[Bug tree-optimization/109088] GCC does not always vectorize conditional reduction

[rguenth at gcc dot gnu.org via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109088

--- Comment #18 from Richard Biener <rguenth at gcc dot gnu.org> ---
Ah, so this is for

int foo (int *a, int x)
{
  int sum = 0;
  for (int i = 0; i < 1024; ++i)
    if (a[i] < 10)
      sum = sum + a[i] + x;
  return sum;
}

transforming it to

int foo (int *a, int x)
{
  int sum = 0;
  for (int i = 0; i < 1024; ++i)
    {
      tem = a[i] + x;
      if (a[i] < 10)
        sum = sum + tem;
    }
  return sum;
}

note this is re-associating and thus not always valid.  It also executes
stmts unconditionally (also not always valid, for FP spurious exceptions
might be raised).