[all-commits] [llvm/llvm-project] 9c3f5f: [LV] Don't consider the latch block as ScalarPredi...

[Florian Hahn via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 9c3f5fe88f19820360981d0798392799e1924cb7
      https://github.com/llvm/llvm-project/commit/9c3f5fe88f19820360981d0798392799e1924cb7
  Author: Florian Hahn <flo at fhahn.com>
  Date:   2024-04-29 (Mon, 29 Apr 2024)

  Changed paths:
    M llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
    M llvm/test/Transforms/LoopVectorize/AArch64/conditional-branches-cost.ll
    M llvm/test/Transforms/LoopVectorize/AArch64/induction-costs-sve.ll

  Log Message:
  -----------
  [LV] Don't consider the latch block as ScalarPredicatedBB.

The conditional branch from the loop latch will be replaced by a
single branch controlling the loop, so there is no extra overhead from
scalarization. This improves the cost esimates in some cases.



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