http://gcc.gnu.org/bugzilla/show_bug.cgi?id=51766
--- Comment #10 from Jonathan Wakely <redi at gcc dot gnu.org> 2012-01-10 18:22:01 UTC --- (In reply to comment #8) > IBM should have the freedom to choose memory > models that benefit its architectures. I meant to add that the new __atomic builtins give that freedom, by design. Changing the documented behaviour of the __sync builtins to do something they weren't designed for doesn't seem like a good idea - if they're inefficient then convince people not to use them.
