[all-commits] [llvm/llvm-project] 6133b6: [AMDGPU] Precommit test

[Sebastian Neubauer via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 6133b60a27fe0b89a96d5e10f28b2d9fd68d668f
      https://github.com/llvm/llvm-project/commit/6133b60a27fe0b89a96d5e10f28b2d9fd68d668f
  Author: Sebastian Neubauer <sebastian.neubauer at amd.com>
  Date:   2021-05-28 (Fri, 28 May 2021)

  Changed paths:
    M llvm/test/CodeGen/AMDGPU/gfx-callable-argument-types.ll

  Log Message:
  -----------
  [AMDGPU] Precommit test

Add scratch run to gfx-callable-argument-types.ll.


  Commit: 690f5b7a0128a210093e9b217932743ad35b5c5a
      https://github.com/llvm/llvm-project/commit/690f5b7a0128a210093e9b217932743ad35b5c5a
  Author: Sebastian Neubauer <sebastian.neubauer at amd.com>
  Date:   2021-05-28 (Fri, 28 May 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs-packed.ll
    M llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll
    M llvm/test/CodeGen/AMDGPU/gfx-callable-argument-types.ll
    M llvm/test/CodeGen/AMDGPU/non-entry-alloca.ll

  Log Message:
  -----------
  [AMDGPU] Fix function calls with flat scratch

When flat scratch is used, the stack pointer needs to be added when
writing arguments to the stack.
For buffer instructions, this is done in SelectMUBUFScratchOffen
and SelectMUBUFScratchOffset.

Move that to call argument lowering, like it is done in GlobalISel.

Differential Revision: https://reviews.llvm.org/D103166


Compare: https://github.com/llvm/llvm-project/compare/00ecf18979e3...690f5b7a0128