[all-commits] [llvm/llvm-project] 0a3d75: [AMDGPU] Enable divergence-driven BFE selection

[alex-t via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 0a3d755ee9fcef1a84e0290e217d3eba68cdee22
      https://github.com/llvm/llvm-project/commit/0a3d755ee9fcef1a84e0290e217d3eba68cdee22
  Author: alex-t <alexander.timofeev at amd.com>
  Date:   2021-11-03 (Wed, 03 Nov 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.h
    M llvm/lib/Target/AMDGPU/SIInstructions.td
    A llvm/test/CodeGen/AMDGPU/divergence-driven-bfe-isel.ll
    M llvm/test/CodeGen/AMDGPU/llvm.round.f64.ll
    M llvm/test/CodeGen/AMDGPU/srem-seteq-illegal-types.ll

  Log Message:
  -----------
  [AMDGPU] Enable divergence-driven BFE selection

Detailed description: This change enables the bit field extract patterns
selection to s_bfe_u32 or v_bfe_u32 dependent on the pattern root node
divergence.

Reviewed By: rampitec

Differential Revision: https://reviews.llvm.org/D110950