------- Comment #5 from luisgpm at linux dot vnet dot ibm dot com 2008-10-02 01:43 ------- This problem also showed up as a CPU2000 regression in the Sixtrack benchmark for PPC64, causing problems in the ondering of ld/st instructions.
A GCC patched with Richard's fix produced the right code and the regression is gone. -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=37447
