complie kernel to DLL and use it

Accelerated Computing CUDA CUDA Programming and Performance
1

Hi,
I managed to make whole thing with function pointers work and now I want to dynamically load such a kernel.
My code:

#ifndef customkernel_cuh
#define customkernel_cuh

extern "C" pfunctionWhere __declspec(dllexport) getHostPointer();

#endif

__device__
	bool myWhere2(PapayaColumnValue *values)
{
	return ((int)values[1]) == 1 || ((int)values[1]) == 3;
}
__device__ pfunctionWhere pMyWhere2 = myWhere2;

pfunctionWhere __declspec(dllexport) getHostPointer()
{
	cudaError_t cudaStatus;
	pfunctionWhere h_pMyWhere2;
	cudaStatus = cudaMemcpyFromSymbol(&h_pMyWhere2, pMyWhere2, sizeof(pfunctionWhere));
	cudaDeviceSynchronize();
	return h_pMyWhere2;
}

HINSTANCE hGetProcIDDLL = LoadLibrary("xxx.dll");
	if (hGetProcIDDLL == NULL) {
		std::cout << "could not load the dynamic library" << std::endl;
	}
	dll_func dll_getHostPointer = (dll_func)GetProcAddress(hGetProcIDDLL, "getHostPointer");
	DWORD dw = GetLastError(); 
	if (!dll_getHostPointer) {
		std::cout << "could not locate the function" << std::endl;
	}
	pfunctionWhere h_pMyWhere2 = (*dll_getHostPointer)();

And if I debug into dll cudaStatus = cudaSuccess, but pointer to function are null and it is returned from dll invocation. My question is: is it possible to write kernel functions in DLL and then get pointer to such kernels and pass it to main program? I need it to be able to change the kernel while main program is working.
thanks in advance