[all-commits] [llvm/llvm-project] 59cdf4: [AMDGPU] Do not run GCNNSAReassign pass for GFX12 ...

[Jay Foad via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 59cdf41f077661cd2178123cf27dc688823b6b0f
      https://github.com/llvm/llvm-project/commit/59cdf41f077661cd2178123cf27dc688823b6b0f
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2024-01-17 (Wed, 17 Jan 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/GCNNSAReassign.cpp
    M llvm/lib/Target/AMDGPU/GCNSubtarget.h

  Log Message:
  -----------
  [AMDGPU] Do not run GCNNSAReassign pass for GFX12 (#78185)

GFX12 does not have separate NSA and non-NSA encodings.

---------

Co-authored-by: Mirko Brkusanin <Mirko.Brkusanin at amd.com>