[all-commits] [llvm/llvm-project] 43b988: [AMDGPU] Use nan as the identity for atomicrmw fma...

[Jay Foad via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 43b9888214234363e3468ffda5bcd599e9608938
      https://github.com/llvm/llvm-project/commit/43b9888214234363e3468ffda5bcd599e9608938
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2024-07-02 (Tue, 02 Jul 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp
    M llvm/test/CodeGen/AMDGPU/global_atomic_optimizer_fp_rtn.ll
    M llvm/test/CodeGen/AMDGPU/global_atomics_optimizer_fp_no_rtn.ll
    M llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmax.ll
    M llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmin.ll

  Log Message:
  -----------
  [AMDGPU] Use nan as the identity for atomicrmw fmax/fmin (#97411)

atomicrmw fmax/fmin perform the same operation as llvm.maxnum/minnum
which return the other operand if one operand is nan. This means that,
in the presence of nan arguments, +/- inf is not an identity for these
operations but nan is (at least if you don't care about nan payloads).



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