/*
 * Copyright (c) 2019-2021 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_CPU_DEPTHWISECONVOLUTIONASSEMBLYDISPATCH_H
#define ARM_COMPUTE_CPU_DEPTHWISECONVOLUTIONASSEMBLYDISPATCH_H

#include "src/runtime/cpu/ICpuOperator.h"

namespace arm_compute
{
namespace cpu
{
/** Depthwise convolution assembly kernel glue */
class CpuDepthwiseConvolutionAssemblyDispatch : public ICpuOperator
{
public:
    CpuDepthwiseConvolutionAssemblyDispatch();
    /** Prevent instances of this class from being copied (As this class contains pointers) */
    CpuDepthwiseConvolutionAssemblyDispatch(const CpuDepthwiseConvolutionAssemblyDispatch &) = delete;
    /** Default move constructor */
    CpuDepthwiseConvolutionAssemblyDispatch(CpuDepthwiseConvolutionAssemblyDispatch &&) = default;
    /** Prevent instances of this class from being copied (As this class contains pointers) */
    CpuDepthwiseConvolutionAssemblyDispatch &operator=(const CpuDepthwiseConvolutionAssemblyDispatch &) = delete;
    /** Default move assignment operator */
    CpuDepthwiseConvolutionAssemblyDispatch &operator=(CpuDepthwiseConvolutionAssemblyDispatch &&) = default;
    /** Default destructor */
    ~CpuDepthwiseConvolutionAssemblyDispatch();
    /** Initialize the function's source, destination, kernels and border_size.
     *
     * @note Supports only NHWC format
     *
     * @param[in]  input   Source tensor info. Data type supported: QASYMM8/F16/F32. (Written to only for border filling).
     * @param[in]  weights Weights tensor info. These are 3D tensors with shape [W, H, IFM]. Data type supported: Same as @p input.
     * @param[in]  bias    (Optional) Biases tensor info. A 1D tensor with shape [IFM]. Must be nullptr if not needed.
     *                     Data type supported: Same as @p input.
     * @param[out] output  Destination tensor info. Data type supported: same as @p input.
     * @param[in]  info    Depthwise convolution meta-data.
     */
    void configure(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *bias, ITensorInfo *output, const ConvolutionInfo &info);
    /** Static function to check if given info will lead to a valid configuration of @ref CpuDepthwiseConvolutionAssemblyDispatch
     *
     * @note Supports only NHWC format
     *
     * @param[in]  input   Source tensor info. Data type supported: QASYMM8/F16/F32. (Written to only for border filling).
     * @param[in]  weights Weights tensor info. These are 3D tensors with shape [W, H, IFM]. Data type supported: Same as @p input.
     * @param[in]  bias    (Optional) Biases tensor info. A 1D tensor with shape [IFM]. Must be nullptr if not needed.
     *                     Data type supported: Same as @p input.
     * @param[out] output  Destination tensor info. Data type supported: same as @p input.
     * @param[in]  info    Depthwise convolution meta-data.
     *
     * @return An error status
     */
    static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *bias, const ITensorInfo *output, const ConvolutionInfo &info);
    /** Check if the optimized kernel can be used for the given kernel sizes and strides
     *
     * @warning Even if this return true the inputs and outputs might need to get permuted as the only layout supported is NHWC
     *
     * @param[in] input   Input tensor info.
     * @param[in] weights Weights tensor info.
     * @param[in] info    Depthwise convolution meta-data.
     *
     * @return True if the assembly kernel could be used else false. Note that transformations of input/output could be needed.
     */
    static bool is_optimized_supported(const ITensorInfo *input, const ITensorInfo *weights, const ConvolutionInfo &info);

    // Inherited methods overridden:
    void run(ITensorPack &tensors) override;
    void prepare(ITensorPack &tensors) override;
    experimental::MemoryRequirements workspace() const override;

private:
    struct LocalImpl;
    std::unique_ptr<LocalImpl> _pImpl;
};
} // namespace cpu
} // namespace arm_compute
#endif /* ARM_COMPUTE_CPU_DEPTHWISECONVOLUTIONASSEMBLYDISPATCH_H */