Bug#583653: xserver-xorg-video-radeon: 15x-slower performance regression in KMS mode for 2D operations
- To: Sylvain Beucler <beuc@debian.org>
- Cc: Michel Dänzer <daenzer@debian.org>, 583653@bugs.debian.org
- Subject: Bug#583653: xserver-xorg-video-radeon: 15x-slower performance regression in KMS mode for 2D operations
- From: Jonathan Nieder <jrnieder@gmail.com>
- Date: Wed, 23 Nov 2011 07:05:58 -0600
- Message-id: <[🔎] 20111123130558.GA6497@elie.hsd1.il.comcast.net>
- Reply-to: Jonathan Nieder <jrnieder@gmail.com>, 583653@bugs.debian.org
- In-reply-to: <20100613092917.GA3533@perso.beuc.net>
- References: <20100529082132.3611.67275.reportbug@localhost.localdomain> <1275131136.29704.77.camel@thor.local> <20100529130253.GA2562@perso.beuc.net> <1275142906.29704.86.camel@thor.local> <20100529153352.GA2645@perso.beuc.net> <1275291813.29704.151.camel@thor.local> <1275292037.29704.153.camel@thor.local> <20100606203354.GA2641@perso.beuc.net> <20100613092917.GA3533@perso.beuc.net>
Sylvain Beucler wrote:
> On Sun, Jun 06, 2010 at 10:33:54PM +0200, Sylvain Beucler wrote:
>> The test runs at 65FPS with radeon.agpmode=-1 (~3-4x faster than
>> without this option, but ~4-5x slower than without KMS).
>
> On 2.6.34-1-686 (from experimental) the test runs at 150 FPS.
> It's better though still 2x slower.
Hm, how do 3.1.y kernels do?
If the speed regression persists, we should take this upstream
(<http://bugs.freedesktop.org>).
Reply to: