http://gcc.gnu.org/bugzilla/show_bug.cgi?id=52558
--- Comment #2 from Richard Guenther <rguenth at gcc dot gnu.org> 2012-03-12 15:01:36 UTC --- (In reply to comment #1) > Richi, is this something that should also be fixed for 4.7 as well? There is > a > write to g_2 that is introduced on paths that did not have it. So this is not > just a load/load data race. No, we don't want to fix this for 4.7 as this is not a regression. Yes, LIM only avoids introducing traps, not data-races. This was discussed in the past already, btw, and we do not want to generally disallow this optimization. [The C++ memory model is stupid here, it should not treat every variable raceable but only specially marked ones, oh well ...] There will be very many other passes that are affected by this, and even more very many passes that will be affected by load data-races. You will for example slow down SPEC CPU 2006 quite a bit (though technically it does not include C++11 benchmarks).
