[all-commits] [llvm/llvm-project] d797a7: [AMDGPU] Use performOptimizedStructLayout for LDS ...

[Stanislav Mekhanoshin via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: d797a7f8da18e39d8ce1913175601faf2002a005
      https://github.com/llvm/llvm-project/commit/d797a7f8da18e39d8ce1913175601faf2002a005
  Author: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
  Date:   2021-06-22 (Tue, 22 Jun 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
    M llvm/test/CodeGen/AMDGPU/lower-module-lds-constantexpr.ll
    M llvm/test/CodeGen/AMDGPU/lower-module-lds-global-alias.ll
    M llvm/test/CodeGen/AMDGPU/lower-module-lds-global-uses.ll
    M llvm/test/CodeGen/AMDGPU/update-lds-alignment.ll

  Log Message:
  -----------
  [AMDGPU] Use performOptimizedStructLayout for LDS sort

This gives better packing.

Differential Revision: https://reviews.llvm.org/D104331