// Copyright © Advanced Micro Devices, Inc., or its affiliates.
// SPDX-License-Identifier:  MIT

#include <iostream>

#include <hipdnn_data_sdk/utilities/Tensor.hpp>
#include <hipdnn_data_sdk/utilities/Workspace.hpp>
#include <hipdnn_frontend.hpp>

#include "../utils.hpp"

int main()
{
    using InputType = float;

    const int64_t n = 1;
    const int64_t c = 32;
    const int64_t h = 128;
    const int64_t w = 128;
    const int64_t k = 32;
    auto buildScaleBiasReluConvwrwGraph = [=](hipdnnHandle_t handle) {
        auto graph = std::make_shared<hipdnn_frontend::graph::Graph>();
        graph->set_name("scale_bias_relu_convwrw_graph")
            .set_io_data_type(hipdnn_frontend::getDataTypeEnumFromType<InputType>())
            .set_intermediate_data_type(hipdnn_frontend::getDataTypeEnumFromType<InputType>())
            .set_compute_data_type(hipdnn_frontend::DataType::FLOAT);

        auto x = std::make_shared<hipdnn_frontend::graph::TensorAttributes>(
            hipdnn_frontend::graph::Tensor_attributes()
                .set_name("x")
                .set_dim({n, c, h, w})
                .set_stride({c * h * w, 1, c * w, c}));

        auto scale = std::make_shared<hipdnn_frontend::graph::TensorAttributes>(
            hipdnn_frontend::graph::Tensor_attributes()
                .set_name("scale")
                .set_dim({1, c, 1, 1})
                .set_stride({c, 1, c, c}));

        auto bias = std::make_shared<hipdnn_frontend::graph::TensorAttributes>(
            hipdnn_frontend::graph::Tensor_attributes()
                .set_name("bias")
                .set_dim({1, c, 1, 1})
                .set_stride({c, 1, c, c}));

        auto dy = std::make_shared<hipdnn_frontend::graph::TensorAttributes>(
            hipdnn_frontend::graph::Tensor_attributes()
                .set_name("dy")
                .set_dim({n, k, h, w})
                .set_stride({k * h * w, 1, k * w, k}));

        auto mulAttrs = hipdnn_frontend::graph::PointwiseAttributes()
                            .set_name("mul_node")
                            .set_mode(hipdnn_frontend::PointwiseMode::MUL);
        auto mulOut = graph->pointwise(x, scale, mulAttrs);

        auto addAttrs = hipdnn_frontend::graph::PointwiseAttributes()
                            .set_name("add_node")
                            .set_mode(hipdnn_frontend::PointwiseMode::ADD);
        auto addOut = graph->pointwise(mulOut, bias, addAttrs);

        auto reluAttrs = hipdnn_frontend::graph::PointwiseAttributes()
                             .set_name("relu_fwd_node")
                             .set_mode(hipdnn_frontend::PointwiseMode::RELU_FWD);
        auto reluOut = graph->pointwise(addOut, reluAttrs);

        auto convAttrs = hipdnn_frontend::graph::ConvWgradAttributes()
                             .set_name("conv_wgrad_node")
                             .set_padding({1, 1})
                             .set_stride({1, 1})
                             .set_dilation({1, 1});
        auto dw = graph->conv_wgrad(dy, reluOut, convAttrs);
        dw->set_output(true);

        HIPDNN_FE_CHECK(graph->build(handle));

        return std::make_tuple(graph, x, scale, bias, dy, dw);
    };

    auto backend = hipdnn_frontend::detail::hipdnnBackend();
    if(!backend)
    {
        std::cout << "Creat backend failed. \n";
        return 1;
    }

    hipdnnHandle_t handle;
    HIPDNN_CHECK(backend->create(&handle));

    auto [graph, x, scale, bias, dy, dw] = buildScaleBiasReluConvwrwGraph(handle);

    hipdnn_data_sdk::utilities::Tensor<InputType> xTensor(x->get_dim(), x->get_stride());
    hipdnn_data_sdk::utilities::Tensor<InputType> scaleTensor(scale->get_dim(),
                                                              scale->get_stride());
    hipdnn_data_sdk::utilities::Tensor<InputType> biasTensor(bias->get_dim(), bias->get_stride());
    hipdnn_data_sdk::utilities::Tensor<InputType> dyTensor(dy->get_dim(), dy->get_stride());
    hipdnn_data_sdk::utilities::Tensor<InputType> dwTensor(dw->get_dim(), dw->get_stride());

    std::unordered_map<int64_t, void*> variantPack;
    variantPack[x->get_uid()] = xTensor.memory().deviceData();
    variantPack[scale->get_uid()] = scaleTensor.memory().deviceData();
    variantPack[bias->get_uid()] = biasTensor.memory().deviceData();
    variantPack[dy->get_uid()] = dyTensor.memory().deviceData();
    variantPack[dw->get_uid()] = dwTensor.memory().deviceData();

    int64_t workspaceSize = 0;
    HIPDNN_FE_CHECK(graph->get_workspace_size(workspaceSize));
    const hipdnn_data_sdk::utilities::Workspace workspace(static_cast<size_t>(workspaceSize));

    HIPDNN_FE_CHECK(graph->execute(handle, variantPack, workspace.get()));

    std::cout << "ScaleBiasReluConvwrw graph execution complete. \n";

    HIPDNN_CHECK(backend->destroy(handle));
    return 0;
}