using namespace std;

__global__void inc_gpu(int *a, int N)
{
	int idx = blockIdx.x*blockDim.x + threadIdx.x;
	if (idx < N)
		a[idx] = a[idx] + 1;
}

int main()
{
	int N = 100, blocksize = 5;
	int a[N];
	dim3 dimBlock(blocksize);
	dim3 dimGrid(ceil(N/(float)blocksize));
	for(int i = 0; i < N; i++)
        a[i] = i;
	
	inc_gpu<<<dimGrid,dimBlock>>>(a,N);
}