#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 = hipdnn_data_sdk::types::half;

    const int64_t n = 2; // Batch size
    // Input
    const int64_t c = 32; // Number of channels
    const int64_t h = 16; // Height
    const int64_t w = 8; // Width

    // Filter
    const int64_t k = 128; // Number of filters
    const int64_t r = 1; // Height
    const int64_t s = 1; // Width

    // Conv param
    const std::vector<int64_t> strides = {1, 1};
    const std::vector<int64_t> padding = {0, 0};
    const std::vector<int64_t> dilation = {1, 1};
    const int64_t vectorCount = 16;

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

        graph->set_name("fp16_conv_bias_relu_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); //

        // create conv
        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})
                .set_vector_count(vectorCount));
        auto filter = std::make_shared<hipdnn_frontend::graph::TensorAttributes>(
            hipdnn_frontend::graph::Tensor_attributes()
                .set_name("filter")
                .set_dim({k, c, r, s})
                .set_stride({c * r * s, r * s, s, 1})
                .set_vector_count(vectorCount));
        auto convFpropAttributes = hipdnn_frontend::graph::ConvFpropAttributes()
                                       .set_name("conv_fprop_node")
                                       .set_padding(padding)
                                       .set_stride(strides)
                                       .set_dilation(dilation);
        auto convOutput = graph->conv_fprop(input, filter, convFpropAttributes);

        // create bias
        auto bias = std::make_shared<hipdnn_frontend::graph::TensorAttributes>(
            hipdnn_frontend::graph::Tensor_attributes()
                .set_name("bias")
                .set_dim({1, k, 1, 1})
                .set_stride({k, 1, k, k}));
        auto biasAttributes = hipdnn_frontend::graph::PointwiseAttributes()
                                  .set_name("bias_node")
                                  .set_mode(hipdnn_frontend::PointwiseMode_t::ADD);
        auto biasOutput = graph->pointwise(convOutput, bias, biasAttributes);

        // create relu
        auto reluAttributes = hipdnn_frontend::graph::PointwiseAttributes()
                                  .set_name("relu_node")
                                  .set_mode(hipdnn_frontend::PointwiseMode_t::RELU_FWD);
        auto output = graph->pointwise(biasOutput, reluAttributes);
        output->set_output(true).set_vector_count(vectorCount);

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

        return std::make_tuple(graph, input, filter, bias, output);
    };

    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, filter, bias, output] = buildConvBiasReluGraph(handle);

    // Allocate DCU memory
    hipdnn_data_sdk::utilities::Tensor<InputType> inputTensor(input->get_dim(),
                                                              input->get_stride());
    hipdnn_data_sdk::utilities::Tensor<InputType> wTensor(filter->get_dim(), filter->get_stride());
    hipdnn_data_sdk::utilities::Tensor<InputType> biasTensor(bias->get_dim(), bias->get_stride());
    hipdnn_data_sdk::utilities::Tensor<InputType> outTensor(output->get_dim(),
                                                            output->get_stride());

    std::unordered_map<int64_t, void*> variantPack;
    variantPack[input->get_uid()] = inputTensor.memory().deviceData();
    variantPack[filter->get_uid()] = wTensor.memory().deviceData();
    variantPack[bias->get_uid()] = biasTensor.memory().deviceData();
    variantPack[output->get_uid()] = outTensor.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 << "fp16_convolution_bias_relu graph execution complete. \n";

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