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
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
|
/*
* Copyright (c) 2008-2020 Stefan Krah. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS "AS IS" AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
#include "mpdecimal.h"
#include "bits.h"
#include "constants.h"
#include "convolute.h"
#include "fnt.h"
#include "fourstep.h"
#include "numbertheory.h"
#include "sixstep.h"
#include "umodarith.h"
/* Bignum: Fast convolution using the Number Theoretic Transform. Used for
the multiplication of very large coefficients. */
/* Convolute the data in c1 and c2. Result is in c1. */
int
fnt_convolute(mpd_uint_t *c1, mpd_uint_t *c2, mpd_size_t n, int modnum)
{
int (*fnt)(mpd_uint_t *, mpd_size_t, int);
int (*inv_fnt)(mpd_uint_t *, mpd_size_t, int);
#ifdef PPRO
double dmod;
uint32_t dinvmod[3];
#endif
mpd_uint_t n_inv, umod;
mpd_size_t i;
SETMODULUS(modnum);
n_inv = POWMOD(n, (umod-2));
if (ispower2(n)) {
if (n > SIX_STEP_THRESHOLD) {
fnt = six_step_fnt;
inv_fnt = inv_six_step_fnt;
}
else {
fnt = std_fnt;
inv_fnt = std_inv_fnt;
}
}
else {
fnt = four_step_fnt;
inv_fnt = inv_four_step_fnt;
}
if (!fnt(c1, n, modnum)) {
return 0;
}
if (!fnt(c2, n, modnum)) {
return 0;
}
for (i = 0; i < n-1; i += 2) {
mpd_uint_t x0 = c1[i];
mpd_uint_t y0 = c2[i];
mpd_uint_t x1 = c1[i+1];
mpd_uint_t y1 = c2[i+1];
MULMOD2(&x0, y0, &x1, y1);
c1[i] = x0;
c1[i+1] = x1;
}
if (!inv_fnt(c1, n, modnum)) {
return 0;
}
for (i = 0; i < n-3; i += 4) {
mpd_uint_t x0 = c1[i];
mpd_uint_t x1 = c1[i+1];
mpd_uint_t x2 = c1[i+2];
mpd_uint_t x3 = c1[i+3];
MULMOD2C(&x0, &x1, n_inv);
MULMOD2C(&x2, &x3, n_inv);
c1[i] = x0;
c1[i+1] = x1;
c1[i+2] = x2;
c1[i+3] = x3;
}
return 1;
}
/* Autoconvolute the data in c1. Result is in c1. */
int
fnt_autoconvolute(mpd_uint_t *c1, mpd_size_t n, int modnum)
{
int (*fnt)(mpd_uint_t *, mpd_size_t, int);
int (*inv_fnt)(mpd_uint_t *, mpd_size_t, int);
#ifdef PPRO
double dmod;
uint32_t dinvmod[3];
#endif
mpd_uint_t n_inv, umod;
mpd_size_t i;
SETMODULUS(modnum);
n_inv = POWMOD(n, (umod-2));
if (ispower2(n)) {
if (n > SIX_STEP_THRESHOLD) {
fnt = six_step_fnt;
inv_fnt = inv_six_step_fnt;
}
else {
fnt = std_fnt;
inv_fnt = std_inv_fnt;
}
}
else {
fnt = four_step_fnt;
inv_fnt = inv_four_step_fnt;
}
if (!fnt(c1, n, modnum)) {
return 0;
}
for (i = 0; i < n-1; i += 2) {
mpd_uint_t x0 = c1[i];
mpd_uint_t x1 = c1[i+1];
MULMOD2(&x0, x0, &x1, x1);
c1[i] = x0;
c1[i+1] = x1;
}
if (!inv_fnt(c1, n, modnum)) {
return 0;
}
for (i = 0; i < n-3; i += 4) {
mpd_uint_t x0 = c1[i];
mpd_uint_t x1 = c1[i+1];
mpd_uint_t x2 = c1[i+2];
mpd_uint_t x3 = c1[i+3];
MULMOD2C(&x0, &x1, n_inv);
MULMOD2C(&x2, &x3, n_inv);
c1[i] = x0;
c1[i+1] = x1;
c1[i+2] = x2;
c1[i+3] = x3;
}
return 1;
}
|
