#include <stdio.h>
#include <iostream>
using namespace std;

float mRandom(){return 666f;}

__global__ void checkPoint ( float* X )
{
   int idx = blockIdx.x * blockDim.x + threadIdx.x;
   X[idx] = mRandom();
}

int main(int argc, char *  argv [])
{
	setlocale(0, "rus");
	int N=16*1024*1024, n=0, numBytes=N*sizeof ( POINT );
	float *X = new float [N];
	for (int i=0; i<N; i++) X[i]=1;
	float *cdev = NULL;
        cudaMalloc ( (void**)&cdev, numBytes );
	dim3 threads = dim3(256, 1);
        dim3 blocks  = dim3(N / threads.x, 1);
        cudaMemcpy      ( cdev, X, numBytes, cudaMemcpyHostToDevice );
        checkPoint<<<blocks, threads>>>(cdev);
        cudaMemcpy      ( X, cdev, numBytes, cudaMemcpyDeviceToHost );
        for (int i=0; i<300; i++)cout<<X[i]<<endl;
	cudaFree(cdev);
        delete X;
	system("pause");
	return 0;
}