src/gpu/cl/operators/ClDirectConv2d.h

/*
 * Copyright (c) 2021, 2023 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_CL_DIRECT_CONV2D_H
#define ARM_COMPUTE_CL_DIRECT_CONV2D_H

#include "arm_compute/function_info/ActivationLayerInfo.h"
#include "src/gpu/cl/ClCompileContext.h"
#include "src/gpu/cl/IClKernel.h"
#include "src/gpu/cl/IClOperator.h"

#include <memory>

namespace arm_compute
{
namespace opencl
{
/** Basic function to simulate a directly convolution layer. This function calls the following OpenCL kernels:
 *
 * -# @ref CLFillBorderKernel (executed if padding size is different from zero)
 * -# @ref opencl::ClDirectConv2d
 */
class ClDirectConv2d : public IClOperator
{
public:
    ClDirectConv2d() = default;
    /** Set the src and dst tensors.
     *
     * @param[in]  compile_context The compile context to be used.
     * @param[in]  src             Source tensor. 3 lower dimensions represent a single src [width, height, IFM],
     *                             while every optional dimension from 4 and above represent a batch of srcs.
     *                             Data types supported: QASYMM8_SIGNED/QASYMM8/F16/F32.
     * @param[in]  weights         Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported:Same as @p src.
     * @param[in]  biases          Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
     *                             Data type supported: Should match @p src data type, except for src of QASYMM8 and QASYMM8_SIGNED type where biases should be of S32 type.
     * @param[out] dst             Destination tensor. 3 lower dimensions represent a single dst [width, height, OFM], while the rest represent batch of dsts.
     *                             Data types supported: Same as @p src.
     * @param[in]  conv_info       Contains padding and stride information described in @ref PadStrideInfo.
     * @param[in]  act_info        (Optional) Activation layer information in case of a fused activation.
     *
     */
    void configure(const CLCompileContext &compile_context, ITensorInfo *src, ITensorInfo *weights, ITensorInfo *biases, ITensorInfo *dst, const PadStrideInfo &conv_info,
                   const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Static function to check if given info will lead to a valid configuration
     *
     * Similar to ClDirectConv2d::configure()
     *
     * @return a status
     */
    static Status validate(const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *dst, const PadStrideInfo &conv_info,
                           const ActivationLayerInfo &act_info = ActivationLayerInfo());

    // Inherited method overridden
    void run(ITensorPack &tensors) override;

private:
    std::unique_ptr<IClKernel> _direct_conv_kernel{ nullptr };
    std::unique_ptr<IClKernel> _src_border_handler{ nullptr };
    std::unique_ptr<IClKernel> _activation_kernel{ nullptr };
};
} // namespace opencl
} // namespace arm_compute
#endif /* ARM_COMPUTE_CL_DIRECT_CONV2D_H */