[Bug target/49133] [4.6/4.7 Regression] modification of aliased __m128d miscompiles

["kretz at kde dot org" <gcc-bugzilla at gcc dot gnu dot org>]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=49133

--- Comment #2 from Matthias Kretz <kretz at kde dot org> 2011-05-24 10:16:41 UTC ---
I applied the patch to the latest 4.6 snapshot. I confirm that it fixes the
bug. Also, there are no regressions in my testsuite.

Just for confirmation, the patched sse.md looks like this for me now (starting
from line 4952):
(define_insn "sse2_loadhpd"
  [(set (match_operand:V2DF 0 "nonimmediate_operand"     "=x,x,x,o,o,o")
    (vec_concat:V2DF
      (vec_select:DF
        (match_operand:V2DF 1 "nonimmediate_operand" " 0,0,x,0,0,0")
        (parallel [(const_int 0)]))
      (match_operand:DF 2 "nonimmediate_operand"     " m,x,0,x,*f,r")))]
  "TARGET_SSE2 && !(MEM_P (operands[1]) && MEM_P (operands[2]))"
  "@
   movhpd\t{%2, %0|%0, %2}
   unpcklpd\t{%2, %0|%0, %2}
   shufpd\t{$0, %1, %0|%0, %1, 0}
   #

Question, why not use unpcklpd instead of shufpd $0? On older CPUs unpcklpd
should be slightly faster than shufpd.