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 89C523858D20; Fri, 31 Mar 2023 07:19:19 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 89C523858D20
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1680247159;
	bh=1MdJfE7C/1oQhTdjDLgK6OuYXywnY5TpfeieJVXobLg=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=q0T052RA1I9Tn4YXcdZzrdJ0SRWDHUw7LDwRVvqmc0tTYiOJfHu/rUQt/DSdYiF3+
	 T5CNvsFXSSXhX3bVIRb64XFW0Ha9UJFk1EFjwK7xK2uNptAoF2H33mIcwojH79Yxgo
	 kesoQexHJadHw52avjE170sCw2Tx8TLW4RVsBFOs=
From: "crazylht at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/109029] __builtin_signbit for 64bit fp does
 not vectorize
Date: Fri, 31 Mar 2023 07:19:19 +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: 13.0
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-109029-4-GPJySFuUel@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-109029-4@http.gcc.gnu.org/bugzilla/>
References: <bug-109029-4@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=3D109029

--- Comment #9 from Hongtao.liu <crazylht at gmail dot com> ---
(In reply to Hongtao.liu from comment #8)
> >=20
> > One solution is handling it in ix86_builtin_vectorized_function just li=
ke
> > other math functions which has different input/output sizes.
>=20
> Or extend vectorizable_call to handle NARROW/WIDEN cases when output of i=
fn
> is same-sized vector integer of vectype_in, and do NARROW/WIDEN between
> ifn_output and vectype_out.
>=20
>  3472  /* For now, we only vectorize functions if a target specific built=
in
>  3473     is available.  TODO -- in some cases, it might be profitable to
>  3474     insert the calls for pieces of the vector, in order to be able
>  3475     to vectorize other operations in the loop.  */
>  3476  fndecl =3D NULL_TREE;
>  3477  internal_fn ifn =3D IFN_LAST;
>  3478  tree callee =3D gimple_call_fndecl (stmt);
>  3479
>  3480  /* First try using an internal function.  */
>  3481  tree_code convert_code =3D ERROR_MARK;

Another alternative it's we can recognize signbit as shift in the vectorize=
r.=