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 2D97E3858D38; Fri, 22 Mar 2024 05:39:27 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 2D97E3858D38
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1711085967;
	bh=1mtKePZmtZDGT/l38r+47cjequU9WTsCtfCIf9x6/5k=;
	h=From:To:Subject:Date:From;
	b=W5V5CTmGF0RXIUxvFx5L3s26GH6juuB0vtraGUnKOlMnAByap42BUEiTfYFiRw1Mi
	 uXMXu0VW0B4wpEjK0ry61c5u43RjLHv3zzI5tIdGBR5gIcoBhT/kq/QmIZ7PSU/78Q
	 uEcQI7LU+bTo/HZrh//MIpCTdKyqAQ6UjO4MVQ/4=
From: "liuhongt at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/114429] New: [x86] (neg a) ashifrt>> 31 can be optimized
 to a > 0.
Date: Fri, 22 Mar 2024 05:39:26 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: new
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: target
X-Bugzilla-Version: 14.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: liuhongt at gcc dot gnu.org
X-Bugzilla-Status: UNCONFIRMED
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: bug_id short_desc product version bug_status
 bug_severity priority component assigned_to reporter target_milestone
Message-ID: <bug-114429-4@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=3D114429

            Bug ID: 114429
           Summary: [x86] (neg a) ashifrt>> 31 can be optimized to a > 0.
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: liuhongt at gcc dot gnu.org
  Target Milestone: ---

typedef unsigned char uint8_t;
uint8_t x264_clip_uint8( int x )
{
    return x&(~255) ? (-x)>>31 : x;
}

void
foo (int* a, int* __restrict b, int n)
{
    for (int i =3D 0; i !=3D 8; i++)
      b[i] =3D x264_clip_uint8 (a[i]);
}

gcc -O2 -march=3Dx86-64-v3 -S


foo(int*, int*, int):
        ..
        mov     eax, 255
        vpxor   xmm0, xmm0, xmm0
        vmovd   xmm1, eax
        vpbroadcastd    ymm1, xmm1
        vmovdqu ymm2, YMMWORD PTR [rdi]
        vpminud ymm3, ymm2, ymm1
        vpsubd  ymm0, ymm0, ymm2
        vmovdqa YMMWORD PTR [rsp-32], ymm3
        vpsrad  ymm0, ymm0, 31
        vpcmpeqd        ymm3, ymm2, YMMWORD PTR [rsp-32]
        vpblendvb       ymm0, ymm0, ymm2, ymm3
        vpand   ymm1, ymm1, ymm0
        vmovdqu YMMWORD PTR [rsi], ymm1


It can be better with

        mov     eax, 255
        vmovd   xmm1, eax
        vpxor xmm0, xmm0, xmm0.=20
        vpbroadcastd    ymm1, xmm1
        vmovdqu ymm2, YMMWORD PTR [rdi]
        vpminud ymm3, ymm2, ymm1
        vmovdqa YMMWORD PTR [rsp-32], ymm3
        vcmpgtps  ymm0, ymm2, ymm0
        vpcmpeqd        ymm3, ymm2, YMMWORD PTR [rsp-32]
        vpblendvb       ymm0, ymm0, ymm2, ymm3
        vpand   ymm1, ymm1, ymm0
        vmovdqu YMMWORD PTR [rsi], ymm1=