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 E5E2C395340E; Thu,  7 Jan 2021 12:52:05 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org E5E2C395340E
From: "ktkachov at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/98581] New: unexpected reassociation for
 umin/umax ?
Date: Thu, 07 Jan 2021 12:52:05 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: new
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: tree-optimization
X-Bugzilla-Version: unknown
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: ktkachov 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
 keywords bug_severity priority component assigned_to reporter
 target_milestone
Message-ID: <bug-98581-4@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: Thu, 07 Jan 2021 12:52:06 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D98581

            Bug ID: 98581
           Summary: unexpected reassociation for umin/umax ?
           Product: gcc
           Version: unknown
            Status: UNCONFIRMED
          Keywords: missed-optimization
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: ktkachov at gcc dot gnu.org
  Target Milestone: ---

typedef signed int *__restrict__ pSINT;
typedef unsigned int *__restrict__ pUINT;

#define MIN(a, b) ((a) < (b) ? (a) : (b))
#define MAX(a, b) ((a) > (b) ? (a) : (b))

void saba_s (pSINT a, pSINT b, pSINT c)
{
  int i;
  for (i =3D 0; i < 4; i++)
    c[i] +=3D (MAX (a[i], b[i]) - MIN (a[i], b[i]));
}

void saba_u (pUINT a, pUINT b, pUINT c)
{
  int i;
  for (i =3D 0; i < 4; i++)
    c[i] +=3D (MAX (a[i], b[i]) - MIN (a[i], b[i]));
}

On aarch64 at -O3 generates:
saba_s:
        ldr     q0, [x0]
        ldr     q1, [x1]
        ldr     q2, [x2]
        sabd    v0.4s, v0.4s, v1.4s
        add     v0.4s, v0.4s, v2.4s
        str     q0, [x2]
        ret

saba_u:
        ldr     q1, [x0]
        ldr     q2, [x1]
        ldr     q3, [x2]
        umax    v0.4s, v1.4s, v2.4s
        umin    v1.4s, v1.4s, v2.4s
        add     v0.4s, v0.4s, v3.4s
        sub     v0.4s, v0.4s, v1.4s
        str     q0, [x2]
        ret

I would expect the (MAX (a[i], b[i]) - MIN (a[i], b[i])) part to match a ua=
bd
instruction for the unsigned case, but it looks like the add and sub operat=
ions
are swapped which prevents the RTL pattern matching the operation.
This comes out this way out of GIMPLE. At expand the signed version is:
  vect__4.6_40 =3D MEM <vector(4) int> [(int *)c_16(D)];
  vect__6.9_37 =3D MEM <vector(4) int> [(int *)b_17(D)];
  vect__8.12_34 =3D MEM <vector(4) int> [(int *)a_18(D)];
  vect__9.13_33 =3D MAX_EXPR <vect__8.12_34, vect__6.9_37>;
  vect__10.14_32 =3D MIN_EXPR <vect__8.12_34, vect__6.9_37>;
  vect__11.15_31 =3D vect__9.13_33 - vect__10.14_32;
  vect__12.16_30 =3D vect__11.15_31 + vect__4.6_40;
  MEM <vector(4) int> [(int *)c_16(D)] =3D vect__12.16_30;
  return;


the unsigned is:
  vect__4.25_38 =3D MEM <vector(4) unsigned int> [(unsigned int *)c_16(D)];
  vect__6.28_35 =3D MEM <vector(4) unsigned int> [(unsigned int *)b_17(D)];
  vect__8.31_32 =3D MEM <vector(4) unsigned int> [(unsigned int *)a_18(D)];
  vect__9.32_31 =3D MAX_EXPR <vect__8.31_32, vect__6.28_35>;
  vect__10.33_30 =3D MIN_EXPR <vect__8.31_32, vect__6.28_35>;
  vect__13.34_29 =3D vect__9.32_31 + vect__4.25_38;
  vect__12.35_28 =3D vect__13.34_29 - vect__10.33_30;
  MEM <vector(4) unsigned int> [(unsigned int *)c_16(D)] =3D vect__12.35_28;
  return;=