EXA distorts windows

[Paulo J. Matos]

On 6/19/07, Michel Dänzer <michel at tungstengraphics.com> wrote:
> On Tue, 2007-06-19 at 10:11 +0100, Paulo J. Matos wrote:
> > On 6/18/07, Michel Dänzer <michel at tungstengraphics.com> wrote:
> > > On Mon, 2007-06-18 at 16:26 +0100, Paulo J. Matos wrote:
> > > >
> > > > gtkperf goes from 25s (100 cycles, XAA) to 41s (100cycles, EXA).
> > >
> > > Is that with or without a (non-GLX) compositing manger running? Is
> > > Option "AccelDFS" enabled?
> >
> > Without. Is AccelDFS useful?
>
> Generally yes, YMMV.
>

I'll add it and check if I note any diff in performance.

>
> > > > Is there anything I can provide to aid debugging/optimization?
> > >
> > > Did you see the recent threads about Cairo performance with EXA?
> > >
> >
> > No, which thread should I look at?
>
> 'Baselining EXA performance (r100)', 'Comparing EXA to NoAccel' etc.
>

I'll read those.

> > I think EXA is supposed to improve 2D performance.
>
> With a compositing manager, yes.
>

Do you mean I need to load the composite extension (and AIGLX?!?) ?

>
> --
> Earthling Michel Dänzer           |          http://tungstengraphics.com
> Libre software enthusiast         |          Debian, X and DRI developer
>
>
>
>


-- 
Paulo Jorge Matos - pocm at soton.ac.uk
http://www.personal.soton.ac.uk/pocm
PhD Student @ ECS
University of Southampton, UK