Address another opportunity for reducing x86 sequence for GP pair to XMM

Making use of punpckldq to interleave two 32-bit values in xmm registers
in OpRegCopyWide.

Change-Id: Ibe3b9de88d69a081f08b79fee834837d0157a4a3
Signed-off-by: Razvan A Lupusoru <razvan.a.lupusoru@intel.com>
diff --git a/compiler/dex/quick/x86/int_x86.cc b/compiler/dex/quick/x86/int_x86.cc
index e665f70..cbf2658 100644
--- a/compiler/dex/quick/x86/int_x86.cc
+++ b/compiler/dex/quick/x86/int_x86.cc
@@ -157,8 +157,7 @@
       NewLIR2(kX86MovdxrRR, dest_lo, src_lo);
       dest_hi = AllocTempDouble();
       NewLIR2(kX86MovdxrRR, dest_hi, src_hi);
-      NewLIR2(kX86PsllqRI, dest_hi, 32);
-      NewLIR2(kX86OrpsRR, dest_lo, dest_hi);
+      NewLIR2(kX86PunpckldqRR, dest_lo, dest_hi);
       FreeTemp(dest_hi);
     }
   } else {