https://gcc.gnu.org/bugzilla/show_bug.cgi?id=68923
Peter Cordes <peter at cordes dot ca> changed: What |Removed |Added ---------------------------------------------------------------------------- Keywords| |missed-optimization, ssemmx Target| |x86_64-linux-gnu URL| |http://stackoverflow.com/qu | |estions/34279513/loading-8- | |chars-from-memory-into-an-m | |256-variable-as-packed-sing | |le-precision-f --- Comment #1 from Peter Cordes <peter at cordes dot ca> --- The other issue (that there's no intrinsic to generate a movq m64, %xmm in 32bit mode), is addressed in https://gcc.gnu.org/bugzilla/show_bug.cgi?id=68924. This bug is just about the optimization failure to fold the load into pmovzx.