[PATCH] D70592: [ARM,MVE] Rename and clean up VCTP IR intrinsics.
Dave Green via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Fri Nov 22 07:36:20 PST 2019
dmgreen added a subscriber: samparker.
dmgreen added a comment.
I agree that this is the best way forward. Any 2 wide masked vectors loads/stores would be expanded, as far as I understand, so the MVETailPredication pass would never handle those cases (although I'm not sure that is explicit in the pass anywhere), and we would never generate them.
@samparker you happy with removing arm_vctp64? Maybe one to try and get working in the future if it makes sense.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D70592/new/
https://reviews.llvm.org/D70592
More information about the llvm-commits
mailing list