[PATCH] D65319: [ScalarizeMaskedMemIntrin] Bitcast the mask to the scalar domain and use scalar bit tests for the branches.

Wed Jul 31 15:05:57 PDT 2019

RKSimon accepted this revision.
RKSimon added a comment.
This revision is now accepted and ready to land.

LGTM - I think this is the way forward for the scalarization of a lot of masked ops and I've already raised some similar bugs for arm/aarch64/ppc (PR41634, PR41635, PR41636) to better handle bitcasts of <X x i1> to iX for reductions - this patch should be able to make use of those upcoming improvements.

Please can you raise bugs for the expandload/compressstore improvements you mentioned and the duplication of test+branch instructions.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D65319/new/

https://reviews.llvm.org/D65319