On 1/30/13 8:03 PM, Ehsan Akhgari wrote:
We then tried to get a sense of how much of a win the PGO optimizations are. Thanks to a series of measurements by dmandelin, we know that disabling PGO/LTCG will result in a regression of about 10-20% on benchmarks which examine DOM and layout performance such as Dromaeo and guimark2 (and 40% in one case), but no significant regressions in the startup time, and gmail interactions. Thanks to a series of telemetry measurements performed by Vladan on a Nightly build we did last week which had PGO/LTCG disabled, there are no telemetry probes which show a significant regression on builds without PGO/LTCG. Vladan is going to try to get this data out of a Tp5 run tomorrow as well, but we don't have any evidence to believe that the results of that experiments will be any different.
Given the headaches PGO has caused and will likely continue to cause, I believe KISS applies and it is up to PGO advocates to justify the continued use of PGO with data showing a clear benefit.
My reading of Ehsan's summary is that there is no significant *user* benefit (read: perf win) of PGO.
If there is no *user* benefit, then the only data that remains to justify PGO are the benchmark results.
Therefore, I believe we should disable PGO unless there is a convincing argument for the benchmark results that sufficiently offsets the pain PGO inflicts. Is there?
_______________________________________________ dev-platform mailing list dev-platform@lists.mozilla.org https://lists.mozilla.org/listinfo/dev-platform
