[PATCH] D133787: [AMDGPU][SILoadStoreOptimizer] Merge SGPR_IMM scalar buffer loads.

[Jay Foad via Phabricator via llvm-commits]

foad added a comment.

I can't resist pointing out that this patch would be simpler if we never used the _SGPR form on subtargets where the _SGPR_IMM form is available.



================
Comment at: llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp:640
     return Result;
+  case AMDGPU::S_BUFFER_LOAD_DWORD_SGPR_IMM:
+  case AMDGPU::S_BUFFER_LOAD_DWORDX2_SGPR_IMM:
----------------
Don't you need to list the _SGPR forms here too?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D133787/new/

https://reviews.llvm.org/D133787