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 A3EFC3858C74; Wed, 27 Sep 2023 02:58:51 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org A3EFC3858C74
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1695783531;
	bh=Fh/ByXNbFs8Br+i4obuFUAVo454B1mb3hlcohC/dHU4=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=AEHHsOp+rjHM+lGYeSvxihNyv7uNdPWVteCXf/5zdOmrLYeksWmJb2jxDKseURoKB
	 138rwGE/nRzbRlTc7a+0t0pSfPr9nBlXRNFC3EDPv6nfqt6CMLuxu4k0Z49wJ4//ao
	 iSk5Kw7SC1vJD2Q0SJgNdsKTSC55DUV6HYyQBKMA=
From: "juzhe.zhong at rivai dot ai" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/109088] GCC does not always vectorize
 conditional reduction
Date: Wed, 27 Sep 2023 02:58:51 +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: enhancement
X-Bugzilla-Who: juzhe.zhong at rivai dot ai
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-109088-4-tHldMzFDoZ@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-109088-4@http.gcc.gnu.org/bugzilla/>
References: <bug-109088-4@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=3D109088

--- Comment #8 from JuzheZhong <juzhe.zhong at rivai dot ai> ---
It's because the order of the operations we are doing:

For code as follows:

result +=3D mask ? a[i] + x : 0;

GCC:
result_ssa_1 =3D PHI <result_ssa_2, 0>
...
STMT 1. tmp =3D a[i] + x;
STMT 2. tmp2 =3D tmp + result_ssa_1;
STMT 3. result_ssa_2 =3D mask ? tmp2 : result_ssa_1;

Here we can see both STMT 2 and STMT 3 are using 'result_ssa_1',
we end up with 2 uses of the PHI result. Then, we failed to vectorize.

Wheras LLVM:

result_ssa_1 =3D PHI <result_ssa_2, 0>
...
IR 1. tmp =3D a[i] + x;
IR 2. tmp2 =3D mask ? tmp : 0;
IR 3. result_ssa_2 =3D tmp2 + result_ssa_1.

LLVM only has 1 use.

Is it reasonable to swap the order in match.pd ?=