« Call for testing: cairo backend for win32 (Take 2) | Main | SVG Performance »
March 3, 2006
Cairo improvements
Got curious about how much cairo had improved since the version that's included in Firefox 1.5, so reran Hixie's simple SVG performance tests on 1.5, the trunk, and on Adobe's SVG viewer. All tests done on a 1.7GHz Pentium-M WinXP machine, time in seconds.
Keep in mind when reading this table that the tests aren't formal benchmarks, and have some builtin overhead - fifteen seconds in the first two, five seconds in the rest.
| Firefox 1.5.0.1 | Firefox trunk | Adobe SVG 3.03 | |
|---|---|---|---|
| test1 (complex paths) | 15.9 | 15.9 | 15.0 |
| test2 (complex paths with transparency) | 16.8 | 17.4 | 15.0 |
| test3 (text) | 5.4 | 5.3 | 5.0 |
| test4 (images) | 18.9 | 9.0 (1) | 9.6 (2) |
| test5 (linear gradients) | 43.0 | 10.9 | 5.1 |
| test6 (radial gradients) | 47.4 | 20.5 | 6.8 |
Notes:
- Full images shown, but are blue shifted. This number has a lot of room for improvement, because we're doing a lot of conversion work not necessary in the new all-cairo world.
- Full images shown, but with the wrong transform that stretches them.
Posted by tor at March 3, 2006 8:50 PM
Comments
btw: what's the current status of foreignObject?
I personally think you should more focus on mixed SVG, using xmlns, without object/embed. This would really simplify code & development of graphically stunning applications...
Posted by: pascal at March 3, 2006 10:56 PM
> pascal
foreignObject is already enabled on Windows nightly :-).
See Bug 326966 (https://bugzilla.mozilla.org/show_bug.cgi?id=3269669)
Posted by: Taken at March 3, 2006 11:29 PM
Well, compared to before cairo, performance has really deteriorated, see:
https://bugzilla.mozilla.org/show_bug.cgi?id=328367
https://bugzilla.mozilla.org/show_bug.cgi?id=328374
https://bugzilla.mozilla.org/show_bug.cgi?id=328380
https://bugzilla.mozilla.org/show_bug.cgi?id=328388
These are performance measurements for html content.
Posted by: Martijn at March 4, 2006 1:01 AM
Would be interesting to test Opera too...
Posted by: Robert O'Callahan ![[TypeKey Profile Page]](http://weblogs.mozillazine.org/tor/nav-commenters.gif)
at March 4, 2006 5:28 AM
I ran the tests on Opera:
1: 16.70 (1.5 branch: 16.97)
2: 16.70 (1.5 branch: 17.51)
3: 5.48 (1.5 branch: 5.41)
4: 16.75 (1.5 branch: 15.30)
5: 22.69 (1.5 branch: 39.83)
6: 32.78 (1.5 branch: 44.00)
so i would guess that trunk builds beat opera, good to know ;)
Posted by: Arpad Borsos at March 4, 2006 8:53 AM
The link from Taken should be https://bugzilla.mozilla.org/show_bug.cgi?id=326966
Posted by: Ian at March 6, 2006 10:42 AM
sadd
Posted by: qwe at December 22, 2006 2:02 AM