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 2C3A43858C60; Mon, 31 Jul 2023 05:26:04 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 2C3A43858C60
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1690781164;
	bh=IZ5MUsNrm7qb0kt3gZiMiZ1A/0kI9S9QWbmbvRpHAVg=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=xqBAJDzI2pMyfBQqD7Y39BkD9HqOAQ1j8mI9nKhR+92BRB/CSTeyGeqExJuEOssY0
	 xaLI77MmoPM6AGTwWYrYBmeKMejR+Ib0DBJNDsXxrQK6W9Z6AQGa/DeUIqVR6RI6OD
	 FaGT3X9l3PslhD7rM6VCM1sEA5jUKZCVMr4IgqMU=
From: "crazylht at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/81904] FMA and addsub instructions
Date: Mon, 31 Jul 2023 05:26:03 +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: 8.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: crazylht at gmail dot com
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-81904-4-V1eaG0OUN1@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-81904-4@http.gcc.gnu.org/bugzilla/>
References: <bug-81904-4@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=3D81904

--- Comment #4 from Hongtao.liu <crazylht at gmail dot com> ---
(In reply to Richard Biener from comment #2)
> __m128d h(__m128d x, __m128d y, __m128d z){
>     __m128d tem =3D _mm_mul_pd (x,y);
>     __m128d tem2 =3D tem + z;
>     __m128d tem3 =3D tem - z;
>     return __builtin_shuffle (tem2, tem3, (__m128i) {0, 3});
> }
>=20
> doesn't quite work (the combiner pattern for fmaddsub is missing).  Tried
> {0, 2} as well.
>=20
> :
> .LFB5021:
>         .cfi_startproc
>         vmovapd %xmm0, %xmm3
>         vfmsub132pd     %xmm1, %xmm2, %xmm0
>         vfmadd132pd     %xmm1, %xmm2, %xmm3
>         vshufpd $2, %xmm0, %xmm3, %xmm0

  tem2_6 =3D .FMA (x_2(D), y_3(D), z_5(D));
  # DEBUG tem2 =3D> tem2_6
  # DEBUG BEGIN_STMT
  tem3_7 =3D .FMS (x_2(D), y_3(D), z_5(D));
  # DEBUG tem3 =3D> NULL
  # DEBUG BEGIN_STMT
  _8 =3D VEC_PERM_EXPR <tem2_6, tem3_7, { 0, 3 }>;

Can it be handled in match.pd? rewrite fmaddsub pattern into vec_merge fma =
fms
<addsub_cst> looks too complex.

Similar for VEC_ADDSUB + MUL -> VEC_FMADDSUB.=