From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-bugs-return-484179-listarch-gcc-bugs=gcc.gnu.org@gcc.gnu.org>
Received: (qmail 51445 invoked by alias); 21 Apr 2015 13:56:05 -0000
Mailing-List: contact gcc-bugs-help@gcc.gnu.org; run by ezmlm
Precedence: bulk
List-Id: <gcc-bugs.gcc.gnu.org>
List-Archive: <http://gcc.gnu.org/ml/gcc-bugs/>
List-Post: <mailto:gcc-bugs@gcc.gnu.org>
List-Help: <mailto:gcc-bugs-help@gcc.gnu.org>
Sender: gcc-bugs-owner@gcc.gnu.org
Received: (qmail 51419 invoked by uid 48); 21 Apr 2015 13:56:01 -0000
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/65832] New: Inefficient vector construction
Date: Tue, 21 Apr 2015 13:56:00 -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: 6.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rguenth at gcc dot gnu.org
X-Bugzilla-Status: UNCONFIRMED
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 keywords bug_severity priority component assigned_to reporter cf_gcctarget
Message-ID: <bug-65832-4@http.gcc.gnu.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: 7bit
X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
X-SW-Source: 2015-04/txt/msg01731.txt.bz2

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65832

            Bug ID: 65832
           Summary: Inefficient vector construction
           Product: gcc
           Version: 6.0
            Status: UNCONFIRMED
          Keywords: missed-optimization
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: rguenth at gcc dot gnu.org
            Target: x86_64-*-*, i?86-*-*

typedef int v4si __attribute__((vector_size(16)));

v4si foo (int i, int j, int k, int l)
{
  return (v4si) { i, j, k, l };
}

produces

        movl    %edx, -12(%rsp)
        movd    -12(%rsp), %xmm1
        movl    %ecx, -12(%rsp)
        movd    -12(%rsp), %xmm2
        movl    %edi, -12(%rsp)
        movd    -12(%rsp), %xmm0
        movl    %esi, -12(%rsp)
        movd    -12(%rsp), %xmm3
        punpckldq       %xmm2, %xmm1
        punpckldq       %xmm3, %xmm0
        punpcklqdq      %xmm1, %xmm0
        ret

as we spill everything to the stack we could as well use a vector load, thus
something like

        movl    %edx, -12(%rsp)
        movl    %ecx, -16(%rsp)
        movl    %edi, -20(%rsp)
        movl    %esi, -24(%rsp)
        movdqu  -12(%rsp), %xmm0
        ret