[all-commits] [llvm/llvm-project] 959390: AMDGPU: Custom expand flat cmpxchg which may acces...

[Matt Arsenault via All-commits]

  Branch: refs/heads/users/arsenm/atomic-expand-allow-custom-cmpxchg-expand
  Home:   https://github.com/llvm/llvm-project
  Commit: 9593907be9e3fe6ecd1bdd8274f8bfb144fb3914
      https://github.com/llvm/llvm-project/commit/9593907be9e3fe6ecd1bdd8274f8bfb144fb3914
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-11-01 (Fri, 01 Nov 2024)

  Changed paths:
    M llvm/include/llvm/CodeGen/TargetLowering.h
    M llvm/include/llvm/Transforms/Utils/LowerAtomic.h
    M llvm/lib/CodeGen/AtomicExpandPass.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.h
    M llvm/lib/Transforms/Utils/LowerAtomic.cpp
    M llvm/test/CodeGen/AMDGPU/flat_atomics_i64.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomicrmw-flat-noalias-addrspace.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomicrmw-integer-ops-0-to-add-0.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-cmpxchg-flat-maybe-private.ll

  Log Message:
  -----------
  AMDGPU: Custom expand flat cmpxchg which may access private

64-bit flat cmpxchg instructions do not work correctly for scratch
addresses, and need to be expanded as non-atomic.

Allow custom expansion of cmpxchg in AtomicExpand, as is
already the case for atomicrmw.


  Commit: 96bcb08b4fa165e3dcc130e6e44c2d6c5c8017e9
      https://github.com/llvm/llvm-project/commit/96bcb08b4fa165e3dcc130e6e44c2d6c5c8017e9
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-11-01 (Fri, 01 Nov 2024)

  Changed paths:
    M llvm/include/llvm/Transforms/Utils/LowerAtomic.h
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/lib/Transforms/Utils/LowerAtomic.cpp

  Log Message:
  -----------
  Rename helper function


  Commit: 67036ee40454425f477fca957e9ec66ccd5b3ff2
      https://github.com/llvm/llvm-project/commit/67036ee40454425f477fca957e9ec66ccd5b3ff2
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-11-01 (Fri, 01 Nov 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-cmpxchg-flat-maybe-private.ll

  Log Message:
  -----------
  Fix check of noalias range

Switch from using range parsing was off and also didn't handle
the wrapped range case


Compare: https://github.com/llvm/llvm-project/compare/37a7ec41ec7e...67036ee40454

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