[PATCH] D148185: Add more efficient bitwise vector reductions on AArch64
Markus Everling via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Thu Apr 13 06:39:12 PDT 2023
Sp00ph added a comment.
The patch as it is right now has decreased the codegen quality on some of the tests with non-power-of-2 vector reductions. I have a fix for that (padding the vectors to the next larger power of 2), but I'm not sure if that still fits in the scope of this patch or if I should put that in a follow up patch, especially since you currently can't really trust LLVM to generate good code with non-power-of-2 sized vectors anyways.
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D148185/new/
https://reviews.llvm.org/D148185
More information about the llvm-commits
mailing list