[PATCH] D158779: [VPlan] Add active-lane-mask as VPlan-to-VPlan transformation.

[Florian Hahn via Phabricator via llvm-commits]

fhahn created this revision.
fhahn added reviewers: Ayal, gilr, rengolin, dmgreen, ABataev.
Herald added subscribers: StephenFan, tschuett, psnobl, rogfer01, zzheng, bollu, hiraditya.
Herald added a project: All.
fhahn requested review of this revision.
Herald added subscribers: wangpc, vkmr.
Herald added a project: LLVM.

This patch updates the mask creation code to always create compares of
the form (ICMP_ULE, wide canonical IV, backedge-taken-count) up front
when tail folding and introduce active-lane-mask as later
transformation.

This effectively makes (ICMP_ULE, wide canonical IV, backedge-taken-count)
the canonical form for tail-folding early on. Introducing more specific
active-lane-mask recipes is treated as a VPlan-to-VPlan optimization.

This has the advantage of keeping the logic  (and complexity) of
introducing active-lane-mask recipes in a single place, instead of
spreading the logic out across multiple functions. It also simplifies
initial VPlan construction and enables treating introducing EVL as
similar optimization.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D158779

Files:
  llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
  llvm/lib/Transforms/Vectorize/VPlan.cpp
  llvm/lib/Transforms/Vectorize/VPlan.h
  llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
  llvm/lib/Transforms/Vectorize/VPlanTransforms.h
  llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
  llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-masked-accesses.ll
  llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-forced.ll
  llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-overflow-checks.ll
  llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-reductions.ll
  llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-unroll.ll
  llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
  llvm/test/Transforms/LoopVectorize/AArch64/tail-fold-uniform-memops.ll
  llvm/test/Transforms/LoopVectorize/AArch64/tail-folding-styles.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D158779.553257.patch
Type: text/x-patch
Size: 68717 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230824/cc40d806/attachment-0001.bin>