#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <math.h>
#include <stdio.h>
#include <iostream>
#include <cstdlib>

cudaError_t CheckPrimeCUDA(bool *upsik, unsigned long long *dzielnik, unsigned long long *pitca, unsigned long long size);

__global__ void CheckPrimeKernel(bool *upsik, unsigned long long int *dzielnik, unsigned long long *pitca)
{
	*dzielnik = 5 + (threadIdx.x + blockDim.x*blockIdx.x ) * 6;
	if ((*pitca % *dzielnik) == 0)
		*upsik = false;
	if ((*pitca % (*dzielnik + 2)) == 0)
		*upsik = false;
}

int main()
{
	unsigned long long superliczba = 2305843009213693951;
	unsigned long long dzielnik;
	bool sprawdzto = 1;

	if (superliczba % 2 == 0)
		sprawdzto = 0;
	if (superliczba % 3 == 0)
		sprawdzto = 0;
#pragma omp parallel for
	for (dzielnik = 5; dzielnik <= sqrt(superliczba); dzielnik += 6)
	{
		if (superliczba%dzielnik == 0)
			sprawdzto = 0;
			break;
		if (superliczba%dzielnik + 2 == 0)
			sprawdzto = 0;
			break;
	}

	if (sprawdzto == 1)
		printf("pizza supreme\n\n");
	else
	{
		printf("woah\n\n");
	}
	system("pause");

    // Add vectors in parallel.
   // cudaError_t cudaStatus = CheckPrimeKernel(sprawdzto, superliczba, dzielnik);
    //if (cudaStatus != cudaSuccess) {
    //    fprintf(stderr, "addWithCuda failed!");
    //    return 1;
  //  }

  //  printf("{1,2,3,4,5} + {10,20,30,40,50} = {%d,%d,%d,%d,%d}\n",
   //     c[0], c[1], c[2], c[3], c[4]);

    // cudaDeviceReset must be called before exiting in order for profiling and
    // tracing tools such as Nsight and Visual Profiler to show complete traces.
  //  cudaStatus = cudaDeviceReset();
   // if (cudaStatus != cudaSuccess) {
   //     fprintf(stderr, "cudaDeviceReset failed!");
   //     return 1;
   // }

    return 0;
}

// Helper function for using CUDA to add vectors in parallel.
cudaError_t CheckPrimeCUDA(bool *upsik, unsigned long long *dzielnik, unsigned long long *pitca, unsigned long long size)
{
    unsigned long long int *wsk_pitca = 0;
	unsigned long long int *wsk_dzielnik = 0;
	bool * wsk_upsik = 0;
	size = sizeof(unsigned long long int);
    cudaError_t cudaStatus;

    // Choose which GPU to run on, change this on a multi-GPU system.
    cudaStatus = cudaSetDevice(0);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaSetDevice failed!  Do you have a CUDA-capable GPU installed?");
        goto Error;
    }

    // Allocate GPU buffers for three vectors (two input, one output)    .
    cudaStatus = cudaMalloc((void**)&wsk_upsik, size * sizeof(int));
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMalloc failed!");
        goto Error;
    }

    cudaStatus = cudaMalloc((void**)&wsk_pitca, size * sizeof(int));
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMalloc failed!");
        goto Error;
    }

    cudaStatus = cudaMalloc((void**)&wsk_dzielnik, size * sizeof(int));
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMalloc failed!");
        goto Error;
    }

    // Copy input vectors from host memory to GPU buffers.
    cudaStatus = cudaMemcpy(wsk_pitca, pitca, size * sizeof(unsigned long long), cudaMemcpyHostToDevice);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMemcpy failed!");
        goto Error;
    }

    cudaStatus = cudaMemcpy(wsk_dzielnik, dzielnik, size * sizeof(unsigned long long), cudaMemcpyHostToDevice);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMemcpy failed!");
        goto Error;
    }

    // Launch a kernel on the GPU with one thread for each element.
    CheckPrimeKernel<<<2048, 2048>>>(wsk_upsik, wsk_pitca, wsk_dzielnik);

    // Check for any errors launching the kernel
    cudaStatus = cudaGetLastError();
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "addKernel launch failed: %s\n", cudaGetErrorString(cudaStatus));
        goto Error;
    }

    // cudaDeviceSynchronize waits for the kernel to finish, and returns
    // any errors encountered during the launch.
    cudaStatus = cudaDeviceSynchronize();
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaDeviceSynchronize returned error code %d after launching addKernel!\n", cudaStatus);
        goto Error;
    }

    // Copy output vector from GPU buffer to host memory.
    cudaStatus = cudaMemcpy(upsik, wsk_upsik, size * sizeof(unsigned long long), cudaMemcpyDeviceToHost);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMemcpy failed!");
        goto Error;
    }

Error:
    cudaFree(wsk_pitca);
    cudaFree(wsk_dzielnik);
    cudaFree(wsk_upsik);

    return cudaStatus;
}