I have a dynamically declared 2D array in my C program, the contents of which I want to transfer to a CUDA kernel for further processing. Once processed, I want to populate the dynamically declared 2D array in my C code with the CUDA processed data. I am able to do this with static 2D C arrays but not with dynamically declared C arrays. Any inputs would be welcome!

I mean the dynamic array of dynamic arrays. The test code that I have written is as below.

#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <stdio.h>
#include <conio.h>
#include <math.h>
#include <stdlib.h>

const int nItt = 10;
const int nP = 5;

__device__ int d_nItt = 10;
__device__ int d_nP = 5;


__global__ void arr_chk(float *d_x_k, float *d_w_k, int row_num)
{

int index = (blockIdx.x * blockDim.x) + threadIdx.x;
int index1 = (row_num * d_nP) + index; 
if ( (index1 >= row_num * d_nP) && (index1 < ((row_num +1)*d_nP)))              //Modifying only one row data pertaining to one particular iteration
{

        d_x_k[index1] = row_num * d_nP;
        d_w_k[index1] = index;
}

}

float **mat_create2(int r, int c)
{
float **dynamicArray;
dynamicArray = (float **) malloc (sizeof (float)*r);
for(int i=0; i<r; i++)
    {
    dynamicArray[i] = (float *) malloc (sizeof (float)*c);
        for(int j= 0; j<c;j++)
        {
            dynamicArray[i][j] = 0;
        }
    }
return dynamicArray;
}

/* Freeing memory - here only number of rows are passed*/
void cleanup2d(float **mat_arr, int x)
{
int i;
for(i=0; i<x; i++)
{
    free(mat_arr[i]);
}
free(mat_arr);
}

int main()
{

//float w_k[nItt][nP]; //Static array declaration - works!
//float x_k[nItt][nP];
// if I uncomment this dynamic declaration and comment the static one, it does not work.....
float **w_k = mat_create2(nItt,nP); 
float **x_k = mat_create2(nItt,nP);
float *d_w_k, *d_x_k;       // Device variables for w_k and x_k
int nblocks, blocksize, nthreads;
for(int i=0;i<nItt;i++)
{
    for(int j=0;j<nP;j++)
    {
        x_k[i][j] = (nP*i);
        w_k[i][j] = j;
    }
}

for(int i=0;i<nItt;i++)
{
    for(int j=0;j<nP;j++)
    {
        printf("x_k[%d][%d] = %f\t",i,j,x_k[i][j]);
        printf("w_k[%d][%d] = %f\n",i,j,w_k[i][j]);
    }
}
int size1 = nItt * nP * sizeof(float);
printf("\nThe array size in memory bytes is: %d\n",size1);
cudaMalloc( (void**)&d_x_k, size1 );
cudaMalloc( (void**)&d_w_k, size1 );

if((nP*nItt)<32)    
{
    blocksize = nP*nItt;
    nblocks = 1;
}
else
{
    blocksize = 32;     // Defines the number of threads running per block. Taken equal to warp size
    nthreads = blocksize;
    nblocks =  ceil(float(nP*nItt) / nthreads);     // Calculated total number of blocks thus required
}

for(int i = 0; i< nItt; i++)
{
    cudaMemcpy( d_x_k, x_k, size1,cudaMemcpyHostToDevice ); //copy of x_k to device
    cudaMemcpy( d_w_k, w_k, size1,cudaMemcpyHostToDevice ); //copy of w_k to device
    arr_chk<<<nblocks, blocksize>>>(d_x_k,d_w_k,i);
    cudaMemcpy( x_k, d_x_k, size1, cudaMemcpyDeviceToHost );
    cudaMemcpy( w_k, d_w_k, size1, cudaMemcpyDeviceToHost );
}
printf("\nVerification after return from gpu\n");
for(int i = 0; i<nItt; i++)
{
    for(int j=0;j<nP;j++)
    {
        printf("x_k[%d][%d] = %f\t",i,j,x_k[i][j]);
        printf("w_k[%d][%d] = %f\n",i,j,w_k[i][j]);
    }
}
cudaFree( d_x_k );
cudaFree( d_w_k );
cleanup2d(x_k,nItt);
cleanup2d(w_k,nItt);
getch();
return 0;