[all-commits] [llvm/llvm-project] 63081d: LoadStoreVectorizer: Match nested adds to prove ve...

[Volkan Keles via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 63081dc6f642a6be61b3ef213f5c6e257f35671c
      https://github.com/llvm/llvm-project/commit/63081dc6f642a6be61b3ef213f5c6e257f35671c
  Author: Volkan Keles <vkeles at apple.com>
  Date:   2020-05-18 (Mon, 18 May 2020)

  Changed paths:
    M llvm/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
    A llvm/test/Transforms/LoadStoreVectorizer/X86/vectorize-i8-nested-add.ll

  Log Message:
  -----------
  LoadStoreVectorizer: Match nested adds to prove vectorization is safe

If both OpA and OpB is an add with NSW/NUW and with the same LHS operand,
we can guarantee that the transformation is safe if we can prove that OpA
won't overflow when IdxDiff added to the RHS of OpA.

Review: https://reviews.llvm.org/D79817