[all-commits] [llvm/llvm-project] c1511a: [AMDGPU] Folding imm offset in more cases for scra...

[Ruiling, Song via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c1511a65d5c09f7cff15feba91ce9bda23d74b6e
      https://github.com/llvm/llvm-project/commit/c1511a65d5c09f7cff15feba91ce9bda23d74b6e
  Author: Ruiling, Song <ruiling.song at amd.com>
  Date:   2023-11-29 (Wed, 29 Nov 2023)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.h
    M llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.h
    M llvm/test/CodeGen/AMDGPU/GlobalISel/flat-scratch.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-load-private.mir
    M llvm/test/CodeGen/AMDGPU/chain-hi-to-lo.ll
    M llvm/test/CodeGen/AMDGPU/flat-scratch-i8-i16.ll
    M llvm/test/CodeGen/AMDGPU/flat-scratch-svs.ll
    M llvm/test/CodeGen/AMDGPU/flat-scratch.ll
    M llvm/test/CodeGen/AMDGPU/function-returns.ll
    M llvm/test/CodeGen/AMDGPU/gfx-callable-return-types.ll
    M llvm/test/CodeGen/AMDGPU/memory_clause.ll

  Log Message:
  -----------
  [AMDGPU] Folding imm offset in more cases for scratch access (#70634)

For scratch load/store, our hardware only accept non-negative value in
SGPR/VGPR. Besides the case that we can prove from known bits, we can
also prove that the value in `base` will be non-negative: 1.) When the
ADD for the address calculation has NonUnsignedWrap flag. 2.) When the
immediate offset is already negative.