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 95E7F3858C60; Mon, 21 Feb 2022 08:45:35 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 95E7F3858C60
From: "pinskia at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/104600] VCE<integer_type>(vector){} should be
 converted (or expanded) into BIT_INSERT_EXPR
Date: Mon, 21 Feb 2022 08:45:35 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: tree-optimization
X-Bugzilla-Version: 12.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: pinskia 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: 
Message-ID: <bug-104600-4-lJ8GCjWmeB@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-104600-4@http.gcc.gnu.org/bugzilla/>
References: <bug-104600-4@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: Mon, 21 Feb 2022 08:45:35 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D104600

--- Comment #2 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
Here is another example even with 32bit int and 64bit long:
#define vector __attribute__((vector_size(8)))

long f(int a, int b)
{
  vector int t =3D {a, b};
  return (long)t;
}

void f1(long *t1, int a, int b)
{
  vector int t =3D {a, b};
  *t1 =3D  (long)t;
}

void f2(long *t1, int a, int b)
{
  vector int t =3D {a, b};
  *t1 =3D  ((long)t) + 1;
}

long f_1(unsigned a, unsigned b)
{
  long t =3D (((unsigned long)a) << 32) | (unsigned long)b;
  return (long)t;
}

void f1_1(long *t1, unsigned a, unsigned b)
{
  long t =3D (((unsigned long)a) << 32) | (unsigned long)b;
  *t1 =3D  (long)t;
}

void f2_1(long *t1, unsigned a, unsigned b)
{
  long t =3D (((unsigned long)a) << 32) | (unsigned long)b;
  *t1 =3D  ((long)t) + 1;
}

----- CUT ----
For f2 and f2_1 we have:

        movd    %esi, %xmm0
        movd    %edx, %xmm1
        punpckldq       %xmm1, %xmm0
        movq    %xmm0, %rsi
        addq    $1, %rsi
        movq    %rsi, (%rdi)

vs
        salq    $32, %rsi
        movl    %edx, %edx
        orq     %rdx, %rsi
        addq    $1, %rsi
        movq    %rsi, (%rdi)

It all depends on how fast move between GPRs and SSE register sets is vs do=
ing
it all in the integer.

I only think this should be done for the 2x size case and nothing more.=