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 32C453857C50; Wed, 24 Mar 2021 12:57:38 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 32C453857C50
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/65847] SSE2 code for adding two structs is much worse at
 -O3 than at -O2
Date: Wed, 24 Mar 2021 12:57:37 +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: 6.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rguenth at gcc dot gnu.org
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-65847-4-fwdZB7B2e9@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-65847-4@http.gcc.gnu.org/bugzilla/>
References: <bug-65847-4@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
X-BeenThere: gcc-bugs@gcc.gnu.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Gcc-bugs mailing list <gcc-bugs.gcc.gnu.org>
List-Unsubscribe: <https://gcc.gnu.org/mailman/options/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=unsubscribe>
List-Archive: <https://gcc.gnu.org/pipermail/gcc-bugs/>
List-Post: <mailto:gcc-bugs@gcc.gnu.org>
List-Help: <mailto:gcc-bugs-request@gcc.gnu.org?subject=help>
List-Subscribe: <https://gcc.gnu.org/mailman/listinfo/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=subscribe>
X-List-Received-Date: Wed, 24 Mar 2021 12:57:38 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D65847

--- Comment #3 from Richard Biener <rguenth at gcc dot gnu.org> ---
Similarly

struct X { int a; int b; int c; int d; };

struct X foo (struct X x, struct X y)
{
  struct X res;
  res.a =3D x.a + y.a;
  res.b =3D x.b + y.b;
  res.c =3D x.c + y.c;
  res.d =3D x.d + y.d;
  return res;
}

is vectorized as

foo:
.LFB0:
        .cfi_startproc
        movq    %rdi, -40(%rsp)
        movq    %rsi, -32(%rsp)
        movdqa  -40(%rsp), %xmm0
        movq    %rdx, -24(%rsp)
        movq    %rcx, -16(%rsp)
        paddd   -24(%rsp), %xmm0
        movaps  %xmm0, -40(%rsp)
        movq    -40(%rsp), %rax
        movq    -32(%rsp), %rdx
        ret

which is bad because the on-stack construction of %xmm0 causes a STLF fail.
Unvectorized code isn't necessarily worse, but the vectorized sequence
can be improved=20

foo:
.LFB0:
        .cfi_startproc
        movq    %rdi, %rax
        movq    %rdi, %r10
        movq    %rdx, %rdi
        movq    %rsi, %r9
        sarq    $32, %r10
        sarq    $32, %rdi
        addl    %edx, %eax
        movq    %rcx, %r8
        addl    %r10d, %edi
        sarq    $32, %r9
        movl    %eax, %eax
        leal    (%rsi,%rcx), %edx
        movl    %edi, %edi
        sarq    $32, %r8
        salq    $32, %rdi
        orq     %rdi, %rax
        leal    (%r9,%r8), %edi
        salq    $32, %rdi
        orq     %rdi, %rdx
        ret

in this case the spill is caused by LRA not knowing how to re-load
the TImode reg build by pieces by the RTL expansion code.=