Caxpy

asdBlasCaxpy算子调用示例：

#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::NO_ERROR) {                                      \
            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;
}

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 vecSize = 8;
    int64_t resultSize = 8;
    std::complex<float> alpha = {-2.0f, -4.0f};

    std::vector<std::complex<float>> tensorInVecData;
    tensorInVecData.reserve(vecSize);
    for (int i = 0; i < vecSize; i++) {
        tensorInVecData.push_back({(float)(1.0 + i), (float)(2.0 + i)});
    }

    std::vector<std::complex<float>> tensorResultData;
    tensorResultData.reserve(resultSize);

    for (int i = 0; i < vecSize; i++) {
        tensorResultData.push_back({(float)(0.0), (float)(0.0)});
    }

    std::cout << "alpha = " << alpha << std::endl;
    std::cout << "------- input vec -------" << std::endl;
    printTensor(tensorInVecData, vecSize);

    std::vector<int64_t> vecShape = {vecSize};
    std::vector<int64_t> resultShape = {resultSize};

    aclTensor *inVec = nullptr;
    aclTensor *outResult = nullptr;
    void *inpVecDeviceAddr = nullptr;
    void *outResultDeviceAddr = nullptr;

    ret = CreateAclTensor<std::complex<float>>(
        tensorInVecData, vecShape, &inpVecDeviceAddr, aclDataType::ACL_COMPLEX64, &inVec);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    ret = CreateAclTensor<std::complex<float>>(
        tensorResultData, resultShape, &outResultDeviceAddr, aclDataType::ACL_COMPLEX64, &outResult);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    asdBlasHandle handle;
    asdBlasCreate(handle);

    size_t lwork = 0;
    void *buffer = nullptr;
    asdBlasMakeCaxpyPlan(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(asdBlasCaxpy(handle, vecSize, alpha, inVec, 1, outResult, 1));

    asdBlasSynchronize(handle);
    asdBlasDestroy(handle);

    ret = aclrtMemcpy(tensorResultData.data(),
        resultSize * sizeof(std::complex<float>),
        outResultDeviceAddr,
        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(tensorResultData, resultSize);

    aclDestroyTensor(inVec);
    aclDestroyTensor(outResult);
    aclrtFree(inpVecDeviceAddr);
    aclrtFree(outResultDeviceAddr);

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