------- Comment #12 from hjl dot tools at gmail dot com 2010-01-14 17:34 ------- Intel AVX architecture won't fault on unaligned load-op instructions and unaligned VMOV* instructions are as fast as aligned VMOV* instructions on aligned memory. For AVX, we can always use unaligned VMOV* instructions, even on aligned memory, to work around this issue without any performance penalty.
-- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=42652
