[all-commits] [llvm/llvm-project] 0fa666: [VPlan] Add VPDerivedIVRecipe, use for VPScalarIVS...

[Florian Hahn via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 0fa666ecedc3f36471c0fee925d664512e7525a8
      https://github.com/llvm/llvm-project/commit/0fa666ecedc3f36471c0fee925d664512e7525a8
  Author: Florian Hahn <flo at fhahn.com>
  Date:   2022-11-28 (Mon, 28 Nov 2022)

  Changed paths:
    M llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
    M llvm/lib/Transforms/Vectorize/VPlan.cpp
    M llvm/lib/Transforms/Vectorize/VPlan.h
    M llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
    M llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
    M llvm/lib/Transforms/Vectorize/VPlanValue.h
    M llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-forced.ll
    M llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll
    M llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
    M llvm/test/Transforms/LoopVectorize/first-order-recurrence-chains-vplan.ll
    M llvm/test/Transforms/LoopVectorize/first-order-recurrence-sink-replicate-region.ll
    M llvm/test/Transforms/LoopVectorize/icmp-uniforms.ll
    M llvm/test/Transforms/LoopVectorize/interleave-and-scalarize-only.ll
    M llvm/test/Transforms/LoopVectorize/vplan-dot-printing.ll
    M llvm/test/Transforms/LoopVectorize/vplan-printing.ll
    M llvm/test/Transforms/LoopVectorize/vplan-sink-scalars-and-merge-vf1.ll
    M llvm/test/Transforms/LoopVectorize/vplan-sink-scalars-and-merge.ll

  Log Message:
  -----------
  [VPlan] Add VPDerivedIVRecipe, use for VPScalarIVStepsRecipe.

This patch splits off the logic to transform the canonical IV to a
a value for an induction with a different start and step. This
transformation only needs to be done once (independent of VF/UF) and
enables sinking of VPScalarIVStepsRecipe as follow-up.

Reviewed By: Ayal

Differential Revision: https://reviews.llvm.org/D133758