-
Notifications
You must be signed in to change notification settings - Fork 0
/
xoshiro256starstar.c
113 lines (88 loc) · 3.06 KB
/
xoshiro256starstar.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
/* Written in 2018 by David Blackman and Sebastiano Vigna ([email protected])
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 <https://creativecommons.org/publicdomain/zero/1.0/>. */
// Obtained using wget https://prng.di.unimi.it/xoshiro256starstar.c
#include <stdint.h>
#include "splitmix64.h"
/* This is xoshiro256** 1.0, one of our all-purpose, rock-solid
generators. It has excellent (sub-ns) speed, a state (256 bits) that is
large enough for any parallel application, and it passes all tests we
are aware of.
For generating just floating-point numbers, xoshiro256+ is even 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. */
#define ARRAY_S_LEN 4
static inline uint64_t rotl(const uint64_t x, int k) {
return (x << k) | (x >> (64 - k));
}
static uint64_t s[ARRAY_S_LEN];
void init_xoshiro256starstar(void) {
for (int index = 0; index < ARRAY_S_LEN; ++index) {
s[index] = splitmix64_get_next();
}
}
uint64_t xoshiro256starstar_get_next(void) {
const uint64_t result = rotl(s[1] * 5, 7) * 9;
const uint64_t t = s[1] << 17;
s[2] ^= s[0];
s[3] ^= s[1];
s[1] ^= s[2];
s[0] ^= s[3];
s[2] ^= t;
s[3] = rotl(s[3], 45);
return result;
}
/* This is the jump function for the generator. It is equivalent
to 2^128 calls to next(); it can be used to generate 2^128
non-overlapping subsequences for parallel computations. */
void xoshiro256starstar_jump(void) {
static const uint64_t JUMP[] = {0x180ec6d33cfd0aba, 0xd5a61266f0c9392c,
0xa9582618e03fc9aa, 0x39abdc4529b1661c};
uint64_t s0 = 0;
uint64_t s1 = 0;
uint64_t s2 = 0;
uint64_t s3 = 0;
for (int i = 0; i < sizeof JUMP / sizeof *JUMP; i++)
for (int b = 0; b < 64; b++) {
if (JUMP[i] & UINT64_C(1) << b) {
s0 ^= s[0];
s1 ^= s[1];
s2 ^= s[2];
s3 ^= s[3];
}
xoshiro256starstar_get_next();
}
s[0] = s0;
s[1] = s1;
s[2] = s2;
s[3] = s3;
}
/* This is the long-jump function for the generator. It is equivalent to
2^192 calls to next(); it can be used to generate 2^64 starting points,
from each of which jump() will generate 2^64 non-overlapping
subsequences for parallel distributed computations. */
void xoshiro256starstar_long_jump(void) {
static const uint64_t LONG_JUMP[] = {0x76e15d3efefdcbbf, 0xc5004e441c522fb3,
0x77710069854ee241, 0x39109bb02acbe635};
uint64_t s0 = 0;
uint64_t s1 = 0;
uint64_t s2 = 0;
uint64_t s3 = 0;
for (int i = 0; i < sizeof LONG_JUMP / sizeof *LONG_JUMP; i++)
for (int b = 0; b < 64; b++) {
if (LONG_JUMP[i] & UINT64_C(1) << b) {
s0 ^= s[0];
s1 ^= s[1];
s2 ^= s[2];
s3 ^= s[3];
}
xoshiro256starstar_get_next();
}
s[0] = s0;
s[1] = s1;
s[2] = s2;
s[3] = s3;
}