[all-commits] [llvm/llvm-project] d7ec41: AMDGPU: Support VALU add instructions in localstac...

[Matt Arsenault via All-commits]

  Branch: refs/heads/users/arsenm/local-stack-slot-alloc-v-add-support
  Home:   https://github.com/llvm/llvm-project
  Commit: d7ec4102298af97fb89282231a646bc482cc53fd
      https://github.com/llvm/llvm-project/commit/d7ec4102298af97fb89282231a646bc482cc53fd
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-08-02 (Fri, 02 Aug 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
    M llvm/lib/Target/AMDGPU/SOPInstructions.td
    M llvm/lib/Target/AMDGPU/VOP2Instructions.td
    A llvm/test/CodeGen/AMDGPU/local-stack-alloc-add-references.gfx10.mir
    A llvm/test/CodeGen/AMDGPU/local-stack-alloc-add-references.gfx8.mir
    A llvm/test/CodeGen/AMDGPU/local-stack-alloc-add-references.gfx9.mir

  Log Message:
  -----------
  AMDGPU: Support VALU add instructions in localstackalloc

Pre-enable this optimization before allowing folds of frame
indexes into add instructions. Disables this fold when using
scratch instructions for now. I see some code size improvements
with it, but the optimization needs to be smarter about the
uses depending on the register classes.



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