http://gcc.gnu.org/bugzilla/show_bug.cgi?id=52890
--- Comment #11 from Martin Jambor <jamborm at gcc dot gnu.org> 2012-09-14 13:55:04 UTC --- (In reply to comment #10) > > Martin, > Have you done any more digging on this? I just discovered that cpu2006 > benchmark 471.omnetpp suffers the same problem (8 byte loads turned in to > sequence of byte loads/shifts/ors). It causes a 12% degradation on PowerPC, > and > also goes away when -fno-ipa-sra is added. I'm attaching a reduced testcase > that can be compiled with g++ -S -O3 -m64 -mcpu=power7. Thanks for the reduced testcase. This PR is still on my radar but so far other issues have had higher priority. On the other hand, I agree I have not looked at this for too long, I'll do my best to look at it soon. I can't promise much in the next 2-3 weeks, though.
