[all-commits] [llvm/llvm-project] af6ff9: [AMDGPU] Move WWM register pre-allocation to durin...

[Carl Ritson via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: af6ff98c5338748cd3c38310febb5de31c8e4a37
      https://github.com/llvm/llvm-project/commit/af6ff98c5338748cd3c38310febb5de31c8e4a37
  Author: Carl Ritson <carl.ritson at amd.com>
  Date:   2023-11-08 (Wed, 08 Nov 2023)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
    M llvm/lib/Target/AMDGPU/SIPreAllocateWWMRegs.cpp
    M llvm/test/CodeGen/AMDGPU/bb-prolog-spill-during-regalloc.ll
    M llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
    M llvm/test/CodeGen/AMDGPU/sgpr-regalloc-flags.ll
    M llvm/test/CodeGen/AMDGPU/wwm-reserved-spill.ll

  Log Message:
  -----------
  [AMDGPU] Move WWM register pre-allocation to during regalloc (#70618)

Move SIPreAllocateWWMRegs pass to just before VGPR allocation. This
saves recomputation of the virtual matrix and live reg map, with the
slight regression in O0 that live intervals and slot indexes must be
computed.