X86: Implement the X86 sse2 haddpd instruction
authorVince Weaver <vince@csl.cornell.edu>
Fri, 30 Oct 2009 18:19:06 +0000 (14:19 -0400)
committerVince Weaver <vince@csl.cornell.edu>
Fri, 30 Oct 2009 18:19:06 +0000 (14:19 -0400)
commitb2067840a6ad7e70495ad4dc6c74bf080e68133f
tree9f759489d90cf18e301f3f3c6770d9c5f52bcadf
parentcf269025f9e51eebb56d04fea6994fd72b1be4f9
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.
src/arch/x86/isa/decoder/two_byte_opcodes.isa
src/arch/x86/isa/insts/simd128/floating_point/arithmetic/horizontal_addition.py