CUDA:在 C++ 中包装设备内存分配

1. Is my placement new overload semantically correct? Does it leak memory?
2. Does anybody have information about future CUDA developments that go in this general direction (let's face it: C interfaces in C++ s*ck)?
3. How can I take this further in a consistent manner (there are other APIs to consider, e.g. there's not only device memory but also a constant memory store and texture memory)?

<小时>

// Singleton tag for CUDA device memory placement.
struct CudaDevice {
    static CudaDevice const& get() { return instance; }
private:
    static CudaDevice const instance;
    CudaDevice() { }
    CudaDevice(CudaDevice const&);
    CudaDevice& operator =(CudaDevice const&);
} const& cudaDevice = CudaDevice::get();

CudaDevice const CudaDevice::instance;

inline void* operator new [](std::size_t nbytes, CudaDevice const&) {
    void* ret;
    cudaMalloc(&ret, nbytes);
    return ret;
}

inline void operator delete [](void* p, CudaDevice const&) throw() {
    cudaFree(p);
}

template <typename T>
class CudaArray {
public:
    explicit
    CudaArray(std::size_t size) : size(size), data(new (cudaDevice) T[size]) { }

    operator T* () { return data; }

    ~CudaArray() {
        operator delete [](data, cudaDevice);
    }

private:
    std::size_t const size;
    T* const data;

    CudaArray(CudaArray const&);
    CudaArray& operator =(CudaArray const&);
};

关于这里使用的单例:是的，我知道它的缺点.但是，这些在这种情况下无关紧要.我在这里只需要一个不可复制的小型标签.其他所有内容(即多线程注意事项、初始化时间)均不适用.