[X86][SSE] Canonicalize scalar fp arithmetic shuffle patterns

As discussed on PR38197, this canonicalizes MOVS*(N0, OP(N0, N1)) --> MOVS*(N0, SCALAR_TO_VECTOR(OP(N0[0], N1[0])))

This returns the scalar-fp codegen lost by rL336971.

Additionally it handles the OP(N1, N0)) case for commutable (FADD/FMUL) ops.

Differential Revision: https://reviews.llvm.org/D49474

llvm-svn: 337419