[all-commits] [llvm/llvm-project] f0d510: [VPlan] Handle some VPInstructions in may{Read, Wri...

[Luke Lau via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: f0d5104c944b329c479802788571ed6df41e0e86
      https://github.com/llvm/llvm-project/commit/f0d5104c944b329c479802788571ed6df41e0e86
  Author: Luke Lau <luke at igalia.com>
  Date:   2025-01-08 (Wed, 08 Jan 2025)

  Changed paths:
    M llvm/lib/Transforms/Vectorize/VPlan.h
    M llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
    M llvm/test/Transforms/LoopVectorize/AArch64/blend-costs.ll
    M llvm/test/Transforms/LoopVectorize/AArch64/force-target-instruction-cost.ll
    M llvm/test/Transforms/LoopVectorize/RISCV/blend-any-of-reduction-cost.ll
    M llvm/test/Transforms/LoopVectorize/RISCV/divrem.ll
    M llvm/test/Transforms/LoopVectorize/X86/pr109581-unused-blend.ll
    M llvm/test/Transforms/LoopVectorize/X86/replicate-uniform-call.ll
    M llvm/test/Transforms/LoopVectorize/X86/scatter_crash.ll
    M llvm/test/Transforms/LoopVectorize/blend-in-header.ll
    M llvm/test/Transforms/LoopVectorize/if-pred-stores.ll
    M llvm/test/Transforms/LoopVectorize/induction.ll
    M llvm/test/Transforms/LoopVectorize/invariant-store-vectorization-2.ll
    M llvm/test/Transforms/LoopVectorize/pr37248.ll
    M llvm/test/Transforms/LoopVectorize/pr55167-fold-tail-live-out.ll
    M llvm/test/Transforms/LoopVectorize/reduction-small-size.ll
    M llvm/test/Transforms/LoopVectorize/select-cmp.ll
    M llvm/test/Transforms/LoopVectorize/single_early_exit.ll
    M llvm/test/Transforms/LoopVectorize/tail-folding-switch.ll
    M llvm/test/Transforms/LoopVectorize/uniform-blend.ll
    M llvm/unittests/Transforms/Vectorize/VPlanTest.cpp

  Log Message:
  -----------
  [VPlan] Handle some VPInstructions in may{Read,Write}FromMemory (#120058)

This just copies the same conservative definition from mayWriteToMemory,
and enables more VPInstructions to be hoisted out in LICM.

I think this should give more accurate costs, and I was able to build
llvm-test-suite without the legacy-vplan cost model assertion going off.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications