[all-commits] [llvm/llvm-project] 678d89: [AMDGPU] Add bf16 storage support

[Pierre van Houtryve via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 678d8946ba2ba790c4c52e96e2134ee136e30057
      https://github.com/llvm/llvm-project/commit/678d8946ba2ba790c4c52e96e2134ee136e30057
  Author: Pierre van Houtryve <pierre.vanhoutryve at amd.com>
  Date:   2022-12-13 (Tue, 13 Dec 2022)

  Changed paths:
    M clang/lib/Basic/Targets/AMDGPU.cpp
    M clang/lib/Basic/Targets/AMDGPU.h
    A clang/test/CodeGenCUDA/amdgpu-bf16.cu
    A clang/test/SemaCUDA/amdgpu-bf16.cu
    M llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
    M llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
    M llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h
    M llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    A llvm/test/CodeGen/AMDGPU/bf16-ops.ll
    A llvm/test/CodeGen/AMDGPU/bf16.ll

  Log Message:
  -----------
  [AMDGPU] Add bf16 storage support

- [Clang] Declare AMDGPU target as supporting BF16 for storage-only purposes on amdgcn
  - Add Sema & CodeGen tests cases.
  - Also add cases that D138651 would have covered as this patch replaces it.
- [AMDGPU] Add BF16 storage-only support
  - Support legalization/dealing with bf16 operations in DAGIsel.
  - bf16 as a type remains illegal and is represented as i16 for storage purposes.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D139398