#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <iostream>
#include <string>
#include <math.h>
#include <ctime>

#include <stdio.h>
using namespace std;

const short L = 4;

__global__ void mulMat(int Reg[L][L], int Q[L])
{
	int i = blockIdx.x;
	int newQ[L];
	int temp = 0;
	for (int j = 0; j < L; j++) {
		temp += Reg[i][j] * Q[j];
	}
	newQ[i] = temp % 2;
	Q[i] = newQ[i];
}

int main()
{
	const clock_t begin_time = clock();
	int Register[L][L] = { {0,0,0,1}, {1,1,1,0}, {0,1,1,0}, {0,0,1,1} };
	int Q[L] = { 1,0,0,0 };
	//int newQ[L];
	bool* tab = new bool[(int)pow(2, L) - 1];
	bool isMax = true;
	int dec;

	for (int i = 0; i < pow(2, L); i++) {
		tab[i] = false;
	}

	for (int i = 0; i < L; i++) {
		for (int j = 0; j < L; j++)
		{
			cout << Register[i][j] << " ";
		}
		cout << endl;
	}
	cout << endl;

	dec = 0;
	for (int i = 0; i < L; i++) {
		dec += Q[L - i - 1] * pow(2, L - i - 1);
		cout << Q[i] << " ";
	}
	cout << " decimal: " << dec << endl;

	int(*aReg)[L];
	int(*aQ);
	int(*aDec);
	cudaMalloc((void**)&aReg, (L * L) * sizeof(int));
	cudaMalloc((void**)&aQ, L * sizeof(int));
	cudaMemcpy(aReg, Register, (L * L) * sizeof(int), cudaMemcpyHostToDevice);
	cudaMemcpy(aQ, Q, L * sizeof(int), cudaMemcpyHostToDevice);

	for (int k = 0; k < pow(2, L) - 1; k++) {
		mulMat << <L, 1 >> > (aReg, aQ);
		cudaMemcpy(Q, aQ, L * sizeof(int), cudaMemcpyDeviceToHost);
		dec = 0;
		for (int i = 0; i < L; i++) {
			dec += Q[i] * pow(2, i);
			cout << Q[i] << " ";
		}
		cout << " decimal: " << dec << endl;

		if (!tab[dec]) {
			tab[dec] = true;
		}
		else {
			isMax = false;
			break;
		}
	}
	cudaFree(aReg);
	cudaFree(aQ);
	if (isMax) {
		cout << "CYKL MAKSYMALNY";
	}
	else {
		cout << "CYKL NIEMAKSYMALNY";
	}

	cout << endl;
	cout << float(clock() - begin_time) / CLOCKS_PER_SEC;
	cout << endl;
	system("pause");
	return 0;
}