summaryrefslogtreecommitdiffstats
path: root/libtommath/bn_fast_s_mp_mul_high_digs.c
blob: 8b662ed193a64ef14f0b59b65ba57c2ecdd95a18 (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
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
#include <tommath_private.h>
#ifdef BN_FAST_S_MP_MUL_HIGH_DIGS_C
/* LibTomMath, multiple-precision integer library -- Tom St Denis
 *
 * LibTomMath is a library that provides multiple-precision
 * integer arithmetic as well as number theoretic functionality.
 *
 * The library was designed directly after the MPI library by
 * Michael Fromberger but has been written from scratch with
 * additional optimizations in place.
 *
 * The library is free for all purposes without any express
 * guarantee it works.
 *
 * Tom St Denis, tstdenis82@gmail.com, http://libtom.org
 */

/* this is a modified version of fast_s_mul_digs that only produces
 * output digits *above* digs.  See the comments for fast_s_mul_digs
 * to see how it works.
 *
 * This is used in the Barrett reduction since for one of the multiplications
 * only the higher digits were needed.  This essentially halves the work.
 *
 * Based on Algorithm 14.12 on pp.595 of HAC.
 */
int fast_s_mp_mul_high_digs(const mp_int *a, const mp_int *b, mp_int *c, int digs)
{
   int     olduse, res, pa, ix, iz;
   mp_digit W[MP_WARRAY];
   mp_word  _W;

   /* grow the destination as required */
   pa = a->used + b->used;
   if (c->alloc < pa) {
      if ((res = mp_grow(c, pa)) != MP_OKAY) {
         return res;
      }
   }

   /* number of output digits to produce */
   pa = a->used + b->used;
   _W = 0;
   for (ix = digs; ix < pa; ix++) {
      int      tx, ty, iy;
      mp_digit *tmpx, *tmpy;

      /* get offsets into the two bignums */
      ty = MIN(b->used-1, ix);
      tx = ix - ty;

      /* setup temp aliases */
      tmpx = a->dp + tx;
      tmpy = b->dp + ty;

      /* this is the number of times the loop will iterrate, essentially its
         while (tx++ < a->used && ty-- >= 0) { ... }
       */
      iy = MIN(a->used-tx, ty+1);

      /* execute loop */
      for (iz = 0; iz < iy; iz++) {
         _W += ((mp_word)*tmpx++)*((mp_word)*tmpy--);
      }

      /* store term */
      W[ix] = ((mp_digit)_W) & MP_MASK;

      /* make next carry */
      _W = _W >> ((mp_word)DIGIT_BIT);
   }

   /* setup dest */
   olduse  = c->used;
   c->used = pa;

   {
      mp_digit *tmpc;

      tmpc = c->dp + digs;
      for (ix = digs; ix < pa; ix++) {
         /* now extract the previous digit [below the carry] */
         *tmpc++ = W[ix];
      }

      /* clear unused digits [that existed in the old copy of c] */
      for (; ix < olduse; ix++) {
         *tmpc++ = 0;
      }
   }
   mp_clamp(c);
   return MP_OKAY;
}
#endif

/* ref:         $Format:%D$ */
/* git commit:  $Format:%H$ */
/* commit time: $Format:%ai$ */