On Mon, May 20, 2013 at 3:28 PM, Josh Matthews <[email protected]>wrote:
> Are you sure that's testing the hard case? Setting style attributes > doesn't trigger any kind of layout modification right now. > I think Patrick is saying that in Gecko today, a "cheap layout operation" is on the order of 50 microseconds, so an overhead of 2 microseconds for switching to the layout task in Servo is not going to be a problem for that workload. Which sounds reasonable. He's not testing that page in Servo, just Gecko. BTW Patrick does the 47 microseconds hold up if you use a fixed number of iterations instead of calling Date.now() every iteration? How about if the layout work function in Brian's test does something that damages the cache? It would be interesting to measure that :-). Rob -- q“qIqfq qyqoquq qlqoqvqeq qtqhqoqsqeq qwqhqoq qlqoqvqeq qyqoquq,q qwqhqaqtq qcqrqeqdqiqtq qiqsq qtqhqaqtq qtqoq qyqoquq?q qEqvqeqnq qsqiqnqnqeqrqsq qlqoqvqeq qtqhqoqsqeq qwqhqoq qlqoqvqeq qtqhqeqmq.q qAqnqdq qiqfq qyqoquq qdqoq qgqoqoqdq qtqoq qtqhqoqsqeq qwqhqoq qaqrqeq qgqoqoqdq qtqoq qyqoquq,q qwqhqaqtq qcqrqeqdqiqtq qiqsq qtqhqaqtq qtqoq qyqoquq?q qEqvqeqnq qsqiqnqnqeqrqsq qdqoq qtqhqaqtq.q" _______________________________________________ dev-servo mailing list [email protected] https://lists.mozilla.org/listinfo/dev-servo
