[all-commits] [llvm/llvm-project] a080e3: AMDGPU: Fix missing immarg on buffer.atomic.fadd i...

[Matt Arsenault via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: a080e345e439936d7f2d4733d0512c1b7d51e648
      https://github.com/llvm/llvm-project/commit/a080e345e439936d7f2d4733d0512c1b7d51e648
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2020-06-05 (Fri, 05 Jun 2020)

  Changed paths:
    M llvm/include/llvm/IR/IntrinsicsAMDGPU.td
    M llvm/test/Verifier/AMDGPU/intrinsic-immarg.ll

  Log Message:
  -----------
  AMDGPU: Fix missing immarg on buffer.atomic.fadd intrinsic


  Commit: 43bb1c239c27de0ef9fdb8a43da1ef0bc16fc42a
      https://github.com/llvm/llvm-project/commit/43bb1c239c27de0ef9fdb8a43da1ef0bc16fc42a
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2020-06-05 (Fri, 05 Jun 2020)

  Changed paths:
    M llvm/lib/Target/AMDGPU/BUFInstructions.td
    A llvm/test/CodeGen/AMDGPU/fail-select-buffer-atomic-fadd.ll

  Log Message:
  -----------
  AMDGPU: Fix incorrect selection of buffer atomic fadd

There were additional standalone patterns for these nodes which were
missing the subtarget predicate.


Compare: https://github.com/llvm/llvm-project/compare/7c9a89fed8f5...43bb1c239c27