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 7D1563858C41; Tue, 10 Oct 2023 09:32:58 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 7D1563858C41
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1696930378;
	bh=tXrsaDMy3iHjaSAb6YGkygeh5bUZVB5nx9LJDd9G/0c=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=FVvaF/IFRndIcCrItf7T4qjirVyv8n1OOWzHwtOxD3Y24cryLRMLC5yfG8/O9Sy83
	 LRdhtYkQN5qnkvSsSAXklun3wwJOI3FXyu7HmtCSshvF7+W1Z1fzAzbEy7Zzj/L059
	 qyxOWWb4yg/V83ogotXOaaO6Kod8L4fgjxNHh5Y0=
From: "rguenther at suse dot de" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/111751] RISC-V: RVV unexpected vectorization
Date: Tue, 10 Oct 2023 09:32:57 +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
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rguenther at suse dot de
X-Bugzilla-Status: ASSIGNED
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: rguenth at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-111751-4-ZZpAP3dorR@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-111751-4@http.gcc.gnu.org/bugzilla/>
References: <bug-111751-4@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=3D111751

--- Comment #10 from rguenther at suse dot de <rguenther at suse dot de> ---
On Tue, 10 Oct 2023, juzhe.zhong at rivai dot ai wrote:

> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D111751
>=20
> --- Comment #9 from JuzheZhong <juzhe.zhong at rivai dot ai> ---
> (In reply to Richard Biener from comment #8)
> >   ic =3D "\x00\x03\x06\t\f\x0f\x12\x15\x18\x1b\x1e!$\'*-";
> >   ib =3D "\x00\x03\x06\t\f\x0f\x12\x15\x18\x1b\x1e!$\'*-";
> >   vect__1.7_10 =3D MEM <vector(16) char> [(char *)&ib];
> >   vect__2.10_34 =3D MEM <vector(16) char> [(char *)&ic];
> >=20
> > so these.  The lookup result is a STRING_CST object.  I'm testing a pat=
ch.
>=20
> I have compare and debug between ARM SVE and RVV.
> It seems that ARM SVE produce result of visit_reference_op_load is
> CONST_VECTOR:
>=20
> (gdb) p debug(to)
> { 0, 3, 6, 9, 12, 15, 18, 21, 24, 27, 30, 33, 36, 39, 42, 45 }
> (gdb) p to->typed.type->type_common.mode
> $23 =3D E_V16QImode
>=20
> However, RVV produce result of visit_reference_op_load is STRING_CST:
>=20
> (gdb) p debug (result)
> "\x00\x03\x06\t\f\x0f\x12\x15\x18\x1b\x1e!$\'*-"
>=20
> This is the BLKmode.
>=20
> Could you tell me where I should fix in RISC-V backend?
> It seems that it is not middle-end issue.

The IL into the SVE case is likely different.  The difference is
wheher we have a direct hashtable hit for the load or whether we
need to go through vn_reference_lookup_3 which will perform the
type punning on its own.=