ConvDepthWiseImpl.cpp

/********************************************************************************
 * Copyright (c) 2023 CEA-List
 *
 * This program and the accompanying materials are made available under the
 * terms of the Eclipse Public License 2.0 which is available at
 * http://www.eclipse.org/legal/epl-2.0.
 *
 * SPDX-License-Identifier: EPL-2.0
 *
 ********************************************************************************/

#include <cassert>
#include <chrono>  // std::chrono::milliseconds
#include <numeric> // std::accumulate
#include <thread>  // std::this_thread::sleep_for
#include <vector>

#include "aidge/utils/Types.h"
#include "aidge/operator/ConvDepthWise.hpp"

#include "aidge/backend/cpu/operator/ConvDepthWiseImpl.hpp"
#include "aidge/backend/cpu/operator/ConvDepthWiseImpl_forward_kernels.hpp"

Aidge::NbElts_t Aidge::ConvDepthWiseImpl2D_cpu::getNbRequiredProtected(IOIndex_t /*inputIdx*/) const {
    // this implementation can be in-place
    return 0;
}

void Aidge::ConvDepthWiseImpl2D_cpu::forward() {
    assert(mOp.getRawInput(0) && "missing input #0");
    assert(mOp.getRawInput(1) && "missing input #1");
    assert(mOp.getRawInput(2) && "missing input #2");

    assert((std::static_pointer_cast<Tensor>(mOp.getRawInput(0))->nbDims() == 4) && "support for 4-dimensions tensors only");

    // Find the correct kernel type
    auto kernelFunc =
            Registrar<ConvDepthWiseImpl2DForward_cpu>::create({std::static_pointer_cast<Tensor>(mOp.getRawInput(0))->dataType(),
                                                               std::static_pointer_cast<Tensor>(mOp.getRawInput(1))->dataType(),
                                                               std::static_pointer_cast<Tensor>(mOp.getRawInput(2))->dataType(),
                                                               std::static_pointer_cast<Tensor>(mOp.getRawOutput(0))->dataType()});

    // Call kernel
    kernelFunc(dynamic_cast<const ConvDepthWise_Op<2>&>(mOp).getStaticAttributes(), std::static_pointer_cast<Tensor>(mOp.getRawInput(0))->template dims<4>(),
               std::static_pointer_cast<Tensor>(mOp.getRawInput(0))->getImpl()->rawPtr(),
               std::static_pointer_cast<Tensor>(mOp.getRawInput(1))->getImpl()->rawPtr(),
               std::static_pointer_cast<Tensor>(mOp.getRawInput(2))->getImpl()->rawPtr(),
               std::static_pointer_cast<Tensor>(mOp.getRawOutput(0))->getImpl()->rawPtr());
}