https://gcc.gnu.org/bugzilla/show_bug.cgi?id=19779
Jakub Jelinek <jakub at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |jakub at gcc dot gnu.org
--- Comment #2 from Jakub Jelinek <jakub at gcc dot gnu.org> ---
We do fold it with -ffast-math or -funsafe-math-optimizations.
PR19405 explains the reasons why we can't fold those results that aren't
exactly representable in double double.
