[all-commits] [llvm/llvm-project] 872e89: AMDGPU/GlobalISel: Legalize unpacked d16 image ope...

[Matt Arsenault via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 872e899b7563a033228be935a04bfb853bd73acd
      https://github.com/llvm/llvm-project/commit/872e899b7563a033228be935a04bfb853bd73acd
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2020-01-30 (Thu, 30 Jan 2020)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.h
    A llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-llvm.amdgcn.image.load.2d.d16.ll
    A llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-llvm.amdgcn.image.store.2d.d16.ll

  Log Message:
  -----------
  AMDGPU/GlobalISel: Legalize unpacked d16 image operations

On targets that don't have the normal packed f16 layout, handle these
during legalization. Directly modify the register types. We can infer
this was a d16 load based on the mem operand size during selection.

A16 operands should possibly be handled here as well, but don't worry
about that yet.