/***************************************************************************************************
 * Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 * SPDX-License-Identifier: BSD-3-Clause
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright notice, this
 * list of conditions and the following disclaimer.
 *
 * 2. 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.
 *
 * 3. Neither the name of the copyright holder 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 THE COPYRIGHT HOLDER OR CONTRIBUTORS 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 TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 **************************************************************************************************/
/*! \file
    \brief Templates exposing architecture support for warp-level multiply-add operations
*/

#pragma once

#include "cutlass/cutlass.h"
#include "cutlass/array.h"
#include "cutlass/numeric_types.h"
#include "cutlass/gemm/gemm.h"
#include "cutlass/arch/mma.h"

/////////////////////////////////////////////////////////////////////////////////////////////////

namespace cutlass {
namespace gemm {
namespace thread {

/////////////////////////////////////////////////////////////////////////////////////////////////

/// Structure to compute the matrix product
template <
  /// Size of the Gemm problem - concept: gemm::GemmShape<>
  typename Shape,
  /// Data type of A elements
  typename ElementA,
  /// Layout of A matrix (concept: MatrixLayout)
  typename LayoutA,
  /// Data type of B elements
  typename ElementB,
  /// Layout of B matrix (concept: MatrixLayout)
  typename LayoutB,
  /// Element type of C matrix
  typename ElementC,
  /// Layout of C matrix (concept: MatrixLayout)
  typename LayoutC,
  /// Concept: arch::OpMultiplyAdd or arch::Mma<>
  typename Operator = arch::OpMultiplyAdd,
  /// Used for partial specialization
  typename Enable = bool
>
struct Mma;

/////////////////////////////////////////////////////////////////////////////////////////////////

} // namespace thread
} // namespace gemm
} // namespace cutlass

/////////////////////////////////////////////////////////////////////////////////////////////////

//
// Overloads specialized for existing architectures
//

#include "cutlass/gemm/thread/mma_sm50.h"
#include "cutlass/gemm/thread/mma_sm60.h"
#include "cutlass/gemm/thread/mma_sm61.h"

/////////////////////////////////////////////////////////////////////////////////////////////////