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

#include <iostream>
#include <ctime>

using namespace std;

#define N           100
#define BLOCKDIM    10

__host__ void addOnGPU(int* a, int* b, int* c);
__host__ void addOnCPU(int* a, int* b, int* c);

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

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

    int* a = new int[N];
    int* b = new int[N];
    int* c = new int[N];

    for (i = 0; i<N; i++)
    {
        a[i] = -i;
        b[i] = 3 * i;
    }

    addOnGPU(a, b, c);
    addOnCPU(a, b, c);

    return 0;
}

__host__ void addOnGPU(int* a, int* b, int* c)
{
    int* dev_a;
    int* dev_b;
    int* dev_c;

    int start_gpu_full = clock();

    cudaMalloc((void**)&dev_a, N * sizeof(int));
    cout << cudaGetErrorString(cudaGetLastError()) << endl;
    cudaMalloc((void**)&dev_b, N * sizeof(int));
    cout << cudaGetErrorString(cudaGetLastError()) << endl;
    cudaMalloc((void**)&dev_c, N * sizeof(int));
    cout << cudaGetErrorString(cudaGetLastError()) << endl;

    cudaMemcpy(dev_a, a, N * sizeof(int), cudaMemcpyHostToDevice);
    cout << cudaGetErrorString(cudaGetLastError()) << endl;
    cudaMemcpy(dev_b, b, N * sizeof(int), cudaMemcpyHostToDevice);
    cout << cudaGetErrorString(cudaGetLastError()) << endl;

    cudaDeviceSynchronize();

    int start_kernel = clock();

    addKernel << <(N + BLOCKDIM - 1) / (BLOCKDIM), BLOCKDIM >> >(dev_a, dev_b, dev_c);
    cout << cudaGetErrorString(cudaGetLastError()) << endl;

    cudaDeviceSynchronize();

    cout << "Kernel Excution time: " << clock() - start_kernel << endl;

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

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

    cout << "Full GPU time: " << clock() - start_gpu_full << endl;

    int correct = 1;
    for (int i = 0; i<N; i++)
    {
        if (a[i] + b[i] != c[i])
        {
            correct = 0;
            break;
        }
    }

    if (correct) {
        cout << "GPU: A szamitas helyes. :)" << endl;
    }
    else {
        cout << "GPU: A szamitas helytelen. :(" << endl;
    }

}

__host__ void addOnCPU(int* a, int* b, int* c)
{
    int start_cpu = clock();

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

    cout << "Full CPU time: " << clock() - start_cpu << endl;

    int correct = 1;
    for (int i = 0; i<N; i++)
    {
        if (a[i] + b[i] != c[i])
        {
            correct = 0;
            break;
        }
    }

    if (correct) {
        cout << "CPU: A szamitas helyes. :)" << endl;
    }
    else {
        cout << "CPU: A szamitas helytelen. :(" << endl;
    }

    return;
}


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

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

    return;
}