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 607F43858429; Mon, 30 Aug 2021 09:28:15 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 607F43858429
From: "changyp6 at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/102124] [11/12 Regression] -ftree-loop-vectorize Causing
 Data To Lose Sign Bit on AARCH64 Platform
Date: Mon, 30 Aug 2021 09:28:15 +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: 11.2.1
X-Bugzilla-Keywords: wrong-code
X-Bugzilla-Severity: normal
X-Bugzilla-Who: changyp6 at gmail dot com
X-Bugzilla-Status: NEW
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P2
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: 11.3
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-102124-4-vPg3dMagFv@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-102124-4@http.gcc.gnu.org/bugzilla/>
References: <bug-102124-4@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
X-BeenThere: gcc-bugs@gcc.gnu.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Gcc-bugs mailing list <gcc-bugs.gcc.gnu.org>
List-Unsubscribe: <https://gcc.gnu.org/mailman/options/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=unsubscribe>
List-Archive: <https://gcc.gnu.org/pipermail/gcc-bugs/>
List-Post: <mailto:gcc-bugs@gcc.gnu.org>
List-Help: <mailto:gcc-bugs-request@gcc.gnu.org?subject=help>
List-Subscribe: <https://gcc.gnu.org/mailman/listinfo/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=subscribe>
X-List-Received-Date: Mon, 30 Aug 2021 09:28:15 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D102124

--- Comment #4 from Tomas Chang <changyp6 at gmail dot com> ---
(In reply to Jakub Jelinek from comment #3)
> Before vectorization the loop body is:
>   _1 =3D a_19(D) + i_29;
>   _2 =3D *_1;
>   _3 =3D (int) _2;
>   _4 =3D b_20(D) + i_29;
>   _5 =3D *_4;
>   _6 =3D (int) _5;
>   _7 =3D _3 - _6;
>   ab_21 =3D _7 | ab_25;
>   _10 =3D _6 - _3;
>   ba_22 =3D _10 | ba_27;
> where _2 and _5 are unsigned char and _3, _6, _7, _10 are int.
> It is vectorized as
>   vect_patt_54.17_61 =3D WIDEN_MINUS_LO_EXPR <vect__2.13_56, vect__5.16_1=
7>;
>   vect_patt_54.17_62 =3D WIDEN_MINUS_HI_EXPR <vect__2.13_56, vect__5.16_1=
7>;
>   vect_patt_53.18_63 =3D [vec_unpack_lo_expr] vect_patt_54.17_61;
>   vect_patt_53.18_64 =3D [vec_unpack_hi_expr] vect_patt_54.17_61;
>   vect_patt_53.18_65 =3D [vec_unpack_lo_expr] vect_patt_54.17_62;
>   vect_patt_53.18_66 =3D [vec_unpack_hi_expr] vect_patt_54.17_62;
>   _7 =3D _3 - _6;
>   vect_ab_21.19_67 =3D vect_patt_53.18_63 | vect_ab_25.9_13;
>   vect_ab_21.19_68 =3D vect_patt_53.18_64 | vect_ab_21.19_67;
>   vect_ab_21.19_69 =3D vect_patt_53.18_65 | vect_ab_21.19_68;
>   vect_ab_21.19_70 =3D vect_patt_53.18_66 | vect_ab_21.19_69;
>   ab_21 =3D _7 | ab_25;
> which means it is vectorized as if it was instead of (int) _2 - (int) _6
> (int) (unsigned short) ((unsigned short) _2 - (unsigned short) _6).

Thank you very much for confirming this issue so quicky!
Hope this issue can be fixed soon!=