[X86][MMX] Support MMX build vectors to avoid SSE usage (PR29222)

[X86][MMX] Support MMX build vectors to avoid SSE usage (PR29222)

64-bit MMX vector generation usually ends up lowering into SSE instructions before being spilled/reloaded as a MMX type.

This patch creates a MMX vector from MMX source values, taking the lowest element from each source and constructing broadcasts/build_vectors with direct calls to the MMX PUNPCKL/PSHUFW intrinsics.

We're missing a few consecutive load combines that could be handled in a future patch if that would be useful - my main interest here is just avoiding a lot of the MMX/SSE crossover.

Differential Revision: https://reviews.llvm.org/D43618

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@327247 91177308-0d34-0410-b5e6-96231b3b80d8