#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 = 32; // Height
    const int64_t w = 32; // Width
    const int32_t blockSize = 1;

    auto buildBlockScaleQuantizeGraph = [=](hipdnnHandle_t handle) {
        auto graph = std::make_shared<hipdnn_frontend::graph::Graph>();
        graph->set_name("block_scale_quantize_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 blockScaleQuantizeAttributes = hipdnn_frontend::graph::BlockScaleQuantizeAttributes()
                                                .set_name("block_scale_quantize_node")
                                                .set_block_size(blockSize);

        auto [y, scale] = graph->block_scale_quantize(x, blockScaleQuantizeAttributes);
        y->set_output(true);
        scale->set_output(true);

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

        return std::make_tuple(graph, x, y, scale);
    };

    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, y, scale] = buildBlockScaleQuantizeGraph(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> yTensor(y->get_dim(), y->get_stride());

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

    std::unordered_map<int64_t, void*> variantPack;
    variantPack[x->get_uid()] = xTensor.memory().deviceData();
    variantPack[scale->get_uid()] = scaleTensor.memory().deviceData();
    variantPack[y->get_uid()] = yTensor.memory().deviceData();

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

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

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