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 D86C6385ED4C; Fri, 17 May 2024 08:48:22 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org D86C6385ED4C
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1715935702;
	bh=VwlR2kYv0f+Pua3R8Jn80gx/jB3+8Qv0jLsdwSEY6x8=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=D0VK98jCXvch3MdC1O70la1M4TYdDSIvS5XGqoL3oA3kLVN0aTfvYA8tQVRGc2qP6
	 1YDwE0o3H+KXDj2ZstH/mv8xYma8gQvYJrFmS2q7JsQYiZaEF1ZFv/U1PKn6rm3quy
	 kcTNUBj9m1RRg4QDtGpcC56I3BvO6L+rt4/IA4Vs=
From: "ubizjak at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/115069] [14/15 regression] 8 bit integer vector
 performance regression, x86, between gcc-14 and gcc-13 using avx2 target
 clones on skylake platform
Date: Fri, 17 May 2024 08:48:22 +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: 14.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: ubizjak 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: 14.2
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-115069-4-SRu3z3OqsO@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-115069-4@http.gcc.gnu.org/bugzilla/>
References: <bug-115069-4@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=3D115069

--- Comment #9 from Uro=C5=A1 Bizjak <ubizjak at gmail dot com> ---
(In reply to Uro=C5=A1 Bizjak from comment #8)
> A better patch:

The real issue is that the following permutation (truncation):

+      for (i =3D 0; i < d.nelt; ++i)
+       d.perm[i] =3D i * 2;
+
+      ok =3D ix86_expand_vec_perm_const_1 (&d);

results in a slow code involving VPERMQ. Ideally, ix86_expand_vec_perm_cons=
t_1
should emit faster code for truncation, because this will benefit other cod=
e as
well.=