// 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 = 4;
    const int64_t c = 64;
    const int64_t h = 16;
    const int64_t w = 16;
    const int64_t k = 32;
    const int64_t r = 3;
    const int64_t s = 3;

    auto buildConvGenstatsGraph = [=](hipdnnHandle_t handle) {
        auto graph = std::make_shared<hipdnn_frontend::graph::Graph>();
        graph->set_name("conv_genstats_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 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, 1, c * s, c}));

        auto convAttrs = hipdnn_frontend::graph::ConvFpropAttributes()
                             .set_name("conv_fprop_node")
                             .set_padding({1, 1})
                             .set_stride({1, 1})
                             .set_dilation({1, 1});
        auto y = graph->conv_fprop(x, filter, convAttrs);

        auto genstatsAttrs = hipdnn_frontend::graph::GenstatsAttributes().set_name("genstats_node");
        auto [sum, sqSum] = graph->genstats(y, genstatsAttrs);

        y->set_output(true);
        sum->set_output(true);
        sqSum->set_output(true);

        HIPDNN_FE_CHECK(graph->build(handle));

        return std::make_tuple(graph, x, filter, y, sum, sqSum);
    };

    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, filter, y, sum, sqSum] = buildConvGenstatsGraph(handle);

    hipdnn_data_sdk::utilities::Tensor<InputType> xTensor(x->get_dim(), x->get_stride());
    hipdnn_data_sdk::utilities::Tensor<InputType> filterTensor(filter->get_dim(),
                                                               filter->get_stride());
    hipdnn_data_sdk::utilities::Tensor<InputType> yTensor(y->get_dim(), y->get_stride());
    hipdnn_data_sdk::utilities::Tensor<InputType> sumTensor(sum->get_dim(), sum->get_stride());
    hipdnn_data_sdk::utilities::Tensor<InputType> sqSumTensor(sqSum->get_dim(),
                                                              sqSum->get_stride());

    std::unordered_map<int64_t, void*> variantPack;
    variantPack[x->get_uid()] = xTensor.memory().deviceData();
    variantPack[filter->get_uid()] = filterTensor.memory().deviceData();
    variantPack[y->get_uid()] = yTensor.memory().deviceData();
    variantPack[sum->get_uid()] = sumTensor.memory().deviceData();
    variantPack[sqSum->get_uid()] = sqSumTensor.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 << "ConvGenstats graph execution complete. \n";

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