[all-commits] [llvm/llvm-project] b90cfe: [AMDGPU] New ttracedata intrinsics (#70235)

[Jay Foad via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: b90cfe46015d9d12317146251e633d2ca07dccd7
      https://github.com/llvm/llvm-project/commit/b90cfe46015d9d12317146251e633d2ca07dccd7
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2023-11-02 (Thu, 02 Nov 2023)

  Changed paths:
    M llvm/include/llvm/IR/IntrinsicsAMDGPU.td
    M llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
    M llvm/lib/Target/AMDGPU/SOPInstructions.td
    A llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.ttracedata.ll

  Log Message:
  -----------
  [AMDGPU] New ttracedata intrinsics (#70235)

Add llvm.amdgcn.s.ttracedata and llvm.amdgcn.s.ttracedata.imm which map
directly to the corresponding instructions s_ttracedata and
s_ttracedata_imm. These are inherently whole-wave operations so any
non-uniform inputs are readfirstlaned.