[all-commits] [llvm/llvm-project] 849f96: [CodeGen] Improve ExpandMemCmp for more efficient ...

[Igor Kirillov via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 849f963e3139d79eba9989554a299ec6a1a16b10
      https://github.com/llvm/llvm-project/commit/849f963e3139d79eba9989554a299ec6a1a16b10
  Author: Igor Kirillov <igor.kirillov at arm.com>
  Date:   2023-10-30 (Mon, 30 Oct 2023)

  Changed paths:
    M llvm/include/llvm/Analysis/TargetTransformInfo.h
    M llvm/lib/CodeGen/ExpandMemCmp.cpp
    M llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
    A llvm/test/CodeGen/AArch64/memcmp.ll
    A llvm/test/Transforms/ExpandMemCmp/AArch64/memcmp.ll

  Log Message:
  -----------
  [CodeGen] Improve ExpandMemCmp for more efficient non-register aligned sizes handling (#70469)

* Enhanced the logic of ExpandMemCmp pass to merge contiguous
subsequences
  in LoadSequence, based on sizes allowed in `AllowedTailExpansions`.
* This enhancement seeks to minimize the number of basic blocks and
produce
  optimized code when using memcmp with non-register aligned sizes.
* Enable this feature for AArch64 with memcmp sizes modulo 8 equal to
  3, 5, and 6.

Reapplication of #69942 after fixing a bug