Using std::vector in CUDA device code

Question

The question is that: is there a way to use the class \"vector\" in Cuda kernels? When I try I get the following error:

error : calling a host function(\"std         


        

Answer 1

In the cuda library thrust, you can use thrust::device_vector<classT> to define a vector on device, and the data transfer between host STL vector and device vector is very straightforward. you can refer to this useful link:http://docs.nvidia.com/cuda/thrust/index.html to find some useful examples.

Answer 2

I think you can implement a device vector by youself, because CUDA supports dynamic memory alloction in device codes. Operator new/delete are also supported. Here is an extremely simple prototype of device vector in CUDA, but it does work. It hasn't been tested sufficiently.

template<typename T>
class LocalVector
{
private:
    T* m_begin;
    T* m_end;

    size_t capacity;
    size_t length;
    __device__ void expand() {
        capacity *= 2;
        size_t tempLength = (m_end - m_begin);
        T* tempBegin = new T[capacity];

        memcpy(tempBegin, m_begin, tempLength * sizeof(T));
        delete[] m_begin;
        m_begin = tempBegin;
        m_end = m_begin + tempLength;
        length = static_cast<size_t>(m_end - m_begin);
    }
public:
    __device__  explicit LocalVector() : length(0), capacity(16) {
        m_begin = new T[capacity];
        m_end = m_begin;
    }
    __device__ T& operator[] (unsigned int index) {
        return *(m_begin + index);//*(begin+index)
    }
    __device__ T* begin() {
        return m_begin;
    }
    __device__ T* end() {
        return m_end;
    }
    __device__ ~LocalVector()
    {
        delete[] m_begin;
        m_begin = nullptr;
    }

    __device__ void add(T t) {

        if ((m_end - m_begin) >= capacity) {
            expand();
        }

        new (m_end) T(t);
        m_end++;
        length++;
    }
    __device__ T pop() {
        T endElement = (*m_end);
        delete m_end;
        m_end--;
        return endElement;
    }

    __device__ size_t getSize() {
        return length;
    }
};

Answer 3

You can't use the STL in CUDA, but you may be able to use the Thrust library to do what you want. Otherwise just copy the contents of the vector to the device and operate on it normally.

Answer 4

you can't use std::vector in device code, you should use array instead.