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 E78F53857C71; Thu,  1 Apr 2021 09:14:11 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org E78F53857C71
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/99863] [10/11 Regression] wrong code with -O
 -fno-tree-forwprop -mno-sse2
Date: Thu, 01 Apr 2021 09:14:11 +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: 11.0
X-Bugzilla-Keywords: needs-bisection, wrong-code
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rguenth at gcc dot gnu.org
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: 10.3
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-99863-4-f86YY5bq5v@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-99863-4@http.gcc.gnu.org/bugzilla/>
References: <bug-99863-4@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: Thu, 01 Apr 2021 09:14:12 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D99863

--- Comment #2 from Richard Biener <rguenth at gcc dot gnu.org> ---
Also time to fix this stupid veclower behavior:

   _7 =3D (unsigned int) _14;
   _5 =3D {_7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7};
-  v512u32_0_16 =3D _5 * v512u32_0_15(D);
+  _53 =3D {_7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7};
+  _54 =3D BIT_FIELD_REF <_53, 32, 0>;
+  _55 =3D BIT_FIELD_REF <v512u32_0_15(D), 32, 0>;
+  _56 =3D _54 * _55;
+  _57 =3D {_7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7};
+  _58 =3D BIT_FIELD_REF <_57, 32, 32>;
+  _59 =3D BIT_FIELD_REF <v512u32_0_15(D), 32, 32>;
+  _60 =3D _58 * _59;
...

instead of

   _5 =3D {_7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7};
-  v512u32_0_16 =3D _5 * v512u32_0_15(D);
   _54 =3D BIT_FIELD_REF <_5, 32, 0>;
...

or even better

   _5 =3D {_7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7, _7};
-  v512u32_0_16 =3D _5 * v512u32_0_15(D);
+  _55 =3D BIT_FIELD_REF <v512u32_0_15(D), 32, 0>;
+  _56 =3D _7 * _55;

it's all "fixed" later by CSE of course.

The error might be involving the clever handling of

-  v256u8_r_17 =3D _8 + _19;
+  _117 =3D BIT_FIELD_REF <_8, 64, 0>;
+  _118 =3D BIT_FIELD_REF <_19, 64, 0>;
+  _119 =3D _117 ^ _118;
+  _120 =3D _118 & 9187201950435737471;
+  _121 =3D _117 & 9187201950435737471;
+  _122 =3D _119 & 9259542123273814144;
+  _123 =3D _120 + _121;
+  _124 =3D _122 ^ _123;
+  _125 =3D BIT_FIELD_REF <_8, 64, 64>;
+  _126 =3D BIT_FIELD_REF <_19, 64, 64>;
...
+  _149 =3D {_124, _132, _140, _148};
+  _150 =3D VIEW_CONVERT_EXPR<v256u8>(_149);
+  v256u8_r_17 =3D _150;

it's enough to -fdisable-tree-forwprop4 (forwprop after veclower) to make
the problem show up so it might be as well an RTL optimization issue.=