我可以在CUDA设备上为包含浮点数数组的对象分配内存吗

我正在研究具有不同初始条件的相同常微分方程的并行求解。我已经用OpenMP解决了这个问题，现在我想在GPU上实现类似的代码。具体来说，我想在类构造函数中为浮点分配设备上的内存，然后在析构函数中解除分配。这对我来说不起作用，因为我的可执行文件"被信号SIGSEGV(地址边界错误)终止"。CUDA中是否可以使用类、构造函数和析构函数？

顺便说一句，我是CUDA的新手，在C++方面也不是很有经验。

我附上了代码，以防我对我的问题描述不好。

#include <cmath>
#include <iostream>
#include <fstream>
#include <iomanip>
#include <random>
#include <string>
#include <chrono>
#include <ctime>
using namespace std;
template<class ode_sys>
class solver: public ode_sys 
{
public:
int *nn;
float *t,*tt,*dt,*x,*xx,*m0,*m1,*m2,*m3;
using ode_sys::rhs_sys;
__host__ solver(int n): ode_sys(n)
{ //here I try to allocate memory. It works malloc() and doesn't with cudaMalloc() 
size_t size=sizeof(float)*n;
cudaMalloc((void**)&nn,sizeof(int));
*nn=n;
cudaMalloc((void**)&t,sizeof(float));
cudaMalloc((void**)&tt,sizeof(float));
cudaMalloc((void**)&dt,sizeof(float));
cudaMalloc((void**)&x,size);
cudaMalloc((void**)&xx,size);
cudaMalloc((void**)&m0,size);
cudaMalloc((void**)&m1,size);
cudaMalloc((void**)&m2,size);
cudaMalloc((void**)&m3,size);
}
__host__ ~solver()
{
cudaFree(nn);
cudaFree(t);
cudaFree(tt);
cudaFree(dt);
cudaFree(x);
cudaFree(xx);
cudaFree(m0);
cudaFree(m1);
cudaFree(m2);
cudaFree(m3);
}
__host__ __device__ void rk4()
{//this part is not important now. 
}
};
class ode 
{
private:
int *nn;
public:
float *eps,*d;
__host__ ode(int n)
{
cudaMalloc((void**)&nn,sizeof(int));
*nn=n;
cudaMalloc((void**)&eps,sizeof(float));
size_t size=sizeof(float)*n;
cudaMalloc((void**)&d,size);
}
__host__ ~ode()
{
cudaFree(nn);
cudaFree(eps);
cudaFree(d);
}
__host__ __device__ float f(float x_,float y_,float z_,float d_)
{
return d_+*eps*(sinf(x_)+sinf(z_)-2*sinf(y_));
}
__host__ __device__ void rhs_sys(float *t,float *dt,float *x,float *dx)
{
}
};
//const float pi=3.14159265358979f;
__global__ void solver_kernel(int m,int n,solver<ode> *sys_d)
{
int index = threadIdx.x;
int stride = blockDim.x;
//actually ode numerical evaluation should be here
for (int l=index;l<m;l+=stride)
{//this is just to check that i can run kernel
printf("%d Hello n", l);
}
}
int main ()
{
auto start = std::chrono::system_clock::now();
std::time_t start_time = std::chrono::system_clock::to_time_t(start);
cout << "started computation at " << std::ctime(&start_time);
int m=128,n=4,l;// i want to run 128 threads, n is dimension of ode
size_t size=sizeof(solver<ode>(n));
solver<ode> *sys_d;   //an array of objects
cudaMalloc(&sys_d,size*m);    //nvprof shows that this array is allocated
for (l=0;l<m;l++)
{
new (sys_d+l) solver<ode>(n);   //it doesn't work as it meant to
}
solver_kernel<<<1,m>>>(m,n,sys_d);   
for (l=0;l<m;l++)
{
(sys_d+l)->~solver<ode>();    //it doesn't work as it meant to
}
cudaFree(sys_d);    //it works
auto end = std::chrono::system_clock::now();
std::chrono::duration<double> elapsed_seconds = end-start;
std::time_t end_time = std::chrono::system_clock::to_time_t(end);
std::cout << "finished computation at " << std::ctime(&end_time) << "elapsed time: " << elapsed_seconds.count() << "sn";
return 0;
}
//end of file