cuda accessing 3d array

I'm trying to figure out how to allocate a 3d array on the device, populate it and then return it back to the host code.

I tried using the code in the "Cuda C Programming guide" Section 3.2.2 pg, 21 and 22. When I try to compile this code,I get this error:

error: a value of type "void *" cannot be used to initialize an entity of type "char *"

/* host code */
#include <stdio.h>
#include <math.h>
#include "mex.h"

/* Kernel function */
#include "simulate3DArrays.cpp"

/* Define some constants. */
#define width  5
#define height 9
#define depth  5

void mexFunction(int        nlhs,
             mxArray    *plhs[],
             int        nrhs,
             mxArray    *prhs[])
{

double *output;
mwSize ndim3 = 3;
mwSize dims3[] = {height, width, depth};

plhs[0] = mxCreateNumericArray(ndim3, dims3, mxDOUBLE_CLASS, mxREAL);
output = mxGetPr(plhs[0]);

cudaExtent extent = make_cudaExtent(width * sizeof(double), height, depth);
cudaPitchedPtr devicePointer;
cudaMalloc3D(&devicePointer, extent);

cudaMemcpy3DParms deviceOuput = { 0 };
deviceOuput.srcPtr.ptr = devicePointer.ptr;
deviceOuput.srcPtr.pitch = devicePointer.pitch;
deviceOuput.srcPtr.xsize = width;
deviceOuput.srcPtr.ysize = height;

deviceOuput.dstPtr.ptr = output;
deviceOuput.dstPtr.pitch = devicePointer.pitch;
deviceOuput.dstPtr.xsize = width;
deviceOuput.dstPtr.ysize = height;

deviceOuput.kind = cudaMemcpyDeviceToHost;

simulate3DArrays<<<1,depth>>>(devicePointer, width, height, depth);

/* copy 3d array back to 'ouput' */
cudaMemcpy3D(&deviceOuput);

return;
} /* End Mexfunction */

/* device code from pg 22. */
__global__ void simulate3DArrays(cudaPitchedPtr devPitchedPtr, 
                             int width, 
                             int height, 
                             int depth) 
{
char* devPtr = devPitchedPtr.ptr;  /* << error occurs here */
size_t pitch = devPitchedPtr.pitch; 
size_t slicePitch = pitch * height;

for (int z = 0; z < depth; ++z) 
{ 
    char* slice = devPtr + z * slicePitch; 
    for (int y = 0; y < height; ++y)
    {
        float* row = (float*)(slice + y * pitch);
        for (int x = 0; x < width; ++x) 
        {
            float element = row[x]; 
        }
    } 
}
}

Not sure if it's really relevant for this problem, but my environment is:

• Windows 7 x64
• Matlab 2012a
• Cuda SDK 4.2
• Tesla C2050 GPU