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 2BE773858409; Tue, 23 Jan 2024 12:56:21 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 2BE773858409
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1706014581;
	bh=/A+rCHWRsU7Hg5T5/9PSWp4rAxlRApGtwxOi0YJ6jVQ=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=Lv0ThmXrZ0vJoDor+CHrAe7LPshJr+4fAv46BR/HFY9rvDVqel9eZPOzqS5CvBpYI
	 4cI7ZFqrxqyCEX5k2Bw6Qtlrts8wR1c2HJtbYr0lKQcW5AH15fwsye2WP9DTWX5zou
	 zjup8Bebae5aMaNA+Hcg0uSBtq1BVCwJoZqhvoFY=
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/113441] [14 Regression] Fail to fold the last
 element with multiple loop
Date: Tue, 23 Jan 2024 12:56:20 +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: 14.0
X-Bugzilla-Keywords: missed-optimization, needs-bisection
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rguenth at gcc dot gnu.org
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: 14.0
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-113441-4-7WsVqTgrlj@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-113441-4@http.gcc.gnu.org/bugzilla/>
References: <bug-113441-4@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=3D113441

--- Comment #20 from Richard Biener <rguenth at gcc dot gnu.org> ---
(In reply to Richard Biener from comment #19)
> (In reply to Richard Biener from comment #18)
> > (In reply to Tamar Christina from comment #17)
> > > Ok, bisected to
> > >=20
> > > g:2efe3a7de0107618397264017fb045f237764cc7 is the first bad commit
> > > commit 2efe3a7de0107618397264017fb045f237764cc7
> > > Author: Hao Liu <hliu@os.amperecomputing.com>
> > > Date:   Wed Dec 6 14:52:19 2023 +0800
> > >=20
> > >     tree-optimization/112774: extend the SCEV CHREC tree with a nonwr=
apping
> > > flag
> > >=20
> > > Before this commit we were unable to analyse the stride of the access.
> > > After this niters seems to estimate the loop trip count at 4 and afte=
r that
> > > the logs diverge enormously.
> >=20
> > Hum, but that's backward and would match to what I said in comment#2 - =
we
> > should get better code with that.
> >=20
> > Juzhe - when you revert the above ontop of trunk does the generated code
> > look better for Risc-V?
>=20
> It doesn't revert but you can do
>=20
> diff --git a/gcc/tree-scalar-evolution.cc b/gcc/tree-scalar-evolution.cc
> index 25e3130e2f1..7870c8d76fb 100644
> --- a/gcc/tree-scalar-evolution.cc
> +++ b/gcc/tree-scalar-evolution.cc
> @@ -2054,7 +2054,7 @@ analyze_scalar_evolution (class loop *loop, tree va=
r)
>=20=20
>  void record_nonwrapping_chrec (tree chrec)
>  {
> -  CHREC_NOWRAP(chrec) =3D 1;
> +  CHREC_NOWRAP(chrec) =3D 0;
>=20=20
>    if (dump_file && (dump_flags & TDF_SCEV))
>      {

For me with this, on x86-64 we do not vectorize the loop at all.  With
-fno-vect-cost-model we vectorize some of the stores as part of BB
vectorization.=