[all-commits] [llvm/llvm-project] 90ff14: AMDGPU: Account for implicit argument alignment fo...

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 90ff14871904881fb156a1d4d5fb083ca75998ab
      https://github.com/llvm/llvm-project/commit/90ff14871904881fb156a1d4d5fb083ca75998ab
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2021-11-09 (Tue, 09 Nov 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.implicitarg.ptr.ll

  Log Message:
  -----------
  AMDGPU: Account for implicit argument alignment for kernarg segment

If a kernel had no formal arguments but did have the implicit
arguments, we were reporting a required kernarg alignment of 4. For
some reason we require an 8-byte alignment for this, even though
there's no real advantage and I don't see where this is documented in
the ABI.

The code object header code also claims the minimum alignment is 16,
which is what I thought you always got at runtime anyway so I don't
know why this matters.