On 9/25/13 3:09 PM, L. David Baron wrote:
So I think it's probably possible to do a good bit better than
current Gecko. And I also think it might be worth seeing how Gecko
does on your test before/after the 2004 margin collapsing changes.
I just did some more work to optimize our method dispatch and
representation of flows.
I realized that in most of my tests we were counting two Servo
from-scratch reflows instead of one, making the numbers seem twice as
bad as they were (as Servo has no incremental reflow yet). Here are my
numbers:
Warm Servo: 83ms assign-heights + 72ms bubble-widths + 63ms
assign-heights = 218ms
Warm WebKit (Safari 5): 2 calls to layout(), total 282ms
Warm Gecko (Nightly 27): 2 calls to Reflow(), total 287ms
WebKit seems to have a lot of variability. Sometimes I see +/- 50ms.
Servo and Gecko are pretty consistent.
In any case we *seem* to be beating WebKit and Gecko by about 30% in
each case. This is of course very early and could be totally wrong in
myriad ways, as is always the case with benchmarks.
Patrick
_______________________________________________
dev-servo mailing list
dev-servo@lists.mozilla.org
https://lists.mozilla.org/listinfo/dev-servo
