From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 23864 invoked by alias); 18 Dec 2012 15:41:00 -0000 Received: (qmail 22042 invoked by uid 55); 18 Dec 2012 15:40:35 -0000 From: "hubicka at ucw dot cz" To: gcc-bugs@gcc.gnu.org Subject: [Bug gcov-profile/55674] [4.8 Regression] >20% size increase of lto/pgo binaries since r193747 Date: Tue, 18 Dec 2012 15:41:00 -0000 X-Bugzilla-Reason: CC X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: gcc X-Bugzilla-Component: gcov-profile X-Bugzilla-Keywords: X-Bugzilla-Severity: normal X-Bugzilla-Who: hubicka at ucw dot cz X-Bugzilla-Status: RESOLVED X-Bugzilla-Priority: P3 X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org X-Bugzilla-Target-Milestone: 4.8.0 X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/ Auto-Submitted: auto-generated Content-Type: text/plain; charset="UTF-8" MIME-Version: 1.0 Mailing-List: contact gcc-bugs-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Id: List-Archive: List-Post: List-Help: Sender: gcc-bugs-owner@gcc.gnu.org X-SW-Source: 2012-12/txt/msg01773.txt.bz2 http://gcc.gnu.org/bugzilla/show_bug.cgi?id=55674 --- Comment #15 from Jan Hubicka 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