[all-commits] [llvm/llvm-project] 5c974d: [AMDGPU] Fix hazard handling of v_cmpx to permlane

[Stanislav Mekhanoshin via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 5c974d086c22d519e3e649f1d5fe213b03d6ba25
      https://github.com/llvm/llvm-project/commit/5c974d086c22d519e3e649f1d5fe213b03d6ba25
  Author: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
  Date:   2022-06-09 (Thu, 09 Jun 2022)

  Changed paths:
    M llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
    A llvm/test/CodeGen/AMDGPU/vcmpx-permlane-hazard-sdwa.mir
    M llvm/test/CodeGen/AMDGPU/vcmpx-permlane-hazard.mir

  Log Message:
  -----------
  [AMDGPU] Fix hazard handling of v_cmpx to permlane

- VOP3 and SDWA forms of V_CMPX were not handled
- Hazard only exists if the compare defines EXEC (i.e. V_CMPX)
  forwarded to the permlane.

Differential Revision: https://reviews.llvm.org/D127344