[all-commits] [llvm/llvm-project] 01f785: AMDGPU: Expand remaining system atomic operations ...

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 01f785cac4f5863f27012e347b9ae9287830c07e
      https://github.com/llvm/llvm-project/commit/01f785cac4f5863f27012e347b9ae9287830c07e
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2025-08-22 (Fri, 22 Aug 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/GlobalISel/atomicrmw_udec_wrap.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/atomicrmw_uinc_wrap.ll
    M llvm/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll
    M llvm/test/CodeGen/AMDGPU/flat_atomics_i32_system.ll
    M llvm/test/CodeGen/AMDGPU/flat_atomics_i64_system.ll
    M llvm/test/CodeGen/AMDGPU/flat_atomics_i64_system_noprivate.ll
    M llvm/test/CodeGen/AMDGPU/global_atomics_i32_system.ll
    M llvm/test/CodeGen/AMDGPU/global_atomics_i64_system.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i16-system.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i32-system.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i64-system.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i8-system.ll
    M llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomicrmw-integer-ops-0-to-add-0.ll

  Log Message:
  -----------
  AMDGPU: Expand remaining system atomic operations (#122137)

System scope atomics need to use cmpxchg loops if we know
nothing about the allocation the address is from.
aea5980e26e6a87dab9f8acb10eb3a59dd143cb1 started this, this
expands the set to cover the remaining integer operations.

Don't expand xchg and add, those theoretically should work over PCIe.
This is a pre-commit which will introduce performance regressions.
Subsequent changes will add handling of new atomicrmw metadata, which
will avoid the expansion.

Note this still isn't conservative enough; we do need to expand
some device scope atomics if the memory is in fine-grained remote
memory.



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