From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-bugzilla@gcc.gnu.org>
Received: by sourceware.org (Postfix, from userid 48)
	id 0E527395B424; Mon, 12 Dec 2022 09:49:02 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 0E527395B424
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1670838542;
	bh=NS3Ex5XypqRi2nTkG+MkAmb4e4GtCZSoMY27ItRh5XY=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=MdQpjRuXpKmLqIPOhP62P913D/uRTn2y0DhpeO3QE37jQyaFYcYG1ZyYeb95VX9D/
	 1r7vMzULllYnegpq9Ed/awyP0wt4ZGblqWIg39fKUhitdlHeGHaHEUuSO4CB9ELuut
	 M9noepw/HDed47GtyrGTF0fnBvaVoeiXN7uFh8Bk=
From: "rvmallad at amazon dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/107409] Perf loss ~5% on 519.lbm_r SPEC
 cpu2017 benchmark with r10-5090-ga9a4edf0e71bba
Date: Mon, 12 Dec 2022 09:48:59 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: tree-optimization
X-Bugzilla-Version: 13.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rvmallad at amazon dot com
X-Bugzilla-Status: NEW
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-107409-4-jVQ0Ic7JpF@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-107409-4@http.gcc.gnu.org/bugzilla/>
References: <bug-107409-4@http.gcc.gnu.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
List-Id: <gcc-bugs.sourceware.org>

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D107409

--- Comment #14 from Rama Malladi <rvmallad at amazon dot com> ---
(In reply to Martin Li=C5=A1ka from comment #13)
> Note the mentioned revision is a fix and yes, sometimes these revisions c=
an
> end up with a regression as profile estimation is a complex guess.

Yes, possibly. So, from my understanding, the update_max_bb_count() tracks =
the
max basic block count and takes a decision to inline or not in this case/ r=
un.
That is likely why we see a larger instruction count w this function execut=
ed/
enabled.=