default_gemm_splitk_parallel.h

Go to the documentation of this file.

/***************************************************************************************************
 * Copyright (c) 2017-2019, NVIDIA CORPORATION.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without modification, are permitted
 * provided that the following conditions are met:
 *     * Redistributions of source code must retain the above copyright notice, this list of
 *       conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright notice, this list of
 *       conditions and the following disclaimer in the documentation and/or other materials
 *       provided with the distribution.
 *     * Neither the name of the NVIDIA CORPORATION nor the names of its contributors may be used
 *       to endorse or promote products derived from this software without specific prior written
 *       permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR
 * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND
 * FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
 * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
 * STRICT LIABILITY, OR TOR (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 **************************************************************************************************/

#pragma once

#include "cutlass/cutlass.h"
#include "cutlass/gemm/kernel/default_gemm.h"
#include "cutlass/gemm/kernel/gemm_splitk_parallel.h"


namespace cutlass {
namespace gemm {
namespace kernel {


template <
  typename ElementA_,
  typename LayoutA_,
  int kAlignmentA,
  typename ElementB_,
  typename LayoutB_,
  int kAlignmentB,
  typename ElementC_,
  typename LayoutC_,
  typename ElementAccumulator,
  typename OperatorClass,
  typename ArchTag,
  typename ThreadblockShape,
  typename WarpShape,
  typename InstructionShape,
  typename EpilogueOutputOp,
  typename ThreadblockSwizzle,
  int Stages,
  typename Operator
>
struct DefaultGemmSplitKParallel {

  using Default = DefaultGemm<
    ElementA_,
    LayoutA_,
    kAlignmentA,
    ElementB_,
    LayoutB_,
    kAlignmentB,
    ElementAccumulator,
    LayoutC_,
    ElementAccumulator,
    OperatorClass,
    ArchTag,
    ThreadblockShape,
    WarpShape,
    InstructionShape,
    EpilogueOutputOp,
    ThreadblockSwizzle,
    Stages,
    false,
    Operator
  >;

  using Mma = typename Default::Mma;

  using Epilogue = typename Default::Epilogue;

  using GemmKernel = kernel::GemmSplitKParallel<Mma, Epilogue, ThreadblockSwizzle>;
};


}  // namespace kernel
}  // namespace gemm
}  // namespace cutlass