[all-commits] [llvm/llvm-project] ad4a18: AMDGPU: Fix assert on m0_lo16/m0_hi16

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: ad4a18251a37a244e3d4375538abfc0894a1e6ac
      https://github.com/llvm/llvm-project/commit/ad4a18251a37a244e3d4375538abfc0894a1e6ac
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2021-06-18 (Fri, 18 Jun 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
    M llvm/test/CodeGen/AMDGPU/indirect-addressing-si-gfx9.ll

  Log Message:
  -----------
  AMDGPU: Fix assert on m0_lo16/m0_hi16

These get added (redundantly) to the bundle expanded for indirect
register accesses. We hit this path only when there is a call in the
function.