[cairo] Optimizing cairo + pixman [ was: Fwd: cairo+pixman profiling

[Nguyen Vu Hung]

Hi all,

As mentioned in my previous email, the bottleneck of cairo + pixman
falls into fbRasterizeEdges ( pixman ) and  unpremultiply_data ( cairo
).

I want to optimizing them: make them faster.

What can I do? can gcc's -mmmx and -msse make anything faster?

Would it be faster if I write those two functions using inline assembler?

---------- Forwarded message ----------
From: Nguyen Vu Hung <vuhung16plus at gmail.com>
Date: 2007/11/06 12:03
Subject: cairo+pixman profiling
To: cairo at cairographics.org


Hi all,

I've tried profiling my application with gdprof. You can see the
result at the end of this email.

My questions are:

1. Where fbRasterizeEdges and other cairo_pixman_* are called inside
cairo? How do I optimize them?

2. Where unpremultiply_data is callled? What this function does?

BTW, because I am new to profiling and performance optimization,
suggests and comments are appreciated.

  20.12    267.68   267.68                             fbRasterizeEdges
[snip]
  7.18    776.12    95.46
_cairo_pixman_composite_solid_mask_nx8x8888mmx
  4.23    832.34    56.22                             unpremultiply_data
[snip]

-- 
Best Regards,
Nguyen Hung Vu
vuhung16plus{remove}@gmail.dot.com
An inquisitive look at Harajuku
http://www.flickr.com/photos/vuhung/sets/72157600109218238/