Translate NEON vmull, vmlal, and vmlsl builtins to llvm multiply-add/sub

with zext/sext operations, instead of to llvm intrinsics.  I have a plan to
avoid the clang builtins for these, but it is going to take a little longer
and I want to get the NEON intrinsics updated before the 2.8 release.

llvm-svn: 112764