[Bug middle-end/66199] New: [4.9/5 Regression] lastprivate/linear clause issues on combined constructs

[jakub at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66199

            Bug ID: 66199
           Summary: [4.9/5 Regression] lastprivate/linear clause issues on
                    combined constructs
           Product: gcc
           Version: 5.1.1
            Status: UNCONFIRMED
          Keywords: rejects-valid, wrong-code
          Severity: normal
          Priority: P3
         Component: middle-end
          Assignee: jakub at gcc dot gnu.org
          Reporter: jakub at gcc dot gnu.org
  Target Milestone: ---

The following testcase is incorrectly rejected in 4.9/5, eventhough the
variables are either explicitly or implicitly mentioned on the combined
construct.
There is also a wrong-code issue in f3/f4 if default(none) clause is removed.

int u[1024], v[1024], w[1024], m;

__attribute__((noinline, noclone)) long
f1 (long a, long b)
{
  long d;
  #pragma omp parallel for simd default(none) firstprivate (a, b) shared(u, v,
w)
  for (d = a; d < b; d++)
    u[d] = v[d] + w[d];
  return d;
}

__attribute__((noinline, noclone)) long
f2 (long a, long b, long c)
{
  long d;
  #pragma omp parallel for simd default(none) firstprivate (a, b) shared(u, v,
w) linear(d) linear(c:5)
  for (d = a; d < b; d++)
    {
      u[d] = v[d] + w[d];
      c += 5;
    }
  return d + c;
}

__attribute__((noinline, noclone)) long
f3 (long a1, long b1, long a2, long b2)
{
  long d1, d2;
  #pragma omp parallel for simd default(none) firstprivate (a1, b1, a2, b2)
shared(u, v, w) lastprivate(d1, d2) collapse(2)
  for (d1 = a1; d1 < b1; d1++)
    for (d2 = a2; d2 < b2; d2++)
      u[d1 * 32 + d2] = v[d1 * 32 + d2] + w[d1 * 32 + d2];
  return d1 + d2;
}

__attribute__((noinline, noclone)) long
f4 (long a1, long b1, long a2, long b2)
{
  long d1, d2;
  #pragma omp parallel for simd default(none) firstprivate (a1, b1, a2, b2)
shared(u, v, w) collapse(2)
  for (d1 = a1; d1 < b1; d1++)
    for (d2 = a2; d2 < b2; d2++)
      u[d1 * 32 + d2] = v[d1 * 32 + d2] + w[d1 * 32 + d2];
  return d1 + d2;
}

int
main ()
{
  if (f1 (0, 1024) != 1024
      || f2 (0, 1024, 17) != 1024 + 17 + 5 * 1024
      || f3 (0, 32, 0, 32) != 64
      || f4 (0, 32, 0, 32) != 64)
    __builtin_abort ();
  return 0;
}