[all-commits] [llvm/llvm-project] a61c34: AtomicExpand: Use llvm.ptrmask instead of ptrtoint

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: a61c3455c02867f6ef74017e705f238648ef47ca
      https://github.com/llvm/llvm-project/commit/a61c3455c02867f6ef74017e705f238648ef47ca
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2022-09-28 (Wed, 28 Sep 2022)

  Changed paths:
    M llvm/lib/CodeGen/AtomicExpandPass.cpp
    M llvm/test/CodeGen/VE/Scalar/atomic_cmp_swap.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i16.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i8.ll
    M llvm/test/Transforms/AtomicExpand/SPARC/partword.ll

  Log Message:
  -----------
  AtomicExpand: Use llvm.ptrmask instead of ptrtoint

This removes the ptrtoint from the load's pointer operand, although we
can't entirely eliminate these to get the LSB shift. In a future
patch, this will avoid ptrtoint in the case where the atomic is
overaligned to the word size.


  Commit: 01adf1f3e50a87e290cedb47fdf9d1e0cc635015
      https://github.com/llvm/llvm-project/commit/01adf1f3e50a87e290cedb47fdf9d1e0cc635015
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2022-09-28 (Wed, 28 Sep 2022)

  Changed paths:
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i16.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i8.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-rmw-fadd.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-rmw-fsub.ll

  Log Message:
  -----------
  AtomicExpand: Add some more overaligned atomic tests


Compare: https://github.com/llvm/llvm-project/compare/4848f3bf2ff5...01adf1f3e50a