[PATCH] D112725: [SVE][LoopVectorize] Extract the last lane from a uniform store

[Kerry McLaughlin via Phabricator via llvm-commits]

kmclaughlin created this revision.
kmclaughlin added reviewers: sdesmalen, david-arm, fhahn.
Herald added subscribers: psnobl, hiraditya, tschuett.
Herald added a reviewer: efriedma.
kmclaughlin requested review of this revision.
Herald added a project: LLVM.
Herald added a subscriber: llvm-commits.

Changes VPReplicateRecipe to extract the last lane from an unconditional,
uniform store instruction if the VF is scalable.

This fixes an assert ("Cannot yet scalarize uniform stores") in
setCostBasedWideningDecision when we have a loop containing a uniform
i1 store, which we cannot create a scatter store for.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D112725

Files:
  llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
  llvm/test/Transforms/LoopVectorize/AArch64/sve-uniform-store.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D112725.383039.patch
Type: text/x-patch
Size: 10468 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20211028/a3d73839/attachment.bin>