Sanjay Patel 9ebb68843e [x86] use PMOVMSK to replace memcmp libcalls for 16-byte equality
This is the payoff for D31156 - if a target has efficient comparison instructions for vector-sized equality, 
we can replace memcmp calls with inline code that is both smaller and faster.

Differential Revision: https://reviews.llvm.org/D31290

llvm-svn: 298775
2017-03-25 16:05:33 +00:00
..
2017-03-06 21:10:40 +00:00
2017-03-13 20:00:25 +00:00