[all-commits] [llvm/llvm-project] dcc756: [AMDGPU] Pattern for flat atomic fadd f64 intrinsi...

[petar-avramovic via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: dcc756d03e597d6a405493a630f66ce4fcb7d656
      https://github.com/llvm/llvm-project/commit/dcc756d03e597d6a405493a630f66ce4fcb7d656
  Author: Petar Avramovic <Petar.Avramovic at amd.com>
  Date:   2022-09-25 (Sun, 25 Sep 2022)

  Changed paths:
    M clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx90a.cl
    M llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
    M llvm/lib/Target/AMDGPU/DSInstructions.td
    M llvm/test/CodeGen/AMDGPU/fp64-atomics-gfx90a.ll

  Log Message:
  -----------
  [AMDGPU] Pattern for flat atomic fadd f64 intrinsic with local addr

Fix regression from clang opencl test in builtins-fp-atomics-gfx90a.cl
test_flat_add_local_f64 caused by D130579
Revert a3becb333d7faae695e18728e9b8fa3a3579a240.

Differential Revision: https://reviews.llvm.org/D134568