[all-commits] [llvm/llvm-project] 54c525: AMDGPU/GlobalISel: Handle legacy grid ID intrinsics

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 54c525fc53bf3f329e558457f67a175477916799
      https://github.com/llvm/llvm-project/commit/54c525fc53bf3f329e558457f67a175477916799
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2022-04-05 (Tue, 05 Apr 2022)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.h
    M llvm/test/CodeGen/AMDGPU/amdgpu.work-item-intrinsics.deprecated.ll

  Log Message:
  -----------
  AMDGPU/GlobalISel: Handle legacy grid ID intrinsics

Handle the llvm.r600.* intrinsics which are still in use in libclc. I
thought it would be possible to switch it to using
llvm.amdgcn.implicitarg.ptr already, but it turns out the implicit
arguments are currently split into a piece before and after the
explicit kernel arguments.