[Bug tree-optimization/65468] Optimize static schedule with chunk_size one

[vries at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65468

--- Comment #1 from vries at gcc dot gnu.org ---
Using the patch submitted for gomp-4_0-branch at
https://gcc.gnu.org/ml/gcc-patches/2014-07/msg01881.html, we get a simple loop:
...
bar._omp_fn.0 (struct .omp_data_s.0 & restrict .omp_data_i)
{
  int i;
  int a;
  int _3;
  int * _10;
  unsigned int pretmp_14;
  unsigned int _16;
  unsigned int _17;
  unsigned int _19;
  unsigned int prephitmp_22;

  <bb 2>:
  _3 = __builtin_omp_get_num_threads ();
  i_4 = __builtin_omp_get_thread_num ();
  if (i_4 <= 9)
    goto <bb 3>;
  else
    goto <bb 6>;

  <bb 3>:
  # a_5 = PHI <0(2)>
  # i_2 = PHI <i_4(2)>

  <bb 4>:
  # a_18 = PHI <a_5(3), a_7(4)>
  # i_21 = PHI <i_2(3), i_15(4)>
  a_7 = a_18 + i_21;
  _19 = (unsigned int) _3;
  _17 = (unsigned int) i_21;
  _16 = _17 + _19;
  i_15 = (int) _16;
  if (i_15 <= 9)
    goto <bb 4>;
  else
    goto <bb 5>;

  <bb 5>:
  pretmp_14 = (unsigned int) a_7;

  <bb 6>:
  # prephitmp_22 = PHI <pretmp_14(5), 0(2)>
  _10 = &.omp_data_i_9(D)->a;
  __atomic_fetch_add_4 (_10, prephitmp_22, 0); [tail call]
  return;

}
...