[X86] Add patterns to select MOVLPDrm from MOVSD+load and MOVHPD from UNPCKL+load.

These narrow the load so we can only do it if the load isn't
volatile.

There also tests in vector-shuffle-128-v4.ll that this should
support, but we don't seem to fold bitcast+load on pre-sse4.2
targets due to the slow unaligned mem 16 flag.

llvm-svn: 365266