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 E92B03857C43; Wed, 14 Oct 2020 13:58:34 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org E92B03857C43
From: "acoplan at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/97421] New: [10/11 Regression] aarch64: Wrong
 code with -O2 -fmodulo-sched since r10-1318-ga7e8a46
Date: Wed, 14 Oct 2020 13:58:34 +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: 11.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: acoplan 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-97421-4@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, 14 Oct 2020 13:58:35 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D97421

            Bug ID: 97421
           Summary: [10/11 Regression] aarch64: Wrong code with -O2
                    -fmodulo-sched since r10-1318-ga7e8a46
           Product: gcc
           Version: 11.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: acoplan at gcc dot gnu.org
  Target Milestone: ---

AArch64 GCC miscompiles the following testcase:

int a, b, d, e;
int *volatile c =3D &a;

__attribute__((noinline))
void f(void)
{
  for (int g =3D 2; g >=3D 0; g--) {
    d =3D 0;
    for (b =3D 0; b <=3D 2; b++)
      ;
    e =3D *c;
  }
}

int main(void)
{
  f();
  if (b !=3D 3)
    __builtin_abort();
}

with -O2 -fmodulo-sched since
r10-1318-ga7e8a463cd1dbaccf6e7c4fa888768fcd257a30f. Removing -fmodulo-sched,
the testcase is compiled correctly (tested at -O0 through -O3).

Here is the generated code (current trunk) for f at -O2:

f:
        mov     w1, 3
        adrp    x0, .LANCHOR0
        adrp    x3, .LANCHOR1
        mov     w4, w1
        add     x0, x0, :lo12:.LANCHOR0 // x0 <- &d
        add     x3, x3, :lo12:.LANCHOR1 // x3 <- &c
.L2:
        ldr     x2, [x3]      // x2 <- c
        stp     wzr, w4, [x0] // d =3D 0, b =3D 3
        subs    w1, w1, #1
        ldr     w2, [x2]      // w2 <- *c
        str     w2, [x0, 8]   // e <- w2
        bne     .L2
        ret

and the code for f with -O2 -fmodulo-sched:

f:
        mov     w1, 2
        adrp    x0, .LANCHOR0
        mov     w4, w1
        add     x0, x0, :lo12:.LANCHOR0
        adrp    x3, .LANCHOR1
        add     x3, x3, :lo12:.LANCHOR1
        ldr     x2, [x3]    // x2 <- c
        str     w1, [x0, 4] // b =3D 2
.L2:
        str     wzr, [x0]   // d =3D 0
        ldr     w2, [x2]    // w2 <- *c
        subs    w1, w1, #1=20=20
        str     w2, [x0, 8] // e <- w2
        ldr     x2, [x3]    // x2 <- c
        str     w4, [x0, 4] // b =3D 2
        bne     .L2
        ldr     w2, [x2]    // w2 <- *c
        str     w2, [x0, 8] // e <- w2
        ret

In the latter case we end up with b =3D 2 and make the call to __builtin_ab=
ort().=