cudaOccupancyMaxActiveBlocksPerMultiprocessor is undefined

我正在尝试学习cuda并以有效的方式使用它。我从 nvidia 的网站上找到了一个代码，它告诉我们可以了解我们应该用于设备最有效使用的块大小。代码如下：

#include <iostream>
// Device code
__global__ void MyKernel(int *d, int *a, int *b)
{
    int idx = threadIdx.x + blockIdx.x * blockDim.x;
    d[idx] = a[idx] * b[idx];
}
// Host code
int main()
{
    int numBlocks;        // Occupancy in terms of active blocks
    int blockSize = 32;
    // These variables are used to convert occupancy to warps
    int device;
    cudaDeviceProp prop;
    int activeWarps;
    int maxWarps;
    cudaGetDevice(&device);
    cudaGetDeviceProperties(&prop, device);
    cudaOccupancyMaxActiveBlocksPerMultiprocessor(
    &numBlocks,
    MyKernel,
    blockSize,
    0);
    activeWarps = numBlocks * blockSize / prop.warpSize;
    maxWarps = prop.maxThreadsPerMultiProcessor / prop.warpSize;
    std::cout << "Occupancy: " << (double)activeWarps / maxWarps * 100 << "%" << std::endl;
    return 0;
}

但是，当我编译它时，存在以下错误：

编译行：

nvcc ben_deneme2.cu -arch=sm_35 -rdc=true -lcublas -lcublas_device -lcudadevrt -o my

错误：

ben_deneme2.cu(25): error: identifier "cudaOccupancyMaxActiveBlocksPerMultiprocessor" is undefined
1 error detected in the compilation of "/tmp/tmpxft_0000623d_00000000-8_ben_deneme2.cpp1.ii".

我应该为此包含一个库，尽管我在互联网上找不到它的库名称吗？还是我做错了什么？提前致谢