[all-commits] [llvm/llvm-project] bd85a1: [AMDGPU] Do not propagate vgpr count in dVGPR mode...

[Mirko Brkušanin via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: bd85a10b0cbfde6e944da773c435b8006130848f
      https://github.com/llvm/llvm-project/commit/bd85a10b0cbfde6e944da773c435b8006130848f
  Author: Mirko Brkušanin <Mirko.Brkusanin at amd.com>
  Date:   2026-06-02 (Tue, 02 Jun 2026)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUMCResourceInfo.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.h
    M llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
    M llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
    A llvm/test/CodeGen/AMDGPU/dvgpr-vgpr-count-propagation-direct-chain.ll
    A llvm/test/CodeGen/AMDGPU/dvgpr-vgpr-count-propagation-indirect.ll
    A llvm/test/CodeGen/AMDGPU/dvgpr-vgpr-count-propagation.ll
    M llvm/test/CodeGen/AMDGPU/dvgpr_sym_fail_too_many_block_size_16.ll
    M llvm/test/CodeGen/AMDGPU/dvgpr_sym_fail_too_many_block_size_16_anon.ll

  Log Message:
  -----------
  [AMDGPU] Do not propagate vgpr count in dVGPR mode (#187078)

When dVGPR mode is enabled chain functions should not propagate VGPR
counts from other chain callees. VGPRs are allocated before chaining to
a chain functions. We only propagate counts from non-chain callees.



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