[Bug middle-end/59990] [4.7/4.8 regression] incorrect memcpy optimization

[rguenth at gcc dot gnu.org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59990

--- Comment #15 from Richard Biener <rguenth at gcc dot gnu.org> ---
Backporting this to 4.8 regresses

//-m32
FAIL: gcc.target/i386/pr49168-1.c scan-assembler movdqu[\t ]*%xmm[0-9]+,[^,]*

flt128_va:
.LFB0:
        .cfi_startproc
        movl    4(%esp), %eax
        movdqa  20(%esp), %xmm0
        movlps  %xmm0, (%eax)
        movhps  %xmm0, 8(%eax)
        ret

expanding from

flt128_va (void * mem, __float128 d)
{
  uint128_t _2;

;;   basic block 2, loop depth 0
;;    pred:       ENTRY
  _2 = VIEW_CONVERT_EXPR<uint128_t>(d_5(D));
  MEM[(char * {ref-all})mem_3(D)] = _2;
  return;

which doesn't end up using a UNSPEC_STOREU insn as on trunk but

(insn 8 7 0 2 (set (mem:V2SF (plus:SI (reg/v/f:SI 60 [ mem ])
                (const_int 8 [0x8])) [0 MEM[(char * {ref-all})mem_3(D)]+8 S8
A8])
        (vec_select:V2SF (subreg:V4SF (reg/v:TF 61 [ d ]) 0)
            (parallel [
                    (const_int 2 [0x2])
                    (const_int 3 [0x3])
                ])))
/space/rguenther/src/svn/gcc-4_8-branch/gcc/testsuite/gcc.target/i386/pr49168-1.c:10
-1
     (nil))