[all-commits] [llvm/llvm-project] 5a8c0f: AMDGPU/GlobalISel: Avoid handling registers twice ...

Matt Arsenault via All-commits all-commits at lists.llvm.org
Thu Feb 6 09:56:22 PST 2020


  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 5a8c0f552b382cbf4397aff9cc3b0d9418bdf3ff
      https://github.com/llvm/llvm-project/commit/5a8c0f552b382cbf4397aff9cc3b0d9418bdf3ff
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2020-02-06 (Thu, 06 Feb 2020)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp

  Log Message:
  -----------
  AMDGPU/GlobalISel: Avoid handling registers twice in waterfall loops

When multiple instructions are moved into a waterfall loop, it's
possible some of them re-use the same operands. Avoid creating
multiple sequences of readfirstlanes for them. None of the current
uses will hit this, but will be used in a future patch.




More information about the All-commits mailing list