[PATCH] D157368: [VPlan] Consider scalar VF in masked VPReductionRecipe

[Florian Hahn via Phabricator via llvm-commits]

fhahn added inline comments.


================
Comment at: llvm/test/Transforms/LoopVectorize/AArch64/scalar_interleave_masked_reduce.ll:18
+; CHECK: REDUCE ir<%sum.next> = ir<%sum> + reduce.fadd (vp<[[ARG:%.*]]>, vp<[[MASK:%.*]]>)
+; CHECK: Executing best plan with VF=1, UF=4
+
----------------
it's probably worth to check the full IR; the code modifies IR generation so we should check the generated IR


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D157368/new/

https://reviews.llvm.org/D157368