#include <iostream>

#include "utils.hpp"

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

int main()
{
    using InputType = float;

    const int64_t n = 1; // Batch size
    const int64_t c = 2; // Number of channels
    const int64_t h = 3; // Height
    const int64_t w = 4; // Width

    auto buildInstancenormTrainingGraph = [=](hipdnnHandle_t handle) {
        auto graph = std::make_shared<hipdnn_frontend::graph::Graph>();

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

        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, 1, 1}));

        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, 1, 1}));

        auto epsilon = std::make_shared<hipdnn_frontend::graph::TensorAttributes>(
            hipdnn_frontend::graph::Tensor_attributes().set_name("epsilon").set_value(1e-5f));

        auto instancenormAttributes
            = hipdnn_frontend::graph::InstancenormAttributes()
                  .set_name("instancenorm_training_node")
                  .set_epsilon(epsilon)
                  .set_forward_phase(hipdnn_frontend::NormFwdPhase_t::TRAINING);

        auto [output, mean, invVariance]
            = graph->instancenorm(input, scale, bias, instancenormAttributes);
        output->set_output(true);
        mean->set_output(true);
        invVariance->set_output(true);

        // build graph
        HIPDNN_FE_CHECK(graph->build(handle));

        return std::make_tuple(graph, input, scale, bias, output, mean, invVariance);
    };

    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, input, scale, bias, output, mean, invVariance]
        = buildInstancenormTrainingGraph(handle);

    hipdnn_data_sdk::utilities::Tensor<InputType> inputTensor(input->get_dim(),
                                                              input->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> outputTensor(output->get_dim(),
                                                               output->get_stride());
    hipdnn_data_sdk::utilities::Tensor<InputType> meanTensor(mean->get_dim(), mean->get_stride());
    hipdnn_data_sdk::utilities::Tensor<InputType> invVarianceTensor(invVariance->get_dim(),
                                                                    invVariance->get_stride());

    std::unordered_map<int64_t, void*> variantPack;
    variantPack[input->get_uid()] = inputTensor.memory().deviceData();
    variantPack[scale->get_uid()] = scaleTensor.memory().deviceData();
    variantPack[bias->get_uid()] = biasTensor.memory().deviceData();
    variantPack[output->get_uid()] = outputTensor.memory().deviceData();
    variantPack[mean->get_uid()] = meanTensor.memory().deviceData();
    variantPack[invVariance->get_uid()] = invVarianceTensor.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 << "Instancenorm_training graph execution complete. \n";

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