Copy Array of pointers inside a struct using CUDA - c

Question

I wish to copy an array of pointers from one struct to another. The Struct looks like this:
typedef struct COORD3D
{
int x,y,z;
}
COORD3D;
typedef struct structName
{
double *volume;
COORD3D size;
// .. some other vars
}
structName;
I wish to do this inside a function where I pass in the address of an empty instance of the struct and the address of the struct with the data I wish to copy. Currently I do this serially via:
void foo(structName *dest, structName *source)
{
// .. some other work
int size = source->size.x * source->size.y * source->size.z;
dest->volume = (double*)malloc(size*sizeof(double));
int i;
for(i=0;i<size;i++)
dest->volume[i] = source->volume[i];
}
I want to do this in CUDA to speed up the process (as the array is very large [~12 million elements].
I have tried the following however, although the code compiles and runs, I get incorrect results stored in the array (seems to be very large random numbers)
void foo(structName *dest, structName *source)
{
// .. some other work
int size = source->size.x * source->size.y * source->size.z;
dest->volume = (double*)malloc(size*sizeof(double));
// Device Pointers
double *DEVICE_SOURCE, *DEVICE_DEST;
// Declare memory on GPU
cudaMalloc(&DEVICE_DEST,size);
cudaMalloc(&DEVICE_SOURCE,size);
// Copy Source to GPU
cudaMemcpy(DEVICE_SOURCE,source->volume,size,
cudaMemcpyHostToDevice);
// Setup Blocks/Grids
dim3 dimGrid(ceil(source->size.x/10.0),
ceil(source->size.y/10.0),
ceil(source->size.z/10.0));
dim3 dimBlock(10,10,10);
// Run CUDA Kernel
copyVol<<<dimGrid,dimBlock>>> (DEVICE_SOURCE,
DEVICE_DEST,
source->size.x,
source->size.y,
source->size.z);
// Copy Constructed Array back to Host
cudaMemcpy(dest->volume,DEVICE_DEST,size,
cudaMemcpyDeviceToHost);
}
The Kernel looks like this:
__global__ void copyVol(double *source, double *dest,
int x, int y, int z)
{
int posX = blockIdx.x * blockDim.x + threadIdx.x;
int posY = blockIdx.y * blockDim.y + threadIdx.y;
int posZ = blockIdx.z * blockDim.z + threadIdx.z;
if (posX < x && posY < y && posZ < z)
{
dest[posX+(posY*x)+(posZ*y*x)] =
source[posX+(posY*x)+(posZ*y*x)];
}
}
Can anyone tell me where I am going wrong?

Answer 1

I am risking a wrong answer, but have you left out the size of the data type?
cudaMalloc(&DEVICE_DEST,size);
should be
cudaMalloc(&DEVICE_DEST,size*sizeof(double));
Also
cudaMemcpy(DEVICE_SOURCE,source->volume,size, cudaMemcpyHostToDevice);
should be
cudaMemcpy(DEVICE_SOURCE,source->volume,size*sizeof(double), cudaMemcpyHostToDevice);
and so on.