[PATCH] D90445: [SLP] Make SLPVectorizer to use `llvm.masked.gather` intrinsic

Anton Afanasyev via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Wed Nov 25 10:02:37 PST 2020

anton-afanasyev added a comment.

In D90445#2416578 <https://reviews.llvm.org/D90445#2416578>, @vdmitrie wrote:

> It sounds like throttling patch should resolve this issue as cutting out ScatterVectorize entry with high cost will effectively return to previous behavior.

Yes, exactly. The only difference with previous behavior could arise in case of the new tree accumulating other instructions starting from ScatterVectorize and NeedToGather GEPs entries, preventing them from being contained in other parts of tree. But these entries are terminal, with so rare speculative exceptions that I believe it's good euristics for this case as well as for the general SLP drawback you mentioned: build the maximum tree and choose the cheapest subtree.

  rG LLVM Github Monorepo



More information about the llvm-commits mailing list