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
172
173
174
175
|
/* FFdecsa -- fast decsa algorithm
*
* Copyright (C) 2003-2004 fatih89r
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
struct group_t{
unsigned int s1;
unsigned int s2;
};
typedef struct group_t group;
#define GROUP_PARALLELISM 64
group static inline FF0(){
group res;
res.s1=0x0;
res.s2=0x0;
return res;
}
group static inline FF1(){
group res;
res.s1=0xffffffff;
res.s2=0xffffffff;
return res;
}
group static inline FFAND(group a,group b){
group res;
res.s1=a.s1&b.s1;
res.s2=a.s2&b.s2;
return res;
}
group static inline FFOR(group a,group b){
group res;
res.s1=a.s1|b.s1;
res.s2=a.s2|b.s2;
return res;
}
group static inline FFXOR(group a,group b){
group res;
res.s1=a.s1^b.s1;
res.s2=a.s2^b.s2;
return res;
}
group static inline FFNOT(group a){
group res;
res.s1=~a.s1;
res.s2=~a.s2;
return res;
}
/* 64 rows of 64 bits */
void static inline FFTABLEIN(unsigned char *tab, int g, unsigned char *data){
*(((int *)tab)+2*g)=*((int *)data);
*(((int *)tab)+2*g+1)=*(((int *)data)+1);
}
void static inline FFTABLEOUT(unsigned char *data, unsigned char *tab, int g){
*((int *)data)=*(((int *)tab)+2*g);
*(((int *)data)+1)=*(((int *)tab)+2*g+1);
}
void static inline FFTABLEOUTXORNBY(int n, unsigned char *data, unsigned char *tab, int g){
int j;
for(j=0;j<n;j++){
*(data+j)^=*(tab+8*g+j);
}
}
struct batch_t{
unsigned int s1;
unsigned int s2;
};
typedef struct batch_t batch;
#define BYTES_PER_BATCH 8
batch static inline B_FFAND(batch a,batch b){
batch res;
res.s1=a.s1&b.s1;
res.s2=a.s2&b.s2;
return res;
}
batch static inline B_FFOR(batch a,batch b){
batch res;
res.s1=a.s1|b.s1;
res.s2=a.s2|b.s2;
return res;
}
batch static inline B_FFXOR(batch a,batch b){
batch res;
res.s1=a.s1^b.s1;
res.s2=a.s2^b.s2;
return res;
}
batch static inline B_FFN_ALL_29(){
batch res;
res.s1=0x29292929;
res.s2=0x29292929;
return res;
}
batch static inline B_FFN_ALL_02(){
batch res;
res.s1=0x02020202;
res.s2=0x02020202;
return res;
}
batch static inline B_FFN_ALL_04(){
batch res;
res.s1=0x04040404;
res.s2=0x04040404;
return res;
}
batch static inline B_FFN_ALL_10(){
batch res;
res.s1=0x10101010;
res.s2=0x10101010;
return res;
}
batch static inline B_FFN_ALL_40(){
batch res;
res.s1=0x40404040;
res.s2=0x40404040;
return res;
}
batch static inline B_FFN_ALL_80(){
batch res;
res.s1=0x80808080;
res.s2=0x80808080;
return res;
}
batch static inline B_FFSH8L(batch a,int n){
batch res;
res.s1=a.s1<<n;
res.s2=a.s2<<n;
return res;
}
batch static inline B_FFSH8R(batch a,int n){
batch res;
res.s1=a.s1>>n;
res.s2=a.s2>>n;
return res;
}
void static inline M_EMPTY(void){
}
|
