[cairo] Report for the pango patch and proper profiles

Daniel Amelang daniel.amelang at gmail.com
Tue Dec 5 14:21:56 PST 2006


On 12/5/06, Jorn Baayen <jorn at openedhand.com> wrote:
> Hi,
>
> On Mon, 2006-12-04 at 20:15 -0500, Behdad Esfahbod wrote:
>
> > > > In my testings, this didn't affect the timetext test much
> > >
> > > Well, according to these profiles:
> > >
> > > http://folks.o-hand.com/jorn/pango-benchmarks/210-softfloat/pango.txt
> > > http://folks.o-hand.com/jorn/pango-benchmarks/210-softfloat/pango-cairo.txt
> > >
> > > your improvement should make a large difference on the 770. I'll try
> > > to get you numbers, if Xan doesn't beat me to it.
> >
> > Yes, and I kicked some of that out on Friday.  My statement above was
> > about this last improvement today, and on x86 only.  Numbers for Pango
> > 1.15.0 vs. 1.15.1 would be interesting.
>
> I oprofiled them both today (using the timetext test):
>
> http://folks.o-hand.com/~jorn/pango-benchmarks/28-pango-1.15.0/
> http://folks.o-hand.com/~jorn/pango-benchmarks/28-pango-1.15.1/

In summary:

1.15.0: Drawn label 766 times
1.15.1: Drawn label 833 times

Way to go Behdad!

And we can take down that nasty __muldf3 and __floatsidf in pangocairo
(in the loop in draw_glyphs) with a little magic...The __adddf is a
little tough, though, unless the crenderer->*_offset are both 0, I
don't know how often that is true.

I can look at it once I finish the lround bugfix, integrate pdiff,
finish cairo_rectangle optimizations...oh man.

Dan


More information about the cairo mailing list