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 BB85E3858401; Sat,  6 Nov 2021 18:56:26 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org BB85E3858401
From: "tkoenig at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/103109] New: madd not used for multiply add on POWER9
Date: Sat, 06 Nov 2021 18:56:26 +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: 12.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: tkoenig 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-103109-4@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: Sat, 06 Nov 2021 18:56:26 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D103109

            Bug ID: 103109
           Summary: madd not used for multiply add on POWER9
           Product: gcc
           Version: 12.0
            Status: UNCONFIRMED
          Severity: enhancement
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: tkoenig at gcc dot gnu.org
  Target Milestone: ---

The following code

#include <stdint.h>

void Long_multiplication( uint64_t multiplicand[],
                          uint64_t multiplier[],
                          uint64_t sum[],
                          uint64_t ilength, uint64_t jlength )
{
  uint64_t acarry, mcarry, product;

  for( uint64_t i =3D 0;
       i < (ilength + jlength);
       i++ )
    sum[i] =3D 0;

  acarry =3D 0;
  for( uint64_t j =3D 0; j < jlength; j++ )
    {
      mcarry =3D 0;
      for( uint64_t i =3D 0; i < ilength; i++ )
        {
          __uint128_t mcarry_prod;
          __uint128_t acarry_sum;
          mcarry_prod =3D ((__uint128_t) multiplicand[i]) * ((__uint128_t)
multiplier[j])
            + (__uint128_t) mcarry;
          mcarry =3D mcarry_prod >> 64;
          product =3D mcarry_prod;
          acarry_sum =3D ((__uint128_t) sum[i+j]) + ((__uint128_t) acarry) +
product;
          sum[i+j] +=3D acarry_sum;
          acarry =3D acarry_sum >> 64;
          //      {mcarry, product} =3D multiplicand[i]*multiplier[j]
          //                            + mcarry;
          //      {acarry,sum[i+j]} =3D {sum[i+j]+acarry} + product;

        }
    }
}

is translated by

$ gcc -mcpu=3Dpower9 -mtune=3Dpower9 -S -O3 big_int.c

to (assembler output of the loop)

.L4:
        mtctr 25
        mr 12,23
        add 3,24,4
        li 5,0
        .p2align 4,,15
.L5:
        ldu 10,8(12)
        ldx 11,29,4
        ldu 9,8(3)
        mulld 8,10,11
        mulhdu 10,10,11
        addc 30,8,5
        addze 31,10
        and 21,30,6
        and 22,31,7
        addc 10,21,9
        mr 5,31
        adde 8,22,28
        addc 10,10,0
        add 9,9,10
        addze 0,8
        std 9,0(3)
        bdnz .L5
        addi 27,27,1
        addi 4,4,8
        cmpld 0,26,27
        bne 0,.L4

For the idiom to calculate mcarry_prod, I would have expected
a pair of maddhdu and maddld instructions.

This is with

gcc-Version 12.0.0 20211028 (experimental) (GCC)=