[all-commits] [llvm/llvm-project] 33fb23: [AMDGPU] Merge flat with global in the SILoadStore...

[Stanislav Mekhanoshin via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 33fb23f728146cd9a1b8a0bf74c666fb2eeffbb5
      https://github.com/llvm/llvm-project/commit/33fb23f728146cd9a1b8a0bf74c666fb2eeffbb5
  Author: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
  Date:   2022-03-09 (Wed, 09 Mar 2022)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
    A llvm/test/CodeGen/AMDGPU/merge-flat-with-global-load-store.mir

  Log Message:
  -----------
  [AMDGPU] Merge flat with global in the SILoadStoreOptimizer

Flat can be merged with flat global since address cast is a no-op.
A combined memory operation needs to be promoted to flat.

Differential Revision: https://reviews.llvm.org/D120431