// Converted into a C++ class - B. Gregor   bgregor@bu.edu - IS&T  / RCS
// http://scv.bu.edu/examples/random_numbers/xoroshiro128_plus/CPP/
// COMPILE WITH AT LEAST C++11
// e.g. gcc version 4.9.2:  g++ -std=c++0x
//      gcc version 5.3.0:  g++ -std=c++11 or -std=c++14
//      intel version 2015 or 2016:  icc -std=c++11

/*  Written in 2016 by David Blackman and Sebastiano Vigna (vigna@acm.org)

To the extent possible under law, the author has dedicated all copyright
and related and neighboring rights to this software to the public domain
worldwide. This software is distributed without any warranty.

See <http://creativecommons.org/publicdomain/zero/1.0/>. */

#include "xoroshiro128_plus.h"

#include <cstring>
#include <cstdio>
#include <fstream>
#include <random>

/* This is the successor to xorshift128+. It is the fastest full-period
   generator passing BigCrush without systematic failures, but due to the
   relatively short period it is acceptable only for applications with a
   mild amount of parallelism; otherwise, use a xorshift1024* generator.

   Beside passing BigCrush, this generator passes the PractRand test suite
   up to (and included) 16TB, with the exception of binary rank tests,
   which fail due to the lowest bit being an LFSR; all other bits pass all
   tests. We suggest to use a sign test to extract a random Boolean value.

   Note that the generator uses a simulated rotate operation, which most C
   compilers will turn into a single instruction. In Java, you can use
   Long.rotateLeft(). In languages that do not make low-level rotation
   instructions accessible xorshift128+ could be faster.

   The state must be seeded so that it is not everywhere zero. If you have
   a 64-bit seed, we suggest to seed a splitmix64 generator and use its
   output to fill s. */






namespace xoroshiro128_plus {
	// Constructor from seed array.  array must have at least
	// length of 2!
	Xoroshiro128_plus::Xoroshiro128_plus(uint64_t seed_[]) {
		seed_0 = seed_[0];
		seed_1 = seed_[1] ;
	}


	// Copy constructor.
	Xoroshiro128_plus::Xoroshiro128_plus(const Xoroshiro128_plus &obj) {
		seed_0 = obj.seed_0;
		seed_1 = obj.seed_1 ;
	}

	// Get the next uint64_t and update the internal state
	uint64_t Xoroshiro128_plus::next() {
		const uint64_t s0 = seed_0;
		uint64_t s1 = seed_1;
		const uint64_t result = s0 + s1;

		s1 ^= s0;
		seed_0 = Xoroshiro128_plus::rotl(s0, 55) ^ s1 ^ (s1 << 14); // a, b
		seed_1 = Xoroshiro128_plus::rotl(s1, 36); // c

		return result;
	}

        
        // Get the next uint64_t
	uint64_t Xoroshiro128_plus::next_uint64() {
		return next();
	}

	// Return the number of elements in the seed
	const int Xoroshiro128_plus::seed_length = 2 ;

	// Return the total number of bytes in the seed
	int Xoroshiro128_plus::get_seed_bytes() {
		return sizeof(uint64_t)*seed_length ;
	}

	// Return the total number of elements in the seed
	int Xoroshiro128_plus::get_seed_length() {
		return seed_length ;
	}

	/* This is the jump function for the generator. It is equivalent
	   to 2^64 calls to next(); it can be used to generate 2^64
	   non-overlapping subsequences for parallel computations. */
	Xoroshiro128_plus Xoroshiro128_plus::jump() {
		static const uint64_t JUMP[] = { 0xbeac0467eba5facb, 0xd86b048b86aa9922 };

		uint64_t s0 = 0;
		uint64_t s1 = 0;
		for(int i = 0; i < sizeof JUMP / sizeof *JUMP; i++)
			for(int b = 0; b < 64; b++) {
				if (JUMP[i] & 1ULL << b) {
					s0 ^= seed_0;
					s1 ^= seed_1;
				}
				next();
			}
		uint64_t out_seed[2] ;
		out_seed[0] = s0;
		out_seed[1] = s1;
		return Xoroshiro128_plus(out_seed) ;
	}

	// Next double in range (0,1]
	double Xoroshiro128_plus::next_double() {
		// the call to next() advances the state of the RNG
		const union { uint64_t i; double d; } u = { .i = UINT64_C(0x3FF) << 52 |  next()  >> 12 };
	    return u.d - 1.0;
	}

	// Next float in range (0,1]
	float Xoroshiro128_plus::next_float() {
		const union { uint32_t i; float d; } u = { .i =  UINT32_C(0x7F)  << 23 | static_cast<uint32_t>( next() >> 41) };
        return u.d - 1.0f;
	}

	// rotate left.  This gets compiled to a single instruction.
    inline uint64_t Xoroshiro128_plus::rotl(const uint64_t x, int k)  {
		return (x << k) | (x >> (64 - k));
	}

    // Static method to get some random bytes from hardware if available
	// using the C++11 std random library.
    void Xoroshiro128_plus::get_random_seed(uint64_t dest[])
	{
	    // Use hardware random bytes, if available.
        std::random_device rd;
        // Generate a seed sequence.
        // rd() will return an unsigned int: http://www.cplusplus.com/reference/random/random_device/operator()
        // 128 bits are needed, so that's 4 integers.
        dest[0] = static_cast<uint64_t>(rd()) << 32 + static_cast<uint64_t>(rd()) ;
        dest[1] = static_cast<uint64_t>(rd()) << 32 + static_cast<uint64_t>(rd()) ;
        // invert the 2nd seed value to avoid similar reads from hardwar
        dest[1] = 1 - dest[1] ;
    }

}