SIMD pavgb,w for x86/x86_64

Rationale:
Break-out CL of ART Vectorizer.
Enables fast halving add with rounding

Bug: 34083438
Test: assembler_x86[_64]_test
Change-Id: I09173376b803d671a6b05a33e630f45f778cea52

1 files changed, 18 insertions, 0 deletions

diff --git a/compiler/utils/x86/assembler_x86.cc b/compiler/utils/x86/assembler_x86.cc
index 5307dc09d9..9c934b7f39 100644
--- a/compiler/utils/x86/assembler_x86.cc
+++ b/compiler/utils/x86/assembler_x86.cc
@@ -1221,6 +1221,24 @@ void X86Assembler::por(XmmRegister dst, XmmRegister src) {
 }
 
 
+void X86Assembler::pavgb(XmmRegister dst, XmmRegister src) {
+  AssemblerBuffer::EnsureCapacity ensured(&buffer_);
+  EmitUint8(0x66);
+  EmitUint8(0x0F);
+  EmitUint8(0xE0);
+  EmitXmmRegisterOperand(dst, src);
+}
+
+
+void X86Assembler::pavgw(XmmRegister dst, XmmRegister src) {
+  AssemblerBuffer::EnsureCapacity ensured(&buffer_);
+  EmitUint8(0x66);
+  EmitUint8(0x0F);
+  EmitUint8(0xE3);
+  EmitXmmRegisterOperand(dst, src);
+}
+
+
 void X86Assembler::pcmpeqb(XmmRegister dst, XmmRegister src) {
   AssemblerBuffer::EnsureCapacity ensured(&buffer_);
   EmitUint8(0x66);