CUDA 1-D array not getting updated - cuda

Question

this is my first attempt at a CUDA program. This is what it's supposed to do:
Receive 1D Pixel array from host memory
Each Pixel is processed by one thread: it is thread-safe because only "val" is read and only "newval" is updated. Wait for sync.
Each Pixel is processed by one thread: copy "newval" to "val."
Write this array back to host memory.
Repeat 2-4 for several different frames.
What happens, however, is that only a couple of variables, out of about 32000, in the new arrays seem to have decent values at all; the rest are zero.
I've removed the calculations for brevity.
__global__ void kernel(Pixel *array, float dt)
{
const unsigned int tid = threadIdx.x;
Pixel *point = array + tid;
//DO A BUNCH OF CALCULATIONS ON PIXEL KIND OF LIKE THIS
point->newval = point->val + foo;
}
__global__ void copykernel(Pixel *array)
{
const unsigned int tid = threadIdx.x;
Pixel *point = array + tid;
//COPY THE NEWVALS OVER TO THE OLD VALS IN PREPARATION FOR THE NEXT FRAME
point->val = point->newval;
}
extern "C" bool runIt(const int argc, const char **argv, Pixel *inarray, Pixel **outarrays, int arraysize, int numframes, float dt)
{
int memsize = arraysize*sizeof(Pixel);
int i=0;
Pixel *array;
cudaMalloc((void **) &array, memsize);
cudaMemcpy(array, inarray, memsize, cudaMemcpyHostToDevice);
int numthreads = arraysize;
dim3 grid(1,1,1);
dim3 threads(numthreads,1,1);
for(i=0;i<numframes;i++)
{
kernel<<<grid, threads>>>((Pixel *) array, dt);
cudaThreadSynchronize();
copykernel<<<grid, threads>>>((Pixel *) array);
cudaThreadSynchronize();
cudaMemcpy(array, outarrays[i], memsize, cudaMemcpyDeviceToHost);
}
cudaFree(array);
return true;
}
I have a suspicion that I'm setting up the parameters for the device incorrectly, or else I'm getting one of the device-specific keywords wrong or forgetting a crucial step. Does anything jump out at you?

Answer 1

I don't think you can run that many threads, and if you can, its not a good idea. Try setting the number of threads to 256 (16x16 for 2D), then choosing gridsize based on your input size.
dim3 threads(256,1,1);
dim3 grid(arraysize/threads.x,1,1); //Careful of integer division, this is just for example
Also your second copy is incorrect. You need to switch array and out_arrays
cudaMemcpy(outarrays[i], array, memsize, cudaMemcpyDeviceToHost);