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 544A7387093A; Fri, 30 Jun 2023 14:05:21 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 544A7387093A
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1688133921;
	bh=ar4JiqruyftD3obXmIWpLxrVCs1knH09r4W2FTpodLk=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=eQ5tOgHRt1lG7x/uIOFYlNwMrEoVoDB50WT2HGAarfcYU2OXGgedUQYDA6ELCLt5A
	 hvNKNIhanDaHr95Z+k00rZ9SSfKhr52UYudXNjkuxJTUJeH/OLwW0aw0ji28YRypAr
	 ouqrFbyZdLOwwHgfFWTT0jRxsqZRJ2+kXXo8K2yY=
From: "clyon at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/110381] [11/12/13 Regression] double counting
 for sum of structs of floating point types
Date: Fri, 30 Jun 2023 14:05:20 +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: 12.1.0
X-Bugzilla-Keywords: wrong-code
X-Bugzilla-Severity: normal
X-Bugzilla-Who: clyon at gcc dot gnu.org
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: 11.5
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-110381-4-r22js6vvwF@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-110381-4@http.gcc.gnu.org/bugzilla/>
References: <bug-110381-4@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=3D110381

--- Comment #15 from Christophe Lyon <clyon at gcc dot gnu.org> ---
(In reply to Richard Biener from comment #14)
> (In reply to Christophe Lyon from comment #12)
> > The new testcase (gcc.dg/vect/pr110381.c) fails:
> > FAIL: gcc.dg/vect/pr110381.c -flto -ffat-lto-objects execution test
> > FAIL: gcc.dg/vect/pr110381.c execution test
> >=20
> > on arm-linux-gnueabihf configured with --with-float=3Dhard
> > --with-fpu=3Dneon-fp-armv8 --with-mode=3Dthumb --with-arch=3Darmv8-a
>=20
> Can you check if it works now?  I've added a missing check_vect () call in
> case the harness passes in command-line options that your HW doesn't
> support.  Otherwise I'd appreciate command-line options to reproduce.

I still fails (check_vect() passes on my config, so there's no change).

Here is what sum_8_foos looks like:
sum_8_foos:
        @ args =3D 0, pretend =3D 0, frame =3D 0
        @ frame_needed =3D 0, uses_anonymous_args =3D 0
        @ link register save eliminated.
        vmov.i64        d0, #0  @ float
        add     r3, r0, #192
.L10:
        vldr.64 d16, [r0, #8]
        adds    r0, r0, #24
        vldr.64 d18, [r0, #-24]
        vldr.64 d17, [r0, #-8]
        cmp     r3, r0
        vadd.f64        d16, d16, d18
        vadd.f64        d16, d16, d17
        vadd.f64        d0, d0, d16
        bne     .L10
        bx      lr

so we load:
d16=3D5
d17=3D-__DBL_MAX__
d18=3D__DBL_MAX__
the first addition makes d16=3D__DBL_MAX__
and the second one makes d16=3D0


> I cannot get anything to vectorize with a cc1 cross using
>=20
> > ./cc1 -quiet t.c -O2 -ftree-vectorize -fno-vect-cost-model -fopt-info-v=
ec -I include tri
>=20
> but I have a cross configured with --with-float=3Dhard --with-cpu=3Dcorte=
x-a9
> --with-fpu=3Dneon-fp16

Not sure what happens. I tried my native compiler with the above flags, I g=
et
the same code.
I tried to build my native compiler with the same flags, same code too.

>=20
> I hope the FPU is compliant enough to compute __DBL_MAX__ + -__DBL_MAX__ +
> 5. to 5.=