blob: 4a20306383ffe1ea16d9a95a21250187e757d249 (
plain)
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
|
#include "tommath_private.h"
#ifdef S_MP_SQR_C
/* LibTomMath, multiple-precision integer library -- Tom St Denis */
/* SPDX-License-Identifier: Unlicense */
/* low level squaring, b = a*a, HAC pp.596-597, Algorithm 14.16 */
mp_err s_mp_sqr(const mp_int *a, mp_int *b)
{
mp_int t;
int ix, pa;
mp_err err;
pa = a->used;
if ((err = mp_init_size(&t, (2 * pa) + 1)) != MP_OKAY) {
return err;
}
/* default used is maximum possible size */
t.used = (2 * pa) + 1;
for (ix = 0; ix < pa; ix++) {
mp_digit u;
int iy;
/* first calculate the digit at 2*ix */
/* calculate double precision result */
mp_word r = (mp_word)t.dp[2*ix] +
((mp_word)a->dp[ix] * (mp_word)a->dp[ix]);
/* store lower part in result */
t.dp[ix+ix] = (mp_digit)(r & (mp_word)MP_MASK);
/* get the carry */
u = (mp_digit)(r >> (mp_word)MP_DIGIT_BIT);
for (iy = ix + 1; iy < pa; iy++) {
/* first calculate the product */
r = (mp_word)a->dp[ix] * (mp_word)a->dp[iy];
/* now calculate the double precision result, note we use
* addition instead of *2 since it's easier to optimize
*/
r = (mp_word)t.dp[ix + iy] + r + r + (mp_word)u;
/* store lower part */
t.dp[ix + iy] = (mp_digit)(r & (mp_word)MP_MASK);
/* get carry */
u = (mp_digit)(r >> (mp_word)MP_DIGIT_BIT);
}
/* propagate upwards */
while (u != 0uL) {
r = (mp_word)t.dp[ix + iy] + (mp_word)u;
t.dp[ix + iy] = (mp_digit)(r & (mp_word)MP_MASK);
u = (mp_digit)(r >> (mp_word)MP_DIGIT_BIT);
++iy;
}
}
mp_clamp(&t);
mp_exch(&t, b);
mp_clear(&t);
return MP_OKAY;
}
#endif
|
