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 DF2573858D28; Fri, 22 Dec 2023 20:30:21 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org DF2573858D28
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1703277021;
	bh=AW6AzQEomNWA1kuVuTnEX1TbU9EclmmaDSrf28PQt+Q=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=X/hNXzolE93gAZIT7QP+3j8em4qO6vnU/9WOwOqm9xkwQQgDiWakcOQCKdqirhuu2
	 atn5oE4I+9M04PHXooMPKvoZn9Zn2yypVWruSPRQfTyDPO7wsq55kJ6oPCBx97J79t
	 YY40xl/qhx/cREEY7LwwGKA0f3y+DKyUoF8izvVw=
From: "phosit at autistici dot org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/86072] Poor codegen with atomics
Date: Fri, 22 Dec 2023 20:30:20 +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: 9.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: phosit at autistici dot org
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: cc
Message-ID: <bug-86072-4-00u3cIBUN7@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-86072-4@http.gcc.gnu.org/bugzilla/>
References: <bug-86072-4@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=3D86072

Phosit <phosit at autistici dot org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |phosit at autistici dot org

--- Comment #4 from Phosit <phosit at autistici dot org> ---
(In reply to Richard Biener from comment #2)
> Somebody has to decide if it's worth optimizing them and has to sit down =
and
> exactly specify what kind of optimizations are valid.
There is a paper about the optimization of atomics. It might not be detailed
enough.
https://www.open-std.org/jtc1/sc22/wg21/docs/papers/2015/n4455.html
Note that the memory-model changed a bit since the release of that paper.

> I guess it's worth optimizing them if these cases appear in real-world co=
de
> (and then we'd like to see examples).
std::shared_ptr use fetch_add and fetch_sub. When a std::shared_ptr is not =
used
for syncronization this optimization could take effect.
PR 48987 is specifically about combining multiple fetch_add and fetch_sub.=