Bunch of SIMD for x86 and x86_64

Rationale:
Few instructions needed to implement SIMD reductions.

Test: assembler_x86_[64_]test
Bug: 64091002
Change-Id: I785acfc6c8c4ad4f290ddeab32da9b767f944e24
diff --git a/compiler/utils/x86/assembler_x86.h b/compiler/utils/x86/assembler_x86.h
index 8578340..511eeb9 100644
--- a/compiler/utils/x86/assembler_x86.h
+++ b/compiler/utils/x86/assembler_x86.h
@@ -546,6 +546,11 @@
   void punpckldq(XmmRegister dst, XmmRegister src);
   void punpcklqdq(XmmRegister dst, XmmRegister src);
 
+  void punpckhbw(XmmRegister dst, XmmRegister src);
+  void punpckhwd(XmmRegister dst, XmmRegister src);
+  void punpckhdq(XmmRegister dst, XmmRegister src);
+  void punpckhqdq(XmmRegister dst, XmmRegister src);
+
   void psllw(XmmRegister reg, const Immediate& shift_count);
   void pslld(XmmRegister reg, const Immediate& shift_count);
   void psllq(XmmRegister reg, const Immediate& shift_count);