Dot

产品支持情况

产品	是否支持
Atlas 200I/500 A2 推理产品	×
Atlas 推理系列产品	×
Atlas 训练系列产品	×
Atlas A3 训练系列产品/Atlas A3 推理系列产品	√
Atlas A2 训练系列产品/Atlas A2 推理系列产品	√
Ascend 950PR/Ascend 950DT	×

功能说明

接口功能：
asdBlasMakeDotPlan：初始化该句柄对应的Dot算子配置。
asdBlasSdot：计算两个实数向量的点积。
asdBlasCdotu：计算两个复数向量的点积。
asdBlasCdotc：计算一个复数向量取共轭后和另一个复数向量的点积。

计算公式：

asdBlasSdot的公式

result=∑i=1n(x[i]∗y[i])result=\sum _{i=1}^n(x[i] * y[i])

  示例：
   输入“x”为：
  [1.0, 2.0]
  输入“y”为：
  [1.0, 2.0]
  调用asdBlasSdot算子后，输出“result”为：
  5.0

asdBlasCdotu的公式

result=∑i=1n(conj(x[i])∗y[i])result=\sum _{i=1}^n(conj(x[i]) * y[i])

  其中，x[i]和y[i]是复数，conj为共轭操作。
  示例：
  输入“x”为：
  [ 0.1554+0.8840j, -0.3564-0.2552j]
  输入“y”为：
  [-0.1404+1.3380j, -0.4876+0.1842j]
  调用asdBlasCdotu算子后，输出“result”为：
  1.2877-0.1420j

asdBlasCdotc的公式

result=∑i=1n(conj(x[i])∗y[i])result=\sum _{i=1}^n(conj(x[i]) * y[i])

  其中，x[i]和y[i]是复数,conj共轭操作。
  示例：
  输入“x”为：
  [ 0.1554+0.8840j, -0.3564-0.2552j]
  输入“y”为：
  [-0.1404+1.3380j, -0.4876+0.1842j]
  调用asdBlasCdotc算子后，输出“result”为：
  1.2877-0.1420j

函数原型

AspbStatus asdBlasMakeDotPlan(
  asdBlasHandle handle)

AspbStatus asdBlasSdot(
  asdBlasHandle      handle, 
  const int64_t      n, 
  aclTensor *        x, 
  const int64_t      incx, 
  aclTensor *        y,
  const int64_t      incy, 
  aclTensor *        result)

AspbStatus asdBlasCdotu(
  asdBlasHandle      handle, 
  const int64_t      n, 
  aclTensor *        x, 
  const int64_t      incx, 
  aclTensor *        y,
  const int64_t      incy, 
  aclTensor *        result)

AspbStatus asdBlasCdotc(
  asdBlasHandle         handle, 
  const int64_t         n, 
  aclTensor *           x, 
  const int64_t         incx, 
  aclTensor *           y,
  const int64_t         incy, 
  aclTensor *           result)

asdBlasMakeDotPlan

参数说明：

参数名输入/输出描述

handle（asdBlasHandle）输入算子的句柄
返回值：

返回状态码，具体参见SiP返回码。

asdBlasSdot & asdBlasCdotu & asdBlasCdotc

参数说明：

参数名	输入/输出	描述
handle（asdBlasHandle）	输入	算子的句柄
n（int64_t）	输入	向量x或向量y中的元素个数。
x（aclTensor *）	输入	对应公式中的'x'。 asdBlasSdot支持的数据类型支持FLOAT32。 asdBlasCdotu & asdBlasCdotc支持的数据类型支持COMPLEX64。数据格式支持ND。 shape为[n]。
incx（int64_t）	输入	向量x相邻元素间的内存地址偏移量（当前约束为1）。
y（aclTensor *）	输入	对应公式中的'y'。 asdBlasSdot支持的数据类型支持FLOAT32。 asdBlasCdotu & asdBlasCdotc支持的数据类型支持COMPLEX64。数据格式支持ND。 shape为[n]。
incy（int64_t）	输入	向量y相邻元素间的内存地址偏移量（当前约束为1）。
result（aclTensor *）	输出	表示输出的结果，对应公式中的'result'。数据类型支持FLOAT32，只包含一个元素。数据格式支持ND。 shape为[1]。

返回值：

返回状态码，具体参见SiP返回码。

约束说明

输入的元素个数n当前覆盖支持[1,6.71e+06]。
算子输入shape为[n]，输出shape为[1]。
算子实际计算时，不支持ND高维度运算（不支持维度≥3的运算）。

调用示例

示例代码如下，该样例旨在提供快速上手、开发和调试算子的最小化实现，其核心目标是使用最精简的代码展示算子的核心功能，而非提供生产级的安全保障。不推荐用户直接将示例代码作为业务代码，若用户将示例代码应用在自身的真实业务场景中且发生了安全问题，则需用户自行承担。

asdBlasSdot

#include <iostream>
#include <vector>
#include "asdsip.h"
#include "acl/acl.h"
#include "acl_meta.h"

using namespace AsdSip;

#define ASD_STATUS_CHECK(err)                                                \
    do {                                                                     \
        AsdSip::AspbStatus err_ = (err);                                     \
        if (err_ != AsdSip::ErrorType::ACL_SUCCESS) {                                      \
            std::cout << "Execute failed." << std::endl; \
            exit(-1);                                                        \
        }                                                                    \
    } while (0)

#define CHECK_RET(cond, return_expr) \
    do {                             \
        if (!(cond)) {               \
            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，acl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侧数据复制到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
    *tensor = aclCreateTensor(shape.data(),
        shape.size(),
        dataType,
        strides.data(),
        0,
        aclFormat::ACL_FORMAT_ND,
        shape.data(),
        shape.size(),
        *deviceAddr);
    return 0;
}

int main(int argc, char **argv)
{
    // 设置算子使用的device id
    int deviceId = 0;
    //（固定写法）创造执行流
    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    CHECK_RET(ret == ::ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

    // 创造tensor的Host侧数据
    int64_t n = 5;
    int64_t incx = 1;
    int64_t incy = 1;

    int64_t xSize = 5;
    std::vector<float> tensorInXData;
    tensorInXData.reserve(xSize);
    for (int64_t i = 0; i < xSize; i++) {
        tensorInXData[i] = 1.0 + i;
    }

    int64_t ySize = 5;
    std::vector<float> tensorInYData;
    tensorInYData.reserve(xSize);
    for (int64_t i = 0; i < ySize; i++) {
        tensorInYData[i] = 10.0 + i;
    }

    int64_t resultSize = 1;
    std::vector<float> resultData;
    resultData.reserve(resultSize);

    std::cout << "------- input x -------" << std::endl;
    for (int64_t i = 0; i < xSize; i++) {
        std::cout << tensorInXData[i] << " ";
    }
    std::cout << std::endl;

    std::cout << "------- input y -------" << std::endl;
    for (int64_t i = 0; i < ySize; i++) {
        std::cout << tensorInYData[i] << " ";
    }
    std::cout << std::endl;

    // 创造输入/输出tensor
    std::vector<int64_t> xShape = {xSize};
    std::vector<int64_t> yShape = {ySize};
    std::vector<int64_t> resultShape = {resultSize};
    aclTensor *inputX = nullptr;
    aclTensor *inputY = nullptr;
    aclTensor *result = nullptr;
    void *inputXDeviceAddr = nullptr;
    void *inputYDeviceAddr = nullptr;
    void *resultDeviceAddr = nullptr;
    ret = CreateAclTensor(tensorInXData, xShape, &inputXDeviceAddr, aclDataType::ACL_FLOAT, &inputX);
    CHECK_RET(ret == ::ACL_SUCCESS, return ret);
    ret = CreateAclTensor(tensorInYData, yShape, &inputYDeviceAddr, aclDataType::ACL_FLOAT, &inputY);
    CHECK_RET(ret == ::ACL_SUCCESS, return ret);
    ret = CreateAclTensor(resultData, resultShape, &resultDeviceAddr, aclDataType::ACL_FLOAT, &result);
    CHECK_RET(ret == ::ACL_SUCCESS, return ret);

    // 创建算子执行句柄
    asdBlasHandle handle;
    asdBlasCreate(handle);

    // 创造算子执行所需workspace
    size_t lwork = 0;
    void *buffer = nullptr;
    asdBlasMakeDotPlan(handle);
    asdBlasGetWorkspaceSize(handle, lwork);
    std::cout << "lwork = " << lwork << std::endl;
    if (lwork > 0) {
        ret = aclrtMalloc(&buffer, static_cast<int64_t>(lwork), ACL_MEM_MALLOC_HUGE_FIRST);
        CHECK_RET(ret == ::ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
    }
    asdBlasSetWorkspace(handle, buffer);

    // 配置算子执行信息
    asdBlasSetStream(handle, stream);

    // 调用接口执行算子（固定调用逻辑）
    ASD_STATUS_CHECK(asdBlasSdot(handle, n, inputX, incx, inputY, incy, result));
    asdBlasSynchronize(handle);

    // 调度算子后销毁算子句柄
    asdBlasDestroy(handle);

    // 将输出tensor的Device侧数据复制到Host侧内存上
    ret = aclrtMemcpy(resultData.data(),
        resultSize * sizeof(float),
        resultDeviceAddr,
        resultSize * sizeof(float),
        ACL_MEMCPY_DEVICE_TO_HOST);
    CHECK_RET(ret == ::ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);

    std::cout << "------- result -------" << std::endl;
    for (int64_t i = 0; i < 1; i++) {
        std::cout << resultData[i] << " ";
    }
    std::cout << std::endl;
    std::cout << "Execute successfully." << std::endl;

    // 资源释放
    aclDestroyTensor(inputX);
    aclDestroyTensor(inputY);
    aclDestroyTensor(result);
    aclrtFree(inputXDeviceAddr);
    aclrtFree(inputYDeviceAddr);
    aclrtFree(resultDeviceAddr);
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
    return 0;
}

asdBlasCdotu

#include <iostream>
#include <vector>
#include <cmath>
#include <random>
#include <complex>
#include "asdsip.h"
#include "acl/acl.h"
#include "acl_meta.h"

using namespace AsdSip;

#define ASD_STATUS_CHECK(err)                                                \
    do {                                                                     \
        AsdSip::AspbStatus err_ = (err);                                     \
        if (err_ != AsdSip::ErrorType::ACL_SUCCESS) {                                      \
            std::cout << "Execute failed." << std::endl; \
            exit(-1);                                                        \
        } else {                                                             \
            std::cout << "Execute successfully." << std::endl;               \
        }                                                                    \
    } while (0)

void printTensor(const std::complex<float> *tensorData, int64_t tensorSize)
{
    for (int64_t i = 0; i < tensorSize; i++) {
        std::cout << tensorData[i] << " ";
    }
    std::cout << std::endl;
}

#define CHECK_RET(cond, return_expr) \
    do {                             \
        if (!(cond)) {               \
            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，acl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侧数据复制到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
    *tensor = aclCreateTensor(shape.data(),
        shape.size(),
        dataType,
        strides.data(),
        0,
        aclFormat::ACL_FORMAT_ND,
        shape.data(),
        shape.size(),
        *deviceAddr);
    return 0;
}

void printTensor(std::vector<std::complex<float>> tensorData, int64_t tensorSize)
{
    for (int64_t i = 0; i < tensorSize; i++) {
        std::cout << tensorData[i] << " ";
    }
    std::cout << std::endl;
}

int main(int argc, char **argv)
{
    int deviceId = 0;

    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    CHECK_RET(ret == ::ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

    int64_t n = 8;
    int64_t xSize = 8;
    int64_t ySize = 8;

    std::vector<std::complex<float>> tensorInXData;
    tensorInXData.reserve(xSize);
    for (int64_t i = 0; i < xSize; i++) {
        tensorInXData[i] = {2.0, (float)(1.0 + i)};
    }

    std::vector<std::complex<float>> tensorInYData;
    tensorInYData.reserve(ySize);
    for (int64_t i = 0; i < ySize; i++) {
        tensorInYData[i] = {3.0, 4.0};
    }

    int64_t resultSize = 1;
    std::vector<std::complex<float>> resultData;
    resultData.reserve(resultSize);

    std::cout << "------- input TensorInX -------" << std::endl;
    printTensor(tensorInXData.data(), xSize);

    std::cout << "------- input TensorInY -------" << std::endl;
    printTensor(tensorInYData.data(), ySize);

    std::vector<int64_t> xShape = {xSize};
    std::vector<int64_t> yShape = {ySize};
    std::vector<int64_t> resultShape = {resultSize};
    aclTensor *inputX = nullptr;
    aclTensor *inputY = nullptr;
    aclTensor *result = nullptr;
    void *inputXDeviceAddr = nullptr;
    void *inputYDeviceAddr = nullptr;
    void *resultDeviceAddr = nullptr;
    ret = CreateAclTensor(tensorInXData, xShape, &inputXDeviceAddr, aclDataType::ACL_COMPLEX64, &inputX);
    CHECK_RET(ret == ::ACL_SUCCESS, return ret);
    ret = CreateAclTensor(tensorInYData, yShape, &inputYDeviceAddr, aclDataType::ACL_COMPLEX64, &inputY);
    CHECK_RET(ret == ::ACL_SUCCESS, return ret);
    ret = CreateAclTensor(resultData, resultShape, &resultDeviceAddr, aclDataType::ACL_COMPLEX64, &result);
    CHECK_RET(ret == ::ACL_SUCCESS, return ret);

    asdBlasHandle handle;
    asdBlasCreate(handle);

    size_t lwork = 0;
    void *buffer = nullptr;
    asdBlasMakeDotPlan(handle);
    asdBlasGetWorkspaceSize(handle, lwork);
    std::cout << "lwork = " << lwork << std::endl;
    if (lwork > 0) {
        ret = aclrtMalloc(&buffer, static_cast<int64_t>(lwork), ACL_MEM_MALLOC_HUGE_FIRST);
        CHECK_RET(ret == ::ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
    }
    asdBlasSetWorkspace(handle, buffer);
    asdBlasSetStream(handle, stream);

    ASD_STATUS_CHECK(asdBlasCdotu(handle, n, inputX, 1, inputY, 1, result));

    asdBlasSynchronize(handle);
    asdBlasDestroy(handle);

    ret = aclrtMemcpy(resultData.data(),
        resultSize * sizeof(std::complex<float>),
        resultDeviceAddr,
        resultSize * sizeof(std::complex<float>),
        ACL_MEMCPY_DEVICE_TO_HOST);
    CHECK_RET(ret == ::ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);

    std::cout << "------- result -------" << std::endl;
    printTensor(resultData.data(), resultSize);

    aclDestroyTensor(inputX);
    aclDestroyTensor(inputY);
    aclDestroyTensor(result);
    aclrtFree(inputXDeviceAddr);
    aclrtFree(inputYDeviceAddr);
    aclrtFree(resultDeviceAddr);

    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
    return 0;
}

asdBlasCdotc

#include <iostream>
#include <vector>
#include <complex>
#include <cmath>
#include <random>
#include "asdsip.h"
#include "acl/acl.h"
#include "acl_meta.h"

using namespace AsdSip;

#define ASD_STATUS_CHECK(err)                                                \
    do {                                                                     \
        AsdSip::AspbStatus err_ = (err);                                     \
        if (err_ != AsdSip::ErrorType::ACL_SUCCESS) {                                      \
            std::cout << "Execute failed." << std::endl; \
            exit(-1);                                                        \
        } else {                                                             \
            std::cout << "Execute successfully." << std::endl;               \
        }                                                                    \
    } while (0)

void printTensor(const std::complex<float> *tensorData, int64_t tensorSize)
{
    for (int64_t i = 0; i < tensorSize; i++) {
        std::cout << tensorData[i] << " ";
    }
    std::cout << std::endl;
}

#define CHECK_RET(cond, return_expr) \
    do {                             \
        if (!(cond)) {               \
            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，acl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侧数据复制到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
    *tensor = aclCreateTensor(shape.data(),
        shape.size(),
        dataType,
        strides.data(),
        0,
        aclFormat::ACL_FORMAT_ND,
        shape.data(),
        shape.size(),
        *deviceAddr);
    return 0;
}

void printTensor(std::vector<std::complex<float>> tensorData, int64_t tensorSize)
{
    for (int64_t i = 0; i < tensorSize; i++) {
        std::cout << tensorData[i] << " ";
    }
    std::cout << std::endl;
}

int main(int argc, char **argv)
{
    int deviceId = 0;

    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    CHECK_RET(ret == ::ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

    int64_t n = 8;
    int64_t xSize = 8;
    int64_t ySize = 8;

    std::vector<std::complex<float>> tensorInXData;
    tensorInXData.reserve(xSize);
    for (int64_t i = 0; i < xSize; i++) {
        tensorInXData[i] = {2.0, (float)(1.0 + i)};
    }
    std::vector<std::complex<float>> tensorInYData;
    tensorInYData.reserve(ySize);
    for (int64_t i = 0; i < ySize; i++) {
        tensorInYData[i] = {3.0, 4.0};
    }

    int64_t resultSize = 1;
    std::vector<std::complex<float>> resultData;
    resultData.reserve(resultSize);

    std::cout << "------- input TensorInX -------" << std::endl;
    printTensor(tensorInXData.data(), xSize);

    std::cout << "------- input TensorInY -------" << std::endl;
    printTensor(tensorInYData.data(), ySize);

    std::vector<int64_t> xShape = {xSize};
    std::vector<int64_t> yShape = {ySize};
    std::vector<int64_t> resultShape = {resultSize};
    aclTensor *inputX = nullptr;
    aclTensor *inputY = nullptr;
    aclTensor *result = nullptr;
    void *inputXDeviceAddr = nullptr;
    void *inputYDeviceAddr = nullptr;
    void *resultDeviceAddr = nullptr;
    ret = CreateAclTensor(tensorInXData, xShape, &inputXDeviceAddr, aclDataType::ACL_COMPLEX64, &inputX);
    CHECK_RET(ret == ::ACL_SUCCESS, return ret);
    ret = CreateAclTensor(tensorInYData, yShape, &inputYDeviceAddr, aclDataType::ACL_COMPLEX64, &inputY);
    CHECK_RET(ret == ::ACL_SUCCESS, return ret);
    ret = CreateAclTensor(resultData, resultShape, &resultDeviceAddr, aclDataType::ACL_COMPLEX64, &result);
    CHECK_RET(ret == ::ACL_SUCCESS, return ret);

    asdBlasHandle handle;
    asdBlasCreate(handle);

    size_t lwork = 0;
    void *buffer = nullptr;
    asdBlasMakeDotPlan(handle);
    asdBlasGetWorkspaceSize(handle, lwork);
    std::cout << "lwork = " << lwork << std::endl;
    if (lwork > 0) {
        ret = aclrtMalloc(&buffer, static_cast<int64_t>(lwork), ACL_MEM_MALLOC_HUGE_FIRST);
        CHECK_RET(ret == ::ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
    }
    asdBlasSetWorkspace(handle, buffer);
    asdBlasSetStream(handle, stream);

    ASD_STATUS_CHECK(asdBlasCdotc(handle, n, inputX, 1, inputY, 1, result));

    asdBlasSynchronize(handle);
    asdBlasDestroy(handle);

    ret = aclrtMemcpy(resultData.data(),
        resultSize * sizeof(std::complex<float>),
        resultDeviceAddr,
        resultSize * sizeof(std::complex<float>),
        ACL_MEMCPY_DEVICE_TO_HOST);
    CHECK_RET(ret == ::ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);

    std::cout << "------- result -------" << std::endl;
    printTensor(resultData.data(), resultSize);

    aclDestroyTensor(inputX);
    aclDestroyTensor(inputY);
    aclDestroyTensor(result);
    aclrtFree(inputXDeviceAddr);
    aclrtFree(inputYDeviceAddr);
    aclrtFree(resultDeviceAddr);

    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
    return 0;
}