[PATCH] D20172: [AArch64] Disable narrow load merge by default

Jun Bum Lim via llvm-commits llvm-commits at lists.llvm.org
Wed May 11 09:05:04 PDT 2016


junbuml added a comment.

> Have you considered deciding this as a MachineCombiner pattern? This would be a good place to know if the loop is arithmetic or load/store heavy.


Let me take a look if we can move this to MachineCombiner. 
Thanks James!


http://reviews.llvm.org/D20172





More information about the llvm-commits mailing list