[all-commits] [llvm/llvm-project] 3fe1e9: AMDGPU: Set some more attributes on intrinsics

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 3fe1e952070f64363b3eb500674788609a4ff4d9
      https://github.com/llvm/llvm-project/commit/3fe1e952070f64363b3eb500674788609a4ff4d9
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2023-01-10 (Tue, 10 Jan 2023)

  Changed paths:
    M llvm/include/llvm/IR/IntrinsicsAMDGPU.td

  Log Message:
  -----------
  AMDGPU: Set some more attributes on intrinsics


  Commit: a200fa04a34535fb790b5a0496917aa4f8ef4161
      https://github.com/llvm/llvm-project/commit/a200fa04a34535fb790b5a0496917aa4f8ef4161
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2023-01-10 (Tue, 10 Jan 2023)

  Changed paths:
    M llvm/include/llvm/IR/IntrinsicsAMDGPU.td

  Log Message:
  -----------
  AMDGPU: Move intrinsic definition point

This was incorrectly listed under the block for backend internal
intrinsics only.


  Commit: 2e9c663ab4a0385e619a64bc0726be0bb178c0b1
      https://github.com/llvm/llvm-project/commit/2e9c663ab4a0385e619a64bc0726be0bb178c0b1
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2023-01-10 (Tue, 10 Jan 2023)

  Changed paths:
    M clang/test/CodeGenCUDA/builtins-amdgcn.cu

  Log Message:
  -----------
  clang/AMDGPU: Add missing tests for some builtin

These were tested under opencl but need hip testing for the potential
addrspacecasts.


  Commit: 777b905bae1ba0c219143f02d952d9cd5c242f50
      https://github.com/llvm/llvm-project/commit/777b905bae1ba0c219143f02d952d9cd5c242f50
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2023-01-10 (Tue, 10 Jan 2023)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp
    M llvm/test/CodeGen/AMDGPU/opencl-printf.ll

  Log Message:
  -----------
  AMDGPU: Stop trying to specially handle vector stores in printf lowering

This was broken for 1 element vectors and trying to create invalid
casts. We can directly store any type just fine, so don't bother with
this buggy conversion logic.


  Commit: d8534e4e981da5ff9907999eb549b3a1d075a69b
      https://github.com/llvm/llvm-project/commit/d8534e4e981da5ff9907999eb549b3a1d075a69b
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2023-01-10 (Tue, 10 Jan 2023)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp
    M llvm/test/CodeGen/AMDGPU/opencl-printf.ll

  Log Message:
  -----------
  AMDGPU: Don't insert ptrtoint for printf lowering


Compare: https://github.com/llvm/llvm-project/compare/d198c75e5ae0...d8534e4e981d