[all-commits] [llvm/llvm-project] 0fa5df: [LV] Synthesize all true masks for masked vector f...

[huntergr-arm via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 0fa5df1959faaf474697fae4fd36b9749b67f815
      https://github.com/llvm/llvm-project/commit/0fa5df1959faaf474697fae4fd36b9749b67f815
  Author: Graham Hunter <graham.hunter at arm.com>
  Date:   2023-02-14 (Tue, 14 Feb 2023)

  Changed paths:
    M llvm/include/llvm/Analysis/VectorUtils.h
    M llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
    M llvm/lib/Transforms/Vectorize/VPRecipeBuilder.h
    M llvm/lib/Transforms/Vectorize/VPlan.h
    M llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
    M llvm/test/Transforms/LoopVectorize/AArch64/masked-call.ll
    A llvm/test/Transforms/LoopVectorize/AArch64/synthesize-mask-for-call.ll
    M llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll

  Log Message:
  -----------
  [LV] Synthesize all true masks for masked vector function variants

When vectorizing code with function calls in it, if we encounter
a function which only has vectorized variants requiring a mask
we can synthesize an all-true mask to enable us to proceed.

Since we want the mask to be represented in vplan, the pointer
to the chosen Function is now stored as part of the
VPWidenCallRecipe, and mask arguments are added at the
appropriate index to the recipe operands.

Reviewed By: david-arm, fhahn, reames

Differential Revision: https://reviews.llvm.org/D132458