What is the proper way to allocate GPU memory to a member variable of a class?

Basically I hope to allocate GPU memory to class Image‘s member variable frame with cudaMallocManaged:

class Image {
public:
    Color* frame;
};

But with the following code I got CUDA error = 1 when allocating for pointer frame:

#include <iostream>

// limited version of checkCudaErrors from helper_cuda.h in CUDA examples
#define checkCudaErrors(val) check_cuda((val), #val, __FILE__, __LINE__)

void check_cuda(cudaError_t result, char const* const func, const char* const file,
                int const line) {
    if (result) {
        std::cerr << "CUDA error = " << static_cast<unsigned int>(result) << " at " << file << ":"
                << line << " '" << func << "' \n";
        // Make sure we call CUDA Device Reset before exiting
        cudaDeviceReset();
        exit(-1);
    }
}

class Color {
public:
    double r, g, b;

    __host__ __device__ Color() : r(0.0), g(0.0), b(0.0) {
    }
};


class Image {
public:
    Color* frame;
};

int main() {
    int width = 1960;
    int height = 1080;

    Image *image;
    checkCudaErrors(cudaMallocManaged((void **)&image, sizeof(Image)));
    checkCudaErrors(cudaMallocManaged((void **)&(image->frame), sizeof(Color) * width, height));

    return 0;
}

What’s the proper way to allocate GPU memory to this member variable?

>Solution :

cudaMallocManaged is declared like this:

__host__ ​cudaError_t cudaMallocManaged(void** devPtr, size_t size,
                                       unsigned int flags = cudaMemAttachGlobal)

So maybe you can use this:

checkCudaErrors(cudaMallocManaged((void **)&(image->frame),
                                  sizeof(Color) * width * height));

Note: The third argument, flags, is here left to use the default value cudaMemAttachGlobal and the size is calculated by multiplying sizeof(Color), width and height.