EXA distorts windows

[Carl Worth]

On Tue, 19 Jun 2007 15:36:36 +0100, "Paulo J. Matos" wrote:
> > 'Baselining EXA performance (r100)', 'Comparing EXA to NoAccel' etc.
> >
>
> I'll read those.

Also, here's another new one:

	http://www.cworth.org/exa/mozilla_trender/

In addition to cairo's synthetic benchmarks seeing EXA slowdowns, it
appears that Mozilla's Trender benchmark sees EXA slowdowns as well,
(both r100 and i965 this time).

I plan on chasing these further. I'll be doing some profiling and I'm also
cooking up a couple new requests to help log known slow paths getting
hit in the X server, (software fallbacks, pixmap migration, etc.).

I'll appreciate any feedback that people have.

-Carl
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: not available
URL: <http://lists.x.org/archives/xorg/attachments/20070620/1efe3438/attachment.pgp>