[Bug middle-end/112600] Failed to optimize saturating addition using __builtin_add_overflow

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=112600

--- Comment #4 from Richard Biener <rguenth at gcc dot gnu.org> ---
Note we don't have a good middle-end representation for (integer) saturation.

Maybe having variants of .ADD_OVERFLOW and friends specifying an alternate
value (or the value in case the actual value is left unspecified when
overflow occurs) as additional argument would work.  So have the first
fold into

  <bb 2> :
  _8 = .ADD_OVERFLOW (x_6(D), y_7(D), -1u);
  _1 = REALPART_EXPR (_8);
  return _1;

of course that defers the code-generation problem to RTL expansion and
would require to pattern match

    res = x + y;
    res |= -(res < x);

to the same for canonicalization purposes.  I would expect that some
targets implement saturating integer arithmetic (not sure about
multiplication or division though).