with mga has same the problem, so it's not just ati problem. It certainly worked fine with 6.8. Also got report from nv user and again user is sure that 6.8 worked fine. -- Hasso Tepper
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
On Sat, 2006-07-01 at 23:50 +0300, Hasso Tepper wrote: Michel Dänzer wrote: Okay, do the attached patches extracted from the upstream git history make a difference? They're the only substantial changes to the XAA code since X.Org 7.0... No any difference. Thanks for testing anyway. And I just discovered that my old machine with mga has same the problem, so it's not just ati problem. It certainly worked fine with 6.8. Also got report from nv user and again user is sure that 6.8 worked fine. With the mga driver, it may be because it hasn't adapted to changes in the XAA RENDER acceleration interface, so RENDER isn't currently accelerated with it. The radeon driver has adapted to this though, but you may still want to check in the log file that RENDER acceleration is enabled (and/or just send the full log to this report :). There were few changes in the XAA code between 6.8 and 7.0, and none of them look relevant to this problem, but it's possible that changes in fb or another X server component could be relevant. -- Earthling Michel Dänzer | http://tungstengraphics.com Libre software enthusiast | Debian, X and DRI developer
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
Package: xserver-xorg-video-ati Version: 1:6.5.8.0-1 Severity: normal Rendering RGBA images is awfully slow with ATI cards. Several testing and unstable users have been confirmed the issue, most of them mentioning that for them it has been regression after upgrade from 6.8. Good demonstration is http://kde-apps.org/content/show.php?content=10187 with Konqueror browser. First two screenshots are RGBA, third one is RGB. Rendering of first two images is really slow, scrolling is sluggish etc, third one appears instantly and no any problem with scrolling. 01:00.0 VGA compatible controller: ATI Technologies Inc RV350 [Mobility Radeon 9600 M10] (prog-if 00 [VGA]) # cat /etc/X11/xorg.conf Section Files FontPathunix/:7100# local font server # if the local font server has problems, we can fall back on these FontPath/usr/share/fonts/X11/misc FontPath/usr/lib/X11/fonts/misc FontPath/usr/share/fonts/X11/cyrillic FontPath/usr/lib/X11/fonts/cyrillic FontPath/usr/lib/X11/fonts/100dpi/:unscaled FontPath/usr/lib/X11/fonts/75dpi/:unscaled FontPath/usr/share/fonts/X11/Type1 FontPath/usr/lib/X11/fonts/Type1 FontPath/usr/share/fonts/X11/CID FontPath/usr/lib/X11/fonts/CID FontPath/usr/lib/X11/fonts/Speedo FontPath/usr/share/fonts/X11/100dpi FontPath/usr/lib/X11/fonts/100dpi FontPath/usr/share/fonts/X11/75dpi FontPath/usr/lib/X11/fonts/75dpi EndSection Section Module Loadbitmap Loaddbe Loadddc Loaddri Loadextmod Loadfreetype Loadglx Loadint10 Loadrecord Loadtype1 Loadvbe EndSection Section InputDevice Identifier Generic Keyboard Driver keyboard Option CoreKeyboard Option XkbRules xfree86 Option XkbModel pc105 Option XkbLayout ee EndSection Section InputDevice Identifier Configured Mouse Driver mouse Option CorePointer Option Device/dev/psaux Option Protocol PS/2 Option Emulate3Buttons true Option ZAxisMapping 4 5 EndSection Section Device Identifier ATI Technologies, Inc. RV350 [Mobility Radeon 9600 M10] Driver radeon Option DMAForXv true Option BackingStore true EndSection Section Monitor Identifier Generic Monitor HorizSync 30-60 VertRefresh 50-75 Option DPMS EndSection Section Screen Identifier Default Screen Device ATI Technologies, Inc. RV350 [Mobility Radeon 9600 M10] Monitor Generic Monitor DefaultDepth24 SubSection Display Depth 24 Modes 1400x1050 1280x960 1152x864 1024x768 800x600 640x480 EndSubSection EndSection Section Extensions Option RENDEREnable EndSection Section ServerLayout Identifier Default Layout Screen Default Screen InputDevice Generic Keyboard InputDevice Configured Mouse EndSection Section DRI Mode0666 EndSection -- System Information: Debian Release: testing/unstable APT prefers unstable APT policy: (500, 'unstable') Architecture: i386 (i686) Shell: /bin/sh linked to /bin/bash Kernel: Linux 2.6.17-ck1 Locale: LANG=et_EE.iso8859-15, LC_CTYPE=et_EE.iso8859-15 (charmap=ISO-8859-15) Versions of packages xserver-xorg-video-ati depends on: ii libc6 2.3.6-15 GNU C Library: Shared libraries ii xserver-xorg-core 1:1.0.2-8 X.Org X server -- core server xserver-xorg-video-ati recommends no packages. -- no debconf information -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
On Fri, 2006-06-30 at 15:29 +0300, Hasso Tepper wrote: Rendering RGBA images is awfully slow with ATI cards. Several testing and unstable users have been confirmed the issue, most of them mentioning that for them it has been regression after upgrade from 6.8. Good demonstration is http://kde-apps.org/content/show.php?content=10187 with Konqueror browser. First two screenshots are RGBA, third one is RGB. Rendering of first two images is really slow, scrolling is sluggish etc, third one appears instantly and no any problem with scrolling. [...] Section Device Identifier ATI Technologies, Inc. RV350 [Mobility Radeon 9600 M10] Driver radeon Option DMAForXv true Option BackingStore true EndSection Does this also occur without Option BackingStore or with Option AccelMethod EXA? -- Earthling Michel Dänzer | http://tungstengraphics.com Libre software enthusiast | Debian, X and DRI developer
Bug#376132: xserver-xorg-video-ati: Very slow rendering of RGBA images
Michel Dänzer wrote: Does this also occur without Option BackingStore or with Option AccelMethod EXA? Removing BackingStore doesn't have any effect to the issue. But EXA makes rendering RGBA images significantly faster - although not as fast I'd expect to, there is no noticeable impact to scrolling these images in Konqueror. EXA seems to have another performance problems though. It seems to be somewhat slower in general and significantly slower with a lot of small images - Konqueror filemanager view renders several seconds in full screen, while it's almost instant with XAA. -- Hasso Tepper
