X86: Implement the X86 sse2 haddpd instruction

This patch implements the haddpd instruction.

It fixes the problem in the previous version (pointed out by Gabe Black)
where an incorrect result would happen if you issue the instruction
with the same argument twice, i.e. "haddpd %xmm0,%xmm0"

This instruction is used by many spec2k benchmarks.

1 files changed, 21 insertions, 1 deletions

diff --git a/src/arch/x86/isa/insts/simd128/floating_point/arithmetic/horizontal_addition.py b/src/arch/x86/isa/insts/simd128/floating_point/arithmetic/horizontal_addition.py
index 8b307d3da..adf7650b9 100644
--- a/src/arch/x86/isa/insts/simd128/floating_point/arithmetic/horizontal_addition.py
+++ b/src/arch/x86/isa/insts/simd128/floating_point/arithmetic/horizontal_addition.py
@@ -55,5 +55,25 @@
 
 microcode = '''
 # HADDPS
-# HADDPD
+
+def macroop HADDPD_XMM_XMM {
+    maddf ufp1, xmmh , xmml, size=8, ext=1
+    maddf xmmh, xmmlm, xmmhm, size=8, ext=1
+    movfp xmml, ufp1
+};
+
+def macroop HADDPD_XMM_M {
+    ldfp ufp1, seg, sib, disp, dataSize=8
+    ldfp ufp2, seg, sib, "DISPLACEMENT+8", dataSize=8
+    maddf xmml, xmmh, xmml, size=8, ext=1
+    maddf xmmh, ufp1, ufp2, size=8, ext=1
+};
+
+def macroop HADDPD_XMM_P {
+    rdip t7
+    ldfp ufp1, seg, riprel, disp, dataSize=8
+    ldfp ufp2, seg, riprel, "DISPLACEMENT+8", dataSize=8
+    maddf xmml, xmmh, xmml, size=8, ext=1
+    maddf xmmh, ufp1, ufp2, size=8, ext=1
+};
 '''