[PATCH] D105390: [X86] Lower insertions into non-0'th 128-bit subvector as broadcast+blend (PR50971)
Roman Lebedev via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Sat Jul 3 06:46:10 PDT 2021
lebedev.ri added a comment.
In D105390#2856736 <https://reviews.llvm.org/D105390#2856736>, @RKSimon wrote:
> I think the premise is sound, but creating variable shuffle/blend masks isn't great - its also uncovering a number of other poor codegen issues that need addressing.
My main question is, presumably we only want to do this iff that is the only insertion into that 128-bit-wide subreg?
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D105390/new/
https://reviews.llvm.org/D105390
More information about the llvm-commits
mailing list