[Bug tree-optimization/103222] [12 Regression] wrong code at -O2 and above on x86_64-linux-gnu

[hubicka at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103222

Jan Hubicka <hubicka at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|UNCONFIRMED                 |NEW
     Ever confirmed|0                           |1
                 CC|                            |aldyh at gcc dot gnu.org,
                   |                            |hubicka at gcc dot gnu.org
   Last reconfirmed|                            |2021-11-13

--- Comment #1 from Jan Hubicka <hubicka at gcc dot gnu.org> ---
So with -O1 we get:
int main ()
{
  int16_t a_lsm.11;
  int _2;
  unsigned short a.5_4;
  unsigned short _11;
  short int _12;

  <bb 2> [local count: 1073741835]:
  a_lsm.11_16 = a;
  a.5_4 = (unsigned short) a_lsm.11_16;
  _11 = a.5_4 + 2;
  _12 = (short int) _11;
  a = _12;
  _2 = (int) _12;
  printf ("%d\n", _2);
  return 0;

}

while with -O2 we get:
int main ()
{
  int _2;
  short int a.3_8;
  unsigned short a.5_9;
  unsigned short _10;
  short int _11;

  <bb 2> [local count: 1073741824]:
  a.3_8 = a;
  a.5_9 = (unsigned short) a.3_8;
  _10 = a.5_9 + 1;
  _11 = (short int) _10;
  a = _11;
  _2 = (int) _11;
  printf ("%d\n", _2);
  return 0;

}

Adding always_inline to func_2 makes -O1 and -O2 to agree up to ccp2
110t.mergephi2 and then 111t.threadfull makes a difference:

+  FAIL: path through PHI in bb3 (incoming bb:2) crosses loop
+path: 2->3->xx REJECTED
+Checking profitability of path (backwards):  bb:3 (3 insns) bb:5 (latch)
+  Control statement insns: 2
+  Overall: 1 insns
+Checking profitability of path (backwards):  bb:3 (3 insns) bb:5 (latch)
+  Control statement insns: 2
+  Overall: 1 insns
+  [1] Registering jump thread: (5, 3) incoming edge;  (3, 4) nocopy; 
+path: 5->3->4 SUCCESS
+Jump threading proved probability of edge 3->4 too small (it is 11.0%
(guessed) should be always (guessed))

 int main ()
 {
-  uint32_t p3;
   uint32_t p2;
+  uint32_t p3;
   short int a.0_1;
   int _2;
   short int a.3_8;
@@ -13,28 +72,15 @@
   short int _11;

   <bb 2> [local count: 1073741824]:
-
-  <bb 3> [local count: 9761289362]:
-  # p3_7 = PHI <1(2), 0(5)>
-  # p2_17 = PHI <1(2), p3_7(5)>
-  if (p2_17 != 0)
-    goto <bb 5>; [89.00%]
-  else
-    goto <bb 4>; [11.00%]
-
-  <bb 4> [local count: 1073741824]:
-  a.0_1 = a;
-  _2 = (int) a.0_1;
-  printf ("%d\n", _2);
-  return 0;
-
-  <bb 5> [local count: 8687547547]:
   a.3_8 = a;
   a.5_9 = (unsigned short) a.3_8;
   _10 = a.5_9 + 1;
   _11 = (short int) _10;
   a = _11;
-  goto <bb 3>; [100.00%]
+  a.0_1 = a;
+  _2 = (int) a.0_1;
+  printf ("%d\n", _2);
+  return 0;

 }

and --disable-tree-threadfull1 fixes the difference.