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 EF1FB3858C3B; Sun, 29 Aug 2021 12:30:48 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org EF1FB3858C3B
From: "jens.seifert at de dot ibm.com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/102117] New: s390: Inefficient code for 64x64=128 signed
 multiply for <= z13
Date: Sun, 29 Aug 2021 12:30:48 +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: 8.3.1
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: jens.seifert at de dot ibm.com
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-102117-4@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: Sun, 29 Aug 2021 12:30:49 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D102117

            Bug ID: 102117
           Summary: s390: Inefficient code for 64x64=3D128 signed multiply
                    for <=3D z13
           Product: gcc
           Version: 8.3.1
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: jens.seifert at de dot ibm.com
  Target Milestone: ---

__int128 imul128(long long a, long long b)
{
   return (__int128)a * (__int128)b;
}

creates sequence with 3 multiplies:

_Z7imul128xx:
.LFB0:
        .cfi_startproc
        ldgr    %f2,%r12
        .cfi_register 12, 17
        ldgr    %f0,%r13
        .cfi_register 13, 16
        lgr     %r13,%r3
        mlgr    %r12,%r4
        srag    %r1,%r3,63
        msgr    %r1,%r4
        srag    %r4,%r4,63
        msgr    %r4,%r3
        agr     %r4,%r1
        agr     %r12,%r4
        stmg    %r12,%r13,0(%r2)
        lgdr    %r13,%f0
        .cfi_restore 13
        lgdr    %r12,%f2
        .cfi_restore 12
        br      %r14
        .cfi_endproc


The following sequence only requires 1 multiply:

__int128 imul128_opt(long long a, long long b)
{
   unsigned __int128 x =3D (unsigned __int128)(unsigned long long)a;
   unsigned __int128 y =3D (unsigned __int128)(unsigned long long)b;
   unsigned long long t1 =3D (a >> 63) & a;
   unsigned long long t2 =3D (b >> 63) & b;
   unsigned __int128 u128 =3D x * y;
   unsigned long long hi =3D (u128 >> 64) - (t1 + t2);
   unsigned long long lo =3D (unsigned long long)u128;
   unsigned __int128 res =3D hi;
   res <<=3D 64;
   res |=3D lo;
   return (__int128)res;
}

_Z11imul128_optxx:
.LFB1:
        .cfi_startproc
        ldgr    %f2,%r12
        .cfi_register 12, 17
        ldgr    %f0,%r13
        .cfi_register 13, 16
        lgr     %r13,%r3
        mlgr    %r12,%r4
        lgr     %r1,%r3
        srag    %r3,%r3,63
        ngr     %r3,%r1
        srag    %r1,%r4,63
        ngr     %r4,%r1
        agr     %r3,%r4
        sgrk    %r3,%r12,%r3
        stg     %r13,8(%r2)
        lgdr    %r12,%f2
        .cfi_restore 12
        lgdr    %r13,%f0
        .cfi_restore 13
        stg     %r3,0(%r2)
        br      %r14
        .cfi_endproc=