From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id 8125E3858D35; Mon, 7 Nov 2022 07:14:20 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 8125E3858D35 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1667805260; bh=fpq8q5g11ILBR+PSztrajQ3pCrgVgJj2eJoHvIBzzHk=; h=From:To:Subject:Date:In-Reply-To:References:From; b=flSx0nOJIZ+YEFqsRdnhqE9VjCkOPxg2GOY7PxLaaWz2/Hm9QFblFihXDn7MO2At8 Yl2jZBsNa93ZUZE+AdjM76ETNBAAp0lx8fd9FpI7ixiR2ZLJohFy4NwT4yZCE3Jz4N 7RQTIvkXGYpbNQtIBqoUS+38gCSQFehpoud6T9VM= From: "crazylht at gmail dot com" To: gcc-bugs@gcc.gnu.org Subject: [Bug target/107546] [10/11/12/13 Regression] simd, redundant pcmpeqb and pxor Date: Mon, 07 Nov 2022 07:14:20 +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: 12.2.0 X-Bugzilla-Keywords: missed-optimization X-Bugzilla-Severity: normal X-Bugzilla-Who: crazylht at gmail dot com X-Bugzilla-Status: NEW X-Bugzilla-Resolution: X-Bugzilla-Priority: P2 X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org X-Bugzilla-Target-Milestone: 10.5 X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: 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: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D107546 --- Comment #4 from Hongtao.liu --- > even. Notice the < vs <=3D there. > I suspect the <=3D expansion part of the x86_64 backend needs to be fixed= up > to produce better code. Hmm, we do have a extra pcmpeq to negate the result. --------------cut from ix86_expand_int_vec_cmp--------------- rtx cmp =3D ix86_expand_int_sse_cmp (operands[0], code, operands[2], operands[3], NULL, NULL, &negate); if (!cmp) return false; if (negate) cmp =3D ix86_expand_int_sse_cmp (operands[0], EQ, cmp, CONST0_RTX (GET_MODE (cmp)), NULL, NULL, &negate); ---------------cut end-------------------------------=