[all-commits] [llvm/llvm-project] 5157f9: [AMDGPU] Enable divergence-driven XNOR selection

[alex-t via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 5157f984ae2c5e6fe9a8bd3a5dae99d5a96a276d
      https://github.com/llvm/llvm-project/commit/5157f984ae2c5e6fe9a8bd3a5dae99d5a96a276d
  Author: alex-t <alexander.timofeev at amd.com>
  Date:   2022-01-26 (Wed, 26 Jan 2022)

  Changed paths:
    M llvm/include/llvm/CodeGen/TargetLowering.h
    M llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.h
    M llvm/lib/Target/AMDGPU/SOPInstructions.td
    M llvm/lib/Target/AMDGPU/VOP2Instructions.td
    A llvm/test/CodeGen/AMDGPU/divergence-driven-xnor.ll
    M llvm/test/CodeGen/AMDGPU/fused-bitlogic.ll
    M llvm/test/CodeGen/AMDGPU/permute.ll
    M llvm/test/CodeGen/AMDGPU/wwm-reserved-spill.ll
    M llvm/test/CodeGen/AMDGPU/xnor.ll
    M llvm/test/CodeGen/AMDGPU/xor3.ll

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

Currently not (xor_one_use) pattern is always selected to S_XNOR irrelative od the node divergence.
This relies on further custom selection pass which converts to VALU if necessary and replaces with V_NOT_B32 ( V_XOR_B32)
on those targets which have no V_XNOR.
Current change enables the patterns which explicitly select the not (xor_one_use) to appropriate form.
We assume that xor (not) is already turned into the not (xor) by the combiner.

Reviewed By: rampitec

Differential Revision: https://reviews.llvm.org/D116270