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 F27DF3851416; Fri, 18 Jun 2021 07:11:30 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org F27DF3851416
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/87555] There is no need for UNSPEC_FMADDSUB
Date: Fri, 18 Jun 2021 07:11:30 +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: 9.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rguenth at gcc dot gnu.org
X-Bugzilla-Status: NEW
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-87555-4-UJjGWKdmoJ@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-87555-4@http.gcc.gnu.org/bugzilla/>
References: <bug-87555-4@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: Fri, 18 Jun 2021 07:11:31 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D87555

--- Comment #12 from Richard Biener <rguenth at gcc dot gnu.org> ---
(In reply to Hongtao.liu from comment #10)
> > Note I'm not sure that doing fmaddsub as merge of fma and fms will be
> > optimal since that most definitely will preclude combine from recognizi=
ng
> > fmaddsub from (addsub (mul ..) x) which would be another goal to support
> > (PR81904)
>=20
> I guess you're talking about=20
>=20
> #include <x86intrin.h>
> __m128d f(__m128d x, __m128d y, __m128d z){
>   return _mm_addsub_pd(_mm_mul_pd(x,y),z);
> }
>=20
> which pass_combine tries
>=20=20
> Failed to match this instruction:
> (set (reg:V2DF 88)
>     (vec_merge:V2DF (minus:V2DF (mult:V2DF (reg:V2DF 90)
>                 (reg:V2DF 91))
>             (reg:V2DF 92))
>         (plus:V2DF (mult:V2DF (reg:V2DF 90)
>                 (reg:V2DF 91))
>             (reg:V2DF 92))
>         (const_int 1 [0x1])))
>=20
> but doesn't realize fisrt merge operand is fms and second is fma.

Yes.  This situation will happen when I push the SLP pattern detection
for addsub - we then no longer detect FMA on the GIMPLE level (we might
want to improve that as well, of course, exposing standard pattern names
for fmaddsub and fmsubadd).=