/**
 *
 * Feladat: Adatok inicializálása a GPU-n.
 *          - külön függvényben
 *          - vagy direkt konstans-ként
 *
 */



#include "cuda_runtime.h"
#include "device_launch_parameters.h"

#include <stdio.h>

#define N	10

__global__ void addKernel(int* a, int* b, int* c);

int main(int argc, char** argv)
{
	int i;

	int a[N];
	int b[N];
	int c[N];

	int* dev_a;
	int* dev_b;
	int* dev_c;

	cudaMalloc((void**)&dev_a, N * sizeof(int));
	cudaMalloc((void**)&dev_b, N * sizeof(int));
	cudaMalloc((void**)&dev_c, N * sizeof(int));

	for(i=0; i<N; i++)
	{
		a[i] = -i;
		b[i] = i * i;
	}

	cudaMemcpy(dev_a, a, N*sizeof(int), cudaMemcpyHostToDevice);
	cudaMemcpy(dev_b, b, N*sizeof(int), cudaMemcpyHostToDevice);

	addKernel<<<N, 1>>>(dev_a, dev_b, dev_c);

	cudaMemcpy(c, dev_c, N*sizeof(int), cudaMemcpyDeviceToHost);

	for(i=0; i<N; i++)
	{
		printf("%d + %d = %d\n", a[i], b[i], c[i]);
	}

	cudaFree(dev_a);
	cudaFree(dev_b);
	cudaFree(dev_c);

	return 0;
}

__global__ void addKernel(int* a, int* b, int* c)
{
	int tid = blockIdx.x;

	if(tid < N)
		c[tid] = a[tid] + b[tid];

	return;
}