template<typename ElementA_, typename LayoutA_, typename ElementB_, typename LayoutB_, typename ElementC_, typename LayoutC_, typename ElementAccumulator_ = ElementC_, typename OperatorClass_ = arch::OpClassSimt, typename ArchTag_ = arch::Sm70, typename ThreadblockShape_ = typename DefaultGemmConfiguration<        OperatorClass_, ArchTag_, ElementA_, ElementB_, ElementC_,        ElementAccumulator_>::ThreadblockShape, typename WarpShape_ = typename DefaultGemmConfiguration<        OperatorClass_, ArchTag_, ElementA_, ElementB_, ElementC_,        ElementAccumulator_>::WarpShape, typename InstructionShape_ = typename DefaultGemmConfiguration<        OperatorClass_, ArchTag_, ElementA_, ElementB_, ElementC_,        ElementAccumulator_>::InstructionShape, typename EpilogueOutputOp_ = typename DefaultGemmConfiguration<        OperatorClass_, ArchTag_, ElementA_, ElementB_, ElementC_,        ElementAccumulator_>::EpilogueOutputOp, typename ConvertScaledOp_ = cutlass::epilogue::thread::Convert<        ElementAccumulator_,        DefaultGemmConfiguration<OperatorClass_, ArchTag_, ElementA_, ElementB_,                                 ElementAccumulator_,                                 ElementAccumulator_>::EpilogueOutputOp::kCount,        ElementAccumulator_>, typename ReductionOp_ = cutlass::reduction::thread::ReduceAdd<        ElementAccumulator_, typename EpilogueOutputOp_::ElementAccumulator,        EpilogueOutputOp_::kCount>, typename ThreadblockSwizzle_ = threadblock::GemmSplitKHorizontalThreadblockSwizzle, int Stages = DefaultGemmConfiguration<OperatorClass_, ArchTag_, ElementA_, ElementB_,                                 ElementC_, ElementAccumulator_>::kStages, int kAlignmentA = DefaultGemmConfiguration<OperatorClass_, ArchTag_, ElementA_, ElementB_,                                 ElementC_, ElementAccumulator_>::kAlignmentA, int kAlignmentB = DefaultGemmConfiguration<OperatorClass_, ArchTag_, ElementA_, ElementB_,                                 ElementC_, ElementAccumulator_>::kAlignmentB, typename Operator_ = typename DefaultGemmConfiguration<        OperatorClass_, ArchTag_, ElementA_, ElementB_, ElementC_,        ElementAccumulator_>::Operator> 
      
        
          | EpilogueOutputOp::Params cutlass::gemm::device::GemmSplitKParallel< ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, ElementAccumulator_, OperatorClass_, ArchTag_, ThreadblockShape_, WarpShape_, InstructionShape_, EpilogueOutputOp_, ConvertScaledOp_, ReductionOp_, ThreadblockSwizzle_, Stages, kAlignmentA, kAlignmentB, Operator_ >::Arguments::epilogue |