On Sat, 2004-02-21 at 09:54, Chris Ison wrote:
> ok, let me get this in perspective
>
> R9200R8500
> DRI14.62103716.860273
> fglrx39.46159444.228085
>
> I have been trying to hunt down the slowdown in DRI, I even if (0)'s all
> occurances of sched_yield () whic
ok, let me get this in perspective
R9200R8500
DRI14.62103716.860273
fglrx39.46159444.228085
I have been trying to hunt down the slowdown in DRI, I even if (0)'s all
occurances of sched_yield () which is slower in 2.6 than 2.4 due to 2.6
doing it properly.
Acco
And, for comparison, the same benchmark, on the same system, with the
FireGL drivers from ATI.
9200:
18.798862 / 39.684578 / 184.560455 fps rand[1951333785]
Score = 39.461594
8500:
20.887423 / 44.828197 / 195.236023 fps rand[1951333785]
Score = 44.228085
Adam
On Fri, 20 Feb 2
Since I have access to both a 9200SE and an 8500 (but not a 9000 or 9200,
unfortunately), I decided to run a quick benchmark with the cards using
ut2003. With the Inferno Flyby, I got the following results with the
9200:
5.294707 / 14.600776 / 133.766464 fps rand[1951333785]
Score = 14.6
> You know how to verify that...
I've actually forgotten how, I think its an enviroment setting, but none of
the settings I saw when I grep'd for getenv triggered my memory.
> I'm sure you've tried page flipping and ruled out things like usleeps in
> the client side drivers?
enableing page flipp
--- Dieter Nützel <[EMAIL PROTECTED]> wrote:
> Am Freitag, 20. Februar 2004 13:49 schrieb Steve Dawson:
> > Alex Deucher wrote:
> > >--- Chris Ison <[EMAIL PROTECTED]> wrote:
> > >>I brought an AGP Radeon 9200SE yesterday, thinking I would get a
> HUGE
> > >>performance increase over my older PCI
Am Freitag, 20. Februar 2004 13:49 schrieb Steve Dawson:
> Alex Deucher wrote:
> >--- Chris Ison <[EMAIL PROTECTED]> wrote:
> >>I brought an AGP Radeon 9200SE yesterday, thinking I would get a HUGE
> >>performance increase over my older PCI Radeon 9000. And for windows
> >>sure enough, the overkill
Alex Deucher wrote:
--- Chris Ison <[EMAIL PROTECTED]> wrote:
I brought an AGP Radeon 9200SE yesterday, thinking I would get a HUGE
performance increase over my older PCI Radeon 9000. And for windows
sure enough, the overkill demo in quakeforge jumped from 33fps to
122fps within Windows.
When I
> You know how to verify that...
I've actually forgotten how, I think its an enviroment setting, but none of
the settings I saw when I grep's getenv triggered my memory.
> I'm sure you've tried page flipping and ruled out things like usleeps in
> the client side drivers?
usleeps in dri? there wo
On Fri, 2004-02-20 at 15:17, Chris Ison wrote:
> I brought an AGP Radeon 9200SE yesterday, thinking I would get a HUGE
> performance increase over my older PCI Radeon 9000. And for windows
> sure enough, the overkill demo in quakeforge jumped from 33fps to
> 122fps within Windows.
>
> When I trie
ADMIN: ignore my foobar'd post
--
Note also from a Quakeforge developer,
WildCode: maybe you should mention my r100 gets ~44 fps :) (hang on
and I'll get a fresh run)
make that 42, with -nosound (39 with sound)
actually, I'm using a rather old dri
So the gigabyte binary windows drivers for this Radeon 9200SE (AGP) card are
faulty, and it really should perform the same as the PCI Radeon 9000?
> I would expect them to perform about the same, with the
> AGP bus providing a slight performance boost. To be honest, I'm not
> sure why your window
--- Chris Ison <[EMAIL PROTECTED]> wrote:
> I brought an AGP Radeon 9200SE yesterday, thinking I would get a HUGE
> performance increase over my older PCI Radeon 9000. And for windows
> sure enough, the overkill demo in quakeforge jumped from 33fps to
> 122fps within Windows.
>
> When I tried it
I brought an AGP Radeon 9200SE yesterday, thinking
I would get a HUGE performance increase over my older PCI Radeon 9000. And for
windows sure enough, the overkill demo in quakeforge jumped from 33fps to 122fps
within Windows.
When I tried it in linux, the framerates for the
PCI R9000 were
14 matches
Mail list logo
