TeaSpeak/tommath
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

added libtommath-0.35

Browse Source
This commit is contained in:
Tom St Denis 2005-03-12 11:55:11 +00:00 committed by Steffen Jaeckel
parent 3d0fcaab0a
commit fdfa2f4f50
30 changed files with 2139 additions and 1111 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
bn.pdf
View File

Binary file not shown.

2
bn.tex
View File

@ -49,7 +49,7 @@
\begin{document} \begin{document}
\frontmatter \frontmatter
\pagestyle{empty} \pagestyle{empty}
\title{LibTomMath User Manual \\ v0.34} \title{LibTomMath User Manual \\ v0.35}
\author{Tom St Denis \\ tomstdenis@iahu.ca} \author{Tom St Denis \\ tomstdenis@iahu.ca}
\maketitle \maketitle
This text, the library and the accompanying textbook are all hereby placed in the public domain. This book has been This text, the library and the accompanying textbook are all hereby placed in the public domain. This book has been

2
bn_fast_mp_invmod.c
View File

@ -42,7 +42,7 @@ int fast_mp_invmod (mp_int * a, mp_int * b, mp_int * c)
} }
/* we need y = |a| */ /* we need y = |a| */
if ((res = mp_abs (a, &y)) != MP_OKAY) { if ((res = mp_mod (a, b, &y)) != MP_OKAY) {
goto LBL_ERR; goto LBL_ERR;
} }

8
bn_fast_s_mp_mul_digs.c
View File

@ -62,7 +62,7 @@ int fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
tmpx = a->dp + tx; tmpx = a->dp + tx;
tmpy = b->dp + ty; tmpy = b->dp + ty;
/* this is the number of times the loop will iterrate, essentially its /* this is the number of times the loop will iterrate, essentially
while (tx++ < a->used && ty-- >= 0) { ... } while (tx++ < a->used && ty-- >= 0) { ... }
*/ */
iy = MIN(a->used-tx, ty+1); iy = MIN(a->used-tx, ty+1);
@ -80,16 +80,16 @@ int fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
} }
/* store final carry */ /* store final carry */
W[ix] = _W & MP_MASK; W[ix] = (mp_digit)(_W & MP_MASK);
/* setup dest */ /* setup dest */
olduse = c->used; olduse = c->used;
c->used = digs; c->used = pa;
{ {
register mp_digit *tmpc; register mp_digit *tmpc;
tmpc = c->dp; tmpc = c->dp;
for (ix = 0; ix < digs; ix++) { for (ix = 0; ix < pa+1; ix++) {
/* now extract the previous digit [below the carry] */ /* now extract the previous digit [below the carry] */
*tmpc++ = W[ix]; *tmpc++ = W[ix];
} }

2
bn_fast_s_mp_mul_high_digs.c
View File

@ -71,7 +71,7 @@ int fast_s_mp_mul_high_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
} }
/* store final carry */ /* store final carry */
W[ix] = _W & MP_MASK; W[ix] = (mp_digit)(_W & MP_MASK);
/* setup dest */ /* setup dest */
olduse = c->used; olduse = c->used;

33
bn_fast_s_mp_sqr.c
View File

@ -15,33 +15,14 @@
* Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
*/ */
/* fast squaring
*
* This is the comba method where the columns of the product
* are computed first then the carries are computed. This
* has the effect of making a very simple inner loop that
* is executed the most
*
* W2 represents the outer products and W the inner.
*
* A further optimizations is made because the inner
* products are of the form "A * B * 2". The *2 part does
* not need to be computed until the end which is good
* because 64-bit shifts are slow!
*
* Based on Algorithm 14.16 on pp.597 of HAC.
*
*/
/* the jist of squaring... /* the jist of squaring...
* you do like mult except the offset of the tmpx [one that
you do like mult except the offset of the tmpx [one that starts closer to zero] * starts closer to zero] can't equal the offset of tmpy.
can't equal the offset of tmpy. So basically you set up iy like before then you min it with * So basically you set up iy like before then you min it with
(ty-tx) so that it never happens. You double all those you add in the inner loop * (ty-tx) so that it never happens. You double all those
* you add in the inner loop
After that loop you do the squares and add them in. After that loop you do the squares and add them in.
Remove W2 and don't memset W
*/ */
int fast_s_mp_sqr (mp_int * a, mp_int * b) int fast_s_mp_sqr (mp_int * a, mp_int * b)
@ -76,7 +57,7 @@ int fast_s_mp_sqr (mp_int * a, mp_int * b)
tmpx = a->dp + tx; tmpx = a->dp + tx;
tmpy = a->dp + ty; tmpy = a->dp + ty;
/* this is the number of times the loop will iterrate, essentially its /* this is the number of times the loop will iterrate, essentially
while (tx++ < a->used && ty-- >= 0) { ... } while (tx++ < a->used && ty-- >= 0) { ... }
*/ */
iy = MIN(a->used-tx, ty+1); iy = MIN(a->used-tx, ty+1);
@ -101,7 +82,7 @@ int fast_s_mp_sqr (mp_int * a, mp_int * b)
} }
/* store it */ /* store it */
W[ix] = _W & MP_MASK; W[ix] = (mp_digit)(_W & MP_MASK);
/* make next carry */ /* make next carry */
W1 = _W >> ((mp_word)DIGIT_BIT); W1 = _W >> ((mp_word)DIGIT_BIT);

7
bn_mp_exteuclid.c
View File

@ -59,6 +59,13 @@ int mp_exteuclid(mp_int *a, mp_int *b, mp_int *U1, mp_int *U2, mp_int *U3)
if ((err = mp_copy(&t3, &v3)) != MP_OKAY) { goto _ERR; } if ((err = mp_copy(&t3, &v3)) != MP_OKAY) { goto _ERR; }
} }
/* make sure U3 >= 0 */
if (u3.sign == MP_NEG) {
mp_neg(&u1, &u1);
mp_neg(&u2, &u2);
mp_neg(&u3, &u3);
}
/* copy result out */ /* copy result out */
if (U1 != NULL) { mp_exch(U1, &u1); } if (U1 != NULL) { mp_exch(U1, &u1); }
if (U2 != NULL) { mp_exch(U2, &u2); } if (U2 != NULL) { mp_exch(U2, &u2); }

4
bn_mp_invmod_slow.c
View File

@ -33,8 +33,8 @@ int mp_invmod_slow (mp_int * a, mp_int * b, mp_int * c)
} }
/* x = a, y = b */ /* x = a, y = b */
if ((res = mp_copy (a, &x)) != MP_OKAY) { if ((res = mp_mod(a, b, &x)) != MP_OKAY) {
goto LBL_ERR; goto LBL_ERR;
} }
if ((res = mp_copy (b, &y)) != MP_OKAY) { if ((res = mp_copy (b, &y)) != MP_OKAY) {
goto LBL_ERR; goto LBL_ERR;

1
bn_mp_montgomery_calc_normalization.c
View File

@ -28,7 +28,6 @@ int mp_montgomery_calc_normalization (mp_int * a, mp_int * b)
/* how many bits of last digit does b use */ /* how many bits of last digit does b use */
bits = mp_count_bits (b) % DIGIT_BIT; bits = mp_count_bits (b) % DIGIT_BIT;
if (b->used > 1) { if (b->used > 1) {
if ((res = mp_2expt (a, (b->used - 1) * DIGIT_BIT + bits - 1)) != MP_OKAY) { if ((res = mp_2expt (a, (b->used - 1) * DIGIT_BIT + bits - 1)) != MP_OKAY) {
return res; return res;

10
bn_mp_neg.c
View File

@ -19,12 +19,18 @@
int mp_neg (mp_int * a, mp_int * b) int mp_neg (mp_int * a, mp_int * b)
{ {
int res; int res;
if ((res = mp_copy (a, b)) != MP_OKAY) { if (a != b) {
return res; if ((res = mp_copy (a, b)) != MP_OKAY) {
return res;
}
} }
if (mp_iszero(b) != MP_YES) { if (mp_iszero(b) != MP_YES) {
b->sign = (a->sign == MP_ZPOS) ? MP_NEG : MP_ZPOS; b->sign = (a->sign == MP_ZPOS) ? MP_NEG : MP_ZPOS;
} else {
b->sign = MP_ZPOS;
} }
return MP_OKAY; return MP_OKAY;
} }
#endif #endif

19
bn_mp_radix_size.c
View File

@ -35,22 +35,29 @@ int mp_radix_size (mp_int * a, int radix, int *size)
return MP_VAL; return MP_VAL;
} }
/* init a copy of the input */ if (mp_iszero(a) == MP_YES) {
if ((res = mp_init_copy (&t, a)) != MP_OKAY) { *size = 2;
return res; return MP_OKAY;
} }
/* digs is the digit count */ /* digs is the digit count */
digs = 0; digs = 0;
/* if it's negative add one for the sign */ /* if it's negative add one for the sign */
if (t.sign == MP_NEG) { if (a->sign == MP_NEG) {
++digs; ++digs;
t.sign = MP_ZPOS;
} }
/* init a copy of the input */
if ((res = mp_init_copy (&t, a)) != MP_OKAY) {
return res;
}
/* force temp to positive */
t.sign = MP_ZPOS;
/* fetch out all of the digits */ /* fetch out all of the digits */
while (mp_iszero (&t) == 0) { while (mp_iszero (&t) == MP_NO) {
if ((res = mp_div_d (&t, (mp_digit) radix, &t, &d)) != MP_OKAY) { if ((res = mp_div_d (&t, (mp_digit) radix, &t, &d)) != MP_OKAY) {
mp_clear (&t); mp_clear (&t);
return res; return res;

4
bn_mp_rand.c
View File

@ -29,14 +29,14 @@ mp_rand (mp_int * a, int digits)
/* first place a random non-zero digit */ /* first place a random non-zero digit */
do { do {
d = ((mp_digit) abs (rand ())); d = ((mp_digit) abs (rand ())) & MP_MASK;
} while (d == 0); } while (d == 0);
if ((res = mp_add_d (a, d, a)) != MP_OKAY) { if ((res = mp_add_d (a, d, a)) != MP_OKAY) {
return res; return res;
} }
while (digits-- > 0) { while (--digits > 0) {
if ((res = mp_lshd (a, 1)) != MP_OKAY) { if ((res = mp_lshd (a, 1)) != MP_OKAY) {
return res; return res;
} }

4
bn_mp_reduce.c
View File

@ -39,11 +39,11 @@ int mp_reduce (mp_int * x, mp_int * m, mp_int * mu)
} }
} else { } else {
#ifdef BN_S_MP_MUL_HIGH_DIGS_C #ifdef BN_S_MP_MUL_HIGH_DIGS_C
if ((res = s_mp_mul_high_digs (&q, mu, &q, um - 1)) != MP_OKAY) { if ((res = s_mp_mul_high_digs (&q, mu, &q, um)) != MP_OKAY) {
goto CLEANUP; goto CLEANUP;
} }
#elif defined(BN_FAST_S_MP_MUL_HIGH_DIGS_C) #elif defined(BN_FAST_S_MP_MUL_HIGH_DIGS_C)
if ((res = fast_s_mp_mul_high_digs (&q, mu, &q, um - 1)) != MP_OKAY) { if ((res = fast_s_mp_mul_high_digs (&q, mu, &q, um)) != MP_OKAY) {
goto CLEANUP; goto CLEANUP;
} }
#else #else

7
bn_mp_toom_mul.c
View File

@ -17,9 +17,10 @@
/* multiplication using the Toom-Cook 3-way algorithm /* multiplication using the Toom-Cook 3-way algorithm
* *
* Much more complicated than Karatsuba but has a lower asymptotic running time of * Much more complicated than Karatsuba but has a lower
* O(N**1.464). This algorithm is only particularly useful on VERY large * asymptotic running time of O(N**1.464). This algorithm is
* inputs (we're talking 1000s of digits here...). * only particularly useful on VERY large inputs
* (we're talking 1000s of digits here...).
*/ */
int mp_toom_mul(mp_int *a, mp_int *b, mp_int *c) int mp_toom_mul(mp_int *a, mp_int *b, mp_int *c)
{ {

2
bn_mp_xor.c
View File

@ -37,7 +37,7 @@ mp_xor (mp_int * a, mp_int * b, mp_int * c)
} }
for (ix = 0; ix < px; ix++) { for (ix = 0; ix < px; ix++) {
t.dp[ix] ^= x->dp[ix];
} }
mp_clamp (&t); mp_clamp (&t);
mp_exch (c, &t); mp_exch (c, &t);

12
bn_mp_zero.c
View File

@ -16,11 +16,17 @@
*/ */
/* set to zero */ /* set to zero */
void void mp_zero (mp_int * a)
mp_zero (mp_int * a)
{ {
int n;
mp_digit *tmp;
a->sign = MP_ZPOS; a->sign = MP_ZPOS;
a->used = 0; a->used = 0;
memset (a->dp, 0, sizeof (mp_digit) * a->alloc);
tmp = a->dp;
for (n = 0; n < a->alloc; n++) {
*tmp++ = 0;
}
} }
#endif #endif

3
bn_s_mp_mul_digs.c
View File

@ -19,8 +19,7 @@
* HAC pp. 595, Algorithm 14.12 Modified so you can control how * HAC pp. 595, Algorithm 14.12 Modified so you can control how
* many digits of output are created. * many digits of output are created.
*/ */
int int s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
{ {
mp_int t; mp_int t;
int res, pa, pb, ix, iy; int res, pa, pb, ix, iy;

3
bn_s_mp_sqr.c
View File

@ -16,8 +16,7 @@
*/ */
/* low level squaring, b = a*a, HAC pp.596-597, Algorithm 14.16 */ /* low level squaring, b = a*a, HAC pp.596-597, Algorithm 14.16 */
int int s_mp_sqr (mp_int * a, mp_int * b)
s_mp_sqr (mp_int * a, mp_int * b)
{ {
mp_int t; mp_int t;
int res, ix, iy, pa; int res, ix, iy, pa;

887
callgraph.txt
View File

@ -907,7 +907,64 @@ BN_MP_EXPTMOD_C
| | | +--->BN_MP_CLEAR_C | | | +--->BN_MP_CLEAR_C
| | +--->BN_MP_COPY_C | | +--->BN_MP_COPY_C
| | | +--->BN_MP_GROW_C | | | +--->BN_MP_GROW_C
| | +--->BN_MP_ABS_C | | +--->BN_MP_MOD_C
| | | +--->BN_MP_DIV_C
| | | | +--->BN_MP_CMP_MAG_C
| | | | +--->BN_MP_ZERO_C
| | | | +--->BN_MP_SET_C
| | | | +--->BN_MP_COUNT_BITS_C
| | | | +--->BN_MP_ABS_C
| | | | +--->BN_MP_MUL_2D_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_LSHD_C
| | | | | | +--->BN_MP_RSHD_C
| | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_CMP_C
| | | | +--->BN_MP_SUB_C
| | | | | +--->BN_S_MP_ADD_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_S_MP_SUB_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_ADD_C
| | | | | +--->BN_S_MP_ADD_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_S_MP_SUB_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_DIV_2D_C
| | | | | +--->BN_MP_MOD_2D_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_RSHD_C
| | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_EXCH_C
| | | | +--->BN_MP_EXCH_C
| | | | +--->BN_MP_CLEAR_MULTI_C
| | | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_INIT_SIZE_C
| | | | +--->BN_MP_INIT_COPY_C
| | | | +--->BN_MP_LSHD_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_RSHD_C
| | | | +--->BN_MP_RSHD_C
| | | | +--->BN_MP_MUL_D_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_CLEAR_C
| | | +--->BN_MP_CLEAR_C
| | | +--->BN_MP_ADD_C
| | | | +--->BN_S_MP_ADD_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_CMP_MAG_C
| | | | +--->BN_S_MP_SUB_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_EXCH_C
| | +--->BN_MP_SET_C | | +--->BN_MP_SET_C
| | | +--->BN_MP_ZERO_C | | | +--->BN_MP_ZERO_C
| | +--->BN_MP_DIV_2_C | | +--->BN_MP_DIV_2_C
@ -938,6 +995,66 @@ BN_MP_EXPTMOD_C
| +--->BN_MP_INVMOD_SLOW_C | +--->BN_MP_INVMOD_SLOW_C
| | +--->BN_MP_INIT_MULTI_C | | +--->BN_MP_INIT_MULTI_C
| | | +--->BN_MP_CLEAR_C | | | +--->BN_MP_CLEAR_C
| | +--->BN_MP_MOD_C
| | | +--->BN_MP_DIV_C
| | | | +--->BN_MP_CMP_MAG_C
| | | | +--->BN_MP_COPY_C
| | | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_ZERO_C
| | | | +--->BN_MP_SET_C
| | | | +--->BN_MP_COUNT_BITS_C
| | | | +--->BN_MP_ABS_C
| | | | +--->BN_MP_MUL_2D_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_LSHD_C
| | | | | | +--->BN_MP_RSHD_C
| | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_CMP_C
| | | | +--->BN_MP_SUB_C
| | | | | +--->BN_S_MP_ADD_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_S_MP_SUB_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_ADD_C
| | | | | +--->BN_S_MP_ADD_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_S_MP_SUB_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_DIV_2D_C
| | | | | +--->BN_MP_MOD_2D_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_RSHD_C
| | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_EXCH_C
| | | | +--->BN_MP_EXCH_C
| | | | +--->BN_MP_CLEAR_MULTI_C
| | | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_INIT_SIZE_C
| | | | +--->BN_MP_INIT_COPY_C
| | | | +--->BN_MP_LSHD_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_RSHD_C
| | | | +--->BN_MP_RSHD_C
| | | | +--->BN_MP_MUL_D_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_CLEAR_C
| | | +--->BN_MP_CLEAR_C
| | | +--->BN_MP_ADD_C
| | | | +--->BN_S_MP_ADD_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_CMP_MAG_C
| | | | +--->BN_S_MP_SUB_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_EXCH_C
| | +--->BN_MP_COPY_C | | +--->BN_MP_COPY_C
| | | +--->BN_MP_GROW_C | | | +--->BN_MP_GROW_C
| | +--->BN_MP_SET_C | | +--->BN_MP_SET_C
@ -1874,7 +1991,64 @@ BN_MP_PRIME_FERMAT_C
| | | | +--->BN_MP_CLEAR_C | | | | +--->BN_MP_CLEAR_C
| | | +--->BN_MP_COPY_C | | | +--->BN_MP_COPY_C
| | | | +--->BN_MP_GROW_C | | | | +--->BN_MP_GROW_C
| | | +--->BN_MP_ABS_C | | | +--->BN_MP_MOD_C
| | | | +--->BN_MP_DIV_C
| | | | | +--->BN_MP_CMP_MAG_C
| | | | | +--->BN_MP_ZERO_C
| | | | | +--->BN_MP_SET_C
| | | | | +--->BN_MP_COUNT_BITS_C
| | | | | +--->BN_MP_ABS_C
| | | | | +--->BN_MP_MUL_2D_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_LSHD_C
| | | | | | | +--->BN_MP_RSHD_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CMP_C
| | | | | +--->BN_MP_SUB_C
| | | | | | +--->BN_S_MP_ADD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_S_MP_SUB_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_ADD_C
| | | | | | +--->BN_S_MP_ADD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_S_MP_SUB_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_DIV_2D_C
| | | | | | +--->BN_MP_MOD_2D_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CLEAR_C
| | | | | | +--->BN_MP_RSHD_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_EXCH_C
| | | | | +--->BN_MP_EXCH_C
| | | | | +--->BN_MP_CLEAR_MULTI_C
| | | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_INIT_SIZE_C
| | | | | +--->BN_MP_INIT_COPY_C
| | | | | +--->BN_MP_LSHD_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_RSHD_C
| | | | | +--->BN_MP_RSHD_C
| | | | | +--->BN_MP_MUL_D_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_ADD_C
| | | | | +--->BN_S_MP_ADD_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CMP_MAG_C
| | | | | +--->BN_S_MP_SUB_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_EXCH_C
| | | +--->BN_MP_SET_C | | | +--->BN_MP_SET_C
| | | | +--->BN_MP_ZERO_C | | | | +--->BN_MP_ZERO_C
| | | +--->BN_MP_DIV_2_C | | | +--->BN_MP_DIV_2_C
@ -1904,6 +2078,66 @@ BN_MP_PRIME_FERMAT_C
| | +--->BN_MP_INVMOD_SLOW_C | | +--->BN_MP_INVMOD_SLOW_C
| | | +--->BN_MP_INIT_MULTI_C | | | +--->BN_MP_INIT_MULTI_C
| | | | +--->BN_MP_CLEAR_C | | | | +--->BN_MP_CLEAR_C
| | | +--->BN_MP_MOD_C
| | | | +--->BN_MP_DIV_C
| | | | | +--->BN_MP_CMP_MAG_C
| | | | | +--->BN_MP_COPY_C
| | | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_ZERO_C
| | | | | +--->BN_MP_SET_C
| | | | | +--->BN_MP_COUNT_BITS_C
| | | | | +--->BN_MP_ABS_C
| | | | | +--->BN_MP_MUL_2D_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_LSHD_C
| | | | | | | +--->BN_MP_RSHD_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CMP_C
| | | | | +--->BN_MP_SUB_C
| | | | | | +--->BN_S_MP_ADD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_S_MP_SUB_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_ADD_C
| | | | | | +--->BN_S_MP_ADD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_S_MP_SUB_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_DIV_2D_C
| | | | | | +--->BN_MP_MOD_2D_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CLEAR_C
| | | | | | +--->BN_MP_RSHD_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_EXCH_C
| | | | | +--->BN_MP_EXCH_C
| | | | | +--->BN_MP_CLEAR_MULTI_C
| | | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_INIT_SIZE_C
| | | | | +--->BN_MP_INIT_COPY_C
| | | | | +--->BN_MP_LSHD_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_RSHD_C
| | | | | +--->BN_MP_RSHD_C
| | | | | +--->BN_MP_MUL_D_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_ADD_C
| | | | | +--->BN_S_MP_ADD_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CMP_MAG_C
| | | | | +--->BN_S_MP_SUB_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_EXCH_C
| | | +--->BN_MP_COPY_C | | | +--->BN_MP_COPY_C
| | | | +--->BN_MP_GROW_C | | | | +--->BN_MP_GROW_C
| | | +--->BN_MP_SET_C | | | +--->BN_MP_SET_C
@ -3111,7 +3345,65 @@ BN_MP_INVMOD_C
| | +--->BN_MP_CLEAR_C | | +--->BN_MP_CLEAR_C
| +--->BN_MP_COPY_C | +--->BN_MP_COPY_C
| | +--->BN_MP_GROW_C | | +--->BN_MP_GROW_C
| +--->BN_MP_ABS_C | +--->BN_MP_MOD_C
| | +--->BN_MP_INIT_C
| | +--->BN_MP_DIV_C
| | | +--->BN_MP_CMP_MAG_C
| | | +--->BN_MP_ZERO_C
| | | +--->BN_MP_SET_C
| | | +--->BN_MP_COUNT_BITS_C
| | | +--->BN_MP_ABS_C
| | | +--->BN_MP_MUL_2D_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_LSHD_C
| | | | | +--->BN_MP_RSHD_C
| | | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_CMP_C
| | | +--->BN_MP_SUB_C
| | | | +--->BN_S_MP_ADD_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_S_MP_SUB_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_ADD_C
| | | | +--->BN_S_MP_ADD_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_S_MP_SUB_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_DIV_2D_C
| | | | +--->BN_MP_MOD_2D_C
| | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_RSHD_C
| | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_EXCH_C
| | | +--->BN_MP_EXCH_C
| | | +--->BN_MP_CLEAR_MULTI_C
| | | | +--->BN_MP_CLEAR_C
| | | +--->BN_MP_INIT_SIZE_C
| | | +--->BN_MP_INIT_COPY_C
| | | +--->BN_MP_LSHD_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_RSHD_C
| | | +--->BN_MP_RSHD_C
| | | +--->BN_MP_MUL_D_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_CLEAR_C
| | +--->BN_MP_CLEAR_C
| | +--->BN_MP_ADD_C
| | | +--->BN_S_MP_ADD_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_CMP_MAG_C
| | | +--->BN_S_MP_SUB_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_CLAMP_C
| | +--->BN_MP_EXCH_C
| +--->BN_MP_SET_C | +--->BN_MP_SET_C
| | +--->BN_MP_ZERO_C | | +--->BN_MP_ZERO_C
| +--->BN_MP_DIV_2_C | +--->BN_MP_DIV_2_C
@ -3143,6 +3435,67 @@ BN_MP_INVMOD_C
| +--->BN_MP_INIT_MULTI_C | +--->BN_MP_INIT_MULTI_C
| | +--->BN_MP_INIT_C | | +--->BN_MP_INIT_C
| | +--->BN_MP_CLEAR_C | | +--->BN_MP_CLEAR_C
| +--->BN_MP_MOD_C
| | +--->BN_MP_INIT_C
| | +--->BN_MP_DIV_C
| | | +--->BN_MP_CMP_MAG_C
| | | +--->BN_MP_COPY_C
| | | | +--->BN_MP_GROW_C
| | | +--->BN_MP_ZERO_C
| | | +--->BN_MP_SET_C
| | | +--->BN_MP_COUNT_BITS_C
| | | +--->BN_MP_ABS_C
| | | +--->BN_MP_MUL_2D_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_LSHD_C
| | | | | +--->BN_MP_RSHD_C
| | | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_CMP_C
| | | +--->BN_MP_SUB_C
| | | | +--->BN_S_MP_ADD_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_S_MP_SUB_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_ADD_C
| | | | +--->BN_S_MP_ADD_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_S_MP_SUB_C
| | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_DIV_2D_C
| | | | +--->BN_MP_MOD_2D_C
| | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_RSHD_C
| | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_EXCH_C
| | | +--->BN_MP_EXCH_C
| | | +--->BN_MP_CLEAR_MULTI_C
| | | | +--->BN_MP_CLEAR_C
| | | +--->BN_MP_INIT_SIZE_C
| | | +--->BN_MP_INIT_COPY_C
| | | +--->BN_MP_LSHD_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_RSHD_C
| | | +--->BN_MP_RSHD_C
| | | +--->BN_MP_MUL_D_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_CLEAR_C
| | +--->BN_MP_CLEAR_C
| | +--->BN_MP_ADD_C
| | | +--->BN_S_MP_ADD_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_CMP_MAG_C
| | | +--->BN_S_MP_SUB_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_CLAMP_C
| | +--->BN_MP_EXCH_C
| +--->BN_MP_COPY_C | +--->BN_MP_COPY_C
| | +--->BN_MP_GROW_C | | +--->BN_MP_GROW_C
| +--->BN_MP_SET_C | +--->BN_MP_SET_C
@ -3195,7 +3548,65 @@ BN_FAST_MP_INVMOD_C
| +--->BN_MP_CLEAR_C | +--->BN_MP_CLEAR_C
+--->BN_MP_COPY_C +--->BN_MP_COPY_C
| +--->BN_MP_GROW_C | +--->BN_MP_GROW_C
+--->BN_MP_ABS_C +--->BN_MP_MOD_C
| +--->BN_MP_INIT_C
| +--->BN_MP_DIV_C
| | +--->BN_MP_CMP_MAG_C
| | +--->BN_MP_ZERO_C
| | +--->BN_MP_SET_C
| | +--->BN_MP_COUNT_BITS_C
| | +--->BN_MP_ABS_C
| | +--->BN_MP_MUL_2D_C
| | | +--->BN_MP_GROW_C
| | | +--->BN_MP_LSHD_C
| | | | +--->BN_MP_RSHD_C
| | | +--->BN_MP_CLAMP_C
| | +--->BN_MP_CMP_C
| | +--->BN_MP_SUB_C
| | | +--->BN_S_MP_ADD_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_CLAMP_C
| | | +--->BN_S_MP_SUB_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_CLAMP_C
| | +--->BN_MP_ADD_C
| | | +--->BN_S_MP_ADD_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_CLAMP_C
| | | +--->BN_S_MP_SUB_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_CLAMP_C
| | +--->BN_MP_DIV_2D_C
| | | +--->BN_MP_MOD_2D_C
| | | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_CLEAR_C
| | | +--->BN_MP_RSHD_C
| | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_EXCH_C
| | +--->BN_MP_EXCH_C
| | +--->BN_MP_CLEAR_MULTI_C
| | | +--->BN_MP_CLEAR_C
| | +--->BN_MP_INIT_SIZE_C
| | +--->BN_MP_INIT_COPY_C
| | +--->BN_MP_LSHD_C
| | | +--->BN_MP_GROW_C
| | | +--->BN_MP_RSHD_C
| | +--->BN_MP_RSHD_C
| | +--->BN_MP_MUL_D_C
| | | +--->BN_MP_GROW_C
| | | +--->BN_MP_CLAMP_C
| | +--->BN_MP_CLAMP_C
| | +--->BN_MP_CLEAR_C
| +--->BN_MP_CLEAR_C
| +--->BN_MP_ADD_C
| | +--->BN_S_MP_ADD_C
| | | +--->BN_MP_GROW_C
| | | +--->BN_MP_CLAMP_C
| | +--->BN_MP_CMP_MAG_C
| | +--->BN_S_MP_SUB_C
| | | +--->BN_MP_GROW_C
| | | +--->BN_MP_CLAMP_C
| +--->BN_MP_EXCH_C
+--->BN_MP_SET_C +--->BN_MP_SET_C
| +--->BN_MP_ZERO_C | +--->BN_MP_ZERO_C
+--->BN_MP_DIV_2_C +--->BN_MP_DIV_2_C
@ -3683,7 +4094,55 @@ BN_MP_PRIME_RANDOM_EX_C
| | | | | | +--->BN_MP_CLEAR_C | | | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_COPY_C | | | | | +--->BN_MP_COPY_C
| | | | | | +--->BN_MP_GROW_C | | | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_ABS_C | | | | | +--->BN_MP_MOD_C
| | | | | | +--->BN_MP_DIV_C
| | | | | | | +--->BN_MP_CMP_MAG_C
| | | | | | | +--->BN_MP_ZERO_C
| | | | | | | +--->BN_MP_COUNT_BITS_C
| | | | | | | +--->BN_MP_ABS_C
| | | | | | | +--->BN_MP_MUL_2D_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_LSHD_C
| | | | | | | | | +--->BN_MP_RSHD_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_MP_CMP_C
| | | | | | | +--->BN_MP_SUB_C
| | | | | | | | +--->BN_S_MP_ADD_C
| | | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | | +--->BN_S_MP_SUB_C
| | | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_MP_ADD_C
| | | | | | | | +--->BN_S_MP_ADD_C
| | | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | | +--->BN_S_MP_SUB_C
| | | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_MP_EXCH_C
| | | | | | | +--->BN_MP_CLEAR_MULTI_C
| | | | | | | | +--->BN_MP_CLEAR_C
| | | | | | | +--->BN_MP_INIT_SIZE_C
| | | | | | | +--->BN_MP_LSHD_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_RSHD_C
| | | | | | | +--->BN_MP_RSHD_C
| | | | | | | +--->BN_MP_MUL_D_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_MP_CLEAR_C
| | | | | | +--->BN_MP_CLEAR_C
| | | | | | +--->BN_MP_ADD_C
| | | | | | | +--->BN_S_MP_ADD_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_MP_CMP_MAG_C
| | | | | | | +--->BN_S_MP_SUB_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_EXCH_C
| | | | | +--->BN_MP_DIV_2_C | | | | | +--->BN_MP_DIV_2_C
| | | | | | +--->BN_MP_GROW_C | | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C | | | | | | +--->BN_MP_CLAMP_C
@ -3711,6 +4170,57 @@ BN_MP_PRIME_RANDOM_EX_C
| | | | +--->BN_MP_INVMOD_SLOW_C | | | | +--->BN_MP_INVMOD_SLOW_C
| | | | | +--->BN_MP_INIT_MULTI_C | | | | | +--->BN_MP_INIT_MULTI_C
| | | | | | +--->BN_MP_CLEAR_C | | | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_MOD_C
| | | | | | +--->BN_MP_DIV_C
| | | | | | | +--->BN_MP_CMP_MAG_C
| | | | | | | +--->BN_MP_COPY_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_ZERO_C
| | | | | | | +--->BN_MP_COUNT_BITS_C
| | | | | | | +--->BN_MP_ABS_C
| | | | | | | +--->BN_MP_MUL_2D_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_LSHD_C
| | | | | | | | | +--->BN_MP_RSHD_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_MP_CMP_C
| | | | | | | +--->BN_MP_SUB_C
| | | | | | | | +--->BN_S_MP_ADD_C
| | | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | | +--->BN_S_MP_SUB_C
| | | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_MP_ADD_C
| | | | | | | | +--->BN_S_MP_ADD_C
| | | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | | +--->BN_S_MP_SUB_C
| | | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_MP_EXCH_C
| | | | | | | +--->BN_MP_CLEAR_MULTI_C
| | | | | | | | +--->BN_MP_CLEAR_C
| | | | | | | +--->BN_MP_INIT_SIZE_C
| | | | | | | +--->BN_MP_LSHD_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_RSHD_C
| | | | | | | +--->BN_MP_RSHD_C
| | | | | | | +--->BN_MP_MUL_D_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_MP_CLEAR_C
| | | | | | +--->BN_MP_CLEAR_C
| | | | | | +--->BN_MP_ADD_C
| | | | | | | +--->BN_S_MP_ADD_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_MP_CMP_MAG_C
| | | | | | | +--->BN_S_MP_SUB_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_EXCH_C
| | | | | +--->BN_MP_COPY_C | | | | | +--->BN_MP_COPY_C
| | | | | | +--->BN_MP_GROW_C | | | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_DIV_2_C | | | | | +--->BN_MP_DIV_2_C
@ -5057,7 +5567,55 @@ BN_MP_PRIME_IS_PRIME_C
| | | | | +--->BN_MP_CLEAR_C | | | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_COPY_C | | | | +--->BN_MP_COPY_C
| | | | | +--->BN_MP_GROW_C | | | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_ABS_C | | | | +--->BN_MP_MOD_C
| | | | | +--->BN_MP_DIV_C
| | | | | | +--->BN_MP_CMP_MAG_C
| | | | | | +--->BN_MP_ZERO_C
| | | | | | +--->BN_MP_COUNT_BITS_C
| | | | | | +--->BN_MP_ABS_C
| | | | | | +--->BN_MP_MUL_2D_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_LSHD_C
| | | | | | | | +--->BN_MP_RSHD_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CMP_C
| | | | | | +--->BN_MP_SUB_C
| | | | | | | +--->BN_S_MP_ADD_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_S_MP_SUB_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_ADD_C
| | | | | | | +--->BN_S_MP_ADD_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_S_MP_SUB_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_EXCH_C
| | | | | | +--->BN_MP_CLEAR_MULTI_C
| | | | | | | +--->BN_MP_CLEAR_C
| | | | | | +--->BN_MP_INIT_SIZE_C
| | | | | | +--->BN_MP_LSHD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_RSHD_C
| | | | | | +--->BN_MP_RSHD_C
| | | | | | +--->BN_MP_MUL_D_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_ADD_C
| | | | | | +--->BN_S_MP_ADD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CMP_MAG_C
| | | | | | +--->BN_S_MP_SUB_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_EXCH_C
| | | | +--->BN_MP_DIV_2_C | | | | +--->BN_MP_DIV_2_C
| | | | | +--->BN_MP_GROW_C | | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C | | | | | +--->BN_MP_CLAMP_C
@ -5085,6 +5643,57 @@ BN_MP_PRIME_IS_PRIME_C
| | | +--->BN_MP_INVMOD_SLOW_C | | | +--->BN_MP_INVMOD_SLOW_C
| | | | +--->BN_MP_INIT_MULTI_C | | | | +--->BN_MP_INIT_MULTI_C
| | | | | +--->BN_MP_CLEAR_C | | | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_MOD_C
| | | | | +--->BN_MP_DIV_C
| | | | | | +--->BN_MP_CMP_MAG_C
| | | | | | +--->BN_MP_COPY_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_ZERO_C
| | | | | | +--->BN_MP_COUNT_BITS_C
| | | | | | +--->BN_MP_ABS_C
| | | | | | +--->BN_MP_MUL_2D_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_LSHD_C
| | | | | | | | +--->BN_MP_RSHD_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CMP_C
| | | | | | +--->BN_MP_SUB_C
| | | | | | | +--->BN_S_MP_ADD_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_S_MP_SUB_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_ADD_C
| | | | | | | +--->BN_S_MP_ADD_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_S_MP_SUB_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_EXCH_C
| | | | | | +--->BN_MP_CLEAR_MULTI_C
| | | | | | | +--->BN_MP_CLEAR_C
| | | | | | +--->BN_MP_INIT_SIZE_C
| | | | | | +--->BN_MP_LSHD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_RSHD_C
| | | | | | +--->BN_MP_RSHD_C
| | | | | | +--->BN_MP_MUL_D_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_ADD_C
| | | | | | +--->BN_S_MP_ADD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CMP_MAG_C
| | | | | | +--->BN_S_MP_SUB_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_EXCH_C
| | | | +--->BN_MP_COPY_C | | | | +--->BN_MP_COPY_C
| | | | | +--->BN_MP_GROW_C | | | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_DIV_2_C | | | | +--->BN_MP_DIV_2_C
@ -6894,7 +7503,55 @@ BN_MP_PRIME_NEXT_PRIME_C
| | | | | +--->BN_MP_CLEAR_C | | | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_COPY_C | | | | +--->BN_MP_COPY_C
| | | | | +--->BN_MP_GROW_C | | | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_ABS_C | | | | +--->BN_MP_MOD_C
| | | | | +--->BN_MP_DIV_C
| | | | | | +--->BN_MP_CMP_MAG_C
| | | | | | +--->BN_MP_ZERO_C
| | | | | | +--->BN_MP_COUNT_BITS_C
| | | | | | +--->BN_MP_ABS_C
| | | | | | +--->BN_MP_MUL_2D_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_LSHD_C
| | | | | | | | +--->BN_MP_RSHD_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CMP_C
| | | | | | +--->BN_MP_SUB_C
| | | | | | | +--->BN_S_MP_ADD_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_S_MP_SUB_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_ADD_C
| | | | | | | +--->BN_S_MP_ADD_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_S_MP_SUB_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_EXCH_C
| | | | | | +--->BN_MP_CLEAR_MULTI_C
| | | | | | | +--->BN_MP_CLEAR_C
| | | | | | +--->BN_MP_INIT_SIZE_C
| | | | | | +--->BN_MP_LSHD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_RSHD_C
| | | | | | +--->BN_MP_RSHD_C
| | | | | | +--->BN_MP_MUL_D_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_ADD_C
| | | | | | +--->BN_S_MP_ADD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CMP_MAG_C
| | | | | | +--->BN_S_MP_SUB_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_EXCH_C
| | | | +--->BN_MP_DIV_2_C | | | | +--->BN_MP_DIV_2_C
| | | | | +--->BN_MP_GROW_C | | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_CLAMP_C | | | | | +--->BN_MP_CLAMP_C
@ -6922,6 +7579,57 @@ BN_MP_PRIME_NEXT_PRIME_C
| | | +--->BN_MP_INVMOD_SLOW_C | | | +--->BN_MP_INVMOD_SLOW_C
| | | | +--->BN_MP_INIT_MULTI_C | | | | +--->BN_MP_INIT_MULTI_C
| | | | | +--->BN_MP_CLEAR_C | | | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_MOD_C
| | | | | +--->BN_MP_DIV_C
| | | | | | +--->BN_MP_CMP_MAG_C
| | | | | | +--->BN_MP_COPY_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_ZERO_C
| | | | | | +--->BN_MP_COUNT_BITS_C
| | | | | | +--->BN_MP_ABS_C
| | | | | | +--->BN_MP_MUL_2D_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_LSHD_C
| | | | | | | | +--->BN_MP_RSHD_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CMP_C
| | | | | | +--->BN_MP_SUB_C
| | | | | | | +--->BN_S_MP_ADD_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_S_MP_SUB_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_ADD_C
| | | | | | | +--->BN_S_MP_ADD_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | | +--->BN_S_MP_SUB_C
| | | | | | | | +--->BN_MP_GROW_C
| | | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_EXCH_C
| | | | | | +--->BN_MP_CLEAR_MULTI_C
| | | | | | | +--->BN_MP_CLEAR_C
| | | | | | +--->BN_MP_INIT_SIZE_C
| | | | | | +--->BN_MP_LSHD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_RSHD_C
| | | | | | +--->BN_MP_RSHD_C
| | | | | | +--->BN_MP_MUL_D_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_ADD_C
| | | | | | +--->BN_S_MP_ADD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_MP_CMP_MAG_C
| | | | | | +--->BN_S_MP_SUB_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_EXCH_C
| | | | +--->BN_MP_COPY_C | | | | +--->BN_MP_COPY_C
| | | | | +--->BN_MP_GROW_C | | | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_DIV_2_C | | | | +--->BN_MP_DIV_2_C
@ -7898,6 +8606,67 @@ BN_MP_INVMOD_SLOW_C
+--->BN_MP_INIT_MULTI_C +--->BN_MP_INIT_MULTI_C
| +--->BN_MP_INIT_C | +--->BN_MP_INIT_C
| +--->BN_MP_CLEAR_C | +--->BN_MP_CLEAR_C
+--->BN_MP_MOD_C
| +--->BN_MP_INIT_C
| +--->BN_MP_DIV_C
| | +--->BN_MP_CMP_MAG_C
| | +--->BN_MP_COPY_C
| | | +--->BN_MP_GROW_C
| | +--->BN_MP_ZERO_C
| | +--->BN_MP_SET_C
| | +--->BN_MP_COUNT_BITS_C
| | +--->BN_MP_ABS_C
| | +--->BN_MP_MUL_2D_C
| | | +--->BN_MP_GROW_C
| | | +--->BN_MP_LSHD_C
| | | | +--->BN_MP_RSHD_C
| | | +--->BN_MP_CLAMP_C
| | +--->BN_MP_CMP_C
| | +--->BN_MP_SUB_C
| | | +--->BN_S_MP_ADD_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_CLAMP_C
| | | +--->BN_S_MP_SUB_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_CLAMP_C
| | +--->BN_MP_ADD_C
| | | +--->BN_S_MP_ADD_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_CLAMP_C
| | | +--->BN_S_MP_SUB_C
| | | | +--->BN_MP_GROW_C
| | | | +--->BN_MP_CLAMP_C
| | +--->BN_MP_DIV_2D_C
| | | +--->BN_MP_MOD_2D_C
| | | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_CLEAR_C
| | | +--->BN_MP_RSHD_C
| | | +--->BN_MP_CLAMP_C
| | | +--->BN_MP_EXCH_C
| | +--->BN_MP_EXCH_C
| | +--->BN_MP_CLEAR_MULTI_C
| | | +--->BN_MP_CLEAR_C
| | +--->BN_MP_INIT_SIZE_C
| | +--->BN_MP_INIT_COPY_C
| | +--->BN_MP_LSHD_C
| | | +--->BN_MP_GROW_C
| | | +--->BN_MP_RSHD_C
| | +--->BN_MP_RSHD_C
| | +--->BN_MP_MUL_D_C
| | | +--->BN_MP_GROW_C
| | | +--->BN_MP_CLAMP_C
| | +--->BN_MP_CLAMP_C
| | +--->BN_MP_CLEAR_C
| +--->BN_MP_CLEAR_C
| +--->BN_MP_ADD_C
| | +--->BN_S_MP_ADD_C
| | | +--->BN_MP_GROW_C
| | | +--->BN_MP_CLAMP_C
| | +--->BN_MP_CMP_MAG_C
| | +--->BN_S_MP_SUB_C
| | | +--->BN_MP_GROW_C
| | | +--->BN_MP_CLAMP_C
| +--->BN_MP_EXCH_C
+--->BN_MP_COPY_C +--->BN_MP_COPY_C
| +--->BN_MP_GROW_C | +--->BN_MP_GROW_C
+--->BN_MP_SET_C +--->BN_MP_SET_C
@ -9817,6 +10586,7 @@ BN_MP_EXTEUCLID_C
| +--->BN_S_MP_SUB_C | +--->BN_S_MP_SUB_C
| | +--->BN_MP_GROW_C | | +--->BN_MP_GROW_C
| | +--->BN_MP_CLAMP_C | | +--->BN_MP_CLAMP_C
+--->BN_MP_NEG_C
+--->BN_MP_EXCH_C +--->BN_MP_EXCH_C
+--->BN_MP_CLEAR_MULTI_C +--->BN_MP_CLEAR_MULTI_C
| +--->BN_MP_CLEAR_C | +--->BN_MP_CLEAR_C
@ -10024,7 +10794,56 @@ BN_MP_PRIME_MILLER_RABIN_C
| | | | +--->BN_MP_CLEAR_C | | | | +--->BN_MP_CLEAR_C
| | | +--->BN_MP_COPY_C | | | +--->BN_MP_COPY_C
| | | | +--->BN_MP_GROW_C | | | | +--->BN_MP_GROW_C
| | | +--->BN_MP_ABS_C | | | +--->BN_MP_MOD_C
| | | | +--->BN_MP_DIV_C
| | | | | +--->BN_MP_CMP_MAG_C
| | | | | +--->BN_MP_ZERO_C
| | | | | +--->BN_MP_SET_C
| | | | | +--->BN_MP_COUNT_BITS_C
| | | | | +--->BN_MP_ABS_C
| | | | | +--->BN_MP_MUL_2D_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_LSHD_C
| | | | | | | +--->BN_MP_RSHD_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CMP_C
| | | | | +--->BN_MP_SUB_C
| | | | | | +--->BN_S_MP_ADD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_S_MP_SUB_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_ADD_C
| | | | | | +--->BN_S_MP_ADD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_S_MP_SUB_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_EXCH_C
| | | | | +--->BN_MP_CLEAR_MULTI_C
| | | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_INIT_SIZE_C
| | | | | +--->BN_MP_LSHD_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_RSHD_C
| | | | | +--->BN_MP_RSHD_C
| | | | | +--->BN_MP_MUL_D_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_ADD_C
| | | | | +--->BN_S_MP_ADD_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CMP_MAG_C
| | | | | +--->BN_S_MP_SUB_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_EXCH_C
| | | +--->BN_MP_SET_C | | | +--->BN_MP_SET_C
| | | | +--->BN_MP_ZERO_C | | | | +--->BN_MP_ZERO_C
| | | +--->BN_MP_DIV_2_C | | | +--->BN_MP_DIV_2_C
@ -10054,6 +10873,58 @@ BN_MP_PRIME_MILLER_RABIN_C
| | +--->BN_MP_INVMOD_SLOW_C | | +--->BN_MP_INVMOD_SLOW_C
| | | +--->BN_MP_INIT_MULTI_C | | | +--->BN_MP_INIT_MULTI_C
| | | | +--->BN_MP_CLEAR_C | | | | +--->BN_MP_CLEAR_C
| | | +--->BN_MP_MOD_C
| | | | +--->BN_MP_DIV_C
| | | | | +--->BN_MP_CMP_MAG_C
| | | | | +--->BN_MP_COPY_C
| | | | | | +--->BN_MP_GROW_C
| | | | | +--->BN_MP_ZERO_C
| | | | | +--->BN_MP_SET_C
| | | | | +--->BN_MP_COUNT_BITS_C
| | | | | +--->BN_MP_ABS_C
| | | | | +--->BN_MP_MUL_2D_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_LSHD_C
| | | | | | | +--->BN_MP_RSHD_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CMP_C
| | | | | +--->BN_MP_SUB_C
| | | | | | +--->BN_S_MP_ADD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_S_MP_SUB_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_ADD_C
| | | | | | +--->BN_S_MP_ADD_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | | +--->BN_S_MP_SUB_C
| | | | | | | +--->BN_MP_GROW_C
| | | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_EXCH_C
| | | | | +--->BN_MP_CLEAR_MULTI_C
| | | | | | +--->BN_MP_CLEAR_C
| | | | | +--->BN_MP_INIT_SIZE_C
| | | | | +--->BN_MP_LSHD_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_RSHD_C
| | | | | +--->BN_MP_RSHD_C
| | | | | +--->BN_MP_MUL_D_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_CLEAR_C
| | | | +--->BN_MP_ADD_C
| | | | | +--->BN_S_MP_ADD_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | | +--->BN_MP_CMP_MAG_C
| | | | | +--->BN_S_MP_SUB_C
| | | | | | +--->BN_MP_GROW_C
| | | | | | +--->BN_MP_CLAMP_C
| | | | +--->BN_MP_EXCH_C
| | | +--->BN_MP_COPY_C | | | +--->BN_MP_COPY_C
| | | | +--->BN_MP_GROW_C | | | | +--->BN_MP_GROW_C
| | | +--->BN_MP_SET_C | | | +--->BN_MP_SET_C

11
changes.txt
View File

@ -1,3 +1,14 @@
March 12th, 2005
v0.35 -- Stupid XOR function missing line again... oops.
-- Fixed bug in invmod not handling negative inputs correctly [Wolfgang Ehrhardt]
-- Made exteuclid always give positive u3 output...[ Wolfgang Ehrhardt ]
-- [Wolfgang Ehrhardt] Suggested a fix for mp_reduce() which avoided underruns. ;-)
-- mp_rand() would emit one too many digits and it was possible to get a 0 out of it ... oops
-- Added montgomery to the testing to make sure it handles 1..10 digit moduli correctly
-- Fixed bug in comba that would lead to possible erroneous outputs when "pa < digs"
-- Fixed bug in mp_toradix_size for "0" [Kevin Kenny]
-- Updated chapters 1-5 of the textbook ;-) It now talks about the new comba code!
February 12th, 2005 February 12th, 2005
v0.34 -- Fixed two more small errors in mp_prime_random_ex() v0.34 -- Fixed two more small errors in mp_prime_random_ex()
-- Fixed overflow in mp_mul_d() [Kevin Kenny] -- Fixed overflow in mp_mul_d() [Kevin Kenny]

41
demo/demo.c
View File

@ -56,6 +56,7 @@ int main(void)
gcd_n, lcm_n, inv_n, div2_n, mul2_n, add_d_n, sub_d_n, t; gcd_n, lcm_n, inv_n, div2_n, mul2_n, add_d_n, sub_d_n, t;
unsigned rr; unsigned rr;
int i, n, err, cnt, ix, old_kara_m, old_kara_s; int i, n, err, cnt, ix, old_kara_m, old_kara_s;
mp_digit mp;
mp_init(&a); mp_init(&a);
@ -68,6 +69,40 @@ int main(void)
srand(time(NULL)); srand(time(NULL));
#if 0 #if 0
// test montgomery
printf("Testing montgomery...\n");
for (i = 1; i < 10; i++) {
printf("Testing digit size: %d\n", i);
for (n = 0; n < 1000; n++) {
mp_rand(&a, i);
a.dp[0] |= 1;
// let's see if R is right
mp_montgomery_calc_normalization(&b, &a);
mp_montgomery_setup(&a, &mp);
// now test a random reduction
for (ix = 0; ix < 100; ix++) {
mp_rand(&c, 1 + abs(rand()) % (2*i));
mp_copy(&c, &d);
mp_copy(&c, &e);
mp_mod(&d, &a, &d);
mp_montgomery_reduce(&c, &a, mp);
mp_mulmod(&c, &b, &a, &c);
if (mp_cmp(&c, &d) != MP_EQ) {
printf("d = e mod a, c = e MOD a\n");
mp_todecimal(&a, buf); printf("a = %s\n", buf);
mp_todecimal(&e, buf); printf("e = %s\n", buf);
mp_todecimal(&d, buf); printf("d = %s\n", buf);
mp_todecimal(&c, buf); printf("c = %s\n", buf);
printf("compare no compare!\n"); exit(EXIT_FAILURE); }
}
}
}
printf("done\n");
// test mp_get_int // test mp_get_int
printf("Testing: mp_get_int\n"); printf("Testing: mp_get_int\n");
for (i = 0; i < 1000; ++i) { for (i = 0; i < 1000; ++i) {
@ -139,7 +174,7 @@ int main(void)
printf("\n\n"); printf("\n\n");
/* test for size */ /* test for size */
for (ix = 10; ix < 256; ix++) { for (ix = 10; ix < 128; ix++) {
printf("Testing (not safe-prime): %9d bits \r", ix); printf("Testing (not safe-prime): %9d bits \r", ix);
fflush(stdout); fflush(stdout);
err = err =
@ -156,7 +191,7 @@ int main(void)
} }
} }
for (ix = 16; ix < 256; ix++) { for (ix = 16; ix < 128; ix++) {
printf("Testing ( safe-prime): %9d bits \r", ix); printf("Testing ( safe-prime): %9d bits \r", ix);
fflush(stdout); fflush(stdout);
err = err =
@ -235,7 +270,7 @@ int main(void)
mp_rand(&b, (cnt / DIGIT_BIT + 1) * 2); mp_rand(&b, (cnt / DIGIT_BIT + 1) * 2);
mp_copy(&c, &b); mp_copy(&c, &b);
mp_mod(&c, &a, &c); mp_mod(&c, &a, &c);
mp_reduce_2k(&b, &a, 1); mp_reduce_2k(&b, &a, 2);
if (mp_cmp(&c, &b)) { if (mp_cmp(&c, &b)) {
printf("FAILED\n"); printf("FAILED\n");
exit(0); exit(0);

2
makefile
View File

@ -3,7 +3,7 @@
#Tom St Denis #Tom St Denis
#version of library #version of library
VERSION=0.34 VERSION=0.35
CFLAGS += -I./ -Wall -W -Wshadow -Wsign-compare CFLAGS += -I./ -Wall -W -Wshadow -Wsign-compare

2
makefile.shared
View File

@ -1,7 +1,7 @@
#Makefile for GCC #Makefile for GCC
# #
#Tom St Denis #Tom St Denis
VERSION=0:34 VERSION=0:35
CC = libtool --mode=compile gcc CC = libtool --mode=compile gcc
CFLAGS += -I./ -Wall -W -Wshadow -Wsign-compare CFLAGS += -I./ -Wall -W -Wshadow -Wsign-compare

BIN
poster.pdf
View File

Binary file not shown.

121
pre_gen/mpi.c
View File

@ -90,7 +90,7 @@ int fast_mp_invmod (mp_int * a, mp_int * b, mp_int * c)
} }
/* we need y = |a| */ /* we need y = |a| */
if ((res = mp_abs (a, &y)) != MP_OKAY) { if ((res = mp_mod (a, b, &y)) != MP_OKAY) {
goto LBL_ERR; goto LBL_ERR;
} }
@ -430,7 +430,7 @@ int fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
tmpx = a->dp + tx; tmpx = a->dp + tx;
tmpy = b->dp + ty; tmpy = b->dp + ty;
/* this is the number of times the loop will iterrate, essentially its /* this is the number of times the loop will iterrate, essentially
while (tx++ < a->used && ty-- >= 0) { ... } while (tx++ < a->used && ty-- >= 0) { ... }
*/ */
iy = MIN(a->used-tx, ty+1); iy = MIN(a->used-tx, ty+1);
@ -448,16 +448,16 @@ int fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
} }
/* store final carry */ /* store final carry */
W[ix] = _W & MP_MASK; W[ix] = (mp_digit)(_W & MP_MASK);
/* setup dest */ /* setup dest */
olduse = c->used; olduse = c->used;
c->used = digs; c->used = pa;
{ {
register mp_digit *tmpc; register mp_digit *tmpc;
tmpc = c->dp; tmpc = c->dp;
for (ix = 0; ix < digs; ix++) { for (ix = 0; ix < pa+1; ix++) {
/* now extract the previous digit [below the carry] */ /* now extract the previous digit [below the carry] */
*tmpc++ = W[ix]; *tmpc++ = W[ix];
} }
@ -548,7 +548,7 @@ int fast_s_mp_mul_high_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
} }
/* store final carry */ /* store final carry */
W[ix] = _W & MP_MASK; W[ix] = (mp_digit)(_W & MP_MASK);
/* setup dest */ /* setup dest */
olduse = c->used; olduse = c->used;
@ -593,33 +593,14 @@ int fast_s_mp_mul_high_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
* Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
*/ */
/* fast squaring
*
* This is the comba method where the columns of the product
* are computed first then the carries are computed. This
* has the effect of making a very simple inner loop that
* is executed the most
*
* W2 represents the outer products and W the inner.
*
* A further optimizations is made because the inner
* products are of the form "A * B * 2". The *2 part does
* not need to be computed until the end which is good
* because 64-bit shifts are slow!
*
* Based on Algorithm 14.16 on pp.597 of HAC.
*
*/
/* the jist of squaring... /* the jist of squaring...
* you do like mult except the offset of the tmpx [one that
you do like mult except the offset of the tmpx [one that starts closer to zero] * starts closer to zero] can't equal the offset of tmpy.
can't equal the offset of tmpy. So basically you set up iy like before then you min it with * So basically you set up iy like before then you min it with
(ty-tx) so that it never happens. You double all those you add in the inner loop * (ty-tx) so that it never happens. You double all those
* you add in the inner loop
After that loop you do the squares and add them in. After that loop you do the squares and add them in.
Remove W2 and don't memset W
*/ */
int fast_s_mp_sqr (mp_int * a, mp_int * b) int fast_s_mp_sqr (mp_int * a, mp_int * b)
@ -654,7 +635,7 @@ int fast_s_mp_sqr (mp_int * a, mp_int * b)
tmpx = a->dp + tx; tmpx = a->dp + tx;
tmpy = a->dp + ty; tmpy = a->dp + ty;
/* this is the number of times the loop will iterrate, essentially its /* this is the number of times the loop will iterrate, essentially
while (tx++ < a->used && ty-- >= 0) { ... } while (tx++ < a->used && ty-- >= 0) { ... }
*/ */
iy = MIN(a->used-tx, ty+1); iy = MIN(a->used-tx, ty+1);
@ -679,7 +660,7 @@ int fast_s_mp_sqr (mp_int * a, mp_int * b)
} }
/* store it */ /* store it */
W[ix] = _W & MP_MASK; W[ix] = (mp_digit)(_W & MP_MASK);
/* make next carry */ /* make next carry */
W1 = _W >> ((mp_word)DIGIT_BIT); W1 = _W >> ((mp_word)DIGIT_BIT);
@ -2890,6 +2871,13 @@ int mp_exteuclid(mp_int *a, mp_int *b, mp_int *U1, mp_int *U2, mp_int *U3)
if ((err = mp_copy(&t3, &v3)) != MP_OKAY) { goto _ERR; } if ((err = mp_copy(&t3, &v3)) != MP_OKAY) { goto _ERR; }
} }
/* make sure U3 >= 0 */
if (u3.sign == MP_NEG) {
mp_neg(&u1, &u1);
mp_neg(&u2, &u2);
mp_neg(&u3, &u3);
}
/* copy result out */ /* copy result out */
if (U1 != NULL) { mp_exch(U1, &u1); } if (U1 != NULL) { mp_exch(U1, &u1); }
if (U2 != NULL) { mp_exch(U2, &u2); } if (U2 != NULL) { mp_exch(U2, &u2); }
@ -3564,8 +3552,8 @@ int mp_invmod_slow (mp_int * a, mp_int * b, mp_int * c)
} }
/* x = a, y = b */ /* x = a, y = b */
if ((res = mp_copy (a, &x)) != MP_OKAY) { if ((res = mp_mod(a, b, &x)) != MP_OKAY) {
goto LBL_ERR; goto LBL_ERR;
} }
if ((res = mp_copy (b, &y)) != MP_OKAY) { if ((res = mp_copy (b, &y)) != MP_OKAY) {
goto LBL_ERR; goto LBL_ERR;
@ -4493,7 +4481,6 @@ int mp_montgomery_calc_normalization (mp_int * a, mp_int * b)
/* how many bits of last digit does b use */ /* how many bits of last digit does b use */
bits = mp_count_bits (b) % DIGIT_BIT; bits = mp_count_bits (b) % DIGIT_BIT;
if (b->used > 1) { if (b->used > 1) {
if ((res = mp_2expt (a, (b->used - 1) * DIGIT_BIT + bits - 1)) != MP_OKAY) { if ((res = mp_2expt (a, (b->used - 1) * DIGIT_BIT + bits - 1)) != MP_OKAY) {
return res; return res;
@ -5206,12 +5193,18 @@ LBL_T1:mp_clear (&t1);
int mp_neg (mp_int * a, mp_int * b) int mp_neg (mp_int * a, mp_int * b)
{ {
int res; int res;
if ((res = mp_copy (a, b)) != MP_OKAY) { if (a != b) {
return res; if ((res = mp_copy (a, b)) != MP_OKAY) {
return res;
}
} }
if (mp_iszero(b) != MP_YES) { if (mp_iszero(b) != MP_YES) {
b->sign = (a->sign == MP_ZPOS) ? MP_NEG : MP_ZPOS; b->sign = (a->sign == MP_ZPOS) ? MP_NEG : MP_ZPOS;
} else {
b->sign = MP_ZPOS;
} }
return MP_OKAY; return MP_OKAY;
} }
#endif #endif
@ -5953,22 +5946,29 @@ int mp_radix_size (mp_int * a, int radix, int *size)
return MP_VAL; return MP_VAL;
} }
/* init a copy of the input */ if (mp_iszero(a) == MP_YES) {
if ((res = mp_init_copy (&t, a)) != MP_OKAY) { *size = 2;
return res; return MP_OKAY;
} }
/* digs is the digit count */ /* digs is the digit count */
digs = 0; digs = 0;
/* if it's negative add one for the sign */ /* if it's negative add one for the sign */
if (t.sign == MP_NEG) { if (a->sign == MP_NEG) {
++digs; ++digs;
t.sign = MP_ZPOS;
} }
/* init a copy of the input */
if ((res = mp_init_copy (&t, a)) != MP_OKAY) {
return res;
}
/* force temp to positive */
t.sign = MP_ZPOS;
/* fetch out all of the digits */ /* fetch out all of the digits */
while (mp_iszero (&t) == 0) { while (mp_iszero (&t) == MP_NO) {
if ((res = mp_div_d (&t, (mp_digit) radix, &t, &d)) != MP_OKAY) { if ((res = mp_div_d (&t, (mp_digit) radix, &t, &d)) != MP_OKAY) {
mp_clear (&t); mp_clear (&t);
return res; return res;
@ -6042,14 +6042,14 @@ mp_rand (mp_int * a, int digits)
/* first place a random non-zero digit */ /* first place a random non-zero digit */
do { do {
d = ((mp_digit) abs (rand ())); d = ((mp_digit) abs (rand ())) & MP_MASK;
} while (d == 0); } while (d == 0);
if ((res = mp_add_d (a, d, a)) != MP_OKAY) { if ((res = mp_add_d (a, d, a)) != MP_OKAY) {
return res; return res;
} }
while (digits-- > 0) { while (--digits > 0) {
if ((res = mp_lshd (a, 1)) != MP_OKAY) { if ((res = mp_lshd (a, 1)) != MP_OKAY) {
return res; return res;
} }
@ -6287,11 +6287,11 @@ int mp_reduce (mp_int * x, mp_int * m, mp_int * mu)
} }
} else { } else {
#ifdef BN_S_MP_MUL_HIGH_DIGS_C #ifdef BN_S_MP_MUL_HIGH_DIGS_C
if ((res = s_mp_mul_high_digs (&q, mu, &q, um - 1)) != MP_OKAY) { if ((res = s_mp_mul_high_digs (&q, mu, &q, um)) != MP_OKAY) {
goto CLEANUP; goto CLEANUP;
} }
#elif defined(BN_FAST_S_MP_MUL_HIGH_DIGS_C) #elif defined(BN_FAST_S_MP_MUL_HIGH_DIGS_C)
if ((res = fast_s_mp_mul_high_digs (&q, mu, &q, um - 1)) != MP_OKAY) { if ((res = fast_s_mp_mul_high_digs (&q, mu, &q, um)) != MP_OKAY) {
goto CLEANUP; goto CLEANUP;
} }
#else #else
@ -7433,9 +7433,10 @@ int mp_to_unsigned_bin_n (mp_int * a, unsigned char *b, unsigned long *outlen)
/* multiplication using the Toom-Cook 3-way algorithm /* multiplication using the Toom-Cook 3-way algorithm
* *
* Much more complicated than Karatsuba but has a lower asymptotic running time of * Much more complicated than Karatsuba but has a lower
* O(N**1.464). This algorithm is only particularly useful on VERY large * asymptotic running time of O(N**1.464). This algorithm is
* inputs (we're talking 1000s of digits here...). * only particularly useful on VERY large inputs
* (we're talking 1000s of digits here...).
*/ */
int mp_toom_mul(mp_int *a, mp_int *b, mp_int *c) int mp_toom_mul(mp_int *a, mp_int *b, mp_int *c)
{ {
@ -8154,7 +8155,7 @@ mp_xor (mp_int * a, mp_int * b, mp_int * c)
} }
for (ix = 0; ix < px; ix++) { for (ix = 0; ix < px; ix++) {
t.dp[ix] ^= x->dp[ix];
} }
mp_clamp (&t); mp_clamp (&t);
mp_exch (c, &t); mp_exch (c, &t);
@ -8184,12 +8185,18 @@ mp_xor (mp_int * a, mp_int * b, mp_int * c)
*/ */
/* set to zero */ /* set to zero */
void void mp_zero (mp_int * a)
mp_zero (mp_int * a)
{ {
int n;
mp_digit *tmp;
a->sign = MP_ZPOS; a->sign = MP_ZPOS;
a->used = 0; a->used = 0;
memset (a->dp, 0, sizeof (mp_digit) * a->alloc);
tmp = a->dp;
for (n = 0; n < a->alloc; n++) {
*tmp++ = 0;
}
} }
#endif #endif
@ -8679,8 +8686,7 @@ LBL_M:
* HAC pp. 595, Algorithm 14.12 Modified so you can control how * HAC pp. 595, Algorithm 14.12 Modified so you can control how
* many digits of output are created. * many digits of output are created.
*/ */
int int s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
{ {
mp_int t; mp_int t;
int res, pa, pb, ix, iy; int res, pa, pb, ix, iy;
@ -8848,8 +8854,7 @@ s_mp_mul_high_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
*/ */
/* low level squaring, b = a*a, HAC pp.596-597, Algorithm 14.16 */ /* low level squaring, b = a*a, HAC pp.596-597, Algorithm 14.16 */
int int s_mp_sqr (mp_int * a, mp_int * b)
s_mp_sqr (mp_int * a, mp_int * b)
{ {
mp_int t; mp_int t;
int res, ix, iy, pa; int res, ix, iy, pa;

35
tombc/grammar.txt Normal file
View File

@ -0,0 +1,35 @@
program := program statement | statement | empty
statement := { statement } |
identifier = numexpression; |
identifier[numexpression] = numexpression; |
function(expressionlist); |
for (identifer = numexpression; numexpression; identifier = numexpression) { statement } |
while (numexpression) { statement } |
if (numexpresion) { statement } elif |
break; |
continue;
elif := else statement | empty
function := abs | countbits | exptmod | jacobi | print | isprime | nextprime | issquare | readinteger | exit
expressionlist := expressionlist, expression | expression
// LR(1) !!!?
expression := string | numexpression
numexpression := cmpexpr && cmpexpr | cmpexpr \|\| cmpexpr | cmpexpr
cmpexpr := boolexpr < boolexpr | boolexpr > boolexpr | boolexpr == boolexpr |
boolexpr <= boolexpr | boolexpr >= boolexpr | boolexpr
boolexpr := shiftexpr & shiftexpr | shiftexpr ^ shiftexpr | shiftexpr \| shiftexpr | shiftexpr
shiftexpr := addsubexpr << addsubexpr | addsubexpr >> addsubexpr | addsubexpr
addsubexpr := mulexpr + mulexpr | mulexpr - mulexpr | mulexpr
mulexpr := expr * expr | expr / expr | expr % expr | expr
expr := -nexpr | nexpr
nexpr := integer | identifier | ( numexpression ) | identifier[numexpression]
identifier := identifer digits | identifier alpha | alpha
alpha := a ... z | A ... Z
integer := hexnumber | digits
hexnumber := 0xhexdigits
hexdigits := hexdigits hexdigit | hexdigit
hexdigit := 0 ... 9 | a ... f | A ... F
digits := digits digit | digit
digit := 0 ... 9

BIN
tommath.pdf
View File

Binary file not shown.

491
tommath.src
View File

@ -49,7 +49,7 @@
\begin{document} \begin{document}
\frontmatter \frontmatter
\pagestyle{empty} \pagestyle{empty}
\title{Implementing Multiple Precision Arithmetic \\ ~ \\ Draft Edition } \title{Multi--Precision Math}
\author{\mbox{ \author{\mbox{
%\begin{small} %\begin{small}
\begin{tabular}{c} \begin{tabular}{c}
@ -66,7 +66,7 @@ QUALCOMM Australia \\
} }
} }
\maketitle \maketitle
This text has been placed in the public domain. This text corresponds to the v0.34 release of the This text has been placed in the public domain. This text corresponds to the v0.35 release of the
LibTomMath project. LibTomMath project.
\begin{alltt} \begin{alltt}
@ -85,66 +85,32 @@ This text is formatted to the international B5 paper size of 176mm wide by 250mm
\tableofcontents \tableofcontents
\listoffigures \listoffigures
\chapter*{Prefaces to the Draft Edition} \chapter*{Prefaces}
I started this text in April 2003 to complement my LibTomMath library. That is, explain how to implement the functions When I tell people about my LibTom projects and that I release them as public domain they are often puzzled.
contained in LibTomMath. The goal is to have a textbook that any Computer Science student can use when implementing their They ask why I did it and especially why I continue to work on them for free. The best I can explain it is ``Because I can.''
own multiple precision arithmetic. The plan I wanted to follow was flesh out all the Which seems odd and perhaps too terse for adult conversation. I often qualify it with ``I am able, I am willing.'' which
ideas and concepts I had floating around in my head and then work on it afterwards refining a little bit at a time. Chance perhaps explains it better. I am the first to admit there is not anything that special with what I have done. Perhaps
would have it that I ended up with my summer off from Algonquin College and I was given four months solid to work on the others can see that too and then we would have a society to be proud of. My LibTom projects are what I am doing to give
text. back to society in the form of tools and knowledge that can help others in their endeavours.
Choosing to not waste any time I dove right into the project even before my spring semester was finished. I wrote a bit I started writing this book because it was the most logical task to further my goal of open academia. The LibTomMath source
off and on at first. The moment my exams were finished I jumped into long 12 to 16 hour days. The result after only code itself was written to be easy to follow and learn from. There are times, however, where pure C source code does not
a couple of months was a ten chapter, three hundred page draft that I quickly had distributed to anyone who wanted explain the algorithms properly. Hence this book. The book literally starts with the foundation of the library and works
to read it. I had Jean-Luc Cooke print copies for me and I brought them to Crypto'03 in Santa Barbara. So far I have itself outwards to the more complicated algorithms. The use of both pseudo--code and verbatim source code provides a duality
managed to grab a certain level of attention having people from around the world ask me for copies of the text was certain of ``theory'' and ``practice'' that the computer science students of the world shall appreciate. I never deviate too far
rewarding. from relatively straightforward algebra and I hope that this book can be a valuable learning asset.
Now we are past December 2003. By this time I had pictured that I would have at least finished my second draft of the text. This book and indeed much of the LibTom projects would not exist in their current form if it was not for a plethora
Currently I am far off from this goal. I've done partial re-writes of chapters one, two and three but they are not even of kind people donating their time, resources and kind words to help support my work. Writing a text of significant
finished yet. I haven't given up on the project, only had some setbacks. First O'Reilly declined to publish the text then length (along with the source code) is a tiresome and lengthy process. Currently the LibTom project is four years old,
Addison-Wesley and Greg is tried another which I don't know the name of. However, at this point I want to focus my energy comprises of literally thousands of users and over 100,000 lines of source code, TeX and other material. People like Mads and Greg
onto finishing the book not securing a contract. were there at the beginning to encourage me to work well. It is amazing how timely validation from others can boost morale to
continue the project. Definitely my parents were there for me by providing room and board during the many months of work in 2003.
So why am I writing this text? It seems like a lot of work right? Most certainly it is a lot of work writing a textbook. To my many friends whom I have met through the years I thank you for the good times and the words of encouragement. I hope I
Even the simplest introductory material has to be lined with references and figures. A lot of the text has to be re-written honour your kind gestures with this project.
from point form to prose form to ensure an easier read. Why am I doing all this work for free then? Simple. My philosophy
is quite simply ``Open Source. Open Academia. Open Minds'' which means that to achieve a goal of open minds, that is,
people willing to accept new ideas and explore the unknown you have to make available material they can access freely
without hinderance.
I've been writing free software since I was about sixteen but only recently have I hit upon software that people have come Open Source. Open Academia. Open Minds.
to depend upon. I started LibTomCrypt in December 2001 and now several major companies use it as integral portions of their
software. Several educational institutions use it as a matter of course and many freelance developers use it as
part of their projects. To further my contributions I started the LibTomMath project in December 2002 aimed at providing
multiple precision arithmetic routines that students could learn from. That is write routines that are not only easy
to understand and follow but provide quite impressive performance considering they are all in standard portable ISO C.
The second leg of my philosophy is ``Open Academia'' which is where this textbook comes in. In the end, when all is
said and done the text will be useable by educational institutions as a reference on multiple precision arithmetic.
At this time I feel I should share a little information about myself. The most common question I was asked at
Crypto'03, perhaps just out of professional courtesy, was which school I either taught at or attended. The unfortunate
truth is that I neither teach at or attend a school of academic reputation. I'm currently at Algonquin College which
is what I'd like to call ``somewhat academic but mostly vocational'' college. In otherwords, job training.
I'm a 21 year old computer science student mostly self-taught in the areas I am aware of (which includes a half-dozen
computer science fields, a few fields of mathematics and some English). I look forward to teaching someday but I am
still far off from that goal.
Now it would be improper for me to not introduce the rest of the texts co-authors. While they are only contributing
corrections and editorial feedback their support has been tremendously helpful in presenting the concepts laid out
in the text so far. Greg has always been there for me. He has tracked my LibTom projects since their inception and even
sent cheques to help pay tuition from time to time. His background has provided a wonderful source to bounce ideas off
of and improve the quality of my writing. Mads is another fellow who has just ``been there''. I don't even recall what
his interest in the LibTom projects is but I'm definitely glad he has been around. His ability to catch logical errors
in my written English have saved me on several occasions to say the least.
What to expect next? Well this is still a rough draft. I've only had the chance to update a few chapters. However, I've
been getting the feeling that people are starting to use my text and I owe them some updated material. My current tenative
plan is to edit one chapter every two weeks starting January 4th. It seems insane but my lower course load at college
should provide ample time. By Crypto'04 I plan to have a 2nd draft of the text polished and ready to hand out to as many
people who will take it.
\begin{flushright} Tom St Denis \end{flushright} \begin{flushright} Tom St Denis \end{flushright}
@ -937,7 +903,7 @@ assumed to contain undefined values they are initially set to zero.
EXAM,bn_mp_grow.c EXAM,bn_mp_grow.c
A quick optimization is to first determine if a memory re-allocation is required at all. The if statement (line @23,if@) checks A quick optimization is to first determine if a memory re-allocation is required at all. The if statement (line @24,alloc@) checks
if the \textbf{alloc} member of the mp\_int is smaller than the requested digit count. If the count is not larger than \textbf{alloc} if the \textbf{alloc} member of the mp\_int is smaller than the requested digit count. If the count is not larger than \textbf{alloc}
the function skips the re-allocation part thus saving time. the function skips the re-allocation part thus saving time.
@ -1310,7 +1276,7 @@ After the function is completed, all of the digits are zeroed, the \textbf{used}
With the mp\_int representation of an integer, calculating the absolute value is trivial. The mp\_abs algorithm will compute With the mp\_int representation of an integer, calculating the absolute value is trivial. The mp\_abs algorithm will compute
the absolute value of an mp\_int. the absolute value of an mp\_int.
\newpage\begin{figure}[here] \begin{figure}[here]
\begin{center} \begin{center}
\begin{tabular}{l} \begin{tabular}{l}
\hline Algorithm \textbf{mp\_abs}. \\ \hline Algorithm \textbf{mp\_abs}. \\
@ -1335,6 +1301,9 @@ logic to handle it.
EXAM,bn_mp_abs.c EXAM,bn_mp_abs.c
This fairly trivial algorithm first eliminates non--required duplications (line @27,a != b@) and then sets the
\textbf{sign} flag to \textbf{MP\_ZPOS}.
\subsection{Integer Negation} \subsection{Integer Negation}
With the mp\_int representation of an integer, calculating the negation is also trivial. The mp\_neg algorithm will compute With the mp\_int representation of an integer, calculating the negation is also trivial. The mp\_neg algorithm will compute
the negative of an mp\_int input. the negative of an mp\_int input.
@ -1368,11 +1337,15 @@ zero as negative.
EXAM,bn_mp_neg.c EXAM,bn_mp_neg.c
Like mp\_abs() this function avoids non--required duplications (line @21,a != b@) and then sets the sign. We
have to make sure that only non--zero values get a \textbf{sign} of \textbf{MP\_NEG}. If the mp\_int is zero
than the \textbf{sign} is hard--coded to \textbf{MP\_ZPOS}.
\section{Small Constants} \section{Small Constants}
\subsection{Setting Small Constants} \subsection{Setting Small Constants}
Often a mp\_int must be set to a relatively small value such as $1$ or $2$. For these cases the mp\_set algorithm is useful. Often a mp\_int must be set to a relatively small value such as $1$ or $2$. For these cases the mp\_set algorithm is useful.
\begin{figure}[here] \newpage\begin{figure}[here]
\begin{center} \begin{center}
\begin{tabular}{l} \begin{tabular}{l}
\hline Algorithm \textbf{mp\_set}. \\ \hline Algorithm \textbf{mp\_set}. \\
@ -1397,11 +1370,14 @@ single digit is set (\textit{modulo $\beta$}) and the \textbf{used} count is adj
EXAM,bn_mp_set.c EXAM,bn_mp_set.c
Line @21,mp_zero@ calls mp\_zero() to clear the mp\_int and reset the sign. Line @22,MP_MASK@ copies the digit First we zero (line @21,mp_zero@) the mp\_int to make sure that the other members are initialized for a
into the least significant location. Note the usage of a new constant \textbf{MP\_MASK}. This constant is used to quickly small positive constant. mp\_zero() ensures that the \textbf{sign} is positive and the \textbf{used} count
reduce an integer modulo $\beta$. Since $\beta$ is of the form $2^k$ for any suitable $k$ it suffices to perform a binary AND with is zero. Next we set the digit and reduce it modulo $\beta$ (line @22,MP_MASK@). After this step we have to
$MP\_MASK = 2^k - 1$ to perform the reduction. Finally line @23,a->used@ will set the \textbf{used} member with respect to the check if the resulting digit is zero or not. If it is not then we set the \textbf{used} count to one, otherwise
digit actually set. This function will always make the integer positive. to zero.
We can quickly reduce modulo $\beta$ since it is of the form $2^k$ and a quick binary AND operation with
$2^k - 1$ will perform the same operation.
One important limitation of this function is that it will only set one digit. The size of a digit is not fixed, meaning source that uses One important limitation of this function is that it will only set one digit. The size of a digit is not fixed, meaning source that uses
this function should take that into account. Only trivially small constants can be set using this function. this function should take that into account. Only trivially small constants can be set using this function.
@ -1503,10 +1479,12 @@ the zero'th digit. If after all of the digits have been compared, no difference
EXAM,bn_mp_cmp_mag.c EXAM,bn_mp_cmp_mag.c
The two if statements on lines @24,if@ and @28,if@ compare the number of digits in the two inputs. These two are performed before all of the digits The two if statements (lines @24,if@ and @28,if@) compare the number of digits in the two inputs. These two are
are compared since it is a very cheap test to perform and can potentially save considerable time. The implementation given is also not valid performed before all of the digits are compared since it is a very cheap test to perform and can potentially save
without those two statements. $b.alloc$ may be smaller than $a.used$, meaning that undefined values will be read from $b$ past the end of the considerable time. The implementation given is also not valid without those two statements. $b.alloc$ may be
array of digits. smaller than $a.used$, meaning that undefined values will be read from $b$ past the end of the array of digits.
\subsection{Signed Comparisons} \subsection{Signed Comparisons}
Comparing with sign considerations is also fairly critical in several routines (\textit{division for example}). Based on an unsigned magnitude Comparing with sign considerations is also fairly critical in several routines (\textit{division for example}). Based on an unsigned magnitude
@ -1539,9 +1517,9 @@ $\vert a \vert < \vert b \vert$. Step number four will compare the two when the
EXAM,bn_mp_cmp.c EXAM,bn_mp_cmp.c
The two if statements on lines @22,if@ and @26,if@ perform the initial sign comparison. If the signs are not the equal then which ever The two if statements (lines @22,if@ and @26,if@) perform the initial sign comparison. If the signs are not the equal then which ever
has the positive sign is larger. At line @30,if@, the inputs are compared based on magnitudes. If the signs were both negative then has the positive sign is larger. The inputs are compared (line @30,if@) based on magnitudes. If the signs were both
the unsigned comparison is performed in the opposite direction (\textit{line @31,mp_cmp_mag@}). Otherwise, the signs are assumed to negative then the unsigned comparison is performed in the opposite direction (line @31,mp_cmp_mag@). Otherwise, the signs are assumed to
be both positive and a forward direction unsigned comparison is performed. be both positive and a forward direction unsigned comparison is performed.
\section*{Exercises} \section*{Exercises}
@ -1664,19 +1642,21 @@ The final carry is stored in $c_{max}$ and digits above $max$ upto $oldused$ are
EXAM,bn_s_mp_add.c EXAM,bn_s_mp_add.c
Lines @27,if@ to @35,}@ perform the initial sorting of the inputs and determine the $min$ and $max$ variables. Note that $x$ is a pointer to a We first sort (lines @27,if@ to @35,}@) the inputs based on magnitude and determine the $min$ and $max$ variables.
mp\_int assigned to the largest input, in effect it is a local alias. Lines @37,init@ to @42,}@ ensure that the destination is grown to Note that $x$ is a pointer to an mp\_int assigned to the largest input, in effect it is a local alias. Next we
accomodate the result of the addition. grow the destination (@37,init@ to @42,}@) ensure that it can accomodate the result of the addition.
Similar to the implementation of mp\_copy this function uses the braced code and local aliases coding style. The three aliases that are on Similar to the implementation of mp\_copy this function uses the braced code and local aliases coding style. The three aliases that are on
lines @56,tmpa@, @59,tmpb@ and @62,tmpc@ represent the two inputs and destination variables respectively. These aliases are used to ensure the lines @56,tmpa@, @59,tmpb@ and @62,tmpc@ represent the two inputs and destination variables respectively. These aliases are used to ensure the
compiler does not have to dereference $a$, $b$ or $c$ (respectively) to access the digits of the respective mp\_int. compiler does not have to dereference $a$, $b$ or $c$ (respectively) to access the digits of the respective mp\_int.
The initial carry $u$ is cleared on line @65,u = 0@, note that $u$ is of type mp\_digit which ensures type compatibility within the The initial carry $u$ will be cleared (line @65,u = 0@), note that $u$ is of type mp\_digit which ensures type
implementation. The initial addition loop begins on line @66,for@ and ends on line @75,}@. Similarly the conditional addition loop compatibility within the implementation. The initial addition (line @66,for@ to @75,}@) adds digits from
begins on line @81,for@ and ends on line @90,}@. The addition is finished with the final carry being stored in $tmpc$ on line @94,tmpc++@. both inputs until the smallest input runs out of digits. Similarly the conditional addition loop
Note the ``++'' operator on the same line. After line @94,tmpc++@ $tmpc$ will point to the $c.used$'th digit of the mp\_int $c$. This is useful (line @81,for@ to @90,}@) adds the remaining digits from the larger of the two inputs. The addition is finished
for the next loop on lines @97,for@ to @99,}@ which set any old upper digits to zero. with the final carry being stored in $tmpc$ (line @94,tmpc++@). Note the ``++'' operator within the same expression.
After line @94,tmpc++@, $tmpc$ will point to the $c.used$'th digit of the mp\_int $c$. This is useful
for the next loop (line @97,for@ to @99,}@) which set any old upper digits to zero.
\subsection{Low Level Subtraction} \subsection{Low Level Subtraction}
The low level unsigned subtraction algorithm is very similar to the low level unsigned addition algorithm. The principle difference is that the The low level unsigned subtraction algorithm is very similar to the low level unsigned addition algorithm. The principle difference is that the
@ -1692,7 +1672,7 @@ this algorithm we will assume that the variable $\gamma$ represents the number o
mp\_digit (\textit{this implies $2^{\gamma} > \beta$}). mp\_digit (\textit{this implies $2^{\gamma} > \beta$}).
For example, the default for LibTomMath is to use a ``unsigned long'' for the mp\_digit ``type'' while $\beta = 2^{28}$. In ISO C an ``unsigned long'' For example, the default for LibTomMath is to use a ``unsigned long'' for the mp\_digit ``type'' while $\beta = 2^{28}$. In ISO C an ``unsigned long''
data type must be able to represent $0 \le x < 2^{32}$ meaning that in this case $\gamma = 32$. data type must be able to represent $0 \le x < 2^{32}$ meaning that in this case $\gamma \ge 32$.
\newpage\begin{figure}[!here] \newpage\begin{figure}[!here]
\begin{center} \begin{center}
@ -1759,20 +1739,23 @@ If $b$ has a smaller magnitude than $a$ then step 9 will force the carry and cop
EXAM,bn_s_mp_sub.c EXAM,bn_s_mp_sub.c
Line @24,min@ and @25,max@ perform the initial hardcoded sorting of the inputs. In reality the $min$ and $max$ variables are only aliases and are only Like low level addition we ``sort'' the inputs. Except in this case the sorting is hardcoded
used to make the source code easier to read. Again the pointer alias optimization is used within this algorithm. Lines @42,tmpa@, @43,tmpb@ and @44,tmpc@ initialize the aliases for (lines @24,min@ and @25,max@). In reality the $min$ and $max$ variables are only aliases and are only
$a$, $b$ and $c$ respectively. used to make the source code easier to read. Again the pointer alias optimization is used
within this algorithm. The aliases $tmpa$, $tmpb$ and $tmpc$ are initialized
(lines @42,tmpa@, @43,tmpb@ and @44,tmpc@) for $a$, $b$ and $c$ respectively.
The first subtraction loop occurs on lines @47,u = 0@ through @61,}@. The theory behind the subtraction loop is exactly the same as that for The first subtraction loop (lines @47,u = 0@ through @61,}@) subtract digits from both inputs until the smaller of
the addition loop. As remarked earlier there is an implementation reason for using the ``awkward'' method of extracting the carry the two inputs has been exhausted. As remarked earlier there is an implementation reason for using the ``awkward''
(\textit{see line @57, >>@}). The traditional method for extracting the carry would be to shift by $lg(\beta)$ positions and logically AND method of extracting the carry (line @57, >>@). The traditional method for extracting the carry would be to shift
the least significant bit. The AND operation is required because all of the bits above the $\lg(\beta)$'th bit will be set to one after a carry by $lg(\beta)$ positions and logically AND the least significant bit. The AND operation is required because all of
occurs from subtraction. This carry extraction requires two relatively cheap operations to extract the carry. The other method is to simply the bits above the $\lg(\beta)$'th bit will be set to one after a carry occurs from subtraction. This carry
shift the most significant bit to the least significant bit thus extracting the carry with a single cheap operation. This optimization only works on extraction requires two relatively cheap operations to extract the carry. The other method is to simply shift the
twos compliment machines which is a safe assumption to make. most significant bit to the least significant bit thus extracting the carry with a single cheap operation. This
optimization only works on twos compliment machines which is a safe assumption to make.
If $a$ has a larger magnitude than $b$ an additional loop (\textit{see lines @64,for@ through @73,}@}) is required to propagate the carry through If $a$ has a larger magnitude than $b$ an additional loop (lines @64,for@ through @73,}@) is required to propagate
$a$ and copy the result to $c$. the carry through $a$ and copy the result to $c$.
\subsection{High Level Addition} \subsection{High Level Addition}
Now that both lower level addition and subtraction algorithms have been established an effective high level signed addition algorithm can be Now that both lower level addition and subtraction algorithms have been established an effective high level signed addition algorithm can be
@ -2098,10 +2081,11 @@ FIGU,sliding_window,Sliding Window Movement
EXAM,bn_mp_lshd.c EXAM,bn_mp_lshd.c
The if statement on line @24,if@ ensures that the $b$ variable is greater than zero. The \textbf{used} count is incremented by $b$ before The if statement (line @24,if@) ensures that the $b$ variable is greater than zero since we do not interpret negative
the copy loop begins. This elminates the need for an additional variable in the for loop. The variable $top$ on line @42,top@ is an alias shift counts properly. The \textbf{used} count is incremented by $b$ before the copy loop begins. This elminates
for the leading digit while $bottom$ on line @45,bottom@ is an alias for the trailing edge. The aliases form a window of exactly $b$ digits the need for an additional variable in the for loop. The variable $top$ (line @42,top@) is an alias
over the input. for the leading digit while $bottom$ (line @45,bottom@) is an alias for the trailing edge. The aliases form a
window of exactly $b$ digits over the input.
\subsection{Division by $x$} \subsection{Division by $x$}
@ -2151,9 +2135,9 @@ Once the window copy is complete the upper digits must be zeroed and the \textbf
EXAM,bn_mp_rshd.c EXAM,bn_mp_rshd.c
The only noteworthy element of this routine is the lack of a return type. The only noteworthy element of this routine is the lack of a return type since it cannot fail. Like mp\_lshd() we
form a sliding window except we copy in the other direction. After the window (line @59,for (;@) we then zero
-- Will update later to give it a return type...Tom the upper digits of the input to make sure the result is correct.
\section{Powers of Two} \section{Powers of Two}
@ -2214,7 +2198,15 @@ complete. It is possible to optimize this algorithm down to a $O(n)$ algorithm
EXAM,bn_mp_mul_2d.c EXAM,bn_mp_mul_2d.c
Notes to be revised when code is updated. -- Tom The shifting is performed in--place which means the first step (line @24,a != c@) is to copy the input to the
destination. We avoid calling mp\_copy() by making sure the mp\_ints are different. The destination then
has to be grown (line @31,grow@) to accomodate the result.
If the shift count $b$ is larger than $lg(\beta)$ then a call to mp\_lshd() is used to handle all of the multiples
of $lg(\beta)$. Leaving only a remaining shift of $lg(\beta) - 1$ or fewer bits left. Inside the actual shift
loop (lines @45,if@ to @76,}@) we make use of pre--computed values $shift$ and $mask$. These are used to
extract the carry bit(s) to pass into the next iteration of the loop. The $r$ and $rr$ variables form a
chain between consecutive iterations to propagate the carry.
\subsection{Division by Power of Two} \subsection{Division by Power of Two}
@ -2263,7 +2255,8 @@ ignored by passing \textbf{NULL} as the pointer to the mp\_int variable. The
result of the remainder operation until the end. This allows $d$ and $a$ to represent the same mp\_int without modifying $a$ before result of the remainder operation until the end. This allows $d$ and $a$ to represent the same mp\_int without modifying $a$ before
the quotient is obtained. the quotient is obtained.
The remainder of the source code is essentially the same as the source code for mp\_mul\_2d. (-- Fix this paragraph up later, Tom). The remainder of the source code is essentially the same as the source code for mp\_mul\_2d. The only significant difference is
the direction of the shifts.
\subsection{Remainder of Division by Power of Two} \subsection{Remainder of Division by Power of Two}
@ -2306,7 +2299,13 @@ is copied to $b$, leading digits are removed and the remaining leading digit is
EXAM,bn_mp_mod_2d.c EXAM,bn_mp_mod_2d.c
-- Add comments later, Tom. We first avoid cases of $b \le 0$ by simply mp\_zero()'ing the destination in such cases. Next if $2^b$ is larger
than the input we just mp\_copy() the input and return right away. After this point we know we must actually
perform some work to produce the remainder.
Recalling that reducing modulo $2^k$ and a binary ``and'' with $2^k - 1$ are numerically equivalent we can quickly reduce
the number. First we zero any digits above the last digit in $2^b$ (line @41,for@). Next we reduce the
leading digit of both (line @45,&=@) and then mp\_clamp().
\section*{Exercises} \section*{Exercises}
\begin{tabular}{cl} \begin{tabular}{cl}
@ -2464,33 +2463,46 @@ exceed the precision requested.
EXAM,bn_s_mp_mul_digs.c EXAM,bn_s_mp_mul_digs.c
Lines @31,if@ to @35,}@ determine if the Comba method can be used first. The conditions for using the Comba routine are that min$(a.used, b.used) < \delta$ and First we determine (line @30,if@) if the Comba method can be used first since it's faster. The conditions for
the number of digits of output is less than \textbf{MP\_WARRAY}. This new constant is used to control sing the Comba routine are that min$(a.used, b.used) < \delta$ and the number of digits of output is less than
the stack usage in the Comba routines. By default it is set to $\delta$ but can be reduced when memory is at a premium. \textbf{MP\_WARRAY}. This new constant is used to control the stack usage in the Comba routines. By default it is
set to $\delta$ but can be reduced when memory is at a premium.
Of particular importance is the calculation of the $ix+iy$'th column on lines @64,mp_word@, @65,mp_word@ and @66,mp_word@. Note how all of the If we cannot use the Comba method we proceed to setup the baseline routine. We allocate the the destination mp\_int
variables are cast to the type \textbf{mp\_word}, which is also the type of variable $\hat r$. That is to ensure that double precision operations $t$ (line @36,init@) to the exact size of the output to avoid further re--allocations. At this point we now
are used instead of single precision. The multiplication on line @65,) * (@ makes use of a specific GCC optimizer behaviour. On the outset it looks like begin the $O(n^2)$ loop.
the compiler will have to use a double precision multiplication to produce the result required. Such an operation would be horribly slow on most
processors and drag this to a crawl. However, GCC is smart enough to realize that double wide output single precision multipliers can be used. For This implementation of multiplication has the caveat that it can be trimmed to only produce a variable number of
example, the instruction ``MUL'' on the x86 processor can multiply two 32-bit values and produce a 64-bit result. digits as output. In each iteration of the outer loop the $pb$ variable is set (line @48,MIN@) to the maximum
number of inner loop iterations.
Inside the inner loop we calculate $\hat r$ as the mp\_word product of the two mp\_digits and the addition of the
carry from the previous iteration. A particularly important observation is that most modern optimizing
C compilers (GCC for instance) can recognize that a $N \times N \rightarrow 2N$ multiplication is all that
is required for the product. In x86 terms for example, this means using the MUL instruction.
Each digit of the product is stored in turn (line @68,tmpt@) and the carry propagated (line @71,>>@) to the
next iteration.
\subsection{Faster Multiplication by the ``Comba'' Method} \subsection{Faster Multiplication by the ``Comba'' Method}
MARK,COMBA MARK,COMBA
One of the huge drawbacks of the ``baseline'' algorithms is that at the $O(n^2)$ level the carry must be computed and propagated upwards. This One of the huge drawbacks of the ``baseline'' algorithms is that at the $O(n^2)$ level the carry must be
makes the nested loop very sequential and hard to unroll and implement in parallel. The ``Comba'' \cite{COMBA} method is named after little known computed and propagated upwards. This makes the nested loop very sequential and hard to unroll and implement
(\textit{in cryptographic venues}) Paul G. Comba who described a method of implementing fast multipliers that do not require nested in parallel. The ``Comba'' \cite{COMBA} method is named after little known (\textit{in cryptographic venues}) Paul G.
carry fixup operations. As an interesting aside it seems that Paul Barrett describes a similar technique in Comba who described a method of implementing fast multipliers that do not require nested carry fixup operations. As an
his 1986 paper \cite{BARRETT} written five years before. interesting aside it seems that Paul Barrett describes a similar technique in his 1986 paper \cite{BARRETT} written
five years before.
At the heart of the Comba technique is once again the long-hand algorithm. Except in this case a slight twist is placed on how At the heart of the Comba technique is once again the long-hand algorithm. Except in this case a slight
the columns of the result are produced. In the standard long-hand algorithm rows of products are produced then added together to form the twist is placed on how the columns of the result are produced. In the standard long-hand algorithm rows of products
final result. In the baseline algorithm the columns are added together after each iteration to get the result instantaneously. are produced then added together to form the final result. In the baseline algorithm the columns are added together
after each iteration to get the result instantaneously.
In the Comba algorithm the columns of the result are produced entirely independently of each other. That is at the $O(n^2)$ level a In the Comba algorithm the columns of the result are produced entirely independently of each other. That is at
simple multiplication and addition step is performed. The carries of the columns are propagated after the nested loop to reduce the amount the $O(n^2)$ level a simple multiplication and addition step is performed. The carries of the columns are propagated
of work requiored. Succintly the first step of the algorithm is to compute the product vector $\vec x$ as follows. after the nested loop to reduce the amount of work requiored. Succintly the first step of the algorithm is to compute
the product vector $\vec x$ as follows.
\begin{equation} \begin{equation}
\vec x_n = \sum_{i+j = n} a_ib_j, \forall n \in \lbrace 0, 1, 2, \ldots, i + j \rbrace \vec x_n = \sum_{i+j = n} a_ib_j, \forall n \in \lbrace 0, 1, 2, \ldots, i + j \rbrace
@ -2584,38 +2596,32 @@ $256$ digits would allow for numbers in the range of $0 \le x < 2^{7168}$ which,
\textbf{Input}. mp\_int $a$, mp\_int $b$ and an integer $digs$ \\ \textbf{Input}. mp\_int $a$, mp\_int $b$ and an integer $digs$ \\
\textbf{Output}. $c \leftarrow \vert a \vert \cdot \vert b \vert \mbox{ (mod }\beta^{digs}\mbox{)}$. \\ \textbf{Output}. $c \leftarrow \vert a \vert \cdot \vert b \vert \mbox{ (mod }\beta^{digs}\mbox{)}$. \\
\hline \\ \hline \\
Place an array of \textbf{MP\_WARRAY} double precision digits named $\hat W$ on the stack. \\ Place an array of \textbf{MP\_WARRAY} single precision digits named $W$ on the stack. \\
1. If $c.alloc < digs$ then grow $c$ to $digs$ digits. (\textit{mp\_grow}) \\ 1. If $c.alloc < digs$ then grow $c$ to $digs$ digits. (\textit{mp\_grow}) \\
2. If step 1 failed return(\textit{MP\_MEM}).\\ 2. If step 1 failed return(\textit{MP\_MEM}).\\
\\ \\
Zero the temporary array $\hat W$. \\ 3. $pa \leftarrow \mbox{MIN}(digs, a.used + b.used)$ \\
3. for $n$ from $0$ to $digs - 1$ do \\
\hspace{3mm}3.1 $\hat W_n \leftarrow 0$ \\
\\ \\
Compute the columns. \\ 4. $\_ \hat W \leftarrow 0$ \\
4. for $ix$ from $0$ to $a.used - 1$ do \\ 5. for $ix$ from 0 to $pa - 1$ do \\
\hspace{3mm}4.1 $pb \leftarrow \mbox{min}(b.used, digs - ix)$ \\ \hspace{3mm}5.1 $ty \leftarrow \mbox{MIN}(b.used - 1, ix)$ \\
\hspace{3mm}4.2 If $pb < 1$ then goto step 5. \\ \hspace{3mm}5.2 $tx \leftarrow ix - ty$ \\
\hspace{3mm}4.3 for $iy$ from $0$ to $pb - 1$ do \\ \hspace{3mm}5.3 $iy \leftarrow \mbox{MIN}(a.used - tx, ty + 1)$ \\
\hspace{6mm}4.3.1 $\hat W_{ix+iy} \leftarrow \hat W_{ix+iy} + a_{ix}b_{iy}$ \\ \hspace{3mm}5.4 for $iz$ from 0 to $iy - 1$ do \\
\hspace{6mm}5.4.1 $\_ \hat W \leftarrow \_ \hat W + a_{tx+iy}b_{ty-iy}$ \\
\hspace{3mm}5.5 $W_{ix} \leftarrow \_ \hat W (\mbox{mod }\beta)$\\
\hspace{3mm}5.6 $\_ \hat W \leftarrow \lfloor \_ \hat W / \beta \rfloor$ \\
6. $W_{pa} \leftarrow \_ \hat W (\mbox{mod }\beta)$ \\
\\ \\
Propagate the carries upwards. \\ 7. $oldused \leftarrow c.used$ \\
5. $oldused \leftarrow c.used$ \\ 8. $c.used \leftarrow digs$ \\
6. $c.used \leftarrow digs$ \\ 9. for $ix$ from $0$ to $pa$ do \\
7. If $digs > 1$ then do \\ \hspace{3mm}9.1 $c_{ix} \leftarrow W_{ix}$ \\
\hspace{3mm}7.1. for $ix$ from $1$ to $digs - 1$ do \\ 10. for $ix$ from $pa + 1$ to $oldused - 1$ do \\
\hspace{6mm}7.1.1 $\hat W_{ix} \leftarrow \hat W_{ix} + \lfloor \hat W_{ix-1} / \beta \rfloor$ \\ \hspace{3mm}10.1 $c_{ix} \leftarrow 0$ \\
\hspace{6mm}7.1.2 $c_{ix - 1} \leftarrow \hat W_{ix - 1} \mbox{ (mod }\beta\mbox{)}$ \\
8. else do \\
\hspace{3mm}8.1 $ix \leftarrow 0$ \\
9. $c_{ix} \leftarrow \hat W_{ix} \mbox{ (mod }\beta\mbox{)}$ \\
\\ \\
Zero excess digits. \\ 11. Clamp $c$. \\
10. If $digs < oldused$ then do \\ 12. Return MP\_OKAY. \\
\hspace{3mm}10.1 for $n$ from $digs$ to $oldused - 1$ do \\
\hspace{6mm}10.1.1 $c_n \leftarrow 0$ \\
11. Clamp excessive digits of $c$. (\textit{mp\_clamp}) \\
12. Return(\textit{MP\_OKAY}). \\
\hline \hline
\end{tabular} \end{tabular}
\end{center} \end{center}
@ -2625,15 +2631,24 @@ Zero excess digits. \\
\end{figure} \end{figure}
\textbf{Algorithm fast\_s\_mp\_mul\_digs.} \textbf{Algorithm fast\_s\_mp\_mul\_digs.}
This algorithm performs the unsigned multiplication of $a$ and $b$ using the Comba method limited to $digs$ digits of precision. The algorithm This algorithm performs the unsigned multiplication of $a$ and $b$ using the Comba method limited to $digs$ digits of precision.
essentially peforms the same calculation as algorithm s\_mp\_mul\_digs, just much faster.
The array $\hat W$ is meant to be on the stack when the algorithm is used. The size of the array does not change which is ideal. Note also that The outer loop of this algorithm is more complicated than that of the baseline multiplier. This is because on the inside of the
unlike algorithm s\_mp\_mul\_digs no temporary mp\_int is required since the result is calculated directly in $\hat W$. loop we want to produce one column per pass. This allows the accumulator $\_ \hat W$ to be placed in CPU registers and
reduce the memory bandwidth to two \textbf{mp\_digit} reads per iteration.
The $O(n^2)$ loop on step four is where the Comba method's advantages begin to show through in comparison to the baseline algorithm. The lack of The $ty$ variable is set to the minimum count of $ix$ or the number of digits in $b$. That way if $a$ has more digits than
a carry variable or propagation in this loop allows the loop to be performed with only single precision multiplication and additions. Now that each $b$ this will be limited to $b.used - 1$. The $tx$ variable is set to the to the distance past $b.used$ the variable
iteration of the inner loop can be performed independent of the others the inner loop can be performed with a high level of parallelism. $ix$ is. This is used for the immediately subsequent statement where we find $iy$.
The variable $iy$ is the minimum digits we can read from either $a$ or $b$ before running out. Computing one column at a time
means we have to scan one integer upwards and the other downwards. $a$ starts at $tx$ and $b$ starts at $ty$. In each
pass we are producing the $ix$'th output column and we note that $tx + ty = ix$. As we move $tx$ upwards we have to
move $ty$ downards so the equality remains valid. The $iy$ variable is the number of iterations until
$tx \ge a.used$ or $ty < 0$ occurs.
After every inner pass we store the lower half of the accumulator into $W_{ix}$ and then propagate the carry of the accumulator
into the next round by dividing $\_ \hat W$ by $\beta$.
To measure the benefits of the Comba method over the baseline method consider the number of operations that are required. If the To measure the benefits of the Comba method over the baseline method consider the number of operations that are required. If the
cost in terms of time of a multiply and addition is $p$ and the cost of a carry propagation is $q$ then a baseline multiplication would require cost in terms of time of a multiply and addition is $p$ and the cost of a carry propagation is $q$ then a baseline multiplication would require
@ -2643,20 +2658,20 @@ and addition operations in the nested loop in parallel.
EXAM,bn_fast_s_mp_mul_digs.c EXAM,bn_fast_s_mp_mul_digs.c
The memset on line @47,memset@ clears the initial $\hat W$ array to zero in a single step. Like the slower baseline multiplication As per the pseudo--code we first calculate $pa$ (line @47,MIN@) as the number of digits to output. Next we begin the outer loop
implementation a series of aliases (\textit{lines @67, tmpx@, @70, tmpy@ and @75,_W@}) are used to simplify the inner $O(n^2)$ loop. to produce the individual columns of the product. We use the two aliases $tmpx$ and $tmpy$ (lines @61,tmpx@, @62,tmpy@) to point
In this case a new alias $\_\hat W$ has been added which refers to the double precision columns offset by $ix$ in each pass. inside the two multiplicands quickly.
The inner loop on lines @83,for@, @84,mp_word@ and @85,}@ is where the algorithm will spend the majority of the time, which is why it has been The inner loop (lines @70,for@ to @72,}@) of this implementation is where the tradeoff come into play. Originally this comba
stripped to the bones of any extra baggage\footnote{Hence the pointer aliases.}. On x86 processors the multiplication and additions amount to at the implementation was ``row--major'' which means it adds to each of the columns in each pass. After the outer loop it would then fix
very least five instructions (\textit{two loads, two additions, one multiply}) while on the ARMv4 processors they amount to only three the carries. This was very fast except it had an annoying drawback. You had to read a mp\_word and two mp\_digits and write
(\textit{one load, one store, one multiply-add}). For both of the x86 and ARMv4 processors the GCC compiler performs a good job at unrolling the loop one mp\_word per iteration. On processors such as the Athlon XP and P4 this did not matter much since the cache bandwidth
and scheduling the instructions so there are very few dependency stalls. is very high and it can keep the ALU fed with data. It did, however, matter on older and embedded cpus where cache is often
slower and also often doesn't exist. This new algorithm only performs two reads per iteration under the assumption that the
compiler has aliased $\_ \hat W$ to a CPU register.
In theory the difference between the baseline and comba algorithms is a mere $O(qn)$ time difference. However, in the $O(n^2)$ nested loop of the After the inner loop we store the current accumulator in $W$ and shift $\_ \hat W$ (lines @75,W[ix]@, @78,>>@) to forward it as
baseline method there are dependency stalls as the algorithm must wait for the multiplier to finish before propagating the carry to the next a carry for the next pass. After the outer loop we use the final carry (line @82,W[ix]@) as the last digit of the product.
digit. As a result fewer of the often multiple execution units\footnote{The AMD Athlon has three execution units and the Intel P4 has four.} can
be simultaneously used.
\subsection{Polynomial Basis Multiplication} \subsection{Polynomial Basis Multiplication}
To break the $O(n^2)$ barrier in multiplication requires a completely different look at integer multiplication. In the following algorithms To break the $O(n^2)$ barrier in multiplication requires a completely different look at integer multiplication. In the following algorithms
@ -2976,13 +2991,26 @@ result $a \cdot b$ is produced.
EXAM,bn_mp_toom_mul.c EXAM,bn_mp_toom_mul.c
-- Comments to be added during editing phase. The first obvious thing to note is that this algorithm is complicated. The complexity is worth it if you are multiplying very
large numbers. For example, a 10,000 digit multiplication takes approximaly 99,282,205 fewer single precision multiplications with
Toom--Cook than a Comba or baseline approach (this is a savings of more than 99$\%$). For most ``crypto'' sized numbers this
algorithm is not practical as Karatsuba has a much lower cutoff point.
First we split $a$ and $b$ into three roughly equal portions. This has been accomplished (lines @40,mod@ to @69,rshd@) with
combinations of mp\_rshd() and mp\_mod\_2d() function calls. At this point $a = a2 \cdot \beta^2 + a1 \cdot \beta + a0$ and similiarly
for $b$.
Next we compute the five points $w0, w1, w2, w3$ and $w4$. Recall that $w0$ and $w4$ can be computed directly from the portions so
we get those out of the way first (lines @72,mul@ and @77,mul@). Next we compute $w1, w2$ and $w3$ using Horners method.
After this point we solve for the actual values of $w1, w2$ and $w3$ by reducing the $5 \times 5$ system which is relatively
straight forward.
\subsection{Signed Multiplication} \subsection{Signed Multiplication}
Now that algorithms to handle multiplications of every useful dimensions have been developed, a rather simple finishing touch is required. So far all Now that algorithms to handle multiplications of every useful dimensions have been developed, a rather simple finishing touch is required. So far all
of the multiplication algorithms have been unsigned multiplications which leaves only a signed multiplication algorithm to be established. of the multiplication algorithms have been unsigned multiplications which leaves only a signed multiplication algorithm to be established.
\newpage\begin{figure}[!here] \begin{figure}[!here]
\begin{small} \begin{small}
\begin{center} \begin{center}
\begin{tabular}{l} \begin{tabular}{l}
@ -3065,7 +3093,7 @@ Column two of row one is a square and column three is the first unique column.
The baseline squaring algorithm is meant to be a catch-all squaring algorithm. It will handle any of the input sizes that the faster routines The baseline squaring algorithm is meant to be a catch-all squaring algorithm. It will handle any of the input sizes that the faster routines
will not handle. will not handle.
\newpage\begin{figure}[!here] \begin{figure}[!here]
\begin{small} \begin{small}
\begin{center} \begin{center}
\begin{tabular}{l} \begin{tabular}{l}
@ -3121,9 +3149,14 @@ results calculated so far. This involves expensive carry propagation which will
EXAM,bn_s_mp_sqr.c EXAM,bn_s_mp_sqr.c
Inside the outer loop (\textit{see line @32,for@}) the square term is calculated on line @35,r =@. Line @42,>>@ extracts the carry from the square Inside the outer loop (line @32,for@) the square term is calculated on line @35,r =@. The carry (line @42,>>@) has been
term. Aliases for $a_{ix}$ and $t_{ix+iy}$ are initialized on lines @45,tmpx@ and @48,tmpt@ respectively. The doubling is performed using two extracted from the mp\_word accumulator using a right shift. Aliases for $a_{ix}$ and $t_{ix+iy}$ are initialized
additions (\textit{see line @57,r + r@}) since it is usually faster than shifting,if not at least as fast. (lines @45,tmpx@ and @48,tmpt@) to simplify the inner loop. The doubling is performed using two
additions (line @57,r + r@) since it is usually faster than shifting, if not at least as fast.
The important observation is that the inner loop does not begin at $iy = 0$ like for multiplication. As such the inner loops
get progressively shorter as the algorithm proceeds. This is what leads to the savings compared to using a multiplication to
square a number.
\subsection{Faster Squaring by the ``Comba'' Method} \subsection{Faster Squaring by the ``Comba'' Method}
A major drawback to the baseline method is the requirement for single precision shifting inside the $O(n^2)$ nested loop. Squaring has an additional A major drawback to the baseline method is the requirement for single precision shifting inside the $O(n^2)$ nested loop. Squaring has an additional
@ -3135,9 +3168,9 @@ propagation operations from the inner loop. However, the inner product must sti
that $2a + 2b + 2c = 2(a + b + c)$. That is the sum of all of the double products is equal to double the sum of all the products. For example, that $2a + 2b + 2c = 2(a + b + c)$. That is the sum of all of the double products is equal to double the sum of all the products. For example,
$ab + ba + ac + ca = 2ab + 2ac = 2(ab + ac)$. $ab + ba + ac + ca = 2ab + 2ac = 2(ab + ac)$.
However, we cannot simply double all of the columns, since the squares appear only once per row. The most practical solution is to have two mp\_word However, we cannot simply double all of the columns, since the squares appear only once per row. The most practical solution is to have two
arrays. One array will hold the squares and the other array will hold the double products. With both arrays the doubling and carry propagation can be mp\_word arrays. One array will hold the squares and the other array will hold the double products. With both arrays the doubling and
moved to a $O(n)$ work level outside the $O(n^2)$ level. carry propagation can be moved to a $O(n)$ work level outside the $O(n^2)$ level. In this case, we have an even simpler solution in mind.
\newpage\begin{figure}[!here] \newpage\begin{figure}[!here]
\begin{small} \begin{small}
@ -3147,34 +3180,34 @@ moved to a $O(n)$ work level outside the $O(n^2)$ level.
\textbf{Input}. mp\_int $a$ \\ \textbf{Input}. mp\_int $a$ \\
\textbf{Output}. $b \leftarrow a^2$ \\ \textbf{Output}. $b \leftarrow a^2$ \\
\hline \\ \hline \\
Place two arrays of \textbf{MP\_WARRAY} mp\_words named $\hat W$ and $\hat {X}$ on the stack. \\ Place an array of \textbf{MP\_WARRAY} mp\_digits named $W$ on the stack. \\
1. If $b.alloc < 2a.used + 1$ then grow $b$ to $2a.used + 1$ digits. (\textit{mp\_grow}). \\ 1. If $b.alloc < 2a.used + 1$ then grow $b$ to $2a.used + 1$ digits. (\textit{mp\_grow}). \\
2. If step 1 failed return(\textit{MP\_MEM}). \\ 2. If step 1 failed return(\textit{MP\_MEM}). \\
3. for $ix$ from $0$ to $2a.used + 1$ do \\
\hspace{3mm}3.1 $\hat W_{ix} \leftarrow 0$ \\
\hspace{3mm}3.2 $\hat {X}_{ix} \leftarrow 0$ \\
4. for $ix$ from $0$ to $a.used - 1$ do \\
\hspace{3mm}Compute the square.\\
\hspace{3mm}4.1 $\hat {X}_{ix+ix} \leftarrow \left ( a_{ix} \right )^2$ \\
\\ \\
\hspace{3mm}Compute the double products.\\ 3. $pa \leftarrow 2 \cdot a.used$ \\
\hspace{3mm}4.2 for $iy$ from $ix + 1$ to $a.used - 1$ do \\ 4. $\hat W1 \leftarrow 0$ \\
\hspace{6mm}4.2.1 $\hat W_{ix+iy} \leftarrow \hat W_{ix+iy} + a_{ix}a_{iy}$ \\ 5. for $ix$ from $0$ to $pa - 1$ do \\
5. $oldused \leftarrow b.used$ \\ \hspace{3mm}5.1 $\_ \hat W \leftarrow 0$ \\
6. $b.used \leftarrow 2a.used + 1$ \\ \hspace{3mm}5.2 $ty \leftarrow \mbox{MIN}(a.used - 1, ix)$ \\
\hspace{3mm}5.3 $tx \leftarrow ix - ty$ \\
\hspace{3mm}5.4 $iy \leftarrow \mbox{MIN}(a.used - tx, ty + 1)$ \\
\hspace{3mm}5.5 $iy \leftarrow \mbox{MIN}(iy, \lfloor \left (ty - tx + 1 \right )/2 \rfloor)$ \\
\hspace{3mm}5.6 for $iz$ from $0$ to $iz - 1$ do \\
\hspace{6mm}5.6.1 $\_ \hat W \leftarrow \_ \hat W + a_{tx + iz}a_{ty - iz}$ \\
\hspace{3mm}5.7 $\_ \hat W \leftarrow 2 \cdot \_ \hat W + \hat W1$ \\
\hspace{3mm}5.8 if $ix$ is even then \\
\hspace{6mm}5.8.1 $\_ \hat W \leftarrow \_ \hat W + \left ( a_{\lfloor ix/2 \rfloor}\right )^2$ \\
\hspace{3mm}5.9 $W_{ix} \leftarrow \_ \hat W (\mbox{mod }\beta)$ \\
\hspace{3mm}5.10 $\hat W1 \leftarrow \lfloor \_ \hat W / \beta \rfloor$ \\
\\ \\
Double the products and propagate the carries simultaneously. \\ 6. $oldused \leftarrow b.used$ \\
7. $\hat W_0 \leftarrow 2 \hat W_0 + \hat {X}_0$ \\ 7. $b.used \leftarrow 2 \cdot a.used$ \\
8. for $ix$ from $1$ to $2a.used$ do \\ 8. for $ix$ from $0$ to $pa - 1$ do \\
\hspace{3mm}8.1 $\hat W_{ix} \leftarrow 2 \hat W_{ix} + \hat {X}_{ix}$ \\ \hspace{3mm}8.1 $b_{ix} \leftarrow W_{ix}$ \\
\hspace{3mm}8.2 $\hat W_{ix} \leftarrow \hat W_{ix} + \lfloor \hat W_{ix - 1} / \beta \rfloor$ \\ 9. for $ix$ from $pa$ to $oldused - 1$ do \\
\hspace{3mm}8.3 $b_{ix-1} \leftarrow W_{ix-1} \mbox{ (mod }\beta\mbox{)}$ \\ \hspace{3mm}9.1 $b_{ix} \leftarrow 0$ \\
9. $b_{2a.used} \leftarrow \hat W_{2a.used} \mbox{ (mod }\beta\mbox{)}$ \\ 10. Clamp excess digits from $b$. (\textit{mp\_clamp}) \\
10. if $2a.used + 1 < oldused$ then do \\ 11. Return(\textit{MP\_OKAY}). \\
\hspace{3mm}10.1 for $ix$ from $2a.used + 1$ to $oldused$ do \\
\hspace{6mm}10.1.1 $b_{ix} \leftarrow 0$ \\
11. Clamp excess digits from $b$. (\textit{mp\_clamp}) \\
12. Return(\textit{MP\_OKAY}). \\
\hline \hline
\end{tabular} \end{tabular}
\end{center} \end{center}
@ -3183,24 +3216,24 @@ Double the products and propagate the carries simultaneously. \\
\end{figure} \end{figure}
\textbf{Algorithm fast\_s\_mp\_sqr.} \textbf{Algorithm fast\_s\_mp\_sqr.}
This algorithm computes the square of an input using the Comba technique. It is designed to be a replacement for algorithm s\_mp\_sqr when This algorithm computes the square of an input using the Comba technique. It is designed to be a replacement for algorithm
the number of input digits is less than \textbf{MP\_WARRAY} and less than $\delta \over 2$. s\_mp\_sqr when the number of input digits is less than \textbf{MP\_WARRAY} and less than $\delta \over 2$.
This algorithm is very similar to the Comba multiplier except with a few key differences we shall make note of.
This routine requires two arrays of mp\_words to be placed on the stack. The first array $\hat W$ will hold the double products and the second First, we have an accumulator and carry variables $\_ \hat W$ and $\hat W1$ respectively. This is because the inner loop
array $\hat X$ will hold the squares. Though only at most $MP\_WARRAY \over 2$ words of $\hat X$ are used, it has proven faster on most products are to be doubled. If we had added the previous carry in we would be doubling too much. Next we perform an
processors to simply make it a full size array. addition MIN condition on $iy$ (step 5.5) to prevent overlapping digits. For example, $a_3 \cdot a_5$ is equal
$a_5 \cdot a_3$. Whereas in the multiplication case we would have $5 < a.used$ and $3 \ge 0$ is maintained since we double the sum
of the products just outside the inner loop we have to avoid doing this. This is also a good thing since we perform
fewer multiplications and the routine ends up being faster.
The loop on step 3 will zero the two arrays to prepare them for the squaring step. Step 4.1 computes the squares of the product. Note how Finally the last difference is the addition of the ``square'' term outside the inner loop (step 5.8). We add in the square
it simply assigns the value into the $\hat X$ array. The nested loop on step 4.2 computes the doubles of the products. This loop only to even outputs and it is the square of the term at the $\lfloor ix / 2 \rfloor$ position.
computes the sum of the products for each column. They are not doubled until later.
After the squaring loop, the products stored in $\hat W$ musted be doubled and the carries propagated forwards. It makes sense to do both
operations at the same time. The expression $\hat W_{ix} \leftarrow 2 \hat W_{ix} + \hat {X}_{ix}$ computes the sum of the double product and the
squares in place.
EXAM,bn_fast_s_mp_sqr.c EXAM,bn_fast_s_mp_sqr.c
-- Write something deep and insightful later, Tom. This implementation is essentially a copy of Comba multiplication with the appropriate changes added to make it faster for
the special case of squaring.
\subsection{Polynomial Basis Squaring} \subsection{Polynomial Basis Squaring}
The same algorithm that performs optimal polynomial basis multiplication can be used to perform polynomial basis squaring. The minor exception The same algorithm that performs optimal polynomial basis multiplication can be used to perform polynomial basis squaring. The minor exception
@ -3312,14 +3345,13 @@ By inlining the copy and shift operations the cutoff point for Karatsuba multipl
is exactly at the point where Comba squaring can no longer be used (\textit{128 digits}). On slower processors such as the Intel P4 is exactly at the point where Comba squaring can no longer be used (\textit{128 digits}). On slower processors such as the Intel P4
it is actually below the Comba limit (\textit{at 110 digits}). it is actually below the Comba limit (\textit{at 110 digits}).
This routine uses the same error trap coding style as mp\_karatsuba\_sqr. As the temporary variables are initialized errors are redirected to This routine uses the same error trap coding style as mp\_karatsuba\_sqr. As the temporary variables are initialized errors are
the error trap higher up. If the algorithm completes without error the error code is set to \textbf{MP\_OKAY} and mp\_clears are executed normally. redirected to the error trap higher up. If the algorithm completes without error the error code is set to \textbf{MP\_OKAY} and
mp\_clears are executed normally.
\textit{Last paragraph sucks. re-write! -- Tom}
\subsection{Toom-Cook Squaring} \subsection{Toom-Cook Squaring}
The Toom-Cook squaring algorithm mp\_toom\_sqr is heavily based on the algorithm mp\_toom\_mul with the exception that squarings are used The Toom-Cook squaring algorithm mp\_toom\_sqr is heavily based on the algorithm mp\_toom\_mul with the exception that squarings are used
instead of multiplication to find the five relations.. The reader is encouraged to read the description of the latter algorithm and try to instead of multiplication to find the five relations. The reader is encouraged to read the description of the latter algorithm and try to
derive their own Toom-Cook squaring algorithm. derive their own Toom-Cook squaring algorithm.
\subsection{High Level Squaring} \subsection{High Level Squaring}
@ -3362,12 +3394,9 @@ EXAM,bn_mp_sqr.c
$\left [ 3 \right ] $ & Devise an efficient algorithm for selection of the radix point to handle inputs \\ $\left [ 3 \right ] $ & Devise an efficient algorithm for selection of the radix point to handle inputs \\
& that have different number of digits in Karatsuba multiplication. \\ & that have different number of digits in Karatsuba multiplication. \\
& \\ & \\
$\left [ 3 \right ] $ & In ~SQUARE~ the fact that every column of a squaring is made up \\ $\left [ 2 \right ] $ & In ~SQUARE~ the fact that every column of a squaring is made up \\
& of double products and at most one square is stated. Prove this statement. \\ & of double products and at most one square is stated. Prove this statement. \\
& \\ & \\
$\left [ 2 \right ] $ & In the Comba squaring algorithm half of the $\hat X$ variables are not used. \\
& Revise algorithm fast\_s\_mp\_sqr to shrink the $\hat X$ array. \\
& \\
$\left [ 3 \right ] $ & Prove the equation for Karatsuba squaring. \\ $\left [ 3 \right ] $ & Prove the equation for Karatsuba squaring. \\
& \\ & \\
$\left [ 1 \right ] $ & Prove that Karatsuba squaring requires $O \left (n^{lg(3)} \right )$ time. \\ $\left [ 1 \right ] $ & Prove that Karatsuba squaring requires $O \left (n^{lg(3)} \right )$ time. \\
@ -3375,6 +3404,14 @@ $\left [ 1 \right ] $ & Prove that Karatsuba squaring requires $O \left (n^{lg(3
$\left [ 2 \right ] $ & Determine the minimal ratio between addition and multiplication clock cycles \\ $\left [ 2 \right ] $ & Determine the minimal ratio between addition and multiplication clock cycles \\
& required for equation $6.7$ to be true. \\ & required for equation $6.7$ to be true. \\
& \\ & \\
$\left [ 3 \right ] $ & Implement a threaded version of Comba multiplication (and squaring) where you \\
& compute subsets of the columns in each thread. Determine a cutoff point where \\
& it is effective and add the logic to mp\_mul() and mp\_sqr(). \\
&\\
$\left [ 4 \right ] $ & Same as the previous but also modify the Karatsuba and Toom-Cook. You must \\
& increase the throughput of mp\_exptmod() for random odd moduli in the range \\
& $512 \ldots 4096$ bits significantly ($> 2x$) to complete this challenge. \\
& \\
\end{tabular} \end{tabular}
\chapter{Modular Reduction} \chapter{Modular Reduction}
@ -3394,7 +3431,7 @@ other forms of residues.
Modular reductions are normally used to create either finite groups, rings or fields. The most common usage for performance driven modular reductions Modular reductions are normally used to create either finite groups, rings or fields. The most common usage for performance driven modular reductions
is in modular exponentiation algorithms. That is to compute $d = a^b \mbox{ (mod }c\mbox{)}$ as fast as possible. This operation is used in the is in modular exponentiation algorithms. That is to compute $d = a^b \mbox{ (mod }c\mbox{)}$ as fast as possible. This operation is used in the
RSA and Diffie-Hellman public key algorithms, for example. Modular multiplication and squaring also appears as a fundamental operation in RSA and Diffie-Hellman public key algorithms, for example. Modular multiplication and squaring also appears as a fundamental operation in
Elliptic Curve cryptographic algorithms. As will be discussed in the subsequent chapter there exist fast algorithms for computing modular elliptic curve cryptographic algorithms. As will be discussed in the subsequent chapter there exist fast algorithms for computing modular
exponentiations without having to perform (\textit{in this example}) $b - 1$ multiplications. These algorithms will produce partial results in the exponentiations without having to perform (\textit{in this example}) $b - 1$ multiplications. These algorithms will produce partial results in the
range $0 \le x < c^2$ which can be taken advantage of to create several efficient algorithms. They have also been used to create redundancy check range $0 \le x < c^2$ which can be taken advantage of to create several efficient algorithms. They have also been used to create redundancy check
algorithms known as CRCs, error correction codes such as Reed-Solomon and solve a variety of number theoeretic problems. algorithms known as CRCs, error correction codes such as Reed-Solomon and solve a variety of number theoeretic problems.
@ -3610,7 +3647,7 @@ safe to do so.
In order to use algorithm mp\_reduce the value of $\mu$ must be calculated in advance. Ideally this value should be computed once and stored for In order to use algorithm mp\_reduce the value of $\mu$ must be calculated in advance. Ideally this value should be computed once and stored for
future use so that the Barrett algorithm can be used without delay. future use so that the Barrett algorithm can be used without delay.
\begin{figure}[!here] \newpage\begin{figure}[!here]
\begin{small} \begin{small}
\begin{center} \begin{center}
\begin{tabular}{l} \begin{tabular}{l}
@ -5818,6 +5855,8 @@ To explain the Jacobi Symbol we shall first discuss the Legendre function\footno
defined. The Legendre function computes whether or not an integer $a$ is a quadratic residue modulo an odd prime $p$. Numerically it is defined. The Legendre function computes whether or not an integer $a$ is a quadratic residue modulo an odd prime $p$. Numerically it is
equivalent to equation \ref{eqn:legendre}. equivalent to equation \ref{eqn:legendre}.
\textit{-- Tom, don't be an ass, cite your source here...!}
\begin{equation} \begin{equation}
a^{(p-1)/2} \equiv \begin{array}{rl} a^{(p-1)/2} \equiv \begin{array}{rl}
-1 & \mbox{if }a\mbox{ is a quadratic non-residue.} \\ -1 & \mbox{if }a\mbox{ is a quadratic non-residue.} \\

1533
tommath.tex
View File

File diff suppressed because it is too large Load Diff

4
tommath_class.h
View File

@ -137,7 +137,7 @@
#define BN_MP_ISEVEN_C #define BN_MP_ISEVEN_C
#define BN_MP_INIT_MULTI_C #define BN_MP_INIT_MULTI_C
#define BN_MP_COPY_C #define BN_MP_COPY_C
#define BN_MP_ABS_C #define BN_MP_MOD_C
#define BN_MP_SET_C #define BN_MP_SET_C
#define BN_MP_DIV_2_C #define BN_MP_DIV_2_C
#define BN_MP_ISODD_C #define BN_MP_ISODD_C
@ -366,6 +366,7 @@
#define BN_MP_DIV_C #define BN_MP_DIV_C
#define BN_MP_MUL_C #define BN_MP_MUL_C
#define BN_MP_SUB_C #define BN_MP_SUB_C
#define BN_MP_NEG_C
#define BN_MP_EXCH_C #define BN_MP_EXCH_C
#define BN_MP_CLEAR_MULTI_C #define BN_MP_CLEAR_MULTI_C
#endif #endif
@ -440,6 +441,7 @@
#if defined(BN_MP_INVMOD_SLOW_C) #if defined(BN_MP_INVMOD_SLOW_C)
#define BN_MP_ISZERO_C #define BN_MP_ISZERO_C
#define BN_MP_INIT_MULTI_C #define BN_MP_INIT_MULTI_C
#define BN_MP_MOD_C
#define BN_MP_COPY_C #define BN_MP_COPY_C
#define BN_MP_ISEVEN_C #define BN_MP_ISEVEN_C
#define BN_MP_SET_C #define BN_MP_SET_C