/*
 * Copyright (c) 2017 ARM Limited.
 *
 * SPDX-License-Identifier: MIT
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to
 * deal in the Software without restriction, including without limitation the
 * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
 * sell copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in all
 * copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */
#ifndef __ARM_COMPUTE_NEGEMMMATRIXMULTIPLYKERNEL_H__
#define __ARM_COMPUTE_NEGEMMMATRIXMULTIPLYKERNEL_H__

#include "arm_compute/core/NEON/INEKernel.h"

namespace arm_compute
{
class ITensor;

/** NEON kernel to multiply two input matrices "A" and "B". All elements of the output matrix/vector will be multiplied by alpha after the matrix multiplication
 *
 * @note If the output tensor is a matrix, the implementation assumes that the input tensors @p input0 and @p input1 are both matrices and reshaped respectively with @ref NEGEMMInterleave4x4Kernel" and @ref NEGEMMTranspose1xWKernel
 * @note If the output tensor is a vector and the data type is F32, the implementation assumes that the first input tensor @p input0 is a vector and the second input tensor @p input1 a matrix. The implementation also assumes that both tensors have not been reshaped
 *
 */
class NEGEMMMatrixMultiplyKernel : public INEKernel
{
public:
    /** Constructor */
    NEGEMMMatrixMultiplyKernel();
    /** Prevent instances of this class from being copied (As this class contains pointers) */
    NEGEMMMatrixMultiplyKernel(const NEGEMMMatrixMultiplyKernel &) = delete;
    /** Prevent instances of this class from being copied (As this class contains pointers) */
    NEGEMMMatrixMultiplyKernel &operator=(const NEGEMMMatrixMultiplyKernel &) = delete;
    /** Allow instances of this class to be moved */
    NEGEMMMatrixMultiplyKernel(NEGEMMMatrixMultiplyKernel &&) = default;
    /** Allow instances of this class to be moved */
    NEGEMMMatrixMultiplyKernel &operator=(NEGEMMMatrixMultiplyKernel &&) = default;
    /** Initialise the kernel's input and output.
     *
     * @note If the output tensor is a matrix, the input matrices @p input0 and @p input1 should be the output of the kernels: @ref NEGEMMInterleave4x4Kernel and @ref NEGEMMTranspose1xWKernel
     *       These two kernels change the layout of the original matrices to be more cache-friendly.
     *
     * @param[in]  input0 Input tensor containing the interleaved Matrix A or the vector A. Data types supported: QS8/QS16/F16/F32
     * @param[in]  input1 Input tensor containing the transposed Matrix B if the first input tensor A is not a vector.
     *                    If the output tensor is a vector, input1 must contain the matrix B not reshaped. Data type supported: same as @p input0
     * @param[out] output Output tensor to store the result of matrix multiplication. Data type supported: same as @p input0.
     * @param[in]  alpha  Weight of the matrix product
     */
    void configure(const ITensor *input0, const ITensor *input1, ITensor *output, float alpha);

    // Inherited methods overridden:
    void run(const Window &window) override;

private:
    const ITensor *_input0;
    const ITensor *_input1;
    ITensor       *_output;
    float          _alpha;
};
}
#endif /*__ARM_COMPUTE_NEGEMMMATRIXMULTIPLYKERNEL_H__*/