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 0B7ED3858414; Mon, 26 Feb 2024 07:42:45 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 0B7ED3858414
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1708933366;
	bh=6nO2griDUtjYyS+8nm4TSGr1mhoNl9yDOCmlOS0uu/E=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=cAAC2fgmHzwHLUD6h8L8yKIkJrOmRNvrUdBQqrDhzydwZ5plg0jSSkleSz9zIE1ll
	 OjAg1LXHwgDaTnJad5FoA1SnpO5jDthzpRYVzdz6+doB7vT1XMHbnJFPRuLGrQYD8e
	 0nCJn8XLVtVy5gy8MIwaHTVevkLkQXIptj+nhq1Q=
From: "nathanael.schaeffer at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/114107] poor vectorization at -O3 when dealing with
 arrays of different multiplicity, good with -O2
Date: Mon, 26 Feb 2024 07:42:43 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: target
X-Bugzilla-Version: 13.2.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: nathanael.schaeffer at gmail dot com
X-Bugzilla-Status: UNCONFIRMED
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-114107-4-vYvF5SXrOD@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-114107-4@http.gcc.gnu.org/bugzilla/>
References: <bug-114107-4@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=3D114107

--- Comment #9 from N Schaeffer <nathanael.schaeffer at gmail dot com> ---
In addition, optimizing for size with -Os leads to a non-vectorized double-=
loop
(51 bytes) while the vectorized loop with vbroadcastsd (produced by clang -=
Os)
leads to 40 bytes.
It is thus also a missed optimization for -Os.=