/**
 * Copyright (c) 2025 Huawei Technologies Co., Ltd.
 * This program is free software, you can redistribute it and/or modify it under the terms and conditions of
 * CANN Open Software License Agreement Version 2.0 (the "License").
 * Please refer to the License for details. You may not use this file except in compliance with the License.
 * THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED,
 * INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
 * See LICENSE in the root of the software repository for the full text of the License.
 */
/**
 * @brief 编译运行流程说明
 * 
 * 参照 docs/zh/invocation/op_invocation.md 内 [编译与运行] 章节调用
 * 
 * 调用流程示例：
 * 1. 安装nn包: 
 *  ./cann-${soc_name}-ops-nn_${cann_version}_linux-${arch}.run --full --install-path=/usr/local/Ascend/ascend-toolkit
 *  export ASCEND_OPS_NN_PATH=/usr/local/Ascend/ascend-toolkit/latest/ops_nn
 * 2. 执行example:
 *  bash build.sh --run_example convolution_backward eager --example_name=conv_backward_1d
 */
#include <iostream>
#include <memory>
#include <vector>

#include "acl/acl.h"
#include "aclnnop/aclnn_convolution_backward.h"

#define CHECK_RET(cond, return_expr) \
    do {                             \
        if (!(cond)) {               \
            return_expr;             \
        }                            \
    } while (0)

#define CHECK_FREE_RET(cond, return_expr)        \
    do {                                         \
        if (!(cond)) {                           \
            Finalize(deviceId, stream); \
            return_expr;                         \
        }                                        \
    } while (0)

#define LOG_PRINT(message, ...)         \
    do {                                \
        printf(message, ##__VA_ARGS__); \
    } while (0)

int64_t GetShapeSize(const std::vector<int64_t> &shape)
{
    int64_t shapeSize = 1;
    for (auto i : shape) {
        shapeSize *= i;
    }
    return shapeSize;
}

int Init(int32_t deviceId, aclrtStream *stream)
{
    // 固定写法，资源初始化
    auto ret = aclInit(nullptr);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclInit failed. ERROR: %d\n", ret); return ret);
    ret = aclrtSetDevice(deviceId);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSetDevice failed. ERROR: %d\n", ret); return ret);
    ret = aclrtCreateStream(stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtCreateStream failed. ERROR: %d\n", ret); return ret);
    return 0;
}

template <typename T>
int CreateAclTensor(const std::vector<T> &hostData, const std::vector<int64_t> &shape, void **DeviceAddr,
                    aclDataType dataType, aclTensor **tensor)
{
    auto size = GetShapeSize(shape) * sizeof(T);
    // 调用aclrtMalloc申请device侧内存
    auto ret = aclrtMalloc(DeviceAddr, size, ACL_MEM_MALLOC_HUGE_FIRST);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMalloc failed. ERROR: %d\n", ret); return ret);
    // 调用aclrtMemcpy将host侧数据拷贝到device侧内存上
    ret = aclrtMemcpy(*DeviceAddr, size, hostData.data(), size, ACL_MEMCPY_HOST_TO_DEVICE);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMemcpy failed. ERROR: %d\n", ret); return ret);

    // 计算连续tensor的strides
    std::vector<int64_t> strides(shape.size(), 1);
    for (int64_t i = shape.size() - 2; i >= 0; i--) {
        strides[i] = shape[i + 1] * strides[i + 1];
    }

    // 调用aclCreateTensor接口创建aclTensor
    if (shape.size() == 3) {
        *tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_NCL,
                                  shape.data(), shape.size(), *DeviceAddr);
    } else {
        *tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_ND,
                                  shape.data(), shape.size(), *DeviceAddr);
    }

    return 0;
}

void Finalize(int32_t deviceId, aclrtStream stream)
{
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
}

int aclnnConvolutionBackwardTest(int32_t deviceId, aclrtStream &stream)
{
    // 1. 初始化
    auto ret = Init(deviceId, &stream);
    CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
    // 2. 构造输入与输出，需要根据API的接口自定义构造
    std::vector<int64_t> gradOutputShape = {4, 2, 3};
    std::vector<int64_t> inputShape = {4, 2, 9};
    std::vector<int64_t> weightShape = {2, 2, 3};
    std::vector<int64_t> biasSize = {2};
    std::vector<int64_t> stride = {3};
    std::vector<int64_t> padding = {0};
    std::vector<int64_t> dilation = {1};
    bool transposed = false;
    std::vector<int64_t> outputPadding = {0};
    int groups = 1;
    bool outputMask[3] = {true, true, true};
    int8_t cubeMathType = 0;

    std::vector<int64_t> gradInputShape = {4, 2, 9};
    std::vector<int64_t> gradWeightShape = {2, 2, 3};
    std::vector<int64_t> gradBiasShape = {2};

    // 创建gradOutput aclTensor
    std::vector<float> gradOutputData(GetShapeSize(gradOutputShape), 1);
    aclTensor *gradOutput = nullptr;
    void *gradOutputDeviceAddr = nullptr;
    ret = CreateAclTensor(gradOutputData, gradOutputShape, &gradOutputDeviceAddr, aclDataType::ACL_FLOAT, &gradOutput);
    std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> gradOutputTensorPtr(gradOutput, aclDestroyTensor);
    std::unique_ptr<void, aclError (*)(void *)> gradOutputDeviceAddrPtr(gradOutputDeviceAddr, aclrtFree);
    CHECK_FREE_RET(ret == ACL_SUCCESS, return ret);

    // 创建input aclTensor
    std::vector<float> inputData(GetShapeSize(inputShape), 1);
    aclTensor *input = nullptr;
    void *inputDeviceAddr = nullptr;
    ret = CreateAclTensor(inputData, inputShape, &inputDeviceAddr, aclDataType::ACL_FLOAT, &input);
    std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> inputTensorPtr(input, aclDestroyTensor);
    std::unique_ptr<void, aclError (*)(void *)> inputDeviceAddrPtr(inputDeviceAddr, aclrtFree);
    CHECK_FREE_RET(ret == ACL_SUCCESS, return ret);

    // 创建weight aclTensor
    std::vector<float> weightData(GetShapeSize(weightShape), 1);
    aclTensor *weight = nullptr;
    void *weightDeviceAddr = nullptr;
    ret = CreateAclTensor(weightData, weightShape, &weightDeviceAddr, aclDataType::ACL_FLOAT, &weight);
    std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> weightTensorPtr(weight, aclDestroyTensor);
    std::unique_ptr<void, aclError (*)(void *)> weightDeviceAddrPtr(weightDeviceAddr, aclrtFree);
    CHECK_FREE_RET(ret == ACL_SUCCESS, return ret);

    // 创建gradInput aclTensor
    std::vector<float> gradInputData(GetShapeSize(inputShape), 1);
    aclTensor *gradInput = nullptr;
    void *gradInputDeviceAddr = nullptr;
    ret = CreateAclTensor(gradInputData, inputShape, &gradInputDeviceAddr, aclDataType::ACL_FLOAT, &gradInput);
    std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> gradInputTensorPtr(gradInput, aclDestroyTensor);
    std::unique_ptr<void, aclError (*)(void *)> gradInputDeviceAddrPtr(gradInputDeviceAddr, aclrtFree);
    CHECK_FREE_RET(ret == ACL_SUCCESS, return ret);

    // 创建gradWeight aclTensor
    std::vector<float> gradWeightData(GetShapeSize(weightShape), 1);
    aclTensor *gradWeight = nullptr;
    void *gradWeightDeviceAddr = nullptr;
    ret = CreateAclTensor(gradWeightData, weightShape, &gradWeightDeviceAddr, aclDataType::ACL_FLOAT, &gradWeight);
    std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> gradWeightTensorPtr(gradWeight, aclDestroyTensor);
    std::unique_ptr<void, aclError (*)(void *)> gradWeightDeviceAddrPtr(gradWeightDeviceAddr, aclrtFree);
    CHECK_FREE_RET(ret == ACL_SUCCESS, return ret);

    // 创建gradBias aclTensor
    std::vector<float> gradBiasData(GetShapeSize(biasSize), 1);
    aclTensor *gradBias = nullptr;
    void *gradBiasDeviceAddr = nullptr;
    ret = CreateAclTensor(gradBiasData, biasSize, &gradBiasDeviceAddr, aclDataType::ACL_FLOAT, &gradBias);
    std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> gradBiasTensorPtr(gradBias, aclDestroyTensor);
    std::unique_ptr<void, aclError (*)(void *)> gradBiasDeviceAddrPtr(gradBiasDeviceAddr, aclrtFree);
    CHECK_FREE_RET(ret == ACL_SUCCESS, return ret);

    // 创建biasSizes aclIntArray
    aclIntArray *biasSizes = aclCreateIntArray(biasSize.data(), 1);
    std::unique_ptr<aclIntArray, aclnnStatus (*)(const aclIntArray *)> biasSizesPtr(biasSizes, aclDestroyIntArray);
    CHECK_FREE_RET(biasSizes != nullptr, return ACL_ERROR_INTERNAL_ERROR);

    // 创建strides aclIntArray
    aclIntArray *strides = aclCreateIntArray(stride.data(), 1);
    std::unique_ptr<aclIntArray, aclnnStatus (*)(const aclIntArray *)> stridesPtr(strides, aclDestroyIntArray);
    CHECK_FREE_RET(strides != nullptr, return ACL_ERROR_INTERNAL_ERROR);

    // 创建pads aclIntArray
    aclIntArray *pads = aclCreateIntArray(padding.data(), 1);
    std::unique_ptr<aclIntArray, aclnnStatus (*)(const aclIntArray *)> padsPtr(pads, aclDestroyIntArray);
    CHECK_FREE_RET(pads != nullptr, return ACL_ERROR_INTERNAL_ERROR);

    // 创建dilations aclIntArray
    aclIntArray *dilations = aclCreateIntArray(dilation.data(), 1);
    std::unique_ptr<aclIntArray, aclnnStatus (*)(const aclIntArray *)> dilationsPtr(dilations, aclDestroyIntArray);
    CHECK_FREE_RET(dilations != nullptr, return ACL_ERROR_INTERNAL_ERROR);

    // 创建outputPads aclIntArray
    aclIntArray *outputPads = aclCreateIntArray(outputPadding.data(), 1);
    std::unique_ptr<aclIntArray, aclnnStatus (*)(const aclIntArray *)> outputPadsPtr(outputPads, aclDestroyIntArray);
    CHECK_FREE_RET(outputPads != nullptr, return ACL_ERROR_INTERNAL_ERROR);

    // 创建outMask aclBoolArray
    aclBoolArray *outMask = aclCreateBoolArray(outputMask, 3);
    std::unique_ptr<aclBoolArray, aclnnStatus (*)(const aclBoolArray *)> outMaskPtr(outMask, aclDestroyBoolArray);
    CHECK_FREE_RET(outMask != nullptr, return ACL_ERROR_INTERNAL_ERROR);

    // 3. 调用CANN算子库API，需要修改为具体的Api名称
    uint64_t workspaceSize = 0;
    aclOpExecutor *executor;
    // 调用aclnnConvolutionBackwardGetWorkspaceSize第一段接口
    ret = aclnnConvolutionBackwardGetWorkspaceSize(gradOutput, input, weight, biasSizes, strides, pads, dilations,
                                                   transposed, outputPads, groups, outMask, cubeMathType, gradInput,
                                                   gradWeight, gradBias, &workspaceSize, &executor);
    CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnConvolutionBackwardGetWorkspaceSize failed. ERROR: %d\n", ret);
                   return ret);
    // 根据第一段接口计算出的workspaceSize申请device内存
    void *workspaceAddr = nullptr;
    std::unique_ptr<void, aclError (*)(void *)> workspaceAddrPtr(nullptr, aclrtFree);
    if (workspaceSize > 0) {
        ret = aclrtMalloc(&workspaceAddr, workspaceSize, ACL_MEM_MALLOC_HUGE_FIRST);
        CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
        workspaceAddrPtr.reset(workspaceAddr);
    }
    // 调用aclnnConvolutionBackward第二段接口
    ret = aclnnConvolutionBackward(workspaceAddr, workspaceSize, executor, stream);
    CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnConvolutionBackward failed. ERROR: %d\n", ret); return ret);
    // 4. （固定写法）同步等待任务执行结束
    ret = aclrtSynchronizeStream(stream);
    CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
    // 5. 获取输出的值，将device侧内存上的结果拷贝至host侧，需要根据具体API的接口定义修改
    auto size = GetShapeSize(gradInputShape);
    std::vector<float> gradInputResult(size, 0);
    ret = aclrtMemcpy(gradInputResult.data(), gradInputResult.size() * sizeof(gradInputResult[0]), gradInputDeviceAddr,
                      size * sizeof(gradInputResult[0]), ACL_MEMCPY_DEVICE_TO_HOST);
    CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret);
                   return ret);
    for (int64_t i = 0; i < size; i++) {
        LOG_PRINT("gradInputResult[%ld] is: %f\n", i, gradInputResult[i]);
    }

    size = GetShapeSize(gradWeightShape);
    std::vector<float> gradWeightResult(size, 0);
    ret = aclrtMemcpy(gradWeightResult.data(), gradWeightResult.size() * sizeof(gradWeightResult[0]), gradWeightDeviceAddr,
                      size * sizeof(gradWeightResult[0]), ACL_MEMCPY_DEVICE_TO_HOST);
    CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret);
                   return ret);
    for (int64_t i = 0; i < size; i++) {
        LOG_PRINT("gradWeightResult[%ld] is: %f\n", i, gradWeightResult[i]);
    }

    size = GetShapeSize(gradBiasShape);
    std::vector<float> gradBiasResult(size, 0);
    ret = aclrtMemcpy(gradBiasResult.data(), gradBiasResult.size() * sizeof(gradBiasResult[0]), gradBiasDeviceAddr,
                      size * sizeof(gradBiasResult[0]), ACL_MEMCPY_DEVICE_TO_HOST);
    CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret);
                   return ret);
    for (int64_t i = 0; i < size; i++) {
        LOG_PRINT("gradBiasResult[%ld] is: %f\n", i, gradBiasResult[i]);
    }
    return ACL_SUCCESS;
}

int main()
{
    // 1. （固定写法）device/stream初始化
    // 根据自己的实际device填写deviceId
    int32_t deviceId = 0;
    aclrtStream stream;
    auto ret = aclnnConvolutionBackwardTest(deviceId, stream);
    CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnConvolutionBackwardTest failed. ERROR: %d\n", ret); return ret);

    Finalize(deviceId, stream);
    return 0;
}