http://gcc.gnu.org/bugzilla/show_bug.cgi?id=55674
--- Comment #15 from Jan Hubicka <hubicka at ucw dot cz> 2012-12-18 15:40:34 UTC --- > It's hard to say in case of Firefox, because the only thing > that one can reliably measure is the JavaScript performance. > And this varies only very slightly with different compiler options. One way to get better differences is to disable the JIT :) Doesn't snappy allow us to measure things like startup time and other stuff where not much of JITed code is involved? > So you have no way to measure up to which point more inlining > is still beneficial. I will do some testing on SPEC on when the performance starts dropping. Setting limit to 890 seems bit dangerous. -Os can slow down the code considerably, so if 10% of time program will be running -Os code, we probably get measurable slowdowns overall. Thanks! Honza
