[all-commits] [llvm/llvm-project] 508b06: [Remarks] [AMDGPU] Emit optimization remarks for a...

[Anshil Gandhi via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 508b06699a396cc6f2f2602dab350860cb69f087
      https://github.com/llvm/llvm-project/commit/508b06699a396cc6f2f2602dab350860cb69f087
  Author: Anshil Gandhi <Anshil.Gandhi at amd.com>
  Date:   2021-08-19 (Thu, 19 Aug 2021)

  Changed paths:
    A clang/test/CodeGenOpenCL/atomics-cas-remarks-gfx90a.cl
    R clang/test/CodeGenOpenCL/atomics-remarks-gfx90a.cl
    A clang/test/CodeGenOpenCL/atomics-unsafe-hw-remarks-gfx90a.cl
    M llvm/lib/CodeGen/AtomicExpandPass.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    A llvm/test/CodeGen/AMDGPU/atomics-cas-remarks-gfx90a.ll
    A llvm/test/CodeGen/AMDGPU/atomics-hw-remarks-gfx90a.ll
    R llvm/test/CodeGen/AMDGPU/atomics-remarks-gfx90a.ll

  Log Message:
  -----------
  [Remarks] [AMDGPU] Emit optimization remarks for atomics generating hardware instructions

Produce remarks when atomic instructions are expanded into hardware instructions
in SIISelLowering.cpp. Currently, these remarks are only emitted for atomic fadd
instructions.

Differential Revision: https://reviews.llvm.org/D108150