Import of tommath 0.35

68 files changed, 6792 insertions, 4385 deletions

diff --git a/libtommath/bn.pdf b/libtommath/bn.pdf
index 9b873e1..615ff4e 100644
--- a/libtommath/bn.pdf
+++ b/libtommath/bn.pdf
diff --git a/libtommath/bn.tex b/libtommath/bn.tex
index 962d6ea..244bd6f 100644
--- a/libtommath/bn.tex
+++ b/libtommath/bn.tex
@@ -49,7 +49,7 @@
 \begin{document}
 \frontmatter
 \pagestyle{empty}
-\title{LibTomMath User Manual \\ v0.33}
+\title{LibTomMath User Manual \\ v0.35}
 \author{Tom St Denis \\ tomstdenis@iahu.ca}
 \maketitle
 This text, the library and the accompanying textbook are all hereby placed in the public domain.  This book has been 
@@ -263,12 +263,12 @@ are the pros and cons of LibTomMath by comparing it to the math routines from Gn
 \begin{center}
 \begin{tabular}{|l|c|c|l|}
 \hline \textbf{Criteria} & \textbf{Pro} & \textbf{Con} & \textbf{Notes} \\
-\hline Few lines of code per file & X & & GnuPG $ = 300.9$, LibTomMath  $ = 76.04$ \\
+\hline Few lines of code per file & X & & GnuPG $ = 300.9$, LibTomMath  $ = 71.97$ \\
 \hline Commented function prototypes & X && GnuPG function names are cryptic. \\
 \hline Speed && X & LibTomMath is slower.  \\
 \hline Totally free & X & & GPL has unfavourable restrictions.\\
 \hline Large function base & X & & GnuPG is barebones. \\
-\hline Four modular reduction algorithms & X & & Faster modular exponentiation. \\
+\hline Five modular reduction algorithms & X & & Faster modular exponentiation for a variety of moduli. \\
 \hline Portable & X & & GnuPG requires configuration to build. \\
 \hline
 \end{tabular}
@@ -284,9 +284,12 @@ would require when working with large integers.
 So it may feel tempting to just rip the math code out of GnuPG (or GnuMP where it was taken from originally) in your
 own application but I think there are reasons not to.  While LibTomMath is slower than libraries such as GnuMP it is
 not normally significantly slower.  On x86 machines the difference is normally a factor of two when performing modular
-exponentiations.
+exponentiations.  It depends largely on the processor, compiler and the moduli being used.
 
-Essentially the only time you wouldn't use LibTomMath is when blazing speed is the primary concern.
+Essentially the only time you wouldn't use LibTomMath is when blazing speed is the primary concern.  However,
+on the other side of the coin LibTomMath offers you a totally free (public domain) well structured math library
+that is very flexible, complete and performs well in resource contrained environments.  Fast RSA for example can
+be performed with as little as 8KB of ram for data (again depending on build options).  
 
 \chapter{Getting Started with LibTomMath}
 \section{Building Programs}
@@ -809,7 +812,7 @@ mp\_int variables based on their digits only.
 
 \index{mp\_cmp\_mag}
 \begin{alltt}
-int mp_cmp(mp_int * a, mp_int * b);
+int mp_cmp_mag(mp_int * a, mp_int * b);
 \end{alltt}
 This will compare $a$ to $b$ placing $a$ to the left of $b$.  This function cannot fail and will return one of the
 three compare codes listed in figure \ref{fig:CMP}.
@@ -1220,12 +1223,13 @@ int mp_sqr (mp_int * a, mp_int * b);
 \end{alltt}
 
 Will square $a$ and store it in $b$.  Like the case of multiplication there are four different squaring
-algorithms all which can be called from mp\_sqr().  It is ideal to use mp\_sqr over mp\_mul when squaring terms.
+algorithms all which can be called from mp\_sqr().  It is ideal to use mp\_sqr over mp\_mul when squaring terms because
+of the speed difference.  
 
 \section{Tuning Polynomial Basis Routines}
 
 Both of the Toom-Cook and Karatsuba multiplication algorithms are faster than the traditional $O(n^2)$ approach that
-the Comba and baseline algorithms use.  At $O(n^{1.464973})$ and $O(n^{1.584962})$ running times respectfully they require 
+the Comba and baseline algorithms use.  At $O(n^{1.464973})$ and $O(n^{1.584962})$ running times respectively they require 
 considerably less work.  For example, a 10000-digit multiplication would take roughly 724,000 single precision
 multiplications with Toom-Cook or 100,000,000 single precision multiplications with the standard Comba (a factor
 of 138).
@@ -1297,14 +1301,14 @@ of $b$.  This algorithm accepts an input $a$ of any range and is not limited by
 \section{Barrett Reduction}
 
 Barrett reduction is a generic optimized reduction algorithm that requires pre--computation to achieve
-a decent speedup over straight division.  First a $mu$ value must be precomputed with the following function.
+a decent speedup over straight division.  First a $\mu$ value must be precomputed with the following function.
 
 \index{mp\_reduce\_setup}
 \begin{alltt}
 int mp_reduce_setup(mp_int *a, mp_int *b);
 \end{alltt}
 
-Given a modulus in $b$ this produces the required $mu$ value in $a$.  For any given modulus this only has to
+Given a modulus in $b$ this produces the required $\mu$ value in $a$.  For any given modulus this only has to
 be computed once.  Modular reduction can now be performed with the following.
 
 \index{mp\_reduce}
@@ -1312,7 +1316,7 @@ be computed once.  Modular reduction can now be performed with the following.
 int mp_reduce(mp_int *a, mp_int *b, mp_int *c);
 \end{alltt}
 
-This will reduce $a$ in place modulo $b$ with the precomputed $mu$ value in $c$.  $a$ must be in the range
+This will reduce $a$ in place modulo $b$ with the precomputed $\mu$ value in $c$.  $a$ must be in the range
 $0 \le a < b^2$.
 
 \begin{alltt}
@@ -1578,7 +1582,8 @@ will return $-2$.
 This algorithm uses the ``Newton Approximation'' method and will converge on the correct root fairly quickly.  Since
 the algorithm requires raising $a$ to the power of $b$ it is not ideal to attempt to find roots for large
 values of $b$.  If particularly large roots are required then a factor method could be used instead.  For example,
-$a^{1/16}$ is equivalent to $\left (a^{1/4} \right)^{1/4}$.
+$a^{1/16}$ is equivalent to $\left (a^{1/4} \right)^{1/4}$ or simply 
+$\left ( \left ( \left ( a^{1/2} \right )^{1/2} \right )^{1/2} \right )^{1/2}$
 
 \chapter{Prime Numbers}
 \section{Trial Division}
diff --git a/libtommath/bn_fast_mp_invmod.c b/libtommath/bn_fast_mp_invmod.c
index b5b9f10..acc8364 100644
--- a/libtommath/bn_fast_mp_invmod.c
+++ b/libtommath/bn_fast_mp_invmod.c
@@ -21,8 +21,7 @@
  * Based on slow invmod except this is optimized for the case where b is 
  * odd as per HAC Note 14.64 on pp. 610
  */
-int
-fast_mp_invmod (mp_int * a, mp_int * b, mp_int * c)
+int fast_mp_invmod (mp_int * a, mp_int * b, mp_int * c)
 {
   mp_int  x, y, u, v, B, D;
   int     res, neg;
@@ -43,7 +42,7 @@ fast_mp_invmod (mp_int * a, mp_int * b, mp_int * c)
   }
 
   /* we need y = |a| */
-  if ((res = mp_abs (a, &y)) != MP_OKAY) {
+  if ((res = mp_mod (a, b, &y)) != MP_OKAY) {
     goto LBL_ERR;
   }
 
diff --git a/libtommath/bn_fast_mp_montgomery_reduce.c b/libtommath/bn_fast_mp_montgomery_reduce.c
index 7373ae6..14f307f 100644
--- a/libtommath/bn_fast_mp_montgomery_reduce.c
+++ b/libtommath/bn_fast_mp_montgomery_reduce.c
@@ -23,8 +23,7 @@
  *
  * Based on Algorithm 14.32 on pp.601 of HAC.
 */
-int
-fast_mp_montgomery_reduce (mp_int * x, mp_int * n, mp_digit rho)
+int fast_mp_montgomery_reduce (mp_int * x, mp_int * n, mp_digit rho)
 {
   int     ix, res, olduse;
   mp_word W[MP_WARRAY];
diff --git a/libtommath/bn_fast_s_mp_mul_digs.c b/libtommath/bn_fast_s_mp_mul_digs.c
index e1ff5f3..df3da26 100644
--- a/libtommath/bn_fast_s_mp_mul_digs.c
+++ b/libtommath/bn_fast_s_mp_mul_digs.c
@@ -31,8 +31,7 @@
  * Based on Algorithm 14.12 on pp.595 of HAC.
  *
  */
-int
-fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
+int fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
 {
   int     olduse, res, pa, ix, iz;
   mp_digit W[MP_WARRAY];
@@ -63,7 +62,7 @@ fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
       tmpx = a->dp + tx;
       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) { ... }
        */
       iy = MIN(a->used-tx, ty+1);
@@ -81,16 +80,16 @@ fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
   }
 
   /* store final carry */
-  W[ix] = _W;
+  W[ix] = (mp_digit)(_W & MP_MASK);
 
   /* setup dest */
   olduse  = c->used;
-  c->used = digs;
+  c->used = pa;
 
   {
     register mp_digit *tmpc;
     tmpc = c->dp;
-    for (ix = 0; ix < digs; ix++) {
+    for (ix = 0; ix < pa+1; ix++) {
       /* now extract the previous digit [below the carry] */
       *tmpc++ = W[ix];
     }
diff --git a/libtommath/bn_fast_s_mp_mul_high_digs.c b/libtommath/bn_fast_s_mp_mul_high_digs.c
index 064a9dd..ee657f9 100644
--- a/libtommath/bn_fast_s_mp_mul_high_digs.c
+++ b/libtommath/bn_fast_s_mp_mul_high_digs.c
@@ -24,8 +24,7 @@
  *
  * Based on Algorithm 14.12 on pp.595 of HAC.
  */
-int
-fast_s_mp_mul_high_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
+int fast_s_mp_mul_high_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
 {
   int     olduse, res, pa, ix, iz;
   mp_digit W[MP_WARRAY];
@@ -72,7 +71,7 @@ fast_s_mp_mul_high_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
   }
   
   /* store final carry */
-  W[ix] = _W;
+  W[ix] = (mp_digit)(_W & MP_MASK);
 
   /* setup dest */
   olduse  = c->used;
diff --git a/libtommath/bn_fast_s_mp_sqr.c b/libtommath/bn_fast_s_mp_sqr.c
index d6014ab..66a2942 100644
--- a/libtommath/bn_fast_s_mp_sqr.c
+++ b/libtommath/bn_fast_s_mp_sqr.c
@@ -15,33 +15,14 @@
  * 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...
-
-you do like mult except the offset of the tmpx [one that starts closer to zero]
-can't equal the offset of tmpy.  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
+ * you do like mult except the offset of the tmpx [one that 
+ * starts closer to zero] can't equal the offset of tmpy.  
+ * 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
 
 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)
@@ -76,7 +57,7 @@ int fast_s_mp_sqr (mp_int * a, mp_int * b)
       tmpx = a->dp + tx;
       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) { ... }
        */
       iy = MIN(a->used-tx, ty+1);
@@ -101,7 +82,7 @@ int fast_s_mp_sqr (mp_int * a, mp_int * b)
       }
 
       /* store it */
-      W[ix] = _W;
+      W[ix] = (mp_digit)(_W & MP_MASK);
 
       /* make next carry */
       W1 = _W >> ((mp_word)DIGIT_BIT);
diff --git a/libtommath/bn_mp_exptmod.c b/libtommath/bn_mp_exptmod.c
index 7309170..7c4e2f8 100644
--- a/libtommath/bn_mp_exptmod.c
+++ b/libtommath/bn_mp_exptmod.c
@@ -65,21 +65,29 @@ int mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
 #endif
   }
 
+/* modified diminished radix reduction */
+#if defined(BN_MP_REDUCE_IS_2K_L_C) && defined(BN_MP_REDUCE_2K_L_C)
+  if (mp_reduce_is_2k_l(P) == MP_YES) {
+     return s_mp_exptmod(G, X, P, Y, 1);
+  }
+#endif
+
 #ifdef BN_MP_DR_IS_MODULUS_C
   /* is it a DR modulus? */
   dr = mp_dr_is_modulus(P);
 #else
+  /* default to no */
   dr = 0;
 #endif
 
 #ifdef BN_MP_REDUCE_IS_2K_C
-  /* if not, is it a uDR modulus? */
+  /* if not, is it a unrestricted DR modulus? */
   if (dr == 0) {
      dr = mp_reduce_is_2k(P) << 1;
   }
 #endif
     
-  /* if the modulus is odd or dr != 0 use the fast method */
+  /* if the modulus is odd or dr != 0 use the montgomery method */
 #ifdef BN_MP_EXPTMOD_FAST_C
   if (mp_isodd (P) == 1 || dr !=  0) {
     return mp_exptmod_fast (G, X, P, Y, dr);
@@ -87,7 +95,7 @@ int mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
 #endif
 #ifdef BN_S_MP_EXPTMOD_C
     /* otherwise use the generic Barrett reduction technique */
-    return s_mp_exptmod (G, X, P, Y);
+    return s_mp_exptmod (G, X, P, Y, 0);
 #else
     /* no exptmod for evens */
     return MP_VAL;
diff --git a/libtommath/bn_mp_exptmod_fast.c b/libtommath/bn_mp_exptmod_fast.c
index 255e9d9..82be9ac 100644
--- a/libtommath/bn_mp_exptmod_fast.c
+++ b/libtommath/bn_mp_exptmod_fast.c
@@ -29,8 +29,7 @@
    #define TAB_SIZE 256
 #endif
 
-int
-mp_exptmod_fast (mp_int * G, mp_int * X, mp_int * P, mp_int * Y, int redmode)
+int mp_exptmod_fast (mp_int * G, mp_int * X, mp_int * P, mp_int * Y, int redmode)
 {
   mp_int  M[TAB_SIZE], res;
   mp_digit buf, mp;
diff --git a/libtommath/bn_mp_exteuclid.c b/libtommath/bn_mp_exteuclid.c
index 545450b..c4ebab4 100644
--- a/libtommath/bn_mp_exteuclid.c
+++ b/libtommath/bn_mp_exteuclid.c
@@ -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; }
    }
 
+   /* make sure U3 >= 0 */
+   if (u3.sign == MP_NEG) {
+      mp_neg(&u1, &u1);
+      mp_neg(&u2, &u2);
+      mp_neg(&u3, &u3);
+   }
+
    /* copy result out */
    if (U1 != NULL) { mp_exch(U1, &u1); }
    if (U2 != NULL) { mp_exch(U2, &u2); }
diff --git a/libtommath/bn_mp_invmod_slow.c b/libtommath/bn_mp_invmod_slow.c
index c1884c0..c048655 100644
--- a/libtommath/bn_mp_invmod_slow.c
+++ b/libtommath/bn_mp_invmod_slow.c
@@ -33,8 +33,8 @@ int mp_invmod_slow (mp_int * a, mp_int * b, mp_int * c)
   }
 
   /* x = a, y = b */
-  if ((res = mp_copy (a, &x)) != MP_OKAY) {
-    goto LBL_ERR;
+  if ((res = mp_mod(a, b, &x)) != MP_OKAY) {
+      goto LBL_ERR;
   }
   if ((res = mp_copy (b, &y)) != MP_OKAY) {
     goto LBL_ERR;
diff --git a/libtommath/bn_mp_montgomery_calc_normalization.c b/libtommath/bn_mp_montgomery_calc_normalization.c
index 0a760cf..e2efc34 100644
--- a/libtommath/bn_mp_montgomery_calc_normalization.c
+++ b/libtommath/bn_mp_montgomery_calc_normalization.c
@@ -28,7 +28,6 @@ int mp_montgomery_calc_normalization (mp_int * a, mp_int * b)
   /* how many bits of last digit does b use */
   bits = mp_count_bits (b) % DIGIT_BIT;
 
-
   if (b->used > 1) {
      if ((res = mp_2expt (a, (b->used - 1) * DIGIT_BIT + bits - 1)) != MP_OKAY) {
         return res;
diff --git a/libtommath/bn_mp_mul_d.c b/libtommath/bn_mp_mul_d.c
index f936361..9e11eef 100644
--- a/libtommath/bn_mp_mul_d.c
+++ b/libtommath/bn_mp_mul_d.c
@@ -57,8 +57,9 @@ mp_mul_d (mp_int * a, mp_digit b, mp_int * c)
     u       = (mp_digit) (r >> ((mp_word) DIGIT_BIT));
   }
 
-  /* store final carry [if any] */
+  /* store final carry [if any] and increment ix offset  */
   *tmpc++ = u;
+  ++ix;
 
   /* now zero digits above the top */
   while (ix++ < olduse) {
diff --git a/libtommath/bn_mp_neg.c b/libtommath/bn_mp_neg.c
index 3a991db..159cd74 100644
--- a/libtommath/bn_mp_neg.c
+++ b/libtommath/bn_mp_neg.c
@@ -19,12 +19,18 @@
 int mp_neg (mp_int * a, mp_int * b)
 {
   int     res;
-  if ((res = mp_copy (a, b)) != MP_OKAY) {
-    return res;
+  if (a != b) {
+     if ((res = mp_copy (a, b)) != MP_OKAY) {
+        return res;
+     }
   }
+
   if (mp_iszero(b) != MP_YES) {
      b->sign = (a->sign == MP_ZPOS) ? MP_NEG : MP_ZPOS;
+  } else {
+     b->sign = MP_ZPOS;
   }
+
   return MP_OKAY;
 }
 #endif
diff --git a/libtommath/bn_mp_prime_random_ex.c b/libtommath/bn_mp_prime_random_ex.c
index 2010ebe..78c0583 100644
--- a/libtommath/bn_mp_prime_random_ex.c
+++ b/libtommath/bn_mp_prime_random_ex.c
@@ -60,7 +60,7 @@ int mp_prime_random_ex(mp_int *a, int t, int size, int flags, ltm_prime_callback
 
    /* calc the maskOR_msb */
    maskOR_msb        = 0;
-   maskOR_msb_offset = (size - 2) >> 3;
+   maskOR_msb_offset = ((size & 7) == 1) ? 1 : 0;
    if (flags & LTM_PRIME_2MSB_ON) {
       maskOR_msb     |= 1 << ((size - 2) & 7);
    } else if (flags & LTM_PRIME_2MSB_OFF) {
@@ -68,7 +68,7 @@ int mp_prime_random_ex(mp_int *a, int t, int size, int flags, ltm_prime_callback
    } 
 
    /* get the maskOR_lsb */
-   maskOR_lsb         = 0;
+   maskOR_lsb         = 1;
    if (flags & LTM_PRIME_BBS) {
       maskOR_lsb     |= 3;
    }
diff --git a/libtommath/bn_mp_radix_size.c b/libtommath/bn_mp_radix_size.c
index 30b78d9..3d423ba 100644
--- a/libtommath/bn_mp_radix_size.c
+++ b/libtommath/bn_mp_radix_size.c
@@ -35,22 +35,29 @@ int mp_radix_size (mp_int * a, int radix, int *size)
     return MP_VAL;
   }
 
-  /* init a copy of the input */
-  if ((res = mp_init_copy (&t, a)) != MP_OKAY) {
-    return res;
+  if (mp_iszero(a) == MP_YES) {
+     *size = 2;
+    return MP_OKAY;
   }
 
   /* digs is the digit count */
   digs = 0;
 
   /* if it's negative add one for the sign */
-  if (t.sign == MP_NEG) {
+  if (a->sign == MP_NEG) {
     ++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 */
-  while (mp_iszero (&t) == 0) {
+  while (mp_iszero (&t) == MP_NO) {
     if ((res = mp_div_d (&t, (mp_digit) radix, &t, &d)) != MP_OKAY) {
       mp_clear (&t);
       return res;
diff --git a/libtommath/bn_mp_rand.c b/libtommath/bn_mp_rand.c
index 1cc47f1..0dc7019 100644
--- a/libtommath/bn_mp_rand.c
+++ b/libtommath/bn_mp_rand.c
@@ -29,14 +29,14 @@ mp_rand (mp_int * a, int digits)
 
   /* first place a random non-zero digit */
   do {
-    d = ((mp_digit) abs (rand ()));
+    d = ((mp_digit) abs (rand ())) & MP_MASK;
   } while (d == 0);
 
   if ((res = mp_add_d (a, d, a)) != MP_OKAY) {
     return res;
   }
 
-  while (digits-- > 0) {
+  while (--digits > 0) {
     if ((res = mp_lshd (a, 1)) != MP_OKAY) {
       return res;
     }
diff --git a/libtommath/bn_mp_read_radix.c b/libtommath/bn_mp_read_radix.c
index 704bd0f..1ec3937 100644
--- a/libtommath/bn_mp_read_radix.c
+++ b/libtommath/bn_mp_read_radix.c
@@ -16,7 +16,7 @@
  */
 
 /* read a string [ASCII] in a given radix */
-int mp_read_radix (mp_int * a, char *str, int radix)
+int mp_read_radix (mp_int * a, const char *str, int radix)
 {
   int     y, res, neg;
   char    ch;
diff --git a/libtommath/bn_mp_reduce.c b/libtommath/bn_mp_reduce.c
index cfcb55a..d746445 100644
--- a/libtommath/bn_mp_reduce.c
+++ b/libtommath/bn_mp_reduce.c
@@ -19,8 +19,7 @@
  * precomputed via mp_reduce_setup.
  * From HAC pp.604 Algorithm 14.42
  */
-int
-mp_reduce (mp_int * x, mp_int * m, mp_int * mu)
+int mp_reduce (mp_int * x, mp_int * m, mp_int * mu)
 {
   mp_int  q;
   int     res, um = m->used;
@@ -40,11 +39,11 @@ mp_reduce (mp_int * x, mp_int * m, mp_int * mu)
     }
   } else {
 #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;
     }
 #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;
     }
 #else 
diff --git a/libtommath/bn_mp_reduce_2k.c b/libtommath/bn_mp_reduce_2k.c
index a5a9c74..28c3a00 100644
--- a/libtommath/bn_mp_reduce_2k.c
+++ b/libtommath/bn_mp_reduce_2k.c
@@ -16,8 +16,7 @@
  */
 
 /* reduces a modulo n where n is of the form 2**p - d */
-int
-mp_reduce_2k(mp_int *a, mp_int *n, mp_digit d)
+int mp_reduce_2k(mp_int *a, mp_int *n, mp_digit d)
 {
    mp_int q;
    int    p, res;
diff --git a/libtommath/bn_mp_reduce_2k_setup.c b/libtommath/bn_mp_reduce_2k_setup.c
index 5e1fb6e..585e1b7 100644
--- a/libtommath/bn_mp_reduce_2k_setup.c
+++ b/libtommath/bn_mp_reduce_2k_setup.c
@@ -16,8 +16,7 @@
  */
 
 /* determines the setup value */
-int 
-mp_reduce_2k_setup(mp_int *a, mp_digit *d)
+int mp_reduce_2k_setup(mp_int *a, mp_digit *d)
 {
    int res, p;
    mp_int tmp;
diff --git a/libtommath/bn_mp_reduce_is_2k.c b/libtommath/bn_mp_reduce_is_2k.c
index fc81397..0fb8384 100644
--- a/libtommath/bn_mp_reduce_is_2k.c
+++ b/libtommath/bn_mp_reduce_is_2k.c
@@ -22,9 +22,9 @@ int mp_reduce_is_2k(mp_int *a)
    mp_digit iz;
    
    if (a->used == 0) {
-      return 0;
+      return MP_NO;
    } else if (a->used == 1) {
-      return 1;
+      return MP_YES;
    } else if (a->used > 1) {
       iy = mp_count_bits(a);
       iz = 1;
@@ -33,7 +33,7 @@ int mp_reduce_is_2k(mp_int *a)
       /* Test every bit from the second digit up, must be 1 */
       for (ix = DIGIT_BIT; ix < iy; ix++) {
           if ((a->dp[iw] & iz) == 0) {
-             return 0;
+             return MP_NO;
           }
           iz <<= 1;
           if (iz > (mp_digit)MP_MASK) {
@@ -42,7 +42,7 @@ int mp_reduce_is_2k(mp_int *a)
           }
       }
    }
-   return 1;
+   return MP_YES;
 }
 
 #endif
diff --git a/libtommath/bn_mp_to_signed_bin.c b/libtommath/bn_mp_to_signed_bin.c
index 0e40d0f..b0a597e 100644
--- a/libtommath/bn_mp_to_signed_bin.c
+++ b/libtommath/bn_mp_to_signed_bin.c
@@ -16,8 +16,7 @@
  */
 
 /* store in signed [big endian] format */
-int
-mp_to_signed_bin (mp_int * a, unsigned char *b)
+int mp_to_signed_bin (mp_int * a, unsigned char *b)
 {
   int     res;
 
diff --git a/libtommath/bn_mp_to_unsigned_bin.c b/libtommath/bn_mp_to_unsigned_bin.c
index 763e346..000967e 100644
--- a/libtommath/bn_mp_to_unsigned_bin.c
+++ b/libtommath/bn_mp_to_unsigned_bin.c
@@ -16,8 +16,7 @@
  */
 
 /* store in unsigned [big endian] format */
-int
-mp_to_unsigned_bin (mp_int * a, unsigned char *b)
+int mp_to_unsigned_bin (mp_int * a, unsigned char *b)
 {
   int     x, res;
   mp_int  t;
diff --git a/libtommath/bn_mp_toom_mul.c b/libtommath/bn_mp_toom_mul.c
index 2d66779..125331b 100644
--- a/libtommath/bn_mp_toom_mul.c
+++ b/libtommath/bn_mp_toom_mul.c
@@ -17,9 +17,10 @@
 
 /* multiplication using the Toom-Cook 3-way algorithm 
  *
- * Much more complicated than Karatsuba but has a lower asymptotic running time of 
- * O(N**1.464).  This algorithm is only particularly useful on VERY large
- * inputs (we're talking 1000s of digits here...).
+ * Much more complicated than Karatsuba but has a lower 
+ * asymptotic running time of O(N**1.464).  This algorithm is 
+ * 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)
 {
diff --git a/libtommath/bn_mp_unsigned_bin_size.c b/libtommath/bn_mp_unsigned_bin_size.c
index 80da415..091f406 100644
--- a/libtommath/bn_mp_unsigned_bin_size.c
+++ b/libtommath/bn_mp_unsigned_bin_size.c
@@ -16,8 +16,7 @@
  */
 
 /* get the size for an unsigned equivalent */
-int
-mp_unsigned_bin_size (mp_int * a)
+int mp_unsigned_bin_size (mp_int * a)
 {
   int     size = mp_count_bits (a);
   return (size / 8 + ((size & 7) != 0 ? 1 : 0));
diff --git a/libtommath/bn_mp_xor.c b/libtommath/bn_mp_xor.c
index 192aacc..de7e62c 100644
--- a/libtommath/bn_mp_xor.c
+++ b/libtommath/bn_mp_xor.c
@@ -37,7 +37,7 @@ mp_xor (mp_int * a, mp_int * b, mp_int * c)
   }
 
   for (ix = 0; ix < px; ix++) {
-
+     t.dp[ix] ^= x->dp[ix];
   }
   mp_clamp (&t);
   mp_exch (c, &t);
diff --git a/libtommath/bn_mp_zero.c b/libtommath/bn_mp_zero.c
index 0097598..c8d8907 100644
--- a/libtommath/bn_mp_zero.c
+++ b/libtommath/bn_mp_zero.c
@@ -16,11 +16,17 @@
  */
 
 /* set to zero */
-void
-mp_zero (mp_int * a)
+void mp_zero (mp_int * a)
 {
+  int       n;
+  mp_digit *tmp;
+
   a->sign = MP_ZPOS;
   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
diff --git a/libtommath/bn_s_mp_exptmod.c b/libtommath/bn_s_mp_exptmod.c
index 01a766f..597e877 100644
--- a/libtommath/bn_s_mp_exptmod.c
+++ b/libtommath/bn_s_mp_exptmod.c
@@ -21,11 +21,12 @@
    #define TAB_SIZE 256
 #endif
 
-int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
+int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y, int redmode)
 {
   mp_int  M[TAB_SIZE], res, mu;
   mp_digit buf;
   int     err, bitbuf, bitcpy, bitcnt, mode, digidx, x, y, winsize;
+  int (*redux)(mp_int*,mp_int*,mp_int*);
 
   /* find window size */
   x = mp_count_bits (X);
@@ -72,9 +73,18 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
   if ((err = mp_init (&mu)) != MP_OKAY) {
     goto LBL_M;
   }
-  if ((err = mp_reduce_setup (&mu, P)) != MP_OKAY) {
-    goto LBL_MU;
-  }
+  
+  if (redmode == 0) {
+     if ((err = mp_reduce_setup (&mu, P)) != MP_OKAY) {
+        goto LBL_MU;
+     }
+     redux = mp_reduce;
+  } else {
+     if ((err = mp_reduce_2k_setup_l (P, &mu)) != MP_OKAY) {
+        goto LBL_MU;
+     }
+     redux = mp_reduce_2k_l;
+  }    
 
   /* create M table
    *
@@ -96,11 +106,14 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
   }
 
   for (x = 0; x < (winsize - 1); x++) {
+    /* square it */
     if ((err = mp_sqr (&M[1 << (winsize - 1)], 
                        &M[1 << (winsize - 1)])) != MP_OKAY) {
       goto LBL_MU;
     }
-    if ((err = mp_reduce (&M[1 << (winsize - 1)], P, &mu)) != MP_OKAY) {
+
+    /* reduce modulo P */
+    if ((err = redux (&M[1 << (winsize - 1)], P, &mu)) != MP_OKAY) {
       goto LBL_MU;
     }
   }
@@ -112,7 +125,7 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
     if ((err = mp_mul (&M[x - 1], &M[1], &M[x])) != MP_OKAY) {
       goto LBL_MU;
     }
-    if ((err = mp_reduce (&M[x], P, &mu)) != MP_OKAY) {
+    if ((err = redux (&M[x], P, &mu)) != MP_OKAY) {
       goto LBL_MU;
     }
   }
@@ -161,7 +174,7 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
       if ((err = mp_sqr (&res, &res)) != MP_OKAY) {
         goto LBL_RES;
       }
-      if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) {
+      if ((err = redux (&res, P, &mu)) != MP_OKAY) {
         goto LBL_RES;
       }
       continue;
@@ -178,7 +191,7 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
         if ((err = mp_sqr (&res, &res)) != MP_OKAY) {
           goto LBL_RES;
         }
-        if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) {
+        if ((err = redux (&res, P, &mu)) != MP_OKAY) {
           goto LBL_RES;
         }
       }
@@ -187,7 +200,7 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
       if ((err = mp_mul (&res, &M[bitbuf], &res)) != MP_OKAY) {
         goto LBL_RES;
       }
-      if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) {
+      if ((err = redux (&res, P, &mu)) != MP_OKAY) {
         goto LBL_RES;
       }
 
@@ -205,7 +218,7 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
       if ((err = mp_sqr (&res, &res)) != MP_OKAY) {
         goto LBL_RES;
       }
-      if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) {
+      if ((err = redux (&res, P, &mu)) != MP_OKAY) {
         goto LBL_RES;
       }
 
@@ -215,7 +228,7 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
         if ((err = mp_mul (&res, &M[1], &res)) != MP_OKAY) {
           goto LBL_RES;
         }
-        if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) {
+        if ((err = redux (&res, P, &mu)) != MP_OKAY) {
           goto LBL_RES;
         }
       }
diff --git a/libtommath/bn_s_mp_mul_digs.c b/libtommath/bn_s_mp_mul_digs.c
index d9f0a56..b40ae2e 100644
--- a/libtommath/bn_s_mp_mul_digs.c
+++ b/libtommath/bn_s_mp_mul_digs.c
@@ -19,8 +19,7 @@
  * HAC pp. 595, Algorithm 14.12  Modified so you can control how 
  * many digits of output are created.
  */
-int
-s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
+int s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
 {
   mp_int  t;
   int     res, pa, pb, ix, iy;
diff --git a/libtommath/bn_s_mp_sqr.c b/libtommath/bn_s_mp_sqr.c
index 4d12804..9cdb563 100644
--- a/libtommath/bn_s_mp_sqr.c
+++ b/libtommath/bn_s_mp_sqr.c
@@ -16,8 +16,7 @@
  */
 
 /* low level squaring, b = a*a, HAC pp.596-597, Algorithm 14.16 */
-int
-s_mp_sqr (mp_int * a, mp_int * b)
+int s_mp_sqr (mp_int * a, mp_int * b)
 {
   mp_int  t;
   int     res, ix, iy, pa;
diff --git a/libtommath/bncore.c b/libtommath/bncore.c
index cf8a15a..82e3132 100644
--- a/libtommath/bncore.c
+++ b/libtommath/bncore.c
@@ -20,11 +20,12 @@
  CPU                    /Compiler     /MUL CUTOFF/SQR CUTOFF
 -------------------------------------------------------------
  Intel P4 Northwood     /GCC v3.4.1   /        88/       128/LTM 0.32 ;-)
+ AMD Athlon64           /GCC v3.4.4   /        74/       124/LTM 0.34
  
 */
 
-int     KARATSUBA_MUL_CUTOFF = 88,      /* Min. number of digits before Karatsuba multiplication is used. */
-        KARATSUBA_SQR_CUTOFF = 128,     /* Min. number of digits before Karatsuba squaring is used. */
+int     KARATSUBA_MUL_CUTOFF = 74,      /* Min. number of digits before Karatsuba multiplication is used. */
+        KARATSUBA_SQR_CUTOFF = 124,     /* Min. number of digits before Karatsuba squaring is used. */
         
         TOOM_MUL_CUTOFF      = 350,      /* no optimal values of these are known yet so set em high */
         TOOM_SQR_CUTOFF      = 400; 
diff --git a/libtommath/callgraph.txt b/libtommath/callgraph.txt
index 4dc4cba..2efcf24 100644
--- a/libtommath/callgraph.txt
+++ b/libtommath/callgraph.txt
@@ -907,7 +907,64 @@ BN_MP_EXPTMOD_C
 |   |   |   +--->BN_MP_CLEAR_C
 |   |   +--->BN_MP_COPY_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_ZERO_C
 |   |   +--->BN_MP_DIV_2_C
@@ -938,6 +995,66 @@ BN_MP_EXPTMOD_C
 |   +--->BN_MP_INVMOD_SLOW_C
 |   |   +--->BN_MP_INIT_MULTI_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_GROW_C
 |   |   +--->BN_MP_SET_C
@@ -973,93 +1090,63 @@ BN_MP_EXPTMOD_C
 |   +--->BN_MP_COPY_C
 |   |   +--->BN_MP_GROW_C
 +--->BN_MP_CLEAR_MULTI_C
-+--->BN_MP_DR_IS_MODULUS_C
-+--->BN_MP_REDUCE_IS_2K_C
-|   +--->BN_MP_REDUCE_2K_C
-|   |   +--->BN_MP_COUNT_BITS_C
-|   |   +--->BN_MP_DIV_2D_C
-|   |   |   +--->BN_MP_COPY_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_RSHD_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_EXCH_C
-|   |   +--->BN_MP_MUL_D_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CLAMP_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_COUNT_BITS_C
-+--->BN_MP_EXPTMOD_FAST_C
++--->BN_MP_REDUCE_IS_2K_L_C
++--->BN_S_MP_EXPTMOD_C
 |   +--->BN_MP_COUNT_BITS_C
-|   +--->BN_MP_MONTGOMERY_SETUP_C
-|   +--->BN_FAST_MP_MONTGOMERY_REDUCE_C
-|   |   +--->BN_MP_GROW_C
-|   |   +--->BN_MP_RSHD_C
-|   |   |   +--->BN_MP_ZERO_C
-|   |   +--->BN_MP_CLAMP_C
-|   |   +--->BN_MP_CMP_MAG_C
-|   |   +--->BN_S_MP_SUB_C
-|   +--->BN_MP_MONTGOMERY_REDUCE_C
-|   |   +--->BN_MP_GROW_C
-|   |   +--->BN_MP_CLAMP_C
-|   |   +--->BN_MP_RSHD_C
-|   |   |   +--->BN_MP_ZERO_C
-|   |   +--->BN_MP_CMP_MAG_C
-|   |   +--->BN_S_MP_SUB_C
-|   +--->BN_MP_DR_SETUP_C
-|   +--->BN_MP_DR_REDUCE_C
-|   |   +--->BN_MP_GROW_C
-|   |   +--->BN_MP_CLAMP_C
-|   |   +--->BN_MP_CMP_MAG_C
-|   |   +--->BN_S_MP_SUB_C
-|   +--->BN_MP_REDUCE_2K_SETUP_C
+|   +--->BN_MP_REDUCE_SETUP_C
 |   |   +--->BN_MP_2EXPT_C
 |   |   |   +--->BN_MP_ZERO_C
 |   |   |   +--->BN_MP_GROW_C
-|   |   +--->BN_S_MP_SUB_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   +--->BN_MP_REDUCE_2K_C
-|   |   +--->BN_MP_DIV_2D_C
+|   |   +--->BN_MP_DIV_C
+|   |   |   +--->BN_MP_CMP_MAG_C
 |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   +--->BN_MP_SET_C
+|   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   +--->BN_MP_RSHD_C
 |   |   |   |   +--->BN_MP_CLAMP_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_RSHD_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_EXCH_C
 |   |   |   +--->BN_MP_EXCH_C
-|   |   +--->BN_MP_MUL_D_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CLAMP_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_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_MONTGOMERY_CALC_NORMALIZATION_C
-|   |   +--->BN_MP_2EXPT_C
-|   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   +--->BN_MP_SET_C
+|   +--->BN_MP_REDUCE_C
+|   |   +--->BN_MP_INIT_COPY_C
+|   |   |   +--->BN_MP_COPY_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_RSHD_C
 |   |   |   +--->BN_MP_ZERO_C
-|   |   +--->BN_MP_MUL_2_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   +--->BN_MP_CMP_MAG_C
-|   |   +--->BN_S_MP_SUB_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   +--->BN_MP_MULMOD_C
 |   |   +--->BN_MP_MUL_C
 |   |   |   +--->BN_MP_TOOM_MUL_C
 |   |   |   |   +--->BN_MP_INIT_MULTI_C
@@ -1070,8 +1157,6 @@ BN_MP_EXPTMOD_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   +--->BN_MP_MUL_2_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   +--->BN_MP_ADD_C
@@ -1123,8 +1208,6 @@ BN_MP_EXPTMOD_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   +--->BN_MP_LSHD_C
 |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
 |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   +--->BN_MP_CLAMP_C
@@ -1132,62 +1215,150 @@ BN_MP_EXPTMOD_C
 |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   +--->BN_MP_EXCH_C
-|   |   +--->BN_MP_MOD_C
-|   |   |   +--->BN_MP_DIV_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   +--->BN_S_MP_MUL_HIGH_DIGS_C
+|   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_EXCH_C
+|   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_MOD_2D_C
+|   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_COPY_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_EXCH_C
+|   |   +--->BN_MP_SUB_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_CMP_D_C
+|   |   +--->BN_MP_SET_C
+|   |   |   +--->BN_MP_ZERO_C
+|   |   +--->BN_MP_LSHD_C
+|   |   |   +--->BN_MP_GROW_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_CMP_C
+|   |   |   +--->BN_MP_CMP_MAG_C
+|   |   +--->BN_S_MP_SUB_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   +--->BN_MP_REDUCE_2K_SETUP_L_C
+|   |   +--->BN_MP_2EXPT_C
+|   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   +--->BN_S_MP_SUB_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   +--->BN_MP_REDUCE_2K_L_C
+|   |   +--->BN_MP_DIV_2D_C
+|   |   |   +--->BN_MP_COPY_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_RSHD_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_EXCH_C
+|   |   +--->BN_MP_MUL_C
+|   |   |   +--->BN_MP_TOOM_MUL_C
+|   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   +--->BN_MP_SET_C
-|   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_MUL_2_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_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_ADD_C
+|   |   |   |   +--->BN_MP_SUB_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_DIV_2D_C
-|   |   |   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   +--->BN_MP_DIV_2_C
+|   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   +--->BN_MP_INIT_COPY_C
-|   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   +--->BN_MP_MUL_2D_C
 |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   +--->BN_MP_MUL_D_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_ADD_C
-|   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_DIV_3_C
+|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   +--->BN_MP_LSHD_C
 |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_EXCH_C
-|   +--->BN_MP_SET_C
-|   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_KARATSUBA_MUL_C
+|   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_SUB_C
+|   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_ADD_C
+|   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_EXCH_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_MOD_C
 |   |   +--->BN_MP_DIV_C
 |   |   |   +--->BN_MP_CMP_MAG_C
@@ -1195,6 +1366,7 @@ BN_MP_EXPTMOD_C
 |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   +--->BN_MP_ZERO_C
 |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   +--->BN_MP_SET_C
 |   |   |   +--->BN_MP_MUL_2D_C
 |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   +--->BN_MP_LSHD_C
@@ -1379,57 +1551,224 @@ BN_MP_EXPTMOD_C
 |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   +--->BN_MP_EXCH_C
+|   +--->BN_MP_SET_C
+|   |   +--->BN_MP_ZERO_C
 |   +--->BN_MP_EXCH_C
-+--->BN_S_MP_EXPTMOD_C
++--->BN_MP_DR_IS_MODULUS_C
++--->BN_MP_REDUCE_IS_2K_C
+|   +--->BN_MP_REDUCE_2K_C
+|   |   +--->BN_MP_COUNT_BITS_C
+|   |   +--->BN_MP_DIV_2D_C
+|   |   |   +--->BN_MP_COPY_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_RSHD_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_EXCH_C
+|   |   +--->BN_MP_MUL_D_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_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_COUNT_BITS_C
-|   +--->BN_MP_REDUCE_SETUP_C
++--->BN_MP_EXPTMOD_FAST_C
+|   +--->BN_MP_COUNT_BITS_C
+|   +--->BN_MP_MONTGOMERY_SETUP_C
+|   +--->BN_FAST_MP_MONTGOMERY_REDUCE_C
+|   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_RSHD_C
+|   |   |   +--->BN_MP_ZERO_C
+|   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_CMP_MAG_C
+|   |   +--->BN_S_MP_SUB_C
+|   +--->BN_MP_MONTGOMERY_REDUCE_C
+|   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_RSHD_C
+|   |   |   +--->BN_MP_ZERO_C
+|   |   +--->BN_MP_CMP_MAG_C
+|   |   +--->BN_S_MP_SUB_C
+|   +--->BN_MP_DR_SETUP_C
+|   +--->BN_MP_DR_REDUCE_C
+|   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_CMP_MAG_C
+|   |   +--->BN_S_MP_SUB_C
+|   +--->BN_MP_REDUCE_2K_SETUP_C
 |   |   +--->BN_MP_2EXPT_C
 |   |   |   +--->BN_MP_ZERO_C
 |   |   |   +--->BN_MP_GROW_C
-|   |   +--->BN_MP_DIV_C
-|   |   |   +--->BN_MP_CMP_MAG_C
+|   |   +--->BN_S_MP_SUB_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   +--->BN_MP_REDUCE_2K_C
+|   |   +--->BN_MP_DIV_2D_C
 |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   +--->BN_MP_SET_C
-|   |   |   +--->BN_MP_MUL_2D_C
-|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_RSHD_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_EXCH_C
+|   |   +--->BN_MP_MUL_D_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_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_MONTGOMERY_CALC_NORMALIZATION_C
+|   |   +--->BN_MP_2EXPT_C
+|   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_SET_C
+|   |   |   +--->BN_MP_ZERO_C
+|   |   +--->BN_MP_MUL_2_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_CMP_MAG_C
+|   |   +--->BN_S_MP_SUB_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   +--->BN_MP_MULMOD_C
+|   |   +--->BN_MP_MUL_C
+|   |   |   +--->BN_MP_TOOM_MUL_C
+|   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_MUL_2_C
+|   |   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_DIV_3_C
+|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_EXCH_C
 |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_KARATSUBA_MUL_C
+|   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_SUB_C
+|   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_ADD_C
+|   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_CMP_C
-|   |   |   +--->BN_MP_SUB_C
-|   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_EXCH_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_INIT_MULTI_C
+|   |   |   |   +--->BN_MP_SET_C
+|   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   +--->BN_MP_RSHD_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_S_MP_SUB_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_RSHD_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   +--->BN_MP_EXCH_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_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_DIV_2D_C
-|   |   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_EXCH_C
 |   |   |   +--->BN_MP_EXCH_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_SET_C
+|   |   +--->BN_MP_ZERO_C
 |   +--->BN_MP_MOD_C
 |   |   +--->BN_MP_DIV_C
 |   |   |   +--->BN_MP_CMP_MAG_C
@@ -1437,7 +1776,6 @@ BN_MP_EXPTMOD_C
 |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   +--->BN_MP_ZERO_C
 |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   +--->BN_MP_SET_C
 |   |   |   +--->BN_MP_MUL_2D_C
 |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   +--->BN_MP_LSHD_C
@@ -1554,120 +1892,6 @@ BN_MP_EXPTMOD_C
 |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   +--->BN_MP_EXCH_C
-|   +--->BN_MP_REDUCE_C
-|   |   +--->BN_MP_INIT_COPY_C
-|   |   +--->BN_MP_RSHD_C
-|   |   |   +--->BN_MP_ZERO_C
-|   |   +--->BN_MP_MUL_C
-|   |   |   +--->BN_MP_TOOM_MUL_C
-|   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_MUL_2_C
-|   |   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_MUL_2D_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_DIV_3_C
-|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_KARATSUBA_MUL_C
-|   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_SUB_C
-|   |   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_ADD_C
-|   |   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_S_MP_MUL_DIGS_C
-|   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_EXCH_C
-|   |   +--->BN_S_MP_MUL_HIGH_DIGS_C
-|   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_EXCH_C
-|   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   +--->BN_MP_MOD_2D_C
-|   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   +--->BN_S_MP_MUL_DIGS_C
-|   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_EXCH_C
-|   |   +--->BN_MP_SUB_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_CMP_D_C
-|   |   +--->BN_MP_SET_C
-|   |   |   +--->BN_MP_ZERO_C
-|   |   +--->BN_MP_LSHD_C
-|   |   |   +--->BN_MP_GROW_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_CMP_C
-|   |   |   +--->BN_MP_CMP_MAG_C
-|   |   +--->BN_S_MP_SUB_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CLAMP_C
 |   +--->BN_MP_MUL_C
 |   |   +--->BN_MP_TOOM_MUL_C
 |   |   |   +--->BN_MP_INIT_MULTI_C
@@ -1736,8 +1960,6 @@ BN_MP_EXPTMOD_C
 |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   +--->BN_MP_EXCH_C
-|   +--->BN_MP_SET_C
-|   |   +--->BN_MP_ZERO_C
 |   +--->BN_MP_EXCH_C
 
 
@@ -1769,7 +1991,64 @@ BN_MP_PRIME_FERMAT_C
 |   |   |   |   +--->BN_MP_CLEAR_C
 |   |   |   +--->BN_MP_COPY_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_ZERO_C
 |   |   |   +--->BN_MP_DIV_2_C
@@ -1799,6 +2078,66 @@ BN_MP_PRIME_FERMAT_C
 |   |   +--->BN_MP_INVMOD_SLOW_C
 |   |   |   +--->BN_MP_INIT_MULTI_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_GROW_C
 |   |   |   +--->BN_MP_SET_C
@@ -1833,93 +2172,63 @@ BN_MP_PRIME_FERMAT_C
 |   |   +--->BN_MP_COPY_C
 |   |   |   +--->BN_MP_GROW_C
 |   +--->BN_MP_CLEAR_MULTI_C
-|   +--->BN_MP_DR_IS_MODULUS_C
-|   +--->BN_MP_REDUCE_IS_2K_C
-|   |   +--->BN_MP_REDUCE_2K_C
-|   |   |   +--->BN_MP_COUNT_BITS_C
-|   |   |   +--->BN_MP_DIV_2D_C
-|   |   |   |   +--->BN_MP_COPY_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_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_COUNT_BITS_C
-|   +--->BN_MP_EXPTMOD_FAST_C
+|   +--->BN_MP_REDUCE_IS_2K_L_C
+|   +--->BN_S_MP_EXPTMOD_C
 |   |   +--->BN_MP_COUNT_BITS_C
-|   |   +--->BN_MP_MONTGOMERY_SETUP_C
-|   |   +--->BN_FAST_MP_MONTGOMERY_REDUCE_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   +--->BN_S_MP_SUB_C
-|   |   +--->BN_MP_MONTGOMERY_REDUCE_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   +--->BN_S_MP_SUB_C
-|   |   +--->BN_MP_DR_SETUP_C
-|   |   +--->BN_MP_DR_REDUCE_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   +--->BN_S_MP_SUB_C
-|   |   +--->BN_MP_REDUCE_2K_SETUP_C
+|   |   +--->BN_MP_REDUCE_SETUP_C
 |   |   |   +--->BN_MP_2EXPT_C
 |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   +--->BN_MP_REDUCE_2K_C
-|   |   |   +--->BN_MP_DIV_2D_C
+|   |   |   +--->BN_MP_DIV_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
 |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   +--->BN_MP_SET_C
+|   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   +--->BN_MP_RSHD_C
 |   |   |   |   |   +--->BN_MP_CLAMP_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_RSHD_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_EXCH_C
 |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_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_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_MONTGOMERY_CALC_NORMALIZATION_C
-|   |   |   +--->BN_MP_2EXPT_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_SET_C
+|   |   +--->BN_MP_REDUCE_C
+|   |   |   +--->BN_MP_INIT_COPY_C
+|   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_RSHD_C
 |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_MUL_2_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   +--->BN_MP_MULMOD_C
 |   |   |   +--->BN_MP_MUL_C
 |   |   |   |   +--->BN_MP_TOOM_MUL_C
 |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
@@ -1930,8 +2239,6 @@ BN_MP_PRIME_FERMAT_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   +--->BN_MP_MUL_2_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_ADD_C
@@ -1983,8 +2290,6 @@ BN_MP_PRIME_FERMAT_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_LSHD_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
@@ -1992,62 +2297,149 @@ BN_MP_PRIME_FERMAT_C
 |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   +--->BN_MP_MOD_C
-|   |   |   |   +--->BN_MP_DIV_C
-|   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   +--->BN_MP_SUB_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_SET_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   +--->BN_MP_GROW_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_CMP_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_REDUCE_2K_SETUP_L_C
+|   |   |   +--->BN_MP_2EXPT_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_REDUCE_2K_L_C
+|   |   |   +--->BN_MP_DIV_2D_C
+|   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   +--->BN_MP_MUL_C
+|   |   |   |   +--->BN_MP_TOOM_MUL_C
+|   |   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   |   +--->BN_MP_SET_C
-|   |   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_MP_MUL_2_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_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_ADD_C
+|   |   |   |   |   +--->BN_MP_SUB_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_DIV_2D_C
-|   |   |   |   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   +--->BN_MP_DIV_2_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   +--->BN_MP_INIT_COPY_C
-|   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   +--->BN_MP_MUL_2D_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   +--->BN_MP_MUL_D_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_ADD_C
-|   |   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_DIV_3_C
+|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   +--->BN_MP_LSHD_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_EXCH_C
-|   |   +--->BN_MP_SET_C
-|   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
+|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_SUB_C
+|   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_ADD_C
+|   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_EXCH_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_MOD_C
 |   |   |   +--->BN_MP_DIV_C
 |   |   |   |   +--->BN_MP_CMP_MAG_C
@@ -2055,6 +2447,7 @@ BN_MP_PRIME_FERMAT_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   +--->BN_MP_SET_C
 |   |   |   |   +--->BN_MP_MUL_2D_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_LSHD_C
@@ -2239,57 +2632,224 @@ BN_MP_PRIME_FERMAT_C
 |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   +--->BN_MP_EXCH_C
+|   |   +--->BN_MP_SET_C
+|   |   |   +--->BN_MP_ZERO_C
 |   |   +--->BN_MP_EXCH_C
-|   +--->BN_S_MP_EXPTMOD_C
+|   +--->BN_MP_DR_IS_MODULUS_C
+|   +--->BN_MP_REDUCE_IS_2K_C
+|   |   +--->BN_MP_REDUCE_2K_C
+|   |   |   +--->BN_MP_COUNT_BITS_C
+|   |   |   +--->BN_MP_DIV_2D_C
+|   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_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_COUNT_BITS_C
-|   |   +--->BN_MP_REDUCE_SETUP_C
+|   +--->BN_MP_EXPTMOD_FAST_C
+|   |   +--->BN_MP_COUNT_BITS_C
+|   |   +--->BN_MP_MONTGOMERY_SETUP_C
+|   |   +--->BN_FAST_MP_MONTGOMERY_REDUCE_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   +--->BN_MP_MONTGOMERY_REDUCE_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   +--->BN_MP_DR_SETUP_C
+|   |   +--->BN_MP_DR_REDUCE_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   +--->BN_MP_REDUCE_2K_SETUP_C
 |   |   |   +--->BN_MP_2EXPT_C
 |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_DIV_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_REDUCE_2K_C
+|   |   |   +--->BN_MP_DIV_2D_C
 |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   +--->BN_MP_SET_C
-|   |   |   |   +--->BN_MP_MUL_2D_C
-|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_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_MONTGOMERY_CALC_NORMALIZATION_C
+|   |   |   +--->BN_MP_2EXPT_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_SET_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_MUL_2_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_MULMOD_C
+|   |   |   +--->BN_MP_MUL_C
+|   |   |   |   +--->BN_MP_TOOM_MUL_C
+|   |   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_MP_MUL_2_C
+|   |   |   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_DIV_3_C
+|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_EXCH_C
 |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
+|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_SUB_C
+|   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_ADD_C
+|   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_CMP_C
-|   |   |   |   +--->BN_MP_SUB_C
-|   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_EXCH_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_INIT_MULTI_C
+|   |   |   |   |   +--->BN_MP_SET_C
+|   |   |   |   |   +--->BN_MP_MUL_2D_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_RSHD_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_S_MP_SUB_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_RSHD_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   +--->BN_MP_EXCH_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_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_DIV_2D_C
-|   |   |   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_EXCH_C
 |   |   |   |   +--->BN_MP_EXCH_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_SET_C
+|   |   |   +--->BN_MP_ZERO_C
 |   |   +--->BN_MP_MOD_C
 |   |   |   +--->BN_MP_DIV_C
 |   |   |   |   +--->BN_MP_CMP_MAG_C
@@ -2297,7 +2857,6 @@ BN_MP_PRIME_FERMAT_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   +--->BN_MP_SET_C
 |   |   |   |   +--->BN_MP_MUL_2D_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_LSHD_C
@@ -2414,119 +2973,6 @@ BN_MP_PRIME_FERMAT_C
 |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   +--->BN_MP_EXCH_C
-|   |   +--->BN_MP_REDUCE_C
-|   |   |   +--->BN_MP_INIT_COPY_C
-|   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_MUL_C
-|   |   |   |   +--->BN_MP_TOOM_MUL_C
-|   |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_MUL_2_C
-|   |   |   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_MUL_2D_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_DIV_3_C
-|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
-|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_SUB_C
-|   |   |   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_ADD_C
-|   |   |   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_S_MP_MUL_DIGS_C
-|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   +--->BN_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_S_MP_MUL_DIGS_C
-|   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   +--->BN_MP_SUB_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_SET_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   +--->BN_MP_GROW_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_CMP_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
 |   |   +--->BN_MP_MUL_C
 |   |   |   +--->BN_MP_TOOM_MUL_C
 |   |   |   |   +--->BN_MP_INIT_MULTI_C
@@ -2595,8 +3041,6 @@ BN_MP_PRIME_FERMAT_C
 |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   +--->BN_MP_EXCH_C
-|   |   +--->BN_MP_SET_C
-|   |   |   +--->BN_MP_ZERO_C
 |   |   +--->BN_MP_EXCH_C
 +--->BN_MP_CMP_C
 |   +--->BN_MP_CMP_MAG_C
@@ -2901,7 +3345,65 @@ BN_MP_INVMOD_C
 |   |   +--->BN_MP_CLEAR_C
 |   +--->BN_MP_COPY_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_ZERO_C
 |   +--->BN_MP_DIV_2_C
@@ -2933,6 +3435,67 @@ BN_MP_INVMOD_C
 |   +--->BN_MP_INIT_MULTI_C
 |   |   +--->BN_MP_INIT_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_GROW_C
 |   +--->BN_MP_SET_C
@@ -2985,7 +3548,65 @@ BN_FAST_MP_INVMOD_C
 |   +--->BN_MP_CLEAR_C
 +--->BN_MP_COPY_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_ZERO_C
 +--->BN_MP_DIV_2_C
@@ -3473,7 +4094,55 @@ BN_MP_PRIME_RANDOM_EX_C
 |   |   |   |   |   |   +--->BN_MP_CLEAR_C
 |   |   |   |   |   +--->BN_MP_COPY_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_GROW_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
@@ -3501,6 +4170,57 @@ BN_MP_PRIME_RANDOM_EX_C
 |   |   |   |   +--->BN_MP_INVMOD_SLOW_C
 |   |   |   |   |   +--->BN_MP_INIT_MULTI_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_GROW_C
 |   |   |   |   |   +--->BN_MP_DIV_2_C
@@ -3533,73 +4253,52 @@ BN_MP_PRIME_RANDOM_EX_C
 |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   +--->BN_MP_CLEAR_MULTI_C
-|   |   |   +--->BN_MP_DR_IS_MODULUS_C
-|   |   |   +--->BN_MP_REDUCE_IS_2K_C
-|   |   |   |   +--->BN_MP_REDUCE_2K_C
-|   |   |   |   |   +--->BN_MP_COUNT_BITS_C
-|   |   |   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_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_COUNT_BITS_C
-|   |   |   +--->BN_MP_EXPTMOD_FAST_C
+|   |   |   +--->BN_MP_REDUCE_IS_2K_L_C
+|   |   |   +--->BN_S_MP_EXPTMOD_C
 |   |   |   |   +--->BN_MP_COUNT_BITS_C
-|   |   |   |   +--->BN_MP_MONTGOMERY_SETUP_C
-|   |   |   |   +--->BN_FAST_MP_MONTGOMERY_REDUCE_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   +--->BN_MP_MONTGOMERY_REDUCE_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   +--->BN_MP_DR_SETUP_C
-|   |   |   |   +--->BN_MP_DR_REDUCE_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   +--->BN_MP_REDUCE_2K_SETUP_C
+|   |   |   |   +--->BN_MP_REDUCE_SETUP_C
 |   |   |   |   |   +--->BN_MP_2EXPT_C
 |   |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_REDUCE_2K_C
-|   |   |   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_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_MONTGOMERY_CALC_NORMALIZATION_C
-|   |   |   |   |   +--->BN_MP_2EXPT_C
+|   |   |   |   |   +--->BN_MP_DIV_C
+|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_MUL_2_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_INIT_MULTI_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_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_MULMOD_C
+|   |   |   |   +--->BN_MP_REDUCE_C
+|   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   +--->BN_MP_MUL_C
 |   |   |   |   |   |   +--->BN_MP_TOOM_MUL_C
 |   |   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
@@ -3610,8 +4309,6 @@ BN_MP_PRIME_RANDOM_EX_C
 |   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   |   |   +--->BN_MP_MUL_2_C
 |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   |   +--->BN_MP_ADD_C
@@ -3663,8 +4360,6 @@ BN_MP_PRIME_RANDOM_EX_C
 |   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   |   +--->BN_MP_LSHD_C
 |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
@@ -3672,52 +4367,138 @@ BN_MP_PRIME_RANDOM_EX_C
 |   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   |   +--->BN_MP_MOD_C
-|   |   |   |   |   |   +--->BN_MP_DIV_C
-|   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   +--->BN_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   +--->BN_MP_SUB_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_LSHD_C
+|   |   |   |   |   |   +--->BN_MP_GROW_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_CMP_C
+|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_REDUCE_2K_SETUP_L_C
+|   |   |   |   |   +--->BN_MP_2EXPT_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_REDUCE_2K_L_C
+|   |   |   |   |   +--->BN_MP_MUL_C
+|   |   |   |   |   |   +--->BN_MP_TOOM_MUL_C
+|   |   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   |   +--->BN_MP_MUL_2_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_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_ADD_C
+|   |   |   |   |   |   |   +--->BN_MP_SUB_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_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_DIV_2_C
 |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_ADD_C
-|   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   +--->BN_MP_MUL_2D_C
 |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   |   +--->BN_MP_LSHD_C
 |   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   +--->BN_MP_MUL_D_C
 |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   |   |   +--->BN_MP_DIV_3_C
+|   |   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
+|   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   |   +--->BN_MP_SUB_C
+|   |   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_ADD_C
+|   |   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   |   +--->BN_MP_EXCH_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_MOD_C
 |   |   |   |   |   +--->BN_MP_DIV_C
 |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
@@ -3903,48 +4684,191 @@ BN_MP_PRIME_RANDOM_EX_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   |   +--->BN_MP_EXCH_C
 |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   +--->BN_S_MP_EXPTMOD_C
+|   |   |   +--->BN_MP_DR_IS_MODULUS_C
+|   |   |   +--->BN_MP_REDUCE_IS_2K_C
+|   |   |   |   +--->BN_MP_REDUCE_2K_C
+|   |   |   |   |   +--->BN_MP_COUNT_BITS_C
+|   |   |   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_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_COUNT_BITS_C
-|   |   |   |   +--->BN_MP_REDUCE_SETUP_C
+|   |   |   +--->BN_MP_EXPTMOD_FAST_C
+|   |   |   |   +--->BN_MP_COUNT_BITS_C
+|   |   |   |   +--->BN_MP_MONTGOMERY_SETUP_C
+|   |   |   |   +--->BN_FAST_MP_MONTGOMERY_REDUCE_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   +--->BN_MP_MONTGOMERY_REDUCE_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   +--->BN_MP_DR_SETUP_C
+|   |   |   |   +--->BN_MP_DR_REDUCE_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   +--->BN_MP_REDUCE_2K_SETUP_C
 |   |   |   |   |   +--->BN_MP_2EXPT_C
 |   |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_DIV_C
-|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   |   +--->BN_MP_COPY_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_REDUCE_2K_C
+|   |   |   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_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_MONTGOMERY_CALC_NORMALIZATION_C
+|   |   |   |   |   +--->BN_MP_2EXPT_C
 |   |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   |   |   +--->BN_MP_MUL_2D_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_MUL_2_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_MULMOD_C
+|   |   |   |   |   +--->BN_MP_MUL_C
+|   |   |   |   |   |   +--->BN_MP_TOOM_MUL_C
+|   |   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   |   +--->BN_MP_MUL_2_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   |   +--->BN_MP_DIV_3_C
+|   |   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
+|   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   |   +--->BN_MP_SUB_C
+|   |   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_ADD_C
+|   |   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_CMP_C
-|   |   |   |   |   |   +--->BN_MP_SUB_C
-|   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   |   +--->BN_MP_EXCH_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_INIT_MULTI_C
+|   |   |   |   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   |   |   +--->BN_MP_RSHD_C
 |   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   |   +--->BN_S_MP_SUB_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_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_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_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_MOD_C
 |   |   |   |   |   +--->BN_MP_DIV_C
 |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
@@ -4061,116 +4985,6 @@ BN_MP_PRIME_RANDOM_EX_C
 |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   +--->BN_MP_REDUCE_C
-|   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   +--->BN_MP_MUL_C
-|   |   |   |   |   |   +--->BN_MP_TOOM_MUL_C
-|   |   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   |   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   |   +--->BN_MP_MUL_2_C
-|   |   |   |   |   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
-|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   |   +--->BN_MP_MUL_2D_C
-|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   |   +--->BN_MP_DIV_3_C
-|   |   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
-|   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   |   +--->BN_MP_SUB_C
-|   |   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_ADD_C
-|   |   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_S_MP_MUL_DIGS_C
-|   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   |   +--->BN_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_S_MP_MUL_DIGS_C
-|   |   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   |   +--->BN_MP_SUB_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_LSHD_C
-|   |   |   |   |   |   +--->BN_MP_GROW_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_CMP_C
-|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   +--->BN_MP_MUL_C
 |   |   |   |   |   +--->BN_MP_TOOM_MUL_C
 |   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
@@ -4753,7 +5567,55 @@ BN_MP_PRIME_IS_PRIME_C
 |   |   |   |   |   +--->BN_MP_CLEAR_C
 |   |   |   |   +--->BN_MP_COPY_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_GROW_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
@@ -4781,6 +5643,57 @@ BN_MP_PRIME_IS_PRIME_C
 |   |   |   +--->BN_MP_INVMOD_SLOW_C
 |   |   |   |   +--->BN_MP_INIT_MULTI_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_GROW_C
 |   |   |   |   +--->BN_MP_DIV_2_C
@@ -4813,73 +5726,52 @@ BN_MP_PRIME_IS_PRIME_C
 |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   +--->BN_MP_GROW_C
 |   |   +--->BN_MP_CLEAR_MULTI_C
-|   |   +--->BN_MP_DR_IS_MODULUS_C
-|   |   +--->BN_MP_REDUCE_IS_2K_C
-|   |   |   +--->BN_MP_REDUCE_2K_C
-|   |   |   |   +--->BN_MP_COUNT_BITS_C
-|   |   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_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_COUNT_BITS_C
-|   |   +--->BN_MP_EXPTMOD_FAST_C
+|   |   +--->BN_MP_REDUCE_IS_2K_L_C
+|   |   +--->BN_S_MP_EXPTMOD_C
 |   |   |   +--->BN_MP_COUNT_BITS_C
-|   |   |   +--->BN_MP_MONTGOMERY_SETUP_C
-|   |   |   +--->BN_FAST_MP_MONTGOMERY_REDUCE_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   +--->BN_MP_MONTGOMERY_REDUCE_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   +--->BN_MP_DR_SETUP_C
-|   |   |   +--->BN_MP_DR_REDUCE_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   +--->BN_MP_REDUCE_2K_SETUP_C
+|   |   |   +--->BN_MP_REDUCE_SETUP_C
 |   |   |   |   +--->BN_MP_2EXPT_C
 |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_REDUCE_2K_C
-|   |   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_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_MONTGOMERY_CALC_NORMALIZATION_C
-|   |   |   |   +--->BN_MP_2EXPT_C
+|   |   |   |   +--->BN_MP_DIV_C
+|   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_MUL_2_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_INIT_MULTI_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_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_MULMOD_C
+|   |   |   +--->BN_MP_REDUCE_C
+|   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   +--->BN_MP_MUL_C
 |   |   |   |   |   +--->BN_MP_TOOM_MUL_C
 |   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
@@ -4890,8 +5782,6 @@ BN_MP_PRIME_IS_PRIME_C
 |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   |   +--->BN_MP_MUL_2_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_ADD_C
@@ -4943,8 +5833,6 @@ BN_MP_PRIME_IS_PRIME_C
 |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_LSHD_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
@@ -4952,52 +5840,138 @@ BN_MP_PRIME_IS_PRIME_C
 |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   +--->BN_MP_MOD_C
-|   |   |   |   |   +--->BN_MP_DIV_C
-|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   +--->BN_MP_SUB_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_LSHD_C
+|   |   |   |   |   +--->BN_MP_GROW_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_CMP_C
+|   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_REDUCE_2K_SETUP_L_C
+|   |   |   |   +--->BN_MP_2EXPT_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_REDUCE_2K_L_C
+|   |   |   |   +--->BN_MP_MUL_C
+|   |   |   |   |   +--->BN_MP_TOOM_MUL_C
+|   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   +--->BN_MP_MUL_2_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_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_ADD_C
+|   |   |   |   |   |   +--->BN_MP_SUB_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_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_DIV_2_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_ADD_C
-|   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   +--->BN_MP_MUL_2D_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_LSHD_C
 |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   +--->BN_MP_MUL_D_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   |   +--->BN_MP_DIV_3_C
+|   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
+|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_SUB_C
+|   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_ADD_C
+|   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_EXCH_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_MOD_C
 |   |   |   |   +--->BN_MP_DIV_C
 |   |   |   |   |   +--->BN_MP_CMP_MAG_C
@@ -5183,48 +6157,191 @@ BN_MP_PRIME_IS_PRIME_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   +--->BN_MP_EXCH_C
 |   |   |   +--->BN_MP_EXCH_C
-|   |   +--->BN_S_MP_EXPTMOD_C
+|   |   +--->BN_MP_DR_IS_MODULUS_C
+|   |   +--->BN_MP_REDUCE_IS_2K_C
+|   |   |   +--->BN_MP_REDUCE_2K_C
+|   |   |   |   +--->BN_MP_COUNT_BITS_C
+|   |   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_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_COUNT_BITS_C
-|   |   |   +--->BN_MP_REDUCE_SETUP_C
+|   |   +--->BN_MP_EXPTMOD_FAST_C
+|   |   |   +--->BN_MP_COUNT_BITS_C
+|   |   |   +--->BN_MP_MONTGOMERY_SETUP_C
+|   |   |   +--->BN_FAST_MP_MONTGOMERY_REDUCE_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   +--->BN_MP_MONTGOMERY_REDUCE_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   +--->BN_MP_DR_SETUP_C
+|   |   |   +--->BN_MP_DR_REDUCE_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   +--->BN_MP_REDUCE_2K_SETUP_C
 |   |   |   |   +--->BN_MP_2EXPT_C
 |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_DIV_C
-|   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   +--->BN_MP_COPY_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_REDUCE_2K_C
+|   |   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_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_MONTGOMERY_CALC_NORMALIZATION_C
+|   |   |   |   +--->BN_MP_2EXPT_C
 |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   |   +--->BN_MP_MUL_2D_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_MUL_2_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_MULMOD_C
+|   |   |   |   +--->BN_MP_MUL_C
+|   |   |   |   |   +--->BN_MP_TOOM_MUL_C
+|   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   +--->BN_MP_MUL_2_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_DIV_3_C
+|   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
+|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_SUB_C
+|   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_ADD_C
+|   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_CMP_C
-|   |   |   |   |   +--->BN_MP_SUB_C
-|   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_EXCH_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_INIT_MULTI_C
+|   |   |   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_RSHD_C
 |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_S_MP_SUB_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_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_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_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_MOD_C
 |   |   |   |   +--->BN_MP_DIV_C
 |   |   |   |   |   +--->BN_MP_CMP_MAG_C
@@ -5341,116 +6458,6 @@ BN_MP_PRIME_IS_PRIME_C
 |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   +--->BN_MP_REDUCE_C
-|   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_MUL_C
-|   |   |   |   |   +--->BN_MP_TOOM_MUL_C
-|   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_MUL_2_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_MUL_2D_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_DIV_3_C
-|   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
-|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_SUB_C
-|   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_ADD_C
-|   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_S_MP_MUL_DIGS_C
-|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   +--->BN_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_S_MP_MUL_DIGS_C
-|   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   +--->BN_MP_SUB_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_LSHD_C
-|   |   |   |   |   +--->BN_MP_GROW_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_CMP_C
-|   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   +--->BN_MP_MUL_C
 |   |   |   |   +--->BN_MP_TOOM_MUL_C
 |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
@@ -6496,7 +7503,55 @@ BN_MP_PRIME_NEXT_PRIME_C
 |   |   |   |   |   +--->BN_MP_CLEAR_C
 |   |   |   |   +--->BN_MP_COPY_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_GROW_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
@@ -6524,6 +7579,57 @@ BN_MP_PRIME_NEXT_PRIME_C
 |   |   |   +--->BN_MP_INVMOD_SLOW_C
 |   |   |   |   +--->BN_MP_INIT_MULTI_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_GROW_C
 |   |   |   |   +--->BN_MP_DIV_2_C
@@ -6556,73 +7662,52 @@ BN_MP_PRIME_NEXT_PRIME_C
 |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   +--->BN_MP_GROW_C
 |   |   +--->BN_MP_CLEAR_MULTI_C
-|   |   +--->BN_MP_DR_IS_MODULUS_C
-|   |   +--->BN_MP_REDUCE_IS_2K_C
-|   |   |   +--->BN_MP_REDUCE_2K_C
-|   |   |   |   +--->BN_MP_COUNT_BITS_C
-|   |   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_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_COUNT_BITS_C
-|   |   +--->BN_MP_EXPTMOD_FAST_C
+|   |   +--->BN_MP_REDUCE_IS_2K_L_C
+|   |   +--->BN_S_MP_EXPTMOD_C
 |   |   |   +--->BN_MP_COUNT_BITS_C
-|   |   |   +--->BN_MP_MONTGOMERY_SETUP_C
-|   |   |   +--->BN_FAST_MP_MONTGOMERY_REDUCE_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   +--->BN_MP_MONTGOMERY_REDUCE_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   +--->BN_MP_DR_SETUP_C
-|   |   |   +--->BN_MP_DR_REDUCE_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   +--->BN_MP_REDUCE_2K_SETUP_C
+|   |   |   +--->BN_MP_REDUCE_SETUP_C
 |   |   |   |   +--->BN_MP_2EXPT_C
 |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_REDUCE_2K_C
-|   |   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_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_MONTGOMERY_CALC_NORMALIZATION_C
-|   |   |   |   +--->BN_MP_2EXPT_C
+|   |   |   |   +--->BN_MP_DIV_C
+|   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_MUL_2_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_INIT_MULTI_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_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_MULMOD_C
+|   |   |   +--->BN_MP_REDUCE_C
+|   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   +--->BN_MP_MUL_C
 |   |   |   |   |   +--->BN_MP_TOOM_MUL_C
 |   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
@@ -6633,8 +7718,6 @@ BN_MP_PRIME_NEXT_PRIME_C
 |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   |   +--->BN_MP_MUL_2_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_ADD_C
@@ -6686,8 +7769,6 @@ BN_MP_PRIME_NEXT_PRIME_C
 |   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_LSHD_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
@@ -6695,52 +7776,138 @@ BN_MP_PRIME_NEXT_PRIME_C
 |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   +--->BN_MP_MOD_C
-|   |   |   |   |   +--->BN_MP_DIV_C
-|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   +--->BN_MP_SUB_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_LSHD_C
+|   |   |   |   |   +--->BN_MP_GROW_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_CMP_C
+|   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_REDUCE_2K_SETUP_L_C
+|   |   |   |   +--->BN_MP_2EXPT_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_REDUCE_2K_L_C
+|   |   |   |   +--->BN_MP_MUL_C
+|   |   |   |   |   +--->BN_MP_TOOM_MUL_C
+|   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   +--->BN_MP_MUL_2_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_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_ADD_C
+|   |   |   |   |   |   +--->BN_MP_SUB_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_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_DIV_2_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_ADD_C
-|   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   +--->BN_MP_MUL_2D_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_LSHD_C
 |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   +--->BN_MP_MUL_D_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   |   +--->BN_MP_DIV_3_C
+|   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
+|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_SUB_C
+|   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_ADD_C
+|   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_EXCH_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_MOD_C
 |   |   |   |   +--->BN_MP_DIV_C
 |   |   |   |   |   +--->BN_MP_CMP_MAG_C
@@ -6926,48 +8093,191 @@ BN_MP_PRIME_NEXT_PRIME_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   +--->BN_MP_EXCH_C
 |   |   |   +--->BN_MP_EXCH_C
-|   |   +--->BN_S_MP_EXPTMOD_C
+|   |   +--->BN_MP_DR_IS_MODULUS_C
+|   |   +--->BN_MP_REDUCE_IS_2K_C
+|   |   |   +--->BN_MP_REDUCE_2K_C
+|   |   |   |   +--->BN_MP_COUNT_BITS_C
+|   |   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_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_COUNT_BITS_C
-|   |   |   +--->BN_MP_REDUCE_SETUP_C
+|   |   +--->BN_MP_EXPTMOD_FAST_C
+|   |   |   +--->BN_MP_COUNT_BITS_C
+|   |   |   +--->BN_MP_MONTGOMERY_SETUP_C
+|   |   |   +--->BN_FAST_MP_MONTGOMERY_REDUCE_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   +--->BN_MP_MONTGOMERY_REDUCE_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   +--->BN_MP_DR_SETUP_C
+|   |   |   +--->BN_MP_DR_REDUCE_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   +--->BN_MP_REDUCE_2K_SETUP_C
 |   |   |   |   +--->BN_MP_2EXPT_C
 |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_DIV_C
-|   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   +--->BN_MP_COPY_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_REDUCE_2K_C
+|   |   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_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_MONTGOMERY_CALC_NORMALIZATION_C
+|   |   |   |   +--->BN_MP_2EXPT_C
 |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   |   +--->BN_MP_MUL_2D_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_MUL_2_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_MULMOD_C
+|   |   |   |   +--->BN_MP_MUL_C
+|   |   |   |   |   +--->BN_MP_TOOM_MUL_C
+|   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   +--->BN_MP_MUL_2_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_DIV_3_C
+|   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
+|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_SUB_C
+|   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_ADD_C
+|   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_CMP_C
-|   |   |   |   |   +--->BN_MP_SUB_C
-|   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_EXCH_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_INIT_MULTI_C
+|   |   |   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   |   +--->BN_MP_RSHD_C
 |   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_S_MP_SUB_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_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_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_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_MOD_C
 |   |   |   |   +--->BN_MP_DIV_C
 |   |   |   |   |   +--->BN_MP_CMP_MAG_C
@@ -7084,116 +8394,6 @@ BN_MP_PRIME_NEXT_PRIME_C
 |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   +--->BN_MP_REDUCE_C
-|   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_MUL_C
-|   |   |   |   |   +--->BN_MP_TOOM_MUL_C
-|   |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_MUL_2_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_MUL_2D_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_DIV_3_C
-|   |   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
-|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_SUB_C
-|   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_ADD_C
-|   |   |   |   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_S_MP_MUL_DIGS_C
-|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   +--->BN_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_S_MP_MUL_DIGS_C
-|   |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   +--->BN_MP_SUB_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_LSHD_C
-|   |   |   |   |   +--->BN_MP_GROW_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_CMP_C
-|   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   +--->BN_MP_MUL_C
 |   |   |   |   +--->BN_MP_TOOM_MUL_C
 |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
@@ -7406,6 +8606,67 @@ BN_MP_INVMOD_SLOW_C
 +--->BN_MP_INIT_MULTI_C
 |   +--->BN_MP_INIT_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_GROW_C
 +--->BN_MP_SET_C
@@ -7604,6 +8865,107 @@ BN_MP_LCM_C
 |   +--->BN_MP_CLEAR_C
 
 
+BN_MP_REDUCE_2K_L_C
++--->BN_MP_INIT_C
++--->BN_MP_COUNT_BITS_C
++--->BN_MP_DIV_2D_C
+|   +--->BN_MP_COPY_C
+|   |   +--->BN_MP_GROW_C
+|   +--->BN_MP_ZERO_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_MUL_C
+|   +--->BN_MP_TOOM_MUL_C
+|   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   +--->BN_MP_CLEAR_C
+|   |   +--->BN_MP_MOD_2D_C
+|   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_COPY_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_COPY_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_RSHD_C
+|   |   |   +--->BN_MP_ZERO_C
+|   |   +--->BN_MP_MUL_2_C
+|   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_MUL_2D_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_LSHD_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_MUL_D_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_DIV_3_C
+|   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_EXCH_C
+|   |   |   +--->BN_MP_CLEAR_C
+|   |   +--->BN_MP_LSHD_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_CLEAR_MULTI_C
+|   |   |   +--->BN_MP_CLEAR_C
+|   +--->BN_MP_KARATSUBA_MUL_C
+|   |   +--->BN_MP_INIT_SIZE_C
+|   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_SUB_C
+|   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_ADD_C
+|   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_LSHD_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   +--->BN_MP_CLEAR_C
+|   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_CLAMP_C
+|   +--->BN_S_MP_MUL_DIGS_C
+|   |   +--->BN_MP_INIT_SIZE_C
+|   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_EXCH_C
+|   |   +--->BN_MP_CLEAR_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_CLEAR_C
+
+
 BN_REVERSE_C
 
 
@@ -7671,6 +9033,18 @@ BN_MP_GCD_C
 +--->BN_MP_CLEAR_C
 
 
+BN_MP_REDUCE_2K_SETUP_L_C
++--->BN_MP_INIT_C
++--->BN_MP_2EXPT_C
+|   +--->BN_MP_ZERO_C
+|   +--->BN_MP_GROW_C
++--->BN_MP_COUNT_BITS_C
++--->BN_S_MP_SUB_C
+|   +--->BN_MP_GROW_C
+|   +--->BN_MP_CLAMP_C
++--->BN_MP_CLEAR_C
+
+
 BN_MP_READ_RADIX_C
 +--->BN_MP_ZERO_C
 +--->BN_MP_MUL_D_C
@@ -7983,6 +9357,226 @@ BN_S_MP_EXPTMOD_C
 |   |   |   +--->BN_MP_GROW_C
 |   |   |   +--->BN_MP_CLAMP_C
 |   |   +--->BN_MP_CLAMP_C
++--->BN_MP_REDUCE_C
+|   +--->BN_MP_INIT_COPY_C
+|   |   +--->BN_MP_COPY_C
+|   |   |   +--->BN_MP_GROW_C
+|   +--->BN_MP_RSHD_C
+|   |   +--->BN_MP_ZERO_C
+|   +--->BN_MP_MUL_C
+|   |   +--->BN_MP_TOOM_MUL_C
+|   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_COPY_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_MUL_2_C
+|   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_DIV_3_C
+|   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLEAR_MULTI_C
+|   |   +--->BN_MP_KARATSUBA_MUL_C
+|   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_SUB_C
+|   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_ADD_C
+|   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_EXCH_C
+|   +--->BN_S_MP_MUL_HIGH_DIGS_C
+|   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_INIT_SIZE_C
+|   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_EXCH_C
+|   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
+|   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_CLAMP_C
+|   +--->BN_MP_MOD_2D_C
+|   |   +--->BN_MP_ZERO_C
+|   |   +--->BN_MP_COPY_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_CLAMP_C
+|   +--->BN_S_MP_MUL_DIGS_C
+|   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_INIT_SIZE_C
+|   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_EXCH_C
+|   +--->BN_MP_SUB_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_CMP_D_C
+|   +--->BN_MP_SET_C
+|   |   +--->BN_MP_ZERO_C
+|   +--->BN_MP_LSHD_C
+|   |   +--->BN_MP_GROW_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_CMP_C
+|   |   +--->BN_MP_CMP_MAG_C
+|   +--->BN_S_MP_SUB_C
+|   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_CLAMP_C
++--->BN_MP_REDUCE_2K_SETUP_L_C
+|   +--->BN_MP_2EXPT_C
+|   |   +--->BN_MP_ZERO_C
+|   |   +--->BN_MP_GROW_C
+|   +--->BN_S_MP_SUB_C
+|   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_CLAMP_C
++--->BN_MP_REDUCE_2K_L_C
+|   +--->BN_MP_DIV_2D_C
+|   |   +--->BN_MP_COPY_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_ZERO_C
+|   |   +--->BN_MP_MOD_2D_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_RSHD_C
+|   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_EXCH_C
+|   +--->BN_MP_MUL_C
+|   |   +--->BN_MP_TOOM_MUL_C
+|   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_COPY_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_MUL_2_C
+|   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_DIV_3_C
+|   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLEAR_MULTI_C
+|   |   +--->BN_MP_KARATSUBA_MUL_C
+|   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_SUB_C
+|   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_ADD_C
+|   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_EXCH_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_MOD_C
 |   +--->BN_MP_DIV_C
 |   |   +--->BN_MP_CMP_MAG_C
@@ -8110,121 +9704,6 @@ BN_S_MP_EXPTMOD_C
 |   |   +--->BN_MP_INIT_SIZE_C
 |   |   +--->BN_MP_CLAMP_C
 |   |   +--->BN_MP_EXCH_C
-+--->BN_MP_REDUCE_C
-|   +--->BN_MP_INIT_COPY_C
-|   +--->BN_MP_RSHD_C
-|   |   +--->BN_MP_ZERO_C
-|   +--->BN_MP_MUL_C
-|   |   +--->BN_MP_TOOM_MUL_C
-|   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_MUL_2_C
-|   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_MUL_2D_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_DIV_3_C
-|   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CLEAR_MULTI_C
-|   |   +--->BN_MP_KARATSUBA_MUL_C
-|   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_SUB_C
-|   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_ADD_C
-|   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   +--->BN_FAST_S_MP_MUL_DIGS_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   +--->BN_S_MP_MUL_DIGS_C
-|   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_EXCH_C
-|   +--->BN_S_MP_MUL_HIGH_DIGS_C
-|   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   +--->BN_MP_INIT_SIZE_C
-|   |   +--->BN_MP_CLAMP_C
-|   |   +--->BN_MP_EXCH_C
-|   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
-|   |   +--->BN_MP_GROW_C
-|   |   +--->BN_MP_CLAMP_C
-|   +--->BN_MP_MOD_2D_C
-|   |   +--->BN_MP_ZERO_C
-|   |   +--->BN_MP_CLAMP_C
-|   +--->BN_S_MP_MUL_DIGS_C
-|   |   +--->BN_FAST_S_MP_MUL_DIGS_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   +--->BN_MP_INIT_SIZE_C
-|   |   +--->BN_MP_CLAMP_C
-|   |   +--->BN_MP_EXCH_C
-|   +--->BN_MP_SUB_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_CMP_D_C
-|   +--->BN_MP_SET_C
-|   |   +--->BN_MP_ZERO_C
-|   +--->BN_MP_LSHD_C
-|   |   +--->BN_MP_GROW_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_CMP_C
-|   |   +--->BN_MP_CMP_MAG_C
-|   +--->BN_S_MP_SUB_C
-|   |   +--->BN_MP_GROW_C
-|   |   +--->BN_MP_CLAMP_C
 +--->BN_MP_MUL_C
 |   +--->BN_MP_TOOM_MUL_C
 |   |   +--->BN_MP_INIT_MULTI_C
@@ -8529,6 +10008,31 @@ BN_MP_ADD_C
 |   +--->BN_MP_CLAMP_C
 
 
+BN_MP_TO_SIGNED_BIN_N_C
++--->BN_MP_SIGNED_BIN_SIZE_C
+|   +--->BN_MP_UNSIGNED_BIN_SIZE_C
+|   |   +--->BN_MP_COUNT_BITS_C
++--->BN_MP_TO_SIGNED_BIN_C
+|   +--->BN_MP_TO_UNSIGNED_BIN_C
+|   |   +--->BN_MP_INIT_COPY_C
+|   |   |   +--->BN_MP_COPY_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_DIV_2D_C
+|   |   |   +--->BN_MP_COPY_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_ZERO_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_CLEAR_C
+
+
+BN_MP_REDUCE_IS_2K_L_C
+
+
 BN_MP_RAND_C
 +--->BN_MP_ZERO_C
 +--->BN_MP_ADD_D_C
@@ -8556,6 +10060,26 @@ BN_MP_RSHD_C
 BN_MP_SHRINK_C
 
 
+BN_MP_TO_UNSIGNED_BIN_N_C
++--->BN_MP_UNSIGNED_BIN_SIZE_C
+|   +--->BN_MP_COUNT_BITS_C
++--->BN_MP_TO_UNSIGNED_BIN_C
+|   +--->BN_MP_INIT_COPY_C
+|   |   +--->BN_MP_COPY_C
+|   |   |   +--->BN_MP_GROW_C
+|   +--->BN_MP_DIV_2D_C
+|   |   +--->BN_MP_COPY_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   +--->BN_MP_ZERO_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_CLEAR_C
+
+
 BN_MP_REDUCE_C
 +--->BN_MP_REDUCE_SETUP_C
 |   +--->BN_MP_2EXPT_C
@@ -9062,6 +10586,7 @@ BN_MP_EXTEUCLID_C
 |   +--->BN_S_MP_SUB_C
 |   |   +--->BN_MP_GROW_C
 |   |   +--->BN_MP_CLAMP_C
++--->BN_MP_NEG_C
 +--->BN_MP_EXCH_C
 +--->BN_MP_CLEAR_MULTI_C
 |   +--->BN_MP_CLEAR_C
@@ -9269,7 +10794,56 @@ BN_MP_PRIME_MILLER_RABIN_C
 |   |   |   |   +--->BN_MP_CLEAR_C
 |   |   |   +--->BN_MP_COPY_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_ZERO_C
 |   |   |   +--->BN_MP_DIV_2_C
@@ -9299,6 +10873,58 @@ BN_MP_PRIME_MILLER_RABIN_C
 |   |   +--->BN_MP_INVMOD_SLOW_C
 |   |   |   +--->BN_MP_INIT_MULTI_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_GROW_C
 |   |   |   +--->BN_MP_SET_C
@@ -9333,75 +10959,53 @@ BN_MP_PRIME_MILLER_RABIN_C
 |   |   +--->BN_MP_COPY_C
 |   |   |   +--->BN_MP_GROW_C
 |   +--->BN_MP_CLEAR_MULTI_C
-|   +--->BN_MP_DR_IS_MODULUS_C
-|   +--->BN_MP_REDUCE_IS_2K_C
-|   |   +--->BN_MP_REDUCE_2K_C
-|   |   |   +--->BN_MP_COUNT_BITS_C
-|   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_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_COUNT_BITS_C
-|   +--->BN_MP_EXPTMOD_FAST_C
+|   +--->BN_MP_REDUCE_IS_2K_L_C
+|   +--->BN_S_MP_EXPTMOD_C
 |   |   +--->BN_MP_COUNT_BITS_C
-|   |   +--->BN_MP_MONTGOMERY_SETUP_C
-|   |   +--->BN_FAST_MP_MONTGOMERY_REDUCE_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   +--->BN_S_MP_SUB_C
-|   |   +--->BN_MP_MONTGOMERY_REDUCE_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   +--->BN_S_MP_SUB_C
-|   |   +--->BN_MP_DR_SETUP_C
-|   |   +--->BN_MP_DR_REDUCE_C
-|   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   +--->BN_S_MP_SUB_C
-|   |   +--->BN_MP_REDUCE_2K_SETUP_C
-|   |   |   +--->BN_MP_2EXPT_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   +--->BN_MP_REDUCE_2K_C
-|   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_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_MONTGOMERY_CALC_NORMALIZATION_C
+|   |   +--->BN_MP_REDUCE_SETUP_C
 |   |   |   +--->BN_MP_2EXPT_C
 |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_SET_C
+|   |   |   +--->BN_MP_DIV_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_MUL_2_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   +--->BN_MP_SET_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_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_MULMOD_C
+|   |   +--->BN_MP_REDUCE_C
+|   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   +--->BN_MP_MUL_C
 |   |   |   |   +--->BN_MP_TOOM_MUL_C
 |   |   |   |   |   +--->BN_MP_INIT_MULTI_C
@@ -9412,8 +11016,6 @@ BN_MP_PRIME_MILLER_RABIN_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   |   +--->BN_MP_MUL_2_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_ADD_C
@@ -9465,8 +11067,6 @@ BN_MP_PRIME_MILLER_RABIN_C
 |   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_LSHD_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
@@ -9474,55 +11074,140 @@ BN_MP_PRIME_MILLER_RABIN_C
 |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   +--->BN_MP_MOD_C
-|   |   |   |   +--->BN_MP_DIV_C
-|   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   +--->BN_MP_SUB_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_SET_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   +--->BN_MP_GROW_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_CMP_C
+|   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_REDUCE_2K_SETUP_L_C
+|   |   |   +--->BN_MP_2EXPT_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_REDUCE_2K_L_C
+|   |   |   +--->BN_MP_MUL_C
+|   |   |   |   +--->BN_MP_TOOM_MUL_C
+|   |   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   |   +--->BN_MP_COPY_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   |   +--->BN_MP_SET_C
-|   |   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_MP_MUL_2_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_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_ADD_C
+|   |   |   |   |   +--->BN_MP_SUB_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_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_DIV_2_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_ADD_C
-|   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   +--->BN_MP_MUL_2D_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_LSHD_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   +--->BN_MP_MUL_D_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_EXCH_C
-|   |   +--->BN_MP_SET_C
-|   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_MP_DIV_3_C
+|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
+|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_SUB_C
+|   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_ADD_C
+|   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_EXCH_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_MOD_C
 |   |   |   +--->BN_MP_DIV_C
 |   |   |   |   +--->BN_MP_CMP_MAG_C
@@ -9530,6 +11215,7 @@ BN_MP_PRIME_MILLER_RABIN_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   +--->BN_MP_SET_C
 |   |   |   |   +--->BN_MP_MUL_2D_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_LSHD_C
@@ -9707,50 +11393,199 @@ BN_MP_PRIME_MILLER_RABIN_C
 |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   +--->BN_MP_EXCH_C
+|   |   +--->BN_MP_SET_C
+|   |   |   +--->BN_MP_ZERO_C
 |   |   +--->BN_MP_EXCH_C
-|   +--->BN_S_MP_EXPTMOD_C
+|   +--->BN_MP_DR_IS_MODULUS_C
+|   +--->BN_MP_REDUCE_IS_2K_C
+|   |   +--->BN_MP_REDUCE_2K_C
+|   |   |   +--->BN_MP_COUNT_BITS_C
+|   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_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_COUNT_BITS_C
-|   |   +--->BN_MP_REDUCE_SETUP_C
+|   +--->BN_MP_EXPTMOD_FAST_C
+|   |   +--->BN_MP_COUNT_BITS_C
+|   |   +--->BN_MP_MONTGOMERY_SETUP_C
+|   |   +--->BN_FAST_MP_MONTGOMERY_REDUCE_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   +--->BN_MP_MONTGOMERY_REDUCE_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   +--->BN_MP_DR_SETUP_C
+|   |   +--->BN_MP_DR_REDUCE_C
+|   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CLAMP_C
+|   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   +--->BN_MP_REDUCE_2K_SETUP_C
 |   |   |   +--->BN_MP_2EXPT_C
 |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   +--->BN_MP_DIV_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   +--->BN_MP_COPY_C
-|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_REDUCE_2K_C
+|   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_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_MONTGOMERY_CALC_NORMALIZATION_C
+|   |   |   +--->BN_MP_2EXPT_C
 |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   +--->BN_MP_SET_C
-|   |   |   |   +--->BN_MP_MUL_2D_C
-|   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_SET_C
+|   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   +--->BN_MP_MUL_2_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_CLAMP_C
+|   |   +--->BN_MP_MULMOD_C
+|   |   |   +--->BN_MP_MUL_C
+|   |   |   |   +--->BN_MP_TOOM_MUL_C
+|   |   |   |   |   +--->BN_MP_INIT_MULTI_C
+|   |   |   |   |   +--->BN_MP_MOD_2D_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_COPY_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   |   +--->BN_MP_MUL_2_C
+|   |   |   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_MUL_2D_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_MUL_D_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_DIV_3_C
+|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   |   +--->BN_MP_EXCH_C
+|   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
+|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_SUB_C
+|   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   +--->BN_MP_ADD_C
+|   |   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
+|   |   |   |   |   |   +--->BN_S_MP_SUB_C
+|   |   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   |   +--->BN_MP_RSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_ZERO_C
+|   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
+|   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_CMP_C
-|   |   |   |   +--->BN_MP_SUB_C
-|   |   |   |   |   +--->BN_S_MP_ADD_C
+|   |   |   |   +--->BN_S_MP_MUL_DIGS_C
+|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
+|   |   |   |   |   +--->BN_MP_CLAMP_C
+|   |   |   |   |   +--->BN_MP_EXCH_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_INIT_MULTI_C
+|   |   |   |   |   +--->BN_MP_SET_C
+|   |   |   |   |   +--->BN_MP_MUL_2D_C
 |   |   |   |   |   |   +--->BN_MP_GROW_C
+|   |   |   |   |   |   +--->BN_MP_LSHD_C
+|   |   |   |   |   |   |   +--->BN_MP_RSHD_C
 |   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_S_MP_SUB_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_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_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_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_SET_C
+|   |   |   +--->BN_MP_ZERO_C
 |   |   +--->BN_MP_MOD_C
 |   |   |   +--->BN_MP_DIV_C
 |   |   |   |   +--->BN_MP_CMP_MAG_C
@@ -9758,7 +11593,6 @@ BN_MP_PRIME_MILLER_RABIN_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   +--->BN_MP_ZERO_C
 |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   +--->BN_MP_SET_C
 |   |   |   |   +--->BN_MP_MUL_2D_C
 |   |   |   |   |   +--->BN_MP_GROW_C
 |   |   |   |   |   +--->BN_MP_LSHD_C
@@ -9868,118 +11702,6 @@ BN_MP_PRIME_MILLER_RABIN_C
 |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   +--->BN_MP_EXCH_C
-|   |   +--->BN_MP_REDUCE_C
-|   |   |   +--->BN_MP_RSHD_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_MUL_C
-|   |   |   |   +--->BN_MP_TOOM_MUL_C
-|   |   |   |   |   +--->BN_MP_INIT_MULTI_C
-|   |   |   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_MUL_2_C
-|   |   |   |   |   |   +--->BN_MP_GROW_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_SUB_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_DIV_2_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_MUL_2D_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_MUL_D_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_DIV_3_C
-|   |   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_KARATSUBA_MUL_C
-|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_SUB_C
-|   |   |   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_ADD_C
-|   |   |   |   |   |   +--->BN_S_MP_ADD_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   |   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_S_MP_MUL_DIGS_C
-|   |   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   +--->BN_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   +--->BN_FAST_S_MP_MUL_HIGH_DIGS_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_MP_MOD_2D_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   +--->BN_S_MP_MUL_DIGS_C
-|   |   |   |   +--->BN_FAST_S_MP_MUL_DIGS_C
-|   |   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_INIT_SIZE_C
-|   |   |   |   +--->BN_MP_CLAMP_C
-|   |   |   |   +--->BN_MP_EXCH_C
-|   |   |   +--->BN_MP_SUB_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_SET_C
-|   |   |   |   +--->BN_MP_ZERO_C
-|   |   |   +--->BN_MP_LSHD_C
-|   |   |   |   +--->BN_MP_GROW_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_CMP_C
-|   |   |   |   +--->BN_MP_CMP_MAG_C
-|   |   |   +--->BN_S_MP_SUB_C
-|   |   |   |   +--->BN_MP_GROW_C
-|   |   |   |   +--->BN_MP_CLAMP_C
 |   |   +--->BN_MP_MUL_C
 |   |   |   +--->BN_MP_TOOM_MUL_C
 |   |   |   |   +--->BN_MP_INIT_MULTI_C
@@ -10048,8 +11770,6 @@ BN_MP_PRIME_MILLER_RABIN_C
 |   |   |   |   +--->BN_MP_INIT_SIZE_C
 |   |   |   |   +--->BN_MP_CLAMP_C
 |   |   |   |   +--->BN_MP_EXCH_C
-|   |   +--->BN_MP_SET_C
-|   |   |   +--->BN_MP_ZERO_C
 |   |   +--->BN_MP_EXCH_C
 +--->BN_MP_CMP_C
 |   +--->BN_MP_CMP_MAG_C
diff --git a/libtommath/changes.txt b/libtommath/changes.txt
index 0d1ec2e..99e40c1 100644
--- a/libtommath/changes.txt
+++ b/libtommath/changes.txt
@@ -1,3 +1,26 @@
+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
+v0.34  -- Fixed two more small errors in mp_prime_random_ex()
+       -- Fixed overflow in mp_mul_d() [Kevin Kenny]
+       -- Added mp_to_(un)signed_bin_n() functions which do bounds checking for ya [and report the size]
+       -- Added "large" diminished radix support.  Speeds up things like DSA where the moduli is of the form 2^k - P for some P < 2^(k/2) or so
+          Actually is faster than Montgomery on my AMD64 (and probably much faster on a P4)
+       -- Updated the manual a bit
+       -- Ok so I haven't done the textbook work yet... My current freelance gig has landed me in France till the 
+          end of Feb/05.  Once I get back I'll have tons of free time and I plan to go to town on the book.
+          As of this release the API will freeze.  At least until the book catches up with all the changes.  I welcome
+          bug reports but new algorithms will have to wait.
+
 December 23rd, 2004
 v0.33  -- Fixed "small" variant for mp_div() which would munge with negative dividends...
        -- Fixed bug in mp_prime_random_ex() which would set the most significant byte to zero when
diff --git a/libtommath/demo/demo.c b/libtommath/demo/demo.c
index 62615cd..0a6115a 100644
--- a/libtommath/demo/demo.c
+++ b/libtommath/demo/demo.c
@@ -9,15 +9,16 @@
 
 #include "tommath.h"
 
-void ndraw(mp_int *a, char *name)
+void ndraw(mp_int * a, char *name)
 {
    char buf[16000];
+
    printf("%s: ", name);
    mp_toradix(a, buf, 10);
    printf("%s\n", buf);
 }
 
-static void draw(mp_int *a)
+static void draw(mp_int * a)
 {
    ndraw(a, "");
 }
@@ -39,20 +40,23 @@ int lbit(void)
 int myrng(unsigned char *dst, int len, void *dat)
 {
    int x;
-   for (x = 0; x < len; x++) dst[x] = rand() & 0xFF;
+
+   for (x = 0; x < len; x++)
+      dst[x] = rand() & 0xFF;
    return len;
 }
 
 
 
-   char cmd[4096], buf[4096];
+char cmd[4096], buf[4096];
 int main(void)
 {
    mp_int a, b, c, d, e, f;
-   unsigned long expt_n, add_n, sub_n, mul_n, div_n, sqr_n, mul2d_n, div2d_n, gcd_n, lcm_n, inv_n,
-                 div2_n, mul2_n, add_d_n, sub_d_n, t;
+   unsigned long expt_n, add_n, sub_n, mul_n, div_n, sqr_n, mul2d_n, div2d_n,
+      gcd_n, lcm_n, inv_n, div2_n, mul2_n, add_d_n, sub_d_n, t;
    unsigned rr;
    int i, n, err, cnt, ix, old_kara_m, old_kara_s;
+   mp_digit mp;
 
 
    mp_init(&a);
@@ -65,108 +69,152 @@ int main(void)
    srand(time(NULL));
 
 #if 0
-  // test mp_get_int
-  printf("Testing: mp_get_int\n");
-  for(i=0;i<1000;++i) {
-    t = ((unsigned long)rand()*rand()+1)&0xFFFFFFFF;
-    mp_set_int(&a,t);
-    if (t!=mp_get_int(&a)) { 
+   // 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
+   printf("Testing: mp_get_int\n");
+   for (i = 0; i < 1000; ++i) {
+      t = ((unsigned long) rand() * rand() + 1) & 0xFFFFFFFF;
+      mp_set_int(&a, t);
+      if (t != mp_get_int(&a)) {
+	 printf("mp_get_int() bad result!\n");
+	 return 1;
+      }
+   }
+   mp_set_int(&a, 0);
+   if (mp_get_int(&a) != 0) {
       printf("mp_get_int() bad result!\n");
       return 1;
-    }
-  }
-  mp_set_int(&a,0);
-  if (mp_get_int(&a)!=0)
-  { printf("mp_get_int() bad result!\n");
-    return 1;
-  }
-  mp_set_int(&a,0xffffffff);
-  if (mp_get_int(&a)!=0xffffffff)
-  { printf("mp_get_int() bad result!\n");
-    return 1;
-  }
-
-  // test mp_sqrt
-  printf("Testing: mp_sqrt\n");
-  for (i=0;i<1000;++i) { 
-    printf("%6d\r", i); fflush(stdout);
-    n = (rand()&15)+1;
-    mp_rand(&a,n);
-    if (mp_sqrt(&a,&b) != MP_OKAY)
-    { printf("mp_sqrt() error!\n");
-      return 1;
-    }
-    mp_n_root(&a,2,&a);
-    if (mp_cmp_mag(&b,&a) != MP_EQ)
-    { printf("mp_sqrt() bad result!\n");
-      return 1;
-    }
-  }
-
-  printf("\nTesting: mp_is_square\n");
-  for (i=0;i<1000;++i) {
-    printf("%6d\r", i); fflush(stdout);
-
-    /* test mp_is_square false negatives */
-    n = (rand()&7)+1;
-    mp_rand(&a,n);
-    mp_sqr(&a,&a);
-    if (mp_is_square(&a,&n)!=MP_OKAY) { 
-      printf("fn:mp_is_square() error!\n");
-      return 1;
-    }
-    if (n==0) { 
-      printf("fn:mp_is_square() bad result!\n");
+   }
+   mp_set_int(&a, 0xffffffff);
+   if (mp_get_int(&a) != 0xffffffff) {
+      printf("mp_get_int() bad result!\n");
       return 1;
-    }
+   }
+   // test mp_sqrt
+   printf("Testing: mp_sqrt\n");
+   for (i = 0; i < 1000; ++i) {
+      printf("%6d\r", i);
+      fflush(stdout);
+      n = (rand() & 15) + 1;
+      mp_rand(&a, n);
+      if (mp_sqrt(&a, &b) != MP_OKAY) {
+	 printf("mp_sqrt() error!\n");
+	 return 1;
+      }
+      mp_n_root(&a, 2, &a);
+      if (mp_cmp_mag(&b, &a) != MP_EQ) {
+	 printf("mp_sqrt() bad result!\n");
+	 return 1;
+      }
+   }
 
-    /* test for false positives */
-    mp_add_d(&a, 1, &a);
-    if (mp_is_square(&a,&n)!=MP_OKAY) { 
-      printf("fp:mp_is_square() error!\n");
-      return 1;
-    }
-    if (n==1) { 
-      printf("fp:mp_is_square() bad result!\n");
-      return 1;
-    }
+   printf("\nTesting: mp_is_square\n");
+   for (i = 0; i < 1000; ++i) {
+      printf("%6d\r", i);
+      fflush(stdout);
+
+      /* test mp_is_square false negatives */
+      n = (rand() & 7) + 1;
+      mp_rand(&a, n);
+      mp_sqr(&a, &a);
+      if (mp_is_square(&a, &n) != MP_OKAY) {
+	 printf("fn:mp_is_square() error!\n");
+	 return 1;
+      }
+      if (n == 0) {
+	 printf("fn:mp_is_square() bad result!\n");
+	 return 1;
+      }
 
-  }
-  printf("\n\n");
+      /* test for false positives */
+      mp_add_d(&a, 1, &a);
+      if (mp_is_square(&a, &n) != MP_OKAY) {
+	 printf("fp:mp_is_square() error!\n");
+	 return 1;
+      }
+      if (n == 1) {
+	 printf("fp:mp_is_square() bad result!\n");
+	 return 1;
+      }
+
+   }
+   printf("\n\n");
 
    /* test for size */
-   for (ix = 10; ix < 256; ix++) {
-       printf("Testing (not safe-prime): %9d bits    \r", ix); fflush(stdout);
-       err = mp_prime_random_ex(&a, 8, ix, (rand()&1)?LTM_PRIME_2MSB_OFF:LTM_PRIME_2MSB_ON, myrng, NULL);
-       if (err != MP_OKAY) {
-          printf("failed with err code %d\n", err);
-          return EXIT_FAILURE;
-       }
-       if (mp_count_bits(&a) != ix) {
-          printf("Prime is %d not %d bits!!!\n", mp_count_bits(&a), ix);
-          return EXIT_FAILURE;
-       }
+   for (ix = 10; ix < 128; ix++) {
+      printf("Testing (not safe-prime): %9d bits    \r", ix);
+      fflush(stdout);
+      err =
+	 mp_prime_random_ex(&a, 8, ix,
+			    (rand() & 1) ? LTM_PRIME_2MSB_OFF :
+			    LTM_PRIME_2MSB_ON, myrng, NULL);
+      if (err != MP_OKAY) {
+	 printf("failed with err code %d\n", err);
+	 return EXIT_FAILURE;
+      }
+      if (mp_count_bits(&a) != ix) {
+	 printf("Prime is %d not %d bits!!!\n", mp_count_bits(&a), ix);
+	 return EXIT_FAILURE;
+      }
    }
 
-   for (ix = 16; ix < 256; ix++) {
-       printf("Testing (   safe-prime): %9d bits    \r", ix); fflush(stdout);
-       err = mp_prime_random_ex(&a, 8, ix, ((rand()&1)?LTM_PRIME_2MSB_OFF:LTM_PRIME_2MSB_ON)|LTM_PRIME_SAFE, myrng, NULL);
-       if (err != MP_OKAY) {
-          printf("failed with err code %d\n", err);
-          return EXIT_FAILURE;
-       }
-       if (mp_count_bits(&a) != ix) {
-          printf("Prime is %d not %d bits!!!\n", mp_count_bits(&a), ix);
-          return EXIT_FAILURE;
-       }
-       /* let's see if it's really a safe prime */
-       mp_sub_d(&a, 1, &a);
-       mp_div_2(&a, &a);
-       mp_prime_is_prime(&a, 8, &cnt);
-       if (cnt != MP_YES) {
-          printf("sub is not prime!\n");
-          return EXIT_FAILURE;
-       }
+   for (ix = 16; ix < 128; ix++) {
+      printf("Testing (   safe-prime): %9d bits    \r", ix);
+      fflush(stdout);
+      err =
+	 mp_prime_random_ex(&a, 8, ix,
+			    ((rand() & 1) ? LTM_PRIME_2MSB_OFF :
+			     LTM_PRIME_2MSB_ON) | LTM_PRIME_SAFE, myrng,
+			    NULL);
+      if (err != MP_OKAY) {
+	 printf("failed with err code %d\n", err);
+	 return EXIT_FAILURE;
+      }
+      if (mp_count_bits(&a) != ix) {
+	 printf("Prime is %d not %d bits!!!\n", mp_count_bits(&a), ix);
+	 return EXIT_FAILURE;
+      }
+      /* let's see if it's really a safe prime */
+      mp_sub_d(&a, 1, &a);
+      mp_div_2(&a, &a);
+      mp_prime_is_prime(&a, 8, &cnt);
+      if (cnt != MP_YES) {
+	 printf("sub is not prime!\n");
+	 return EXIT_FAILURE;
+      }
    }
 
    printf("\n\n");
@@ -194,51 +242,56 @@ int main(void)
    printf("testing mp_cnt_lsb...\n");
    mp_set(&a, 1);
    for (ix = 0; ix < 1024; ix++) {
-       if (mp_cnt_lsb(&a) != ix) {
-          printf("Failed at %d, %d\n", ix, mp_cnt_lsb(&a));
-          return 0;
-       }
-       mp_mul_2(&a, &a);
+      if (mp_cnt_lsb(&a) != ix) {
+	 printf("Failed at %d, %d\n", ix, mp_cnt_lsb(&a));
+	 return 0;
+      }
+      mp_mul_2(&a, &a);
    }
 
 /* test mp_reduce_2k */
    printf("Testing mp_reduce_2k...\n");
    for (cnt = 3; cnt <= 128; ++cnt) {
-       mp_digit tmp;
-       mp_2expt(&a, cnt);
-       mp_sub_d(&a, 2, &a);  /* a = 2**cnt - 2 */
-
-
-       printf("\nTesting %4d bits", cnt);
-       printf("(%d)", mp_reduce_is_2k(&a));
-       mp_reduce_2k_setup(&a, &tmp);
-       printf("(%d)", tmp);
-       for (ix = 0; ix < 1000; ix++) {
-           if (!(ix & 127)) {printf("."); fflush(stdout); }
-           mp_rand(&b, (cnt/DIGIT_BIT  + 1) * 2);
-           mp_copy(&c, &b);
-           mp_mod(&c, &a, &c);
-           mp_reduce_2k(&b, &a, 1);
-           if (mp_cmp(&c, &b)) {
-              printf("FAILED\n");
-              exit(0);
-           }
-        }
-    }
+      mp_digit tmp;
+
+      mp_2expt(&a, cnt);
+      mp_sub_d(&a, 2, &a);	/* a = 2**cnt - 2 */
+
+
+      printf("\nTesting %4d bits", cnt);
+      printf("(%d)", mp_reduce_is_2k(&a));
+      mp_reduce_2k_setup(&a, &tmp);
+      printf("(%d)", tmp);
+      for (ix = 0; ix < 1000; ix++) {
+	 if (!(ix & 127)) {
+	    printf(".");
+	    fflush(stdout);
+	 }
+	 mp_rand(&b, (cnt / DIGIT_BIT + 1) * 2);
+	 mp_copy(&c, &b);
+	 mp_mod(&c, &a, &c);
+	 mp_reduce_2k(&b, &a, 2);
+	 if (mp_cmp(&c, &b)) {
+	    printf("FAILED\n");
+	    exit(0);
+	 }
+      }
+   }
 
 /* test mp_div_3  */
    printf("Testing mp_div_3...\n");
    mp_set(&d, 3);
-   for (cnt = 0; cnt < 10000; ) {
+   for (cnt = 0; cnt < 10000;) {
       mp_digit r1, r2;
 
-      if (!(++cnt & 127)) printf("%9d\r", cnt);
+      if (!(++cnt & 127))
+	 printf("%9d\r", cnt);
       mp_rand(&a, abs(rand()) % 128 + 1);
       mp_div(&a, &d, &b, &e);
       mp_div_3(&a, &c, &r2);
 
       if (mp_cmp(&b, &c) || mp_cmp_d(&e, r2)) {
-         printf("\n\nmp_div_3 => Failure\n");
+	 printf("\n\nmp_div_3 => Failure\n");
       }
    }
    printf("\n\nPassed div_3 testing\n");
@@ -246,270 +299,438 @@ int main(void)
 /* test the DR reduction */
    printf("testing mp_dr_reduce...\n");
    for (cnt = 2; cnt < 32; cnt++) {
-       printf("%d digit modulus\n", cnt);
-       mp_grow(&a, cnt);
-       mp_zero(&a);
-       for (ix = 1; ix < cnt; ix++) {
-           a.dp[ix] = MP_MASK;
-       }
-       a.used = cnt;
-       a.dp[0] = 3;
-
-       mp_rand(&b, cnt - 1);
-       mp_copy(&b, &c);
+      printf("%d digit modulus\n", cnt);
+      mp_grow(&a, cnt);
+      mp_zero(&a);
+      for (ix = 1; ix < cnt; ix++) {
+	 a.dp[ix] = MP_MASK;
+      }
+      a.used = cnt;
+      a.dp[0] = 3;
+
+      mp_rand(&b, cnt - 1);
+      mp_copy(&b, &c);
 
       rr = 0;
       do {
-         if (!(rr & 127)) { printf("%9lu\r", rr); fflush(stdout); }
-         mp_sqr(&b, &b); mp_add_d(&b, 1, &b);
-         mp_copy(&b, &c);
-
-         mp_mod(&b, &a, &b);
-         mp_dr_reduce(&c, &a, (((mp_digit)1)<<DIGIT_BIT)-a.dp[0]);
-
-         if (mp_cmp(&b, &c) != MP_EQ) {
-            printf("Failed on trial %lu\n", rr); exit(-1);
-
-         }
+	 if (!(rr & 127)) {
+	    printf("%9lu\r", rr);
+	    fflush(stdout);
+	 }
+	 mp_sqr(&b, &b);
+	 mp_add_d(&b, 1, &b);
+	 mp_copy(&b, &c);
+
+	 mp_mod(&b, &a, &b);
+	 mp_dr_reduce(&c, &a, (((mp_digit) 1) << DIGIT_BIT) - a.dp[0]);
+
+	 if (mp_cmp(&b, &c) != MP_EQ) {
+	    printf("Failed on trial %lu\n", rr);
+	    exit(-1);
+
+	 }
       } while (++rr < 500);
       printf("Passed DR test for %d digits\n", cnt);
    }
 
 #endif
 
+/* test the mp_reduce_2k_l code */
+#if 0
+#if 0
+/* first load P with 2^1024 - 0x2A434 B9FDEC95 D8F9D550 FFFFFFFF FFFFFFFF */
+   mp_2expt(&a, 1024);
+   mp_read_radix(&b, "2A434B9FDEC95D8F9D550FFFFFFFFFFFFFFFF", 16);
+   mp_sub(&a, &b, &a);
+#elif 1
+/*  p = 2^2048 - 0x1 00000000 00000000 00000000 00000000 4945DDBF 8EA2A91D 5776399B B83E188F  */
+   mp_2expt(&a, 2048);
+   mp_read_radix(&b,
+		 "1000000000000000000000000000000004945DDBF8EA2A91D5776399BB83E188F",
+		 16);
+   mp_sub(&a, &b, &a);
+#endif
+
+   mp_todecimal(&a, buf);
+   printf("p==%s\n", buf);
+/* now mp_reduce_is_2k_l() should return */
+   if (mp_reduce_is_2k_l(&a) != 1) {
+      printf("mp_reduce_is_2k_l() return 0, should be 1\n");
+      return EXIT_FAILURE;
+   }
+   mp_reduce_2k_setup_l(&a, &d);
+   /* now do a million square+1 to see if it varies */
+   mp_rand(&b, 64);
+   mp_mod(&b, &a, &b);
+   mp_copy(&b, &c);
+   printf("testing mp_reduce_2k_l...");
+   fflush(stdout);
+   for (cnt = 0; cnt < (1UL << 20); cnt++) {
+      mp_sqr(&b, &b);
+      mp_add_d(&b, 1, &b);
+      mp_reduce_2k_l(&b, &a, &d);
+      mp_sqr(&c, &c);
+      mp_add_d(&c, 1, &c);
+      mp_mod(&c, &a, &c);
+      if (mp_cmp(&b, &c) != MP_EQ) {
+	 printf("mp_reduce_2k_l() failed at step %lu\n", cnt);
+	 mp_tohex(&b, buf);
+	 printf("b == %s\n", buf);
+	 mp_tohex(&c, buf);
+	 printf("c == %s\n", buf);
+	 return EXIT_FAILURE;
+      }
+   }
+   printf("...Passed\n");
+#endif
+
    div2_n = mul2_n = inv_n = expt_n = lcm_n = gcd_n = add_n =
-   sub_n = mul_n = div_n = sqr_n = mul2d_n = div2d_n = cnt = add_d_n = sub_d_n= 0;
+      sub_n = mul_n = div_n = sqr_n = mul2d_n = div2d_n = cnt = add_d_n =
+      sub_d_n = 0;
 
    /* force KARA and TOOM to enable despite cutoffs */
    KARATSUBA_SQR_CUTOFF = KARATSUBA_MUL_CUTOFF = 110;
-   TOOM_SQR_CUTOFF      = TOOM_MUL_CUTOFF      = 150;
+   TOOM_SQR_CUTOFF = TOOM_MUL_CUTOFF = 150;
 
    for (;;) {
-       /* randomly clear and re-init one variable, this has the affect of triming the alloc space */
-       switch (abs(rand()) % 7) {
-           case 0:  mp_clear(&a); mp_init(&a); break;
-           case 1:  mp_clear(&b); mp_init(&b); break;
-           case 2:  mp_clear(&c); mp_init(&c); break;
-           case 3:  mp_clear(&d); mp_init(&d); break;
-           case 4:  mp_clear(&e); mp_init(&e); break;
-           case 5:  mp_clear(&f); mp_init(&f); break;
-           case 6:  break; /* don't clear any */
-       }
-
-
-       printf("%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu ", add_n, sub_n, mul_n, div_n, sqr_n, mul2d_n, div2d_n, gcd_n, lcm_n, expt_n, inv_n, div2_n, mul2_n, add_d_n, sub_d_n);
-       fgets(cmd, 4095, stdin);
-       cmd[strlen(cmd)-1] = 0;
-       printf("%s  ]\r",cmd); fflush(stdout);
-       if (!strcmp(cmd, "mul2d")) { ++mul2d_n;
-          fgets(buf, 4095, stdin); mp_read_radix(&a, buf, 64);
-          fgets(buf, 4095, stdin); sscanf(buf, "%d", &rr);
-          fgets(buf, 4095, stdin); mp_read_radix(&b, buf, 64);
-
-          mp_mul_2d(&a, rr, &a);
-          a.sign = b.sign;
-          if (mp_cmp(&a, &b) != MP_EQ) {
-             printf("mul2d failed, rr == %d\n",rr);
-             draw(&a);
-             draw(&b);
-             return 0;
-          }
-       } else if (!strcmp(cmd, "div2d")) { ++div2d_n;
-          fgets(buf, 4095, stdin); mp_read_radix(&a, buf, 64);
-          fgets(buf, 4095, stdin); sscanf(buf, "%d", &rr);
-          fgets(buf, 4095, stdin); mp_read_radix(&b, buf, 64);
-
-          mp_div_2d(&a, rr, &a, &e);
-          a.sign = b.sign;
-          if (a.used == b.used && a.used == 0) { a.sign = b.sign = MP_ZPOS; }
-          if (mp_cmp(&a, &b) != MP_EQ) {
-             printf("div2d failed, rr == %d\n",rr);
-             draw(&a);
-             draw(&b);
-             return 0;
-          }
-       } else if (!strcmp(cmd, "add")) { ++add_n;
-          fgets(buf, 4095, stdin);  mp_read_radix(&a, buf, 64);
-          fgets(buf, 4095, stdin);  mp_read_radix(&b, buf, 64);
-          fgets(buf, 4095, stdin);  mp_read_radix(&c, buf, 64);
-          mp_copy(&a, &d);
-          mp_add(&d, &b, &d);
-          if (mp_cmp(&c, &d) != MP_EQ) {
-             printf("add %lu failure!\n", add_n);
-draw(&a);draw(&b);draw(&c);draw(&d);
-             return 0;
-          }
-
-          /* test the sign/unsigned storage functions */
-
-          rr = mp_signed_bin_size(&c);
-          mp_to_signed_bin(&c, (unsigned char *)cmd);
-          memset(cmd+rr, rand()&255, sizeof(cmd)-rr);
-          mp_read_signed_bin(&d, (unsigned char *)cmd, rr);
-          if (mp_cmp(&c, &d) != MP_EQ) {
-             printf("mp_signed_bin failure!\n");
-             draw(&c);
-             draw(&d);
-             return 0;
-          }
-
-
-          rr = mp_unsigned_bin_size(&c);
-          mp_to_unsigned_bin(&c, (unsigned char *)cmd);
-          memset(cmd+rr, rand()&255, sizeof(cmd)-rr);
-          mp_read_unsigned_bin(&d, (unsigned char *)cmd, rr);
-          if (mp_cmp_mag(&c, &d) != MP_EQ) {
-             printf("mp_unsigned_bin failure!\n");
-             draw(&c);
-             draw(&d);
-             return 0;
-          }
-
-       } else if (!strcmp(cmd, "sub")) { ++sub_n;
-          fgets(buf, 4095, stdin);  mp_read_radix(&a, buf, 64);
-          fgets(buf, 4095, stdin);  mp_read_radix(&b, buf, 64);
-          fgets(buf, 4095, stdin);  mp_read_radix(&c, buf, 64);
-          mp_copy(&a, &d);
-          mp_sub(&d, &b, &d);
-          if (mp_cmp(&c, &d) != MP_EQ) {
-             printf("sub %lu failure!\n", sub_n);
-draw(&a);draw(&b);draw(&c);draw(&d);
-             return 0;
-          }
-       } else if (!strcmp(cmd, "mul")) { ++mul_n;
-          fgets(buf, 4095, stdin);  mp_read_radix(&a, buf, 64);
-          fgets(buf, 4095, stdin);  mp_read_radix(&b, buf, 64);
-          fgets(buf, 4095, stdin);  mp_read_radix(&c, buf, 64);
-          mp_copy(&a, &d);
-          mp_mul(&d, &b, &d);
-          if (mp_cmp(&c, &d) != MP_EQ) {
-             printf("mul %lu failure!\n", mul_n);
-draw(&a);draw(&b);draw(&c);draw(&d);
-             return 0;
-          }
-       } else if (!strcmp(cmd, "div")) { ++div_n;
-          fgets(buf, 4095, stdin); mp_read_radix(&a, buf, 64);
-          fgets(buf, 4095, stdin); mp_read_radix(&b, buf, 64);
-          fgets(buf, 4095, stdin); mp_read_radix(&c, buf, 64);
-          fgets(buf, 4095, stdin); mp_read_radix(&d, buf, 64);
-
-          mp_div(&a, &b, &e, &f);
-          if (mp_cmp(&c, &e) != MP_EQ || mp_cmp(&d, &f) != MP_EQ) {
-             printf("div %lu %d, %d, failure!\n", div_n, mp_cmp(&c, &e), mp_cmp(&d, &f));
-draw(&a);draw(&b);draw(&c);draw(&d); draw(&e); draw(&f);
-             return 0;
-          }
-
-       } else if (!strcmp(cmd, "sqr")) { ++sqr_n;
-          fgets(buf, 4095, stdin);  mp_read_radix(&a, buf, 64);
-          fgets(buf, 4095, stdin);  mp_read_radix(&b, buf, 64);
-          mp_copy(&a, &c);
-          mp_sqr(&c, &c);
-          if (mp_cmp(&b, &c) != MP_EQ) {
-             printf("sqr %lu failure!\n", sqr_n);
-draw(&a);draw(&b);draw(&c);
-             return 0;
-          }
-       } else if (!strcmp(cmd, "gcd")) { ++gcd_n;
-          fgets(buf, 4095, stdin);  mp_read_radix(&a, buf, 64);
-          fgets(buf, 4095, stdin);  mp_read_radix(&b, buf, 64);
-          fgets(buf, 4095, stdin);  mp_read_radix(&c, buf, 64);
-          mp_copy(&a, &d);
-          mp_gcd(&d, &b, &d);
-          d.sign = c.sign;
-          if (mp_cmp(&c, &d) != MP_EQ) {
-             printf("gcd %lu failure!\n", gcd_n);
-draw(&a);draw(&b);draw(&c);draw(&d);
-             return 0;
-          }
-       } else if (!strcmp(cmd, "lcm")) { ++lcm_n;
-             fgets(buf, 4095, stdin);  mp_read_radix(&a, buf, 64);
-             fgets(buf, 4095, stdin);  mp_read_radix(&b, buf, 64);
-             fgets(buf, 4095, stdin);  mp_read_radix(&c, buf, 64);
-             mp_copy(&a, &d);
-             mp_lcm(&d, &b, &d);
-             d.sign = c.sign;
-             if (mp_cmp(&c, &d) != MP_EQ) {
-                printf("lcm %lu failure!\n", lcm_n);
-   draw(&a);draw(&b);draw(&c);draw(&d);
-                return 0;
-             }
-       } else if (!strcmp(cmd, "expt")) {  ++expt_n;
-             fgets(buf, 4095, stdin);  mp_read_radix(&a, buf, 64);
-             fgets(buf, 4095, stdin);  mp_read_radix(&b, buf, 64);
-             fgets(buf, 4095, stdin);  mp_read_radix(&c, buf, 64);
-             fgets(buf, 4095, stdin);  mp_read_radix(&d, buf, 64);
-             mp_copy(&a, &e);
-             mp_exptmod(&e, &b, &c, &e);
-             if (mp_cmp(&d, &e) != MP_EQ) {
-                printf("expt %lu failure!\n", expt_n);
-   draw(&a);draw(&b);draw(&c);draw(&d); draw(&e);
-                return 0;
-             }
-       } else if (!strcmp(cmd, "invmod")) {  ++inv_n;
-             fgets(buf, 4095, stdin);  mp_read_radix(&a, buf, 64);
-             fgets(buf, 4095, stdin);  mp_read_radix(&b, buf, 64);
-             fgets(buf, 4095, stdin);  mp_read_radix(&c, buf, 64);
-             mp_invmod(&a, &b, &d);
-             mp_mulmod(&d,&a,&b,&e);
-             if (mp_cmp_d(&e, 1) != MP_EQ) {
-                printf("inv [wrong value from MPI?!] failure\n");
-                draw(&a);draw(&b);draw(&c);draw(&d);
-                mp_gcd(&a, &b, &e);
-                draw(&e);
-                return 0;
-             }
-
-       } else if (!strcmp(cmd, "div2")) { ++div2_n;
-             fgets(buf, 4095, stdin);  mp_read_radix(&a, buf, 64);
-             fgets(buf, 4095, stdin);  mp_read_radix(&b, buf, 64);
-             mp_div_2(&a, &c);
-             if (mp_cmp(&c, &b) != MP_EQ) {
-                 printf("div_2 %lu failure\n", div2_n);
-                 draw(&a);
-                 draw(&b);
-                 draw(&c);
-                 return 0;
-             }
-       } else if (!strcmp(cmd, "mul2")) { ++mul2_n;
-             fgets(buf, 4095, stdin);  mp_read_radix(&a, buf, 64);
-             fgets(buf, 4095, stdin);  mp_read_radix(&b, buf, 64);
-             mp_mul_2(&a, &c);
-             if (mp_cmp(&c, &b) != MP_EQ) {
-                 printf("mul_2 %lu failure\n", mul2_n);
-                 draw(&a);
-                 draw(&b);
-                 draw(&c);
-                 return 0;
-             }
-       } else if (!strcmp(cmd, "add_d")) { ++add_d_n;
-              fgets(buf, 4095, stdin); mp_read_radix(&a, buf, 64);
-              fgets(buf, 4095, stdin); sscanf(buf, "%d", &ix);
-              fgets(buf, 4095, stdin); mp_read_radix(&b, buf, 64);
-              mp_add_d(&a, ix, &c);
-              if (mp_cmp(&b, &c) != MP_EQ) {
-                 printf("add_d %lu failure\n", add_d_n);
-                 draw(&a);
-                 draw(&b);
-                 draw(&c);
-                 printf("d == %d\n", ix);
-                 return 0;
-              }
-       } else if (!strcmp(cmd, "sub_d")) { ++sub_d_n;
-              fgets(buf, 4095, stdin); mp_read_radix(&a, buf, 64);
-              fgets(buf, 4095, stdin); sscanf(buf, "%d", &ix);
-              fgets(buf, 4095, stdin); mp_read_radix(&b, buf, 64);
-              mp_sub_d(&a, ix, &c);
-              if (mp_cmp(&b, &c) != MP_EQ) {
-                 printf("sub_d %lu failure\n", sub_d_n);
-                 draw(&a);
-                 draw(&b);
-                 draw(&c);
-                 printf("d == %d\n", ix);
-                 return 0;
-              }
-       }
+      /* randomly clear and re-init one variable, this has the affect of triming the alloc space */
+      switch (abs(rand()) % 7) {
+      case 0:
+	 mp_clear(&a);
+	 mp_init(&a);
+	 break;
+      case 1:
+	 mp_clear(&b);
+	 mp_init(&b);
+	 break;
+      case 2:
+	 mp_clear(&c);
+	 mp_init(&c);
+	 break;
+      case 3:
+	 mp_clear(&d);
+	 mp_init(&d);
+	 break;
+      case 4:
+	 mp_clear(&e);
+	 mp_init(&e);
+	 break;
+      case 5:
+	 mp_clear(&f);
+	 mp_init(&f);
+	 break;
+      case 6:
+	 break;			/* don't clear any */
+      }
+
+
+      printf
+	 ("%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu/%4lu ",
+	  add_n, sub_n, mul_n, div_n, sqr_n, mul2d_n, div2d_n, gcd_n, lcm_n,
+	  expt_n, inv_n, div2_n, mul2_n, add_d_n, sub_d_n);
+      fgets(cmd, 4095, stdin);
+      cmd[strlen(cmd) - 1] = 0;
+      printf("%s  ]\r", cmd);
+      fflush(stdout);
+      if (!strcmp(cmd, "mul2d")) {
+	 ++mul2d_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 sscanf(buf, "%d", &rr);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+
+	 mp_mul_2d(&a, rr, &a);
+	 a.sign = b.sign;
+	 if (mp_cmp(&a, &b) != MP_EQ) {
+	    printf("mul2d failed, rr == %d\n", rr);
+	    draw(&a);
+	    draw(&b);
+	    return 0;
+	 }
+      } else if (!strcmp(cmd, "div2d")) {
+	 ++div2d_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 sscanf(buf, "%d", &rr);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+
+	 mp_div_2d(&a, rr, &a, &e);
+	 a.sign = b.sign;
+	 if (a.used == b.used && a.used == 0) {
+	    a.sign = b.sign = MP_ZPOS;
+	 }
+	 if (mp_cmp(&a, &b) != MP_EQ) {
+	    printf("div2d failed, rr == %d\n", rr);
+	    draw(&a);
+	    draw(&b);
+	    return 0;
+	 }
+      } else if (!strcmp(cmd, "add")) {
+	 ++add_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&c, buf, 64);
+	 mp_copy(&a, &d);
+	 mp_add(&d, &b, &d);
+	 if (mp_cmp(&c, &d) != MP_EQ) {
+	    printf("add %lu failure!\n", add_n);
+	    draw(&a);
+	    draw(&b);
+	    draw(&c);
+	    draw(&d);
+	    return 0;
+	 }
+
+	 /* test the sign/unsigned storage functions */
+
+	 rr = mp_signed_bin_size(&c);
+	 mp_to_signed_bin(&c, (unsigned char *) cmd);
+	 memset(cmd + rr, rand() & 255, sizeof(cmd) - rr);
+	 mp_read_signed_bin(&d, (unsigned char *) cmd, rr);
+	 if (mp_cmp(&c, &d) != MP_EQ) {
+	    printf("mp_signed_bin failure!\n");
+	    draw(&c);
+	    draw(&d);
+	    return 0;
+	 }
+
+
+	 rr = mp_unsigned_bin_size(&c);
+	 mp_to_unsigned_bin(&c, (unsigned char *) cmd);
+	 memset(cmd + rr, rand() & 255, sizeof(cmd) - rr);
+	 mp_read_unsigned_bin(&d, (unsigned char *) cmd, rr);
+	 if (mp_cmp_mag(&c, &d) != MP_EQ) {
+	    printf("mp_unsigned_bin failure!\n");
+	    draw(&c);
+	    draw(&d);
+	    return 0;
+	 }
+
+      } else if (!strcmp(cmd, "sub")) {
+	 ++sub_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&c, buf, 64);
+	 mp_copy(&a, &d);
+	 mp_sub(&d, &b, &d);
+	 if (mp_cmp(&c, &d) != MP_EQ) {
+	    printf("sub %lu failure!\n", sub_n);
+	    draw(&a);
+	    draw(&b);
+	    draw(&c);
+	    draw(&d);
+	    return 0;
+	 }
+      } else if (!strcmp(cmd, "mul")) {
+	 ++mul_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&c, buf, 64);
+	 mp_copy(&a, &d);
+	 mp_mul(&d, &b, &d);
+	 if (mp_cmp(&c, &d) != MP_EQ) {
+	    printf("mul %lu failure!\n", mul_n);
+	    draw(&a);
+	    draw(&b);
+	    draw(&c);
+	    draw(&d);
+	    return 0;
+	 }
+      } else if (!strcmp(cmd, "div")) {
+	 ++div_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&c, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&d, buf, 64);
+
+	 mp_div(&a, &b, &e, &f);
+	 if (mp_cmp(&c, &e) != MP_EQ || mp_cmp(&d, &f) != MP_EQ) {
+	    printf("div %lu %d, %d, failure!\n", div_n, mp_cmp(&c, &e),
+		   mp_cmp(&d, &f));
+	    draw(&a);
+	    draw(&b);
+	    draw(&c);
+	    draw(&d);
+	    draw(&e);
+	    draw(&f);
+	    return 0;
+	 }
+
+      } else if (!strcmp(cmd, "sqr")) {
+	 ++sqr_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+	 mp_copy(&a, &c);
+	 mp_sqr(&c, &c);
+	 if (mp_cmp(&b, &c) != MP_EQ) {
+	    printf("sqr %lu failure!\n", sqr_n);
+	    draw(&a);
+	    draw(&b);
+	    draw(&c);
+	    return 0;
+	 }
+      } else if (!strcmp(cmd, "gcd")) {
+	 ++gcd_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&c, buf, 64);
+	 mp_copy(&a, &d);
+	 mp_gcd(&d, &b, &d);
+	 d.sign = c.sign;
+	 if (mp_cmp(&c, &d) != MP_EQ) {
+	    printf("gcd %lu failure!\n", gcd_n);
+	    draw(&a);
+	    draw(&b);
+	    draw(&c);
+	    draw(&d);
+	    return 0;
+	 }
+      } else if (!strcmp(cmd, "lcm")) {
+	 ++lcm_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&c, buf, 64);
+	 mp_copy(&a, &d);
+	 mp_lcm(&d, &b, &d);
+	 d.sign = c.sign;
+	 if (mp_cmp(&c, &d) != MP_EQ) {
+	    printf("lcm %lu failure!\n", lcm_n);
+	    draw(&a);
+	    draw(&b);
+	    draw(&c);
+	    draw(&d);
+	    return 0;
+	 }
+      } else if (!strcmp(cmd, "expt")) {
+	 ++expt_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&c, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&d, buf, 64);
+	 mp_copy(&a, &e);
+	 mp_exptmod(&e, &b, &c, &e);
+	 if (mp_cmp(&d, &e) != MP_EQ) {
+	    printf("expt %lu failure!\n", expt_n);
+	    draw(&a);
+	    draw(&b);
+	    draw(&c);
+	    draw(&d);
+	    draw(&e);
+	    return 0;
+	 }
+      } else if (!strcmp(cmd, "invmod")) {
+	 ++inv_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&c, buf, 64);
+	 mp_invmod(&a, &b, &d);
+	 mp_mulmod(&d, &a, &b, &e);
+	 if (mp_cmp_d(&e, 1) != MP_EQ) {
+	    printf("inv [wrong value from MPI?!] failure\n");
+	    draw(&a);
+	    draw(&b);
+	    draw(&c);
+	    draw(&d);
+	    mp_gcd(&a, &b, &e);
+	    draw(&e);
+	    return 0;
+	 }
+
+      } else if (!strcmp(cmd, "div2")) {
+	 ++div2_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+	 mp_div_2(&a, &c);
+	 if (mp_cmp(&c, &b) != MP_EQ) {
+	    printf("div_2 %lu failure\n", div2_n);
+	    draw(&a);
+	    draw(&b);
+	    draw(&c);
+	    return 0;
+	 }
+      } else if (!strcmp(cmd, "mul2")) {
+	 ++mul2_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+	 mp_mul_2(&a, &c);
+	 if (mp_cmp(&c, &b) != MP_EQ) {
+	    printf("mul_2 %lu failure\n", mul2_n);
+	    draw(&a);
+	    draw(&b);
+	    draw(&c);
+	    return 0;
+	 }
+      } else if (!strcmp(cmd, "add_d")) {
+	 ++add_d_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 sscanf(buf, "%d", &ix);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+	 mp_add_d(&a, ix, &c);
+	 if (mp_cmp(&b, &c) != MP_EQ) {
+	    printf("add_d %lu failure\n", add_d_n);
+	    draw(&a);
+	    draw(&b);
+	    draw(&c);
+	    printf("d == %d\n", ix);
+	    return 0;
+	 }
+      } else if (!strcmp(cmd, "sub_d")) {
+	 ++sub_d_n;
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&a, buf, 64);
+	 fgets(buf, 4095, stdin);
+	 sscanf(buf, "%d", &ix);
+	 fgets(buf, 4095, stdin);
+	 mp_read_radix(&b, buf, 64);
+	 mp_sub_d(&a, ix, &c);
+	 if (mp_cmp(&b, &c) != MP_EQ) {
+	    printf("sub_d %lu failure\n", sub_d_n);
+	    draw(&a);
+	    draw(&b);
+	    draw(&c);
+	    printf("d == %d\n", ix);
+	    return 0;
+	 }
+      }
    }
    return 0;
 }
-
diff --git a/libtommath/demo/timing.c b/libtommath/demo/timing.c
index 7b27d53..bb3be52 100644
--- a/libtommath/demo/timing.c
+++ b/libtommath/demo/timing.c
@@ -11,15 +11,16 @@ ulong64 _tt;
 #endif
 
 
-void ndraw(mp_int *a, char *name)
+void ndraw(mp_int * a, char *name)
 {
    char buf[4096];
+
    printf("%s: ", name);
    mp_toradix(a, buf, 64);
    printf("%s\n", buf);
 }
 
-static void draw(mp_int *a)
+static void draw(mp_int * a)
 {
    ndraw(a, "");
 }
@@ -39,35 +40,38 @@ int lbit(void)
 }
 
 /* RDTSC from Scott Duplichan */
-static ulong64 TIMFUNC (void)
-   {
-   #if defined __GNUC__
-      #if defined(__i386__) || defined(__x86_64__)
-         unsigned long long a;
-         __asm__ __volatile__ ("rdtsc\nmovl %%eax,%0\nmovl %%edx,4+%0\n"::"m"(a):"%eax","%edx");
-         return a;
-      #else /* gcc-IA64 version */
-         unsigned long result;
-         __asm__ __volatile__("mov %0=ar.itc" : "=r"(result) :: "memory");
-         while (__builtin_expect ((int) result == -1, 0))
-         __asm__ __volatile__("mov %0=ar.itc" : "=r"(result) :: "memory");
-         return result;
-      #endif
+static ulong64 TIMFUNC(void)
+{
+#if defined __GNUC__
+#if defined(__i386__) || defined(__x86_64__)
+   unsigned long long a;
+   __asm__ __volatile__("rdtsc\nmovl %%eax,%0\nmovl %%edx,4+%0\n"::
+			"m"(a):"%eax", "%edx");
+   return a;
+#else /* gcc-IA64 version */
+   unsigned long result;
+   __asm__ __volatile__("mov %0=ar.itc":"=r"(result)::"memory");
+
+   while (__builtin_expect((int) result == -1, 0))
+      __asm__ __volatile__("mov %0=ar.itc":"=r"(result)::"memory");
+
+   return result;
+#endif
 
    // Microsoft and Intel Windows compilers
-   #elif defined _M_IX86
-     __asm rdtsc
-   #elif defined _M_AMD64
-     return __rdtsc ();
-   #elif defined _M_IA64
-     #if defined __INTEL_COMPILER
-       #include <ia64intrin.h>
-     #endif
-      return __getReg (3116);
-   #else
-     #error need rdtsc function for this build
-   #endif
-   }
+#elif defined _M_IX86
+   __asm rdtsc
+#elif defined _M_AMD64
+   return __rdtsc();
+#elif defined _M_IA64
+#if defined __INTEL_COMPILER
+#include <ia64intrin.h>
+#endif
+   return __getReg(3116);
+#else
+#error need rdtsc function for this build
+#endif
+}
 
 #define DO(x) x; x;
 //#define DO4(x) DO2(x); DO2(x);
@@ -77,7 +81,7 @@ static ulong64 TIMFUNC (void)
 int main(void)
 {
    ulong64 tt, gg, CLK_PER_SEC;
-   FILE *log, *logb, *logc;
+   FILE *log, *logb, *logc, *logd;
    mp_int a, b, c, d, e, f;
    int n, cnt, ix, old_kara_m, old_kara_s;
    unsigned rr;
@@ -90,168 +94,191 @@ int main(void)
    mp_init(&f);
 
    srand(time(NULL));
- 
-
-      /* temp. turn off TOOM */
-      TOOM_MUL_CUTOFF = TOOM_SQR_CUTOFF = 100000;
-
-      CLK_PER_SEC = TIMFUNC();
-      sleep(1);
-      CLK_PER_SEC = TIMFUNC() - CLK_PER_SEC;
-
-      printf("CLK_PER_SEC == %llu\n", CLK_PER_SEC);
-      
-      log = fopen("logs/add.log", "w");
-      for (cnt = 8; cnt <= 128; cnt += 8) {
-         SLEEP;
-         mp_rand(&a, cnt);
-         mp_rand(&b, cnt);
-         rr = 0;
-         tt = -1;
-         do {
-            gg = TIMFUNC();
-            DO(mp_add(&a,&b,&c));
-            gg = (TIMFUNC() - gg)>>1;
-            if (tt > gg) tt = gg;
-         } while (++rr < 100000);
-         printf("Adding\t\t%4d-bit => %9llu/sec, %9llu cycles\n", mp_count_bits(&a), CLK_PER_SEC/tt, tt);
-         fprintf(log, "%d %9llu\n", cnt*DIGIT_BIT, tt); fflush(log);
-      }
-      fclose(log);
 
-      log = fopen("logs/sub.log", "w");
-      for (cnt = 8; cnt <= 128; cnt += 8) {
-         SLEEP;
-         mp_rand(&a, cnt);
-         mp_rand(&b, cnt);
-         rr = 0;
-         tt = -1;
-         do {
-            gg = TIMFUNC();
-            DO(mp_sub(&a,&b,&c));
-            gg = (TIMFUNC() - gg)>>1;
-            if (tt > gg) tt = gg;
-         } while (++rr < 100000);
-
-         printf("Subtracting\t\t%4d-bit => %9llu/sec, %9llu cycles\n", mp_count_bits(&a), CLK_PER_SEC/tt, tt);
-         fprintf(log, "%d %9llu\n", cnt*DIGIT_BIT, tt);  fflush(log);
-      }
-      fclose(log);
+
+   /* temp. turn off TOOM */
+   TOOM_MUL_CUTOFF = TOOM_SQR_CUTOFF = 100000;
+
+   CLK_PER_SEC = TIMFUNC();
+   sleep(1);
+   CLK_PER_SEC = TIMFUNC() - CLK_PER_SEC;
+
+   printf("CLK_PER_SEC == %llu\n", CLK_PER_SEC);
+   goto exptmod;
+   log = fopen("logs/add.log", "w");
+   for (cnt = 8; cnt <= 128; cnt += 8) {
+      SLEEP;
+      mp_rand(&a, cnt);
+      mp_rand(&b, cnt);
+      rr = 0;
+      tt = -1;
+      do {
+	 gg = TIMFUNC();
+	 DO(mp_add(&a, &b, &c));
+	 gg = (TIMFUNC() - gg) >> 1;
+	 if (tt > gg)
+	    tt = gg;
+      } while (++rr < 100000);
+      printf("Adding\t\t%4d-bit => %9llu/sec, %9llu cycles\n",
+	     mp_count_bits(&a), CLK_PER_SEC / tt, tt);
+      fprintf(log, "%d %9llu\n", cnt * DIGIT_BIT, tt);
+      fflush(log);
+   }
+   fclose(log);
+
+   log = fopen("logs/sub.log", "w");
+   for (cnt = 8; cnt <= 128; cnt += 8) {
+      SLEEP;
+      mp_rand(&a, cnt);
+      mp_rand(&b, cnt);
+      rr = 0;
+      tt = -1;
+      do {
+	 gg = TIMFUNC();
+	 DO(mp_sub(&a, &b, &c));
+	 gg = (TIMFUNC() - gg) >> 1;
+	 if (tt > gg)
+	    tt = gg;
+      } while (++rr < 100000);
+
+      printf("Subtracting\t\t%4d-bit => %9llu/sec, %9llu cycles\n",
+	     mp_count_bits(&a), CLK_PER_SEC / tt, tt);
+      fprintf(log, "%d %9llu\n", cnt * DIGIT_BIT, tt);
+      fflush(log);
+   }
+   fclose(log);
 
    /* do mult/square twice, first without karatsuba and second with */
+ multtest:
    old_kara_m = KARATSUBA_MUL_CUTOFF;
    old_kara_s = KARATSUBA_SQR_CUTOFF;
-   for (ix = 0; ix < 1; ix++) {
-      printf("With%s Karatsuba\n", (ix==0)?"out":"");
-
-      KARATSUBA_MUL_CUTOFF = (ix==0)?9999:old_kara_m;
-      KARATSUBA_SQR_CUTOFF = (ix==0)?9999:old_kara_s;
-
-      log = fopen((ix==0)?"logs/mult.log":"logs/mult_kara.log", "w");
-      for (cnt = 4; cnt <= 288; cnt += 2) {
-         SLEEP;
-         mp_rand(&a, cnt);
-         mp_rand(&b, cnt);
-         rr = 0;
-         tt = -1;
-         do {
-            gg = TIMFUNC();
-            DO(mp_mul(&a, &b, &c));
-            gg = (TIMFUNC() - gg)>>1;
-            if (tt > gg) tt = gg;
-         } while (++rr < 100);
-         printf("Multiplying\t%4d-bit => %9llu/sec, %9llu cycles\n", mp_count_bits(&a), CLK_PER_SEC/tt, tt);
-         fprintf(log, "%d %9llu\n", mp_count_bits(&a), tt);  fflush(log);
+   for (ix = 0; ix < 2; ix++) {
+      printf("With%s Karatsuba\n", (ix == 0) ? "out" : "");
+
+      KARATSUBA_MUL_CUTOFF = (ix == 0) ? 9999 : old_kara_m;
+      KARATSUBA_SQR_CUTOFF = (ix == 0) ? 9999 : old_kara_s;
+
+      log = fopen((ix == 0) ? "logs/mult.log" : "logs/mult_kara.log", "w");
+      for (cnt = 4; cnt <= 10240 / DIGIT_BIT; cnt += 2) {
+	 SLEEP;
+	 mp_rand(&a, cnt);
+	 mp_rand(&b, cnt);
+	 rr = 0;
+	 tt = -1;
+	 do {
+	    gg = TIMFUNC();
+	    DO(mp_mul(&a, &b, &c));
+	    gg = (TIMFUNC() - gg) >> 1;
+	    if (tt > gg)
+	       tt = gg;
+	 } while (++rr < 100);
+	 printf("Multiplying\t%4d-bit => %9llu/sec, %9llu cycles\n",
+		mp_count_bits(&a), CLK_PER_SEC / tt, tt);
+	 fprintf(log, "%d %9llu\n", mp_count_bits(&a), tt);
+	 fflush(log);
       }
       fclose(log);
 
-      log = fopen((ix==0)?"logs/sqr.log":"logs/sqr_kara.log", "w");
-      for (cnt = 4; cnt <= 288; cnt += 2) {
-         SLEEP;
-         mp_rand(&a, cnt);
-         rr = 0;
-         tt = -1;
-         do {
-            gg = TIMFUNC();
-            DO(mp_sqr(&a, &b));
-            gg = (TIMFUNC() - gg)>>1;
-            if (tt > gg) tt = gg;
-         } while (++rr < 100);
-         printf("Squaring\t%4d-bit => %9llu/sec, %9llu cycles\n", mp_count_bits(&a), CLK_PER_SEC/tt, tt);
-         fprintf(log, "%d %9llu\n", mp_count_bits(&a), tt);  fflush(log);
+      log = fopen((ix == 0) ? "logs/sqr.log" : "logs/sqr_kara.log", "w");
+      for (cnt = 4; cnt <= 10240 / DIGIT_BIT; cnt += 2) {
+	 SLEEP;
+	 mp_rand(&a, cnt);
+	 rr = 0;
+	 tt = -1;
+	 do {
+	    gg = TIMFUNC();
+	    DO(mp_sqr(&a, &b));
+	    gg = (TIMFUNC() - gg) >> 1;
+	    if (tt > gg)
+	       tt = gg;
+	 } while (++rr < 100);
+	 printf("Squaring\t%4d-bit => %9llu/sec, %9llu cycles\n",
+		mp_count_bits(&a), CLK_PER_SEC / tt, tt);
+	 fprintf(log, "%d %9llu\n", mp_count_bits(&a), tt);
+	 fflush(log);
       }
       fclose(log);
 
    }
+ exptmod:
 
-  {
+   {
       char *primes[] = {
-         /* 2K moduli mersenne primes */
-         "6864797660130609714981900799081393217269435300143305409394463459185543183397656052122559640661454554977296311391480858037121987999716643812574028291115057151",
-         "531137992816767098689588206552468627329593117727031923199444138200403559860852242739162502265229285668889329486246501015346579337652707239409519978766587351943831270835393219031728127",
-         "10407932194664399081925240327364085538615262247266704805319112350403608059673360298012239441732324184842421613954281007791383566248323464908139906605677320762924129509389220345773183349661583550472959420547689811211693677147548478866962501384438260291732348885311160828538416585028255604666224831890918801847068222203140521026698435488732958028878050869736186900714720710555703168729087",
-         "1475979915214180235084898622737381736312066145333169775147771216478570297878078949377407337049389289382748507531496480477281264838760259191814463365330269540496961201113430156902396093989090226259326935025281409614983499388222831448598601834318536230923772641390209490231836446899608210795482963763094236630945410832793769905399982457186322944729636418890623372171723742105636440368218459649632948538696905872650486914434637457507280441823676813517852099348660847172579408422316678097670224011990280170474894487426924742108823536808485072502240519452587542875349976558572670229633962575212637477897785501552646522609988869914013540483809865681250419497686697771007",
-         "259117086013202627776246767922441530941818887553125427303974923161874019266586362086201209516800483406550695241733194177441689509238807017410377709597512042313066624082916353517952311186154862265604547691127595848775610568757931191017711408826252153849035830401185072116424747461823031471398340229288074545677907941037288235820705892351068433882986888616658650280927692080339605869308790500409503709875902119018371991620994002568935113136548829739112656797303241986517250116412703509705427773477972349821676443446668383119322540099648994051790241624056519054483690809616061625743042361721863339415852426431208737266591962061753535748892894599629195183082621860853400937932839420261866586142503251450773096274235376822938649407127700846077124211823080804139298087057504713825264571448379371125032081826126566649084251699453951887789613650248405739378594599444335231188280123660406262468609212150349937584782292237144339628858485938215738821232393687046160677362909315071",
-         "190797007524439073807468042969529173669356994749940177394741882673528979787005053706368049835514900244303495954950709725762186311224148828811920216904542206960744666169364221195289538436845390250168663932838805192055137154390912666527533007309292687539092257043362517857366624699975402375462954490293259233303137330643531556539739921926201438606439020075174723029056838272505051571967594608350063404495977660656269020823960825567012344189908927956646011998057988548630107637380993519826582389781888135705408653045219655801758081251164080554609057468028203308718724654081055323215860189611391296030471108443146745671967766308925858547271507311563765171008318248647110097614890313562856541784154881743146033909602737947385055355960331855614540900081456378659068370317267696980001187750995491090350108417050917991562167972281070161305972518044872048331306383715094854938415738549894606070722584737978176686422134354526989443028353644037187375385397838259511833166416134323695660367676897722287918773420968982326089026150031515424165462111337527431154890666327374921446276833564519776797633875503548665093914556482031482248883127023777039667707976559857333357013727342079099064400455741830654320379350833236245819348824064783585692924881021978332974949906122664421376034687815350484991",
-
-         /* DR moduli */
-         "14059105607947488696282932836518693308967803494693489478439861164411992439598399594747002144074658928593502845729752797260025831423419686528151609940203368612079",
-         "101745825697019260773923519755878567461315282017759829107608914364075275235254395622580447400994175578963163918967182013639660669771108475957692810857098847138903161308502419410142185759152435680068435915159402496058513611411688900243039",
-         "736335108039604595805923406147184530889923370574768772191969612422073040099331944991573923112581267542507986451953227192970402893063850485730703075899286013451337291468249027691733891486704001513279827771740183629161065194874727962517148100775228363421083691764065477590823919364012917984605619526140821797602431",
-         "38564998830736521417281865696453025806593491967131023221754800625044118265468851210705360385717536794615180260494208076605798671660719333199513807806252394423283413430106003596332513246682903994829528690198205120921557533726473585751382193953592127439965050261476810842071573684505878854588706623484573925925903505747545471088867712185004135201289273405614415899438276535626346098904241020877974002916168099951885406379295536200413493190419727789712076165162175783",
-         "542189391331696172661670440619180536749994166415993334151601745392193484590296600979602378676624808129613777993466242203025054573692562689251250471628358318743978285860720148446448885701001277560572526947619392551574490839286458454994488665744991822837769918095117129546414124448777033941223565831420390846864429504774477949153794689948747680362212954278693335653935890352619041936727463717926744868338358149568368643403037768649616778526013610493696186055899318268339432671541328195724261329606699831016666359440874843103020666106568222401047720269951530296879490444224546654729111504346660859907296364097126834834235287147",
-         "1487259134814709264092032648525971038895865645148901180585340454985524155135260217788758027400478312256339496385275012465661575576202252063145698732079880294664220579764848767704076761853197216563262660046602703973050798218246170835962005598561669706844469447435461092542265792444947706769615695252256130901271870341005768912974433684521436211263358097522726462083917939091760026658925757076733484173202927141441492573799914240222628795405623953109131594523623353044898339481494120112723445689647986475279242446083151413667587008191682564376412347964146113898565886683139407005941383669325997475076910488086663256335689181157957571445067490187939553165903773554290260531009121879044170766615232300936675369451260747671432073394867530820527479172464106442450727640226503746586340279816318821395210726268291535648506190714616083163403189943334431056876038286530365757187367147446004855912033137386225053275419626102417236133948503",
-         "1095121115716677802856811290392395128588168592409109494900178008967955253005183831872715423151551999734857184538199864469605657805519106717529655044054833197687459782636297255219742994736751541815269727940751860670268774903340296040006114013971309257028332849679096824800250742691718610670812374272414086863715763724622797509437062518082383056050144624962776302147890521249477060215148275163688301275847155316042279405557632639366066847442861422164832655874655824221577849928863023018366835675399949740429332468186340518172487073360822220449055340582568461568645259954873303616953776393853174845132081121976327462740354930744487429617202585015510744298530101547706821590188733515880733527449780963163909830077616357506845523215289297624086914545378511082534229620116563260168494523906566709418166011112754529766183554579321224940951177394088465596712620076240067370589036924024728375076210477267488679008016579588696191194060127319035195370137160936882402244399699172017835144537488486396906144217720028992863941288217185353914991583400421682751000603596655790990815525126154394344641336397793791497068253936771017031980867706707490224041075826337383538651825493679503771934836094655802776331664261631740148281763487765852746577808019633679",
-
-         /* generic unrestricted moduli */
-         "17933601194860113372237070562165128350027320072176844226673287945873370751245439587792371960615073855669274087805055507977323024886880985062002853331424203",
-         "2893527720709661239493896562339544088620375736490408468011883030469939904368086092336458298221245707898933583190713188177399401852627749210994595974791782790253946539043962213027074922559572312141181787434278708783207966459019479487",
-         "347743159439876626079252796797422223177535447388206607607181663903045907591201940478223621722118173270898487582987137708656414344685816179420855160986340457973820182883508387588163122354089264395604796675278966117567294812714812796820596564876450716066283126720010859041484786529056457896367683122960411136319",
-         "47266428956356393164697365098120418976400602706072312735924071745438532218237979333351774907308168340693326687317443721193266215155735814510792148768576498491199122744351399489453533553203833318691678263241941706256996197460424029012419012634671862283532342656309677173602509498417976091509154360039893165037637034737020327399910409885798185771003505320583967737293415979917317338985837385734747478364242020380416892056650841470869294527543597349250299539682430605173321029026555546832473048600327036845781970289288898317888427517364945316709081173840186150794397479045034008257793436817683392375274635794835245695887",
-         "436463808505957768574894870394349739623346440601945961161254440072143298152040105676491048248110146278752857839930515766167441407021501229924721335644557342265864606569000117714935185566842453630868849121480179691838399545644365571106757731317371758557990781880691336695584799313313687287468894148823761785582982549586183756806449017542622267874275103877481475534991201849912222670102069951687572917937634467778042874315463238062009202992087620963771759666448266532858079402669920025224220613419441069718482837399612644978839925207109870840278194042158748845445131729137117098529028886770063736487420613144045836803985635654192482395882603511950547826439092832800532152534003936926017612446606135655146445620623395788978726744728503058670046885876251527122350275750995227",
-         "11424167473351836398078306042624362277956429440521137061889702611766348760692206243140413411077394583180726863277012016602279290144126785129569474909173584789822341986742719230331946072730319555984484911716797058875905400999504305877245849119687509023232790273637466821052576859232452982061831009770786031785669030271542286603956118755585683996118896215213488875253101894663403069677745948305893849505434201763745232895780711972432011344857521691017896316861403206449421332243658855453435784006517202894181640562433575390821384210960117518650374602256601091379644034244332285065935413233557998331562749140202965844219336298970011513882564935538704289446968322281451907487362046511461221329799897350993370560697505809686438782036235372137015731304779072430260986460269894522159103008260495503005267165927542949439526272736586626709581721032189532726389643625590680105784844246152702670169304203783072275089194754889511973916207",
-         "1214855636816562637502584060163403830270705000634713483015101384881871978446801224798536155406895823305035467591632531067547890948695117172076954220727075688048751022421198712032848890056357845974246560748347918630050853933697792254955890439720297560693579400297062396904306270145886830719309296352765295712183040773146419022875165382778007040109957609739589875590885701126197906063620133954893216612678838507540777138437797705602453719559017633986486649523611975865005712371194067612263330335590526176087004421363598470302731349138773205901447704682181517904064735636518462452242791676541725292378925568296858010151852326316777511935037531017413910506921922450666933202278489024521263798482237150056835746454842662048692127173834433089016107854491097456725016327709663199738238442164843147132789153725513257167915555162094970853584447993125488607696008169807374736711297007473812256272245489405898470297178738029484459690836250560495461579533254473316340608217876781986188705928270735695752830825527963838355419762516246028680280988020401914551825487349990306976304093109384451438813251211051597392127491464898797406789175453067960072008590614886532333015881171367104445044718144312416815712216611576221546455968770801413440778423979",
-         NULL
+	 /* 2K large moduli */
+	 "179769313486231590772930519078902473361797697894230657273430081157732675805500963132708477322407536021120113879871393357658789768814416622492847430639474124377767893424865485276302219601246094119453082952085005768838150682342462881473913110540827237163350510684586239334100047359817950870678242457666208137217",
+	 "32317006071311007300714876688669951960444102669715484032130345427524655138867890893197201411522913463688717960921898019494119559150490921095088152386448283120630877367300996091750197750389652106796057638384067568276792218642619756161838094338476170470581645852036305042887575891541065808607552399123930385521914333389668342420684974786564569494856176035326322058077805659331026192708460314150258592864177116725943603718461857357598351152301645904403697613233287231227125684710820209725157101726931323469678542580656697935045997268352998638099733077152121140120031150424541696791951097529546801429027668869927491725169",
+	 "1044388881413152506691752710716624382579964249047383780384233483283953907971557456848826811934997558340890106714439262837987573438185793607263236087851365277945956976543709998340361590134383718314428070011855946226376318839397712745672334684344586617496807908705803704071284048740118609114467977783598029006686938976881787785946905630190260940599579453432823469303026696443059025015972399867714215541693835559885291486318237914434496734087811872639496475100189041349008417061675093668333850551032972088269550769983616369411933015213796825837188091833656751221318492846368125550225998300412344784862595674492194617023806505913245610825731835380087608622102834270197698202313169017678006675195485079921636419370285375124784014907159135459982790513399611551794271106831134090584272884279791554849782954323534517065223269061394905987693002122963395687782878948440616007412945674919823050571642377154816321380631045902916136926708342856440730447899971901781465763473223850267253059899795996090799469201774624817718449867455659250178329070473119433165550807568221846571746373296884912819520317457002440926616910874148385078411929804522981857338977648103126085902995208257421855249796721729039744118165938433694823325696642096892124547425283",
+	 /* 2K moduli mersenne primes */
+	 "6864797660130609714981900799081393217269435300143305409394463459185543183397656052122559640661454554977296311391480858037121987999716643812574028291115057151",
+	 "531137992816767098689588206552468627329593117727031923199444138200403559860852242739162502265229285668889329486246501015346579337652707239409519978766587351943831270835393219031728127",
+	 "10407932194664399081925240327364085538615262247266704805319112350403608059673360298012239441732324184842421613954281007791383566248323464908139906605677320762924129509389220345773183349661583550472959420547689811211693677147548478866962501384438260291732348885311160828538416585028255604666224831890918801847068222203140521026698435488732958028878050869736186900714720710555703168729087",
+	 "1475979915214180235084898622737381736312066145333169775147771216478570297878078949377407337049389289382748507531496480477281264838760259191814463365330269540496961201113430156902396093989090226259326935025281409614983499388222831448598601834318536230923772641390209490231836446899608210795482963763094236630945410832793769905399982457186322944729636418890623372171723742105636440368218459649632948538696905872650486914434637457507280441823676813517852099348660847172579408422316678097670224011990280170474894487426924742108823536808485072502240519452587542875349976558572670229633962575212637477897785501552646522609988869914013540483809865681250419497686697771007",
+	 "259117086013202627776246767922441530941818887553125427303974923161874019266586362086201209516800483406550695241733194177441689509238807017410377709597512042313066624082916353517952311186154862265604547691127595848775610568757931191017711408826252153849035830401185072116424747461823031471398340229288074545677907941037288235820705892351068433882986888616658650280927692080339605869308790500409503709875902119018371991620994002568935113136548829739112656797303241986517250116412703509705427773477972349821676443446668383119322540099648994051790241624056519054483690809616061625743042361721863339415852426431208737266591962061753535748892894599629195183082621860853400937932839420261866586142503251450773096274235376822938649407127700846077124211823080804139298087057504713825264571448379371125032081826126566649084251699453951887789613650248405739378594599444335231188280123660406262468609212150349937584782292237144339628858485938215738821232393687046160677362909315071",
+	 "190797007524439073807468042969529173669356994749940177394741882673528979787005053706368049835514900244303495954950709725762186311224148828811920216904542206960744666169364221195289538436845390250168663932838805192055137154390912666527533007309292687539092257043362517857366624699975402375462954490293259233303137330643531556539739921926201438606439020075174723029056838272505051571967594608350063404495977660656269020823960825567012344189908927956646011998057988548630107637380993519826582389781888135705408653045219655801758081251164080554609057468028203308718724654081055323215860189611391296030471108443146745671967766308925858547271507311563765171008318248647110097614890313562856541784154881743146033909602737947385055355960331855614540900081456378659068370317267696980001187750995491090350108417050917991562167972281070161305972518044872048331306383715094854938415738549894606070722584737978176686422134354526989443028353644037187375385397838259511833166416134323695660367676897722287918773420968982326089026150031515424165462111337527431154890666327374921446276833564519776797633875503548665093914556482031482248883127023777039667707976559857333357013727342079099064400455741830654320379350833236245819348824064783585692924881021978332974949906122664421376034687815350484991",
+
+	 /* DR moduli */
+	 "14059105607947488696282932836518693308967803494693489478439861164411992439598399594747002144074658928593502845729752797260025831423419686528151609940203368612079",
+	 "101745825697019260773923519755878567461315282017759829107608914364075275235254395622580447400994175578963163918967182013639660669771108475957692810857098847138903161308502419410142185759152435680068435915159402496058513611411688900243039",
+	 "736335108039604595805923406147184530889923370574768772191969612422073040099331944991573923112581267542507986451953227192970402893063850485730703075899286013451337291468249027691733891486704001513279827771740183629161065194874727962517148100775228363421083691764065477590823919364012917984605619526140821797602431",
+	 "38564998830736521417281865696453025806593491967131023221754800625044118265468851210705360385717536794615180260494208076605798671660719333199513807806252394423283413430106003596332513246682903994829528690198205120921557533726473585751382193953592127439965050261476810842071573684505878854588706623484573925925903505747545471088867712185004135201289273405614415899438276535626346098904241020877974002916168099951885406379295536200413493190419727789712076165162175783",
+	 "542189391331696172661670440619180536749994166415993334151601745392193484590296600979602378676624808129613777993466242203025054573692562689251250471628358318743978285860720148446448885701001277560572526947619392551574490839286458454994488665744991822837769918095117129546414124448777033941223565831420390846864429504774477949153794689948747680362212954278693335653935890352619041936727463717926744868338358149568368643403037768649616778526013610493696186055899318268339432671541328195724261329606699831016666359440874843103020666106568222401047720269951530296879490444224546654729111504346660859907296364097126834834235287147",
+	 "1487259134814709264092032648525971038895865645148901180585340454985524155135260217788758027400478312256339496385275012465661575576202252063145698732079880294664220579764848767704076761853197216563262660046602703973050798218246170835962005598561669706844469447435461092542265792444947706769615695252256130901271870341005768912974433684521436211263358097522726462083917939091760026658925757076733484173202927141441492573799914240222628795405623953109131594523623353044898339481494120112723445689647986475279242446083151413667587008191682564376412347964146113898565886683139407005941383669325997475076910488086663256335689181157957571445067490187939553165903773554290260531009121879044170766615232300936675369451260747671432073394867530820527479172464106442450727640226503746586340279816318821395210726268291535648506190714616083163403189943334431056876038286530365757187367147446004855912033137386225053275419626102417236133948503",
+	 "1095121115716677802856811290392395128588168592409109494900178008967955253005183831872715423151551999734857184538199864469605657805519106717529655044054833197687459782636297255219742994736751541815269727940751860670268774903340296040006114013971309257028332849679096824800250742691718610670812374272414086863715763724622797509437062518082383056050144624962776302147890521249477060215148275163688301275847155316042279405557632639366066847442861422164832655874655824221577849928863023018366835675399949740429332468186340518172487073360822220449055340582568461568645259954873303616953776393853174845132081121976327462740354930744487429617202585015510744298530101547706821590188733515880733527449780963163909830077616357506845523215289297624086914545378511082534229620116563260168494523906566709418166011112754529766183554579321224940951177394088465596712620076240067370589036924024728375076210477267488679008016579588696191194060127319035195370137160936882402244399699172017835144537488486396906144217720028992863941288217185353914991583400421682751000603596655790990815525126154394344641336397793791497068253936771017031980867706707490224041075826337383538651825493679503771934836094655802776331664261631740148281763487765852746577808019633679",
+
+	 /* generic unrestricted moduli */
+	 "17933601194860113372237070562165128350027320072176844226673287945873370751245439587792371960615073855669274087805055507977323024886880985062002853331424203",
+	 "2893527720709661239493896562339544088620375736490408468011883030469939904368086092336458298221245707898933583190713188177399401852627749210994595974791782790253946539043962213027074922559572312141181787434278708783207966459019479487",
+	 "347743159439876626079252796797422223177535447388206607607181663903045907591201940478223621722118173270898487582987137708656414344685816179420855160986340457973820182883508387588163122354089264395604796675278966117567294812714812796820596564876450716066283126720010859041484786529056457896367683122960411136319",
+	 "47266428956356393164697365098120418976400602706072312735924071745438532218237979333351774907308168340693326687317443721193266215155735814510792148768576498491199122744351399489453533553203833318691678263241941706256996197460424029012419012634671862283532342656309677173602509498417976091509154360039893165037637034737020327399910409885798185771003505320583967737293415979917317338985837385734747478364242020380416892056650841470869294527543597349250299539682430605173321029026555546832473048600327036845781970289288898317888427517364945316709081173840186150794397479045034008257793436817683392375274635794835245695887",
+	 "436463808505957768574894870394349739623346440601945961161254440072143298152040105676491048248110146278752857839930515766167441407021501229924721335644557342265864606569000117714935185566842453630868849121480179691838399545644365571106757731317371758557990781880691336695584799313313687287468894148823761785582982549586183756806449017542622267874275103877481475534991201849912222670102069951687572917937634467778042874315463238062009202992087620963771759666448266532858079402669920025224220613419441069718482837399612644978839925207109870840278194042158748845445131729137117098529028886770063736487420613144045836803985635654192482395882603511950547826439092832800532152534003936926017612446606135655146445620623395788978726744728503058670046885876251527122350275750995227",
+	 "11424167473351836398078306042624362277956429440521137061889702611766348760692206243140413411077394583180726863277012016602279290144126785129569474909173584789822341986742719230331946072730319555984484911716797058875905400999504305877245849119687509023232790273637466821052576859232452982061831009770786031785669030271542286603956118755585683996118896215213488875253101894663403069677745948305893849505434201763745232895780711972432011344857521691017896316861403206449421332243658855453435784006517202894181640562433575390821384210960117518650374602256601091379644034244332285065935413233557998331562749140202965844219336298970011513882564935538704289446968322281451907487362046511461221329799897350993370560697505809686438782036235372137015731304779072430260986460269894522159103008260495503005267165927542949439526272736586626709581721032189532726389643625590680105784844246152702670169304203783072275089194754889511973916207",
+	 "1214855636816562637502584060163403830270705000634713483015101384881871978446801224798536155406895823305035467591632531067547890948695117172076954220727075688048751022421198712032848890056357845974246560748347918630050853933697792254955890439720297560693579400297062396904306270145886830719309296352765295712183040773146419022875165382778007040109957609739589875590885701126197906063620133954893216612678838507540777138437797705602453719559017633986486649523611975865005712371194067612263330335590526176087004421363598470302731349138773205901447704682181517904064735636518462452242791676541725292378925568296858010151852326316777511935037531017413910506921922450666933202278489024521263798482237150056835746454842662048692127173834433089016107854491097456725016327709663199738238442164843147132789153725513257167915555162094970853584447993125488607696008169807374736711297007473812256272245489405898470297178738029484459690836250560495461579533254473316340608217876781986188705928270735695752830825527963838355419762516246028680280988020401914551825487349990306976304093109384451438813251211051597392127491464898797406789175453067960072008590614886532333015881171367104445044718144312416815712216611576221546455968770801413440778423979",
+	 NULL
       };
-   log = fopen("logs/expt.log", "w");
-   logb = fopen("logs/expt_dr.log", "w");
-   logc = fopen("logs/expt_2k.log", "w");
-   for (n = 0; primes[n]; n++) {
-      SLEEP;
-      mp_read_radix(&a, primes[n], 10);
-      mp_zero(&b);
-      for (rr = 0; rr < (unsigned)mp_count_bits(&a); rr++) {
-         mp_mul_2(&b, &b);
-         b.dp[0] |= lbit();
-         b.used  += 1;
-      }
-      mp_sub_d(&a, 1, &c);
-      mp_mod(&b, &c, &b);
-      mp_set(&c, 3);
-         rr = 0;
-         tt = -1;
-         do {
-            gg = TIMFUNC();
-            DO(mp_exptmod(&c, &b, &a, &d));
-            gg = (TIMFUNC() - gg)>>1;
-            if (tt > gg) tt = gg;
-         } while (++rr < 10);
-      mp_sub_d(&a, 1, &e);
-      mp_sub(&e, &b, &b);
-      mp_exptmod(&c, &b, &a, &e);  /* c^(p-1-b) mod a */
-      mp_mulmod(&e, &d, &a, &d);   /* c^b * c^(p-1-b) == c^p-1 == 1 */
-      if (mp_cmp_d(&d, 1)) {
-         printf("Different (%d)!!!\n", mp_count_bits(&a));
-         draw(&d);
-         exit(0);
+      log = fopen("logs/expt.log", "w");
+      logb = fopen("logs/expt_dr.log", "w");
+      logc = fopen("logs/expt_2k.log", "w");
+      logd = fopen("logs/expt_2kl.log", "w");
+      for (n = 0; primes[n]; n++) {
+	 SLEEP;
+	 mp_read_radix(&a, primes[n], 10);
+	 mp_zero(&b);
+	 for (rr = 0; rr < (unsigned) mp_count_bits(&a); rr++) {
+	    mp_mul_2(&b, &b);
+	    b.dp[0] |= lbit();
+	    b.used += 1;
+	 }
+	 mp_sub_d(&a, 1, &c);
+	 mp_mod(&b, &c, &b);
+	 mp_set(&c, 3);
+	 rr = 0;
+	 tt = -1;
+	 do {
+	    gg = TIMFUNC();
+	    DO(mp_exptmod(&c, &b, &a, &d));
+	    gg = (TIMFUNC() - gg) >> 1;
+	    if (tt > gg)
+	       tt = gg;
+	 } while (++rr < 10);
+	 mp_sub_d(&a, 1, &e);
+	 mp_sub(&e, &b, &b);
+	 mp_exptmod(&c, &b, &a, &e);	/* c^(p-1-b) mod a */
+	 mp_mulmod(&e, &d, &a, &d);	/* c^b * c^(p-1-b) == c^p-1 == 1 */
+	 if (mp_cmp_d(&d, 1)) {
+	    printf("Different (%d)!!!\n", mp_count_bits(&a));
+	    draw(&d);
+	    exit(0);
+	 }
+	 printf("Exponentiating\t%4d-bit => %9llu/sec, %9llu cycles\n",
+		mp_count_bits(&a), CLK_PER_SEC / tt, tt);
+	 fprintf(n < 4 ? logd : (n < 9) ? logc : (n < 16) ? logb : log,
+		 "%d %9llu\n", mp_count_bits(&a), tt);
       }
-      printf("Exponentiating\t%4d-bit => %9llu/sec, %9llu cycles\n", mp_count_bits(&a), CLK_PER_SEC/tt, tt);
-      fprintf((n < 6) ? logc : (n < 13) ? logb : log, "%d %9llu\n", mp_count_bits(&a), tt);
-   }
    }
    fclose(log);
    fclose(logb);
    fclose(logc);
+   fclose(logd);
 
    log = fopen("logs/invmod.log", "w");
    for (cnt = 4; cnt <= 128; cnt += 4) {
@@ -260,28 +287,29 @@ int main(void)
       mp_rand(&b, cnt);
 
       do {
-         mp_add_d(&b, 1, &b);
-         mp_gcd(&a, &b, &c);
+	 mp_add_d(&b, 1, &b);
+	 mp_gcd(&a, &b, &c);
       } while (mp_cmp_d(&c, 1) != MP_EQ);
 
-         rr = 0;
-         tt = -1;
+      rr = 0;
+      tt = -1;
       do {
-         gg = TIMFUNC();
-         DO(mp_invmod(&b, &a, &c));
-         gg = (TIMFUNC() - gg)>>1;
-         if (tt > gg) tt = gg;
+	 gg = TIMFUNC();
+	 DO(mp_invmod(&b, &a, &c));
+	 gg = (TIMFUNC() - gg) >> 1;
+	 if (tt > gg)
+	    tt = gg;
       } while (++rr < 1000);
       mp_mulmod(&b, &c, &a, &d);
       if (mp_cmp_d(&d, 1) != MP_EQ) {
-         printf("Failed to invert\n");
-         return 0;
+	 printf("Failed to invert\n");
+	 return 0;
       }
-      printf("Inverting mod\t%4d-bit => %9llu/sec, %9llu cycles\n", mp_count_bits(&a), CLK_PER_SEC/tt, tt);
-      fprintf(log, "%d %9llu\n", cnt*DIGIT_BIT, tt);
+      printf("Inverting mod\t%4d-bit => %9llu/sec, %9llu cycles\n",
+	     mp_count_bits(&a), CLK_PER_SEC / tt, tt);
+      fprintf(log, "%d %9llu\n", cnt * DIGIT_BIT, tt);
    }
    fclose(log);
 
    return 0;
 }
-
diff --git a/libtommath/dep.pl b/libtommath/dep.pl
index 22266e3..c39e27e 100644
--- a/libtommath/dep.pl
+++ b/libtommath/dep.pl
@@ -13,6 +13,8 @@ print CLASS "#if !(defined(LTM1) && defined(LTM2) && defined(LTM3))\n#if defined
 foreach my $filename (glob "bn*.c") {
    my $define = $filename;
 
+print "Processing $filename\n";
+
    # convert filename to upper case so we can use it as a define 
    $define =~ tr/[a-z]/[A-Z]/;
    $define =~ tr/\./_/;
diff --git a/libtommath/etc/timer.asm b/libtommath/etc/timer.asm
index 35890d9..326a947 100644
--- a/libtommath/etc/timer.asm
+++ b/libtommath/etc/timer.asm
@@ -1,37 +1,37 @@
-; x86 timer in NASM

-;

-; Tom St Denis, tomstdenis@iahu.ca

-[bits 32]

-[section .data]

-time dd 0, 0

-

-[section .text]

-

-%ifdef USE_ELF

-[global t_start]

-t_start:

-%else

-[global _t_start]

-_t_start:

-%endif

-   push edx

-   push eax

-   rdtsc

-   mov [time+0],edx

-   mov [time+4],eax

-   pop eax

-   pop edx

-   ret

-   

-%ifdef USE_ELF

-[global t_read]

-t_read:

-%else

-[global _t_read]

-_t_read:

-%endif

-   rdtsc

-   sub eax,[time+4]

-   sbb edx,[time+0]

-   ret

+; x86 timer in NASM
+;
+; Tom St Denis, tomstdenis@iahu.ca
+[bits 32]
+[section .data]
+time dd 0, 0
+
+[section .text]
+
+%ifdef USE_ELF
+[global t_start]
+t_start:
+%else
+[global _t_start]
+_t_start:
+%endif
+   push edx
+   push eax
+   rdtsc
+   mov [time+0],edx
+   mov [time+4],eax
+   pop eax
+   pop edx
+   ret
+   
+%ifdef USE_ELF
+[global t_read]
+t_read:
+%else
+[global _t_read]
+_t_read:
+%endif
+   rdtsc
+   sub eax,[time+4]
+   sbb edx,[time+0]
+   ret
    
\ No newline at end of file
diff --git a/libtommath/etc/tune.c b/libtommath/etc/tune.c
index 14aace2..d054d10 100644
--- a/libtommath/etc/tune.c
+++ b/libtommath/etc/tune.c
@@ -10,13 +10,44 @@
  */
 #define TIMES (1UL<<14UL)
 
+/* RDTSC from Scott Duplichan */
+static ulong64 TIMFUNC (void)
+   {
+   #if defined __GNUC__
+      #if defined(__i386__) || defined(__x86_64__)
+         unsigned long long a;
+         __asm__ __volatile__ ("rdtsc\nmovl %%eax,%0\nmovl %%edx,4+%0\n"::"m"(a):"%eax","%edx");
+         return a;
+      #else /* gcc-IA64 version */
+         unsigned long result;
+         __asm__ __volatile__("mov %0=ar.itc" : "=r"(result) :: "memory");
+         while (__builtin_expect ((int) result == -1, 0))
+         __asm__ __volatile__("mov %0=ar.itc" : "=r"(result) :: "memory");
+         return result;
+      #endif
+
+   // Microsoft and Intel Windows compilers
+   #elif defined _M_IX86
+     __asm rdtsc
+   #elif defined _M_AMD64
+     return __rdtsc ();
+   #elif defined _M_IA64
+     #if defined __INTEL_COMPILER
+       #include <ia64intrin.h>
+     #endif
+      return __getReg (3116);
+   #else
+     #error need rdtsc function for this build
+   #endif
+   }
+
 
 #ifndef X86_TIMER
 
 /* generic ISO C timer */
 ulong64 LBL_T;
-void t_start(void) { LBL_T = clock(); }
-ulong64 t_read(void) { return clock() - LBL_T; }
+void t_start(void) { LBL_T = TIMFUNC(); }
+ulong64 t_read(void) { return TIMFUNC() - LBL_T; }
 
 #else
 extern void t_start(void);
diff --git a/libtommath/logs/README b/libtommath/logs/README
index ea20c81..965e7c8 100644
--- a/libtommath/logs/README
+++ b/libtommath/logs/README
@@ -1,13 +1,13 @@
-To use the pretty graphs you have to first build/run the ltmtest from the root directory of the package.  

-Todo this type 

-

-make timing ; ltmtest

-

-in the root.  It will run for a while [about ten minutes on most PCs] and produce a series of .log files in logs/.

-

-After doing that run "gnuplot graphs.dem" to make the PNGs.  If you managed todo that all so far just open index.html to view

-them all :-)

-

-Have fun

-

+To use the pretty graphs you have to first build/run the ltmtest from the root directory of the package.  
+Todo this type 
+
+make timing ; ltmtest
+
+in the root.  It will run for a while [about ten minutes on most PCs] and produce a series of .log files in logs/.
+
+After doing that run "gnuplot graphs.dem" to make the PNGs.  If you managed todo that all so far just open index.html to view
+them all :-)
+
+Have fun
+
 Tom
\ No newline at end of file
diff --git a/libtommath/logs/add.log b/libtommath/logs/add.log
index fa11039..43503ac 100644
--- a/libtommath/logs/add.log
+++ b/libtommath/logs/add.log
@@ -1,10 +1,10 @@
-480        88
-960       113
-1440       138
-1920       163
-2400       202
-2880       226
-3360       251
+480        87
+960       111
+1440       135
+1920       159
+2400       200
+2880       224
+3360       248
 3840       272
 4320       296
 4800       320
diff --git a/libtommath/logs/addsub.png b/libtommath/logs/addsub.png
index a5679ac..441c7b2 100644
--- a/libtommath/logs/addsub.png
+++ b/libtommath/logs/addsub.png
diff --git a/libtommath/logs/expt.log b/libtommath/logs/expt.log
index e65e927..920ba55 100644
--- a/libtommath/logs/expt.log
+++ b/libtommath/logs/expt.log
@@ -1,7 +1,7 @@
-513   1499509
-769   3682671
-1025   8098887
-2049  49332743
-2561  89647783
-3073 149440713
-4097 326135364
+513   1489160
+769   3688476
+1025   8162061
+2049  49260015
+2561  89579052
+3073 148797060
+4097 324449263
diff --git a/libtommath/logs/expt.png b/libtommath/logs/expt.png
index 9ee8bb7..d779cc5 100644
--- a/libtommath/logs/expt.png
+++ b/libtommath/logs/expt.png
diff --git a/libtommath/logs/expt_2k.log b/libtommath/logs/expt_2k.log
index d106280..56b50db 100644
--- a/libtommath/logs/expt_2k.log
+++ b/libtommath/logs/expt_2k.log
@@ -1,6 +1,5 @@
-521   1423346
-607   1841305
-1279   8375656
-2203  34104708
-3217  83830729
-4253 167916804
+607   2272809
+1279   9557382
+2203  36250309
+3217  87666486
+4253 174168369
diff --git a/libtommath/logs/expt_dr.log b/libtommath/logs/expt_dr.log
index 6cfc874..eb93fc9 100644
--- a/libtommath/logs/expt_dr.log
+++ b/libtommath/logs/expt_dr.log
@@ -1,7 +1,7 @@
-532   1803110
-784   3607375
-1036   6089790
-1540  14739797
-2072  33251589
-3080  82794331
-4116 165212734
+532   1989592
+784   3898697
+1036   6519700
+1540  15676650
+2072  33128187
+3080  82963362
+4116 168358337
diff --git a/libtommath/logs/invmod.png b/libtommath/logs/invmod.png
index 0a8a4ad..9dcd7d8 100644
--- a/libtommath/logs/invmod.png
+++ b/libtommath/logs/invmod.png
diff --git a/libtommath/logs/mult.log b/libtommath/logs/mult.log
index 864de46..33563fc 100644
--- a/libtommath/logs/mult.log
+++ b/libtommath/logs/mult.log
@@ -1,143 +1,84 @@
-271       580
-390       861
-511      1177
-630      1598
-749      2115
-871      2670
-991      3276
-1111      3987
-1231      4722
-1351      5474
-1471      6281
-1589      7126
-1710      8114
-1831      8988
-1946     10038
-2071     10995
-2188     12286
-2310     13152
-2430     14480
-2549     15521
-2671     17171
-2790     18081
-2911     19754
-3031     20809
-3150     22849
-3269     23757
-3391     25772
-3508     26832
-3631     29304
-3750     30149
-3865     32581
-3988     33644
-4111     36565
-4231     37309
-4351     40152
-4471     41188
-4590     44658
-4710     45256
-4827     48538
-4951     49490
-5070     53472
-5190     53902
-5308     57619
-5431     58509
-5550     63044
-5664     63333
-5791     67542
-5911     68279
-6028     73477
-6150     73475
-6271     78189
-6390     78842
-6510     84691
-6631     84444
-6751     89721
-6871     90186
-6991     96665
-7111     96119
-7231    101937
-7350    102212
-7471    109439
-7591    108491
-7709    114965
-7829    115025
-7951    123002
-8071    121630
-8190    128725
-8311    128536
-8430    137298
-8550    135568
-8671    143265
-8791    142793
-8911    152432
-9030    150202
-9151    158616
-9271    157848
-9391    168374
-9511    165651
-9627    174775
-9750    173375
-9871    185067
-9985    181845
-10111    191708
-10229    190239
-10351    202585
-10467    198704
-10591    209193
-10711    207322
-10831    220842
-10950    215882
-11071    227761
-11191    225501
-11311    239669
-11430    234809
-11550    243511
-11671    255947
-11791    255243
-11906    267828
-12029    263437
-12149    276571
-12270    275579
-12390    288963
-12510    284001
-12631    298196
-12751    297018
-12869    310848
-12990    305369
-13111    319086
-13230    318940
-13349    333685
-13471    327495
-13588    343678
-13711    341817
-13831    357181
-13948    350440
-14071    367526
-14189    365330
-14311    381551
-14429    374149
-14549    392203
-14670    389764
-14791    406761
-14910    398652
-15026    417718
-15150    414733
-15269    432759
-15390   1037071
-15511   1053454
-15631   1069198
-15748   1086164
-15871   1112820
-15991   1129676
-16111   1145924
-16230   1163016
-16345   1179911
-16471   1197048
-16586   1214352
-16711   1232095
-16829   1249338
-16947   1266987
-17071   1284181
-17188   1302521
-17311   1320539
+271       555
+390       855
+508      1161
+631      1605
+749      2117
+871      2687
+991      3329
+1108      4084
+1231      4786
+1351      5624
+1470      6392
+1586      7364
+1710      8218
+1830      9255
+1951     10217
+2067     11461
+2191     12463
+2308     13677
+2430     14800
+2551     16232
+2671     17460
+2791     18899
+2902     20247
+3028     21902
+3151     23240
+3267     24927
+3391     26441
+3511     28277
+3631     29838
+3749     31751
+3869     33673
+3989     35431
+4111     37518
+4231     39426
+4349     41504
+4471     43567
+4591     45786
+4711     47876
+4831     50299
+4951     52427
+5071     54785
+5189     57241
+5307     59730
+5431     62194
+5551     64761
+5670     67322
+5789     70073
+5907     72663
+6030     75437
+6151     78242
+6268     81202
+6389     83948
+6509     86985
+6631     89903
+6747     93184
+6869     96044
+6991     99286
+7109    102395
+7229    105917
+7351    108940
+7470    112490
+7589    115702
+7711    119508
+7831    122632
+7951    126410
+8071    129808
+8190    133895
+8311    137146
+8431    141218
+8549    144732
+8667    149131
+8790    152462
+8911    156754
+9030    160479
+9149    165138
+9271    168601
+9391    173185
+9511    176988
+9627    181976
+9751    185539
+9870    190388
+9991    194335
+10110    199605
+10228    203298
diff --git a/libtommath/logs/mult.png b/libtommath/logs/mult.png
index 4f7a4ee..d22e8c8 100644
--- a/libtommath/logs/mult.png
+++ b/libtommath/logs/mult.png
diff --git a/libtommath/logs/mult_kara.log b/libtommath/logs/mult_kara.log
index 086feaf..7136c79 100644
--- a/libtommath/logs/mult_kara.log
+++ b/libtommath/logs/mult_kara.log
@@ -1,33 +1,84 @@
-924     16686
-1146     25334
-1371     35304
-1591     47122
-1820     61500
-2044     75254
-2266     91732
-2492    111656
-2716    129428
-2937    147508
-3164    167758
-3388    188248
-3612    210826
-3836    233814
-4059    256898
-4284    280210
-4508    310372
-4731    333902
-4955    376502
-5179    402854
-5404    432004
-5626    459010
-5849    491868
-6076    520550
-6300    547400
-6524    575968
-6747    608482
-6971    642850
-7196    673670
-7419    710680
-7644    743942
-7868    780394
-8092    817342
+271       560
+391       870
+511      1159
+631      1605
+750      2111
+871      2737
+991      3361
+1111      4054
+1231      4778
+1351      5600
+1471      6404
+1591      7323
+1710      8255
+1831      9239
+1948     10257
+2070     11397
+2190     12531
+2308     13665
+2429     14870
+2550     16175
+2671     17539
+2787     18879
+2911     20350
+3031     21807
+3150     23415
+3270     24897
+3388     26567
+3511     28205
+3627     30076
+3751     31744
+3869     33657
+3991     35425
+4111     37522
+4229     39363
+4351     41503
+4470     43491
+4590     45827
+4711     47795
+4828     50166
+4951     52318
+5070     54911
+5191     57036
+5308     58237
+5431     60248
+5551     62678
+5671     64786
+5791     67294
+5908     69343
+6031     71607
+6151     74166
+6271     76590
+6391     78734
+6511     81175
+6631     83742
+6750     86403
+6868     88873
+6990     91150
+7110     94211
+7228     96922
+7351     99445
+7469    102216
+7589    104968
+7711    108113
+7827    110758
+7950    113714
+8071    116511
+8186    119643
+8310    122679
+8425    125581
+8551    128715
+8669    131778
+8788    135116
+8910    138138
+9031    141628
+9148    144754
+9268    148367
+9391    151551
+9511    155033
+9631    158652
+9751    162125
+9871    165248
+9988    168627
+10111    172427
+10231    176412
diff --git a/libtommath/logs/sqr.log b/libtommath/logs/sqr.log
index 0898342..cd29fc5 100644
--- a/libtommath/logs/sqr.log
+++ b/libtommath/logs/sqr.log
@@ -1,143 +1,84 @@
-271       552
-389       883
-510      1191
-629      1572
-750      1996
-863      2428
-991      2891
-1108      3539
-1231      4182
-1351      4980
-1471      5771
-1590      6551
-1711      7313
-1830      8240
-1951      9184
-2070     10087
-2191     11140
-2311     12111
-2431     13219
-2550     14247
-2669     15353
-2791     16446
-2911     17692
-3029     18848
-3151     20028
-3268     21282
-3391     22696
-3511     23971
-3631     25303
-3751     26675
-3871     28245
-3990     29736
-4111     31124
-4229     32714
-4347     34397
-4471     35877
-4587     37269
-4710     39011
-4831     40884
-4950     42501
-5070     44005
-5191     46026
-5310     48168
-5431     49801
-5551     51385
-5671     53604
-5787     55942
-5910     57757
-6031     59391
-6151     61754
-6271     64234
-6390     66110
-6511     67845
-6627     70474
-6751     73113
-6871     75064
-6990     76940
-7111     79681
-7230     82548
-7351     84597
-7471     86507
-7591     89497
-7711    225216
-7831    232192
-7951    239583
-8071    247302
-8191    255497
-8308    261587
-8431    271490
-8550    279492
-8671    286927
-8790    294680
-8910    302974
-9030    311300
-9150    318635
-9271    326740
-9390    335304
-9511    344297
-9630    352056
-9748    358652
-9870    369723
-9991    379119
-10111    386982
-10231    396075
-10349    404396
-10470    415375
-10590    424146
-10711    433390
-10829    442662
-10950    453238
-11071    462178
-11186    469811
-11311    482529
-11431    493214
-11550    503210
-11671    513486
-11791    524244
-11911    535277
-12031    544872
-12151    555695
-12271    566893
-12391    578385
-12510    588658
-12628    596914
-12751    611324
-12871    623437
-12991    633907
-13110    645605
-13231    657684
-13351    670037
-13471    680939
-13591    693047
-13710    705363
-13829    718178
-13949    727930
-14069    739641
-14190    754817
-14310    768192
-14431    779875
-14551    792655
-14667    802847
-14791    819806
-14911    831684
-15031    844936
-15151    858813
-15270    873037
-15387    882123
-15510    899117
-15631    913465
-15750    927989
-15870    940790
-15991    954948
-16110    969483
-16231    984544
-16350    997837
-16470   1012445
-16590   1027834
-16710   1043032
-16831   1056394
-16951   1071408
-17069   1097263
-17191   1113364
-17306   1123650
+265       562
+389       882
+509      1207
+631      1572
+750      1990
+859      2433
+991      2894
+1109      3555
+1230      4228
+1350      5018
+1471      5805
+1591      6579
+1709      7415
+1829      8329
+1949      9225
+2071     10139
+2188     11239
+2309     12178
+2431     13212
+2551     14294
+2671     15551
+2791     16512
+2911     17718
+3030     18876
+3150     20259
+3270     21374
+3391     22650
+3511     23948
+3631     25493
+3750     26756
+3870     28225
+3989     29705
+4110     31409
+4230     32834
+4351     34327
+4471     35818
+4591     37636
+4711     39228
+4830     40868
+4949     42393
+5070     44541
+5191     46269
+5310     48162
+5429     49728
+5548     51985
+5671     53948
+5791     55885
+5910     57584
+6031     60082
+6150     62239
+6270     64309
+6390     66014
+6511     68766
+6631     71012
+6750     73172
+6871     74952
+6991     77909
+7111     80371
+7231     82666
+7351     84531
+7469     87698
+7589     90318
+7711    225384
+7830    232428
+7950    240009
+8070    246522
+8190    253662
+8310    260961
+8431    269253
+8549    275743
+8671    283769
+8789    290811
+8911    300034
+9030    306873
+9149    315085
+9270    323944
+9390    332390
+9508    337519
+9631    348986
+9749    356904
+9871    367013
+9989    373831
+10108    381033
+10230    393475
diff --git a/libtommath/logs/sqr_kara.log b/libtommath/logs/sqr_kara.log
index cafe458..06355a7 100644
--- a/libtommath/logs/sqr_kara.log
+++ b/libtommath/logs/sqr_kara.log
@@ -1,33 +1,84 @@
-922     11272
-1148     16004
-1370     21958
-1596     28684
-1817     37832
-2044     46386
-2262     56218
-2492     66388
-2716     77478
-2940     89380
-3163    103680
-3385    116274
-3612    135334
-3836    151332
-4057    164938
-4284    183178
-4508    198864
-4731    215222
-4954    231986
-5180    251660
-5404    269414
-5626    288454
-5850    307806
-6076    329458
-6299    347726
-6523    369864
-6748    387832
-6971    413010
-7194    453310
-7415    476936
-7643    497118
-7867    521394
-8091    540224
+271       560
+388       878
+511      1179
+629      1625
+751      1988
+871      2423
+989      2896
+1111      3561
+1231      4209
+1350      5015
+1470      5804
+1591      6556
+1709      7420
+1831      8263
+1951      9173
+2070     10153
+2191     11229
+2310     12167
+2431     13211
+2550     14309
+2671     15524
+2788     16525
+2910     17712
+3028     18822
+3148     20220
+3271     21343
+3391     22652
+3511     23944
+3630     25485
+3750     26778
+3868     28201
+3990     29653
+4111     31393
+4225     32841
+4350     34328
+4471     35786
+4590     37652
+4711     39245
+4830     40876
+4951     42433
+5068     44547
+5191     46321
+5311     48140
+5430     49727
+5550     52034
+5671     53954
+5791     55921
+5908     57597
+6031     60084
+6148     62226
+6270     64295
+6390     66045
+6511     68779
+6629     71003
+6751     73169
+6871     74992
+6991     77895
+7110     80376
+7231     82628
+7351     84468
+7470     87664
+7591     90284
+7711     91352
+7828     93995
+7950     96276
+8071     98691
+8190    101256
+8308    103631
+8431    105222
+8550    108343
+8671    110281
+8787    112764
+8911    115397
+9031    117690
+9151    120266
+9271    122715
+9391    124624
+9510    127937
+9630    130313
+9750    132914
+9871    136129
+9991    138517
+10108    141525
+10231    144225
diff --git a/libtommath/logs/sub.log b/libtommath/logs/sub.log
index a42d91e..9f84fa2 100644
--- a/libtommath/logs/sub.log
+++ b/libtommath/logs/sub.log
@@ -1,16 +1,16 @@
-480        87
-960       114
-1440       139
-1920       159
-2400       204
-2880       228
-3360       250
-3840       273
-4320       300
+480        94
+960       116
+1440       140
+1920       164
+2400       205
+2880       229
+3360       253
+3840       277
+4320       299
 4800       321
-5280       348
-5760       370
-6240       393
-6720       420
-7200       444
-7680       466
+5280       345
+5760       371
+6240       395
+6720       419
+7200       441
+7680       465
diff --git a/libtommath/makefile b/libtommath/makefile
index 164a0ab..17873ee 100644
--- a/libtommath/makefile
+++ b/libtommath/makefile
@@ -3,7 +3,7 @@
 #Tom St Denis
 
 #version of library 
-VERSION=0.33
+VERSION=0.35
 
 CFLAGS  +=  -I./ -Wall -W -Wshadow -Wsign-compare
 
@@ -57,11 +57,13 @@ bn_mp_prime_is_prime.o bn_mp_prime_next_prime.o bn_mp_dr_reduce.o \
 bn_mp_dr_is_modulus.o bn_mp_dr_setup.o bn_mp_reduce_setup.o \
 bn_mp_toom_mul.o bn_mp_toom_sqr.o bn_mp_div_3.o bn_s_mp_exptmod.o \
 bn_mp_reduce_2k.o bn_mp_reduce_is_2k.o bn_mp_reduce_2k_setup.o \
+bn_mp_reduce_2k_l.o bn_mp_reduce_is_2k_l.o bn_mp_reduce_2k_setup_l.o \
 bn_mp_radix_smap.o bn_mp_read_radix.o bn_mp_toradix.o bn_mp_radix_size.o \
 bn_mp_fread.o bn_mp_fwrite.o bn_mp_cnt_lsb.o bn_error.o \
 bn_mp_init_multi.o bn_mp_clear_multi.o bn_mp_exteuclid.o bn_mp_toradix_n.o \
 bn_mp_prime_random_ex.o bn_mp_get_int.o bn_mp_sqrt.o bn_mp_is_square.o bn_mp_init_set.o \
-bn_mp_init_set_int.o bn_mp_invmod_slow.o bn_mp_prime_rabin_miller_trials.o
+bn_mp_init_set_int.o bn_mp_invmod_slow.o bn_mp_prime_rabin_miller_trials.o \
+bn_mp_to_signed_bin_n.o bn_mp_to_unsigned_bin_n.o
 
 libtommath.a:  $(OBJECTS)
 	$(AR) $(ARFLAGS) libtommath.a $(OBJECTS)
diff --git a/libtommath/makefile.bcc b/libtommath/makefile.bcc
index 775e9ff..647c69a 100644
--- a/libtommath/makefile.bcc
+++ b/libtommath/makefile.bcc
@@ -27,11 +27,13 @@ bn_mp_prime_is_prime.obj bn_mp_prime_next_prime.obj bn_mp_dr_reduce.obj \
 bn_mp_dr_is_modulus.obj bn_mp_dr_setup.obj bn_mp_reduce_setup.obj \
 bn_mp_toom_mul.obj bn_mp_toom_sqr.obj bn_mp_div_3.obj bn_s_mp_exptmod.obj \
 bn_mp_reduce_2k.obj bn_mp_reduce_is_2k.obj bn_mp_reduce_2k_setup.obj \
+bn_mp_reduce_2k_l.obj bn_mp_reduce_is_2k_l.obj bn_mp_reduce_2k_setup_l.obj \
 bn_mp_radix_smap.obj bn_mp_read_radix.obj bn_mp_toradix.obj bn_mp_radix_size.obj \
 bn_mp_fread.obj bn_mp_fwrite.obj bn_mp_cnt_lsb.obj bn_error.obj \
 bn_mp_init_multi.obj bn_mp_clear_multi.obj bn_mp_exteuclid.obj bn_mp_toradix_n.obj \
 bn_mp_prime_random_ex.obj bn_mp_get_int.obj bn_mp_sqrt.obj bn_mp_is_square.obj \
-bn_mp_init_set.obj bn_mp_init_set_int.obj bn_mp_invmod_slow.obj bn_mp_prime_rabin_miller_trials.obj
+bn_mp_init_set.obj bn_mp_init_set_int.obj bn_mp_invmod_slow.obj bn_mp_prime_rabin_miller_trials.obj \
+bn_mp_to_signed_bin_n.obj bn_mp_to_unsigned_bin_n.obj
 
 TARGET = libtommath.lib
 
diff --git a/libtommath/makefile.cygwin_dll b/libtommath/makefile.cygwin_dll
index c90e5d9..85b10c7 100644
--- a/libtommath/makefile.cygwin_dll
+++ b/libtommath/makefile.cygwin_dll
@@ -32,11 +32,13 @@ bn_mp_prime_is_prime.o bn_mp_prime_next_prime.o bn_mp_dr_reduce.o \
 bn_mp_dr_is_modulus.o bn_mp_dr_setup.o bn_mp_reduce_setup.o \
 bn_mp_toom_mul.o bn_mp_toom_sqr.o bn_mp_div_3.o bn_s_mp_exptmod.o \
 bn_mp_reduce_2k.o bn_mp_reduce_is_2k.o bn_mp_reduce_2k_setup.o \
+bn_mp_reduce_2k_l.o bn_mp_reduce_is_2k_l.o bn_mp_reduce_2k_setup_l.o \
 bn_mp_radix_smap.o bn_mp_read_radix.o bn_mp_toradix.o bn_mp_radix_size.o \
 bn_mp_fread.o bn_mp_fwrite.o bn_mp_cnt_lsb.o bn_error.o \
 bn_mp_init_multi.o bn_mp_clear_multi.o bn_mp_exteuclid.o bn_mp_toradix_n.o \
 bn_mp_prime_random_ex.o bn_mp_get_int.o bn_mp_sqrt.o bn_mp_is_square.o bn_mp_init_set.o \
-bn_mp_init_set_int.o bn_mp_invmod_slow.o bn_mp_prime_rabin_miller_trials.o
+bn_mp_init_set_int.o bn_mp_invmod_slow.o bn_mp_prime_rabin_miller_trials.o \
+bn_mp_to_signed_bin_n.o bn_mp_to_unsigned_bin_n.o
 
 # make a Windows DLL via Cygwin
 windll:  $(OBJECTS)
diff --git a/libtommath/makefile.icc b/libtommath/makefile.icc
index 3775b20..e764253 100644
--- a/libtommath/makefile.icc
+++ b/libtommath/makefile.icc
@@ -59,11 +59,13 @@ bn_mp_prime_is_prime.o bn_mp_prime_next_prime.o bn_mp_dr_reduce.o \
 bn_mp_dr_is_modulus.o bn_mp_dr_setup.o bn_mp_reduce_setup.o \
 bn_mp_toom_mul.o bn_mp_toom_sqr.o bn_mp_div_3.o bn_s_mp_exptmod.o \
 bn_mp_reduce_2k.o bn_mp_reduce_is_2k.o bn_mp_reduce_2k_setup.o \
+bn_mp_reduce_2k_l.o bn_mp_reduce_is_2k_l.o bn_mp_reduce_2k_setup_l.o \
 bn_mp_radix_smap.o bn_mp_read_radix.o bn_mp_toradix.o bn_mp_radix_size.o \
 bn_mp_fread.o bn_mp_fwrite.o bn_mp_cnt_lsb.o bn_error.o \
 bn_mp_init_multi.o bn_mp_clear_multi.o bn_mp_exteuclid.o bn_mp_toradix_n.o \
 bn_mp_prime_random_ex.o bn_mp_get_int.o bn_mp_sqrt.o bn_mp_is_square.o bn_mp_init_set.o \
-bn_mp_init_set_int.o bn_mp_invmod_slow.o bn_mp_prime_rabin_miller_trials.o
+bn_mp_init_set_int.o bn_mp_invmod_slow.o bn_mp_prime_rabin_miller_trials.o \
+bn_mp_to_signed_bin_n.o bn_mp_to_unsigned_bin_n.o
 
 libtommath.a:  $(OBJECTS)
 	$(AR) $(ARFLAGS) libtommath.a $(OBJECTS)
diff --git a/libtommath/makefile.msvc b/libtommath/makefile.msvc
index cf59943..dbbf9f3 100644
--- a/libtommath/makefile.msvc
+++ b/libtommath/makefile.msvc
@@ -26,11 +26,13 @@ bn_mp_prime_is_prime.obj bn_mp_prime_next_prime.obj bn_mp_dr_reduce.obj \
 bn_mp_dr_is_modulus.obj bn_mp_dr_setup.obj bn_mp_reduce_setup.obj \
 bn_mp_toom_mul.obj bn_mp_toom_sqr.obj bn_mp_div_3.obj bn_s_mp_exptmod.obj \
 bn_mp_reduce_2k.obj bn_mp_reduce_is_2k.obj bn_mp_reduce_2k_setup.obj \
+bn_mp_reduce_2k_l.obj bn_mp_reduce_is_2k_l.obj bn_mp_reduce_2k_setup_l.obj \
 bn_mp_radix_smap.obj bn_mp_read_radix.obj bn_mp_toradix.obj bn_mp_radix_size.obj \
 bn_mp_fread.obj bn_mp_fwrite.obj bn_mp_cnt_lsb.obj bn_error.obj \
 bn_mp_init_multi.obj bn_mp_clear_multi.obj bn_mp_exteuclid.obj bn_mp_toradix_n.obj \
 bn_mp_prime_random_ex.obj bn_mp_get_int.obj bn_mp_sqrt.obj bn_mp_is_square.obj \
-bn_mp_init_set.obj bn_mp_init_set_int.obj bn_mp_invmod_slow.obj bn_mp_prime_rabin_miller_trials.obj
+bn_mp_init_set.obj bn_mp_init_set_int.obj bn_mp_invmod_slow.obj bn_mp_prime_rabin_miller_trials.obj \
+bn_mp_to_signed_bin_n.obj bn_mp_to_unsigned_bin_n.obj
 
 library: $(OBJECTS)
 	lib /out:tommath.lib $(OBJECTS)
diff --git a/libtommath/makefile.shared b/libtommath/makefile.shared
index 86a3786..7c35881 100644
--- a/libtommath/makefile.shared
+++ b/libtommath/makefile.shared
@@ -1,7 +1,7 @@
 #Makefile for GCC
 #
 #Tom St Denis
-VERSION=0:33
+VERSION=0:35
 
 CC = libtool --mode=compile gcc
 CFLAGS  +=  -I./ -Wall -W -Wshadow -Wsign-compare
@@ -53,11 +53,14 @@ bn_mp_prime_is_prime.o bn_mp_prime_next_prime.o bn_mp_dr_reduce.o \
 bn_mp_dr_is_modulus.o bn_mp_dr_setup.o bn_mp_reduce_setup.o \
 bn_mp_toom_mul.o bn_mp_toom_sqr.o bn_mp_div_3.o bn_s_mp_exptmod.o \
 bn_mp_reduce_2k.o bn_mp_reduce_is_2k.o bn_mp_reduce_2k_setup.o \
+bn_mp_reduce_2k_l.o bn_mp_reduce_is_2k_l.o bn_mp_reduce_2k_setup_l.o \
 bn_mp_radix_smap.o bn_mp_read_radix.o bn_mp_toradix.o bn_mp_radix_size.o \
 bn_mp_fread.o bn_mp_fwrite.o bn_mp_cnt_lsb.o bn_error.o \
 bn_mp_init_multi.o bn_mp_clear_multi.o bn_mp_exteuclid.o bn_mp_toradix_n.o \
 bn_mp_prime_random_ex.o bn_mp_get_int.o bn_mp_sqrt.o bn_mp_is_square.o bn_mp_init_set.o \
-bn_mp_init_set_int.o bn_mp_invmod_slow.o bn_mp_prime_rabin_miller_trials.o
+bn_mp_init_set_int.o bn_mp_invmod_slow.o bn_mp_prime_rabin_miller_trials.o \
+bn_mp_to_signed_bin_n.o bn_mp_to_unsigned_bin_n.o
+
 
 libtommath.la:  $(OBJECTS)
 	libtool --mode=link gcc *.lo -o libtommath.la -rpath $(LIBPATH) -version-info $(VERSION)
diff --git a/libtommath/pics/expt_state.tif b/libtommath/pics/expt_state.tif
index cb06e8e..0aaee39 100644
--- a/libtommath/pics/expt_state.tif
+++ b/libtommath/pics/expt_state.tif
diff --git a/libtommath/pics/primality.tif b/libtommath/pics/primality.tif
index 76d6be3..83aafe0 100644
--- a/libtommath/pics/primality.tif
+++ b/libtommath/pics/primality.tif
diff --git a/libtommath/poster.pdf b/libtommath/poster.pdf
index e0b4f84..4c3e365 100644
--- a/libtommath/poster.pdf
+++ b/libtommath/poster.pdf
diff --git a/libtommath/pre_gen/mpi.c b/libtommath/pre_gen/mpi.c
index 7d832e7..8ec8a10 100644
--- a/libtommath/pre_gen/mpi.c
+++ b/libtommath/pre_gen/mpi.c
@@ -69,8 +69,7 @@ char *mp_error_to_string(int code)
  * Based on slow invmod except this is optimized for the case where b is 
  * odd as per HAC Note 14.64 on pp. 610
  */
-int
-fast_mp_invmod (mp_int * a, mp_int * b, mp_int * c)
+int fast_mp_invmod (mp_int * a, mp_int * b, mp_int * c)
 {
   mp_int  x, y, u, v, B, D;
   int     res, neg;
@@ -91,7 +90,7 @@ fast_mp_invmod (mp_int * a, mp_int * b, mp_int * c)
   }
 
   /* we need y = |a| */
-  if ((res = mp_abs (a, &y)) != MP_OKAY) {
+  if ((res = mp_mod (a, b, &y)) != MP_OKAY) {
     goto LBL_ERR;
   }
 
@@ -220,8 +219,7 @@ LBL_ERR:mp_clear_multi (&x, &y, &u, &v, &B, &D, NULL);
  *
  * Based on Algorithm 14.32 on pp.601 of HAC.
 */
-int
-fast_mp_montgomery_reduce (mp_int * x, mp_int * n, mp_digit rho)
+int fast_mp_montgomery_reduce (mp_int * x, mp_int * n, mp_digit rho)
 {
   int     ix, res, olduse;
   mp_word W[MP_WARRAY];
@@ -401,8 +399,7 @@ fast_mp_montgomery_reduce (mp_int * x, mp_int * n, mp_digit rho)
  * Based on Algorithm 14.12 on pp.595 of HAC.
  *
  */
-int
-fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
+int fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
 {
   int     olduse, res, pa, ix, iz;
   mp_digit W[MP_WARRAY];
@@ -433,7 +430,7 @@ fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
       tmpx = a->dp + tx;
       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) { ... }
        */
       iy = MIN(a->used-tx, ty+1);
@@ -451,16 +448,16 @@ fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
   }
 
   /* store final carry */
-  W[ix] = _W;
+  W[ix] = (mp_digit)(_W & MP_MASK);
 
   /* setup dest */
   olduse  = c->used;
-  c->used = digs;
+  c->used = pa;
 
   {
     register mp_digit *tmpc;
     tmpc = c->dp;
-    for (ix = 0; ix < digs; ix++) {
+    for (ix = 0; ix < pa+1; ix++) {
       /* now extract the previous digit [below the carry] */
       *tmpc++ = W[ix];
     }
@@ -504,8 +501,7 @@ fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
  *
  * Based on Algorithm 14.12 on pp.595 of HAC.
  */
-int
-fast_s_mp_mul_high_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
+int fast_s_mp_mul_high_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
 {
   int     olduse, res, pa, ix, iz;
   mp_digit W[MP_WARRAY];
@@ -552,7 +548,7 @@ fast_s_mp_mul_high_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
   }
   
   /* store final carry */
-  W[ix] = _W;
+  W[ix] = (mp_digit)(_W & MP_MASK);
 
   /* setup dest */
   olduse  = c->used;
@@ -597,33 +593,14 @@ 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
  */
 
-/* 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...
-
-you do like mult except the offset of the tmpx [one that starts closer to zero]
-can't equal the offset of tmpy.  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
+ * you do like mult except the offset of the tmpx [one that 
+ * starts closer to zero] can't equal the offset of tmpy.  
+ * 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
 
 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)
@@ -658,7 +635,7 @@ int fast_s_mp_sqr (mp_int * a, mp_int * b)
       tmpx = a->dp + tx;
       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) { ... }
        */
       iy = MIN(a->used-tx, ty+1);
@@ -683,7 +660,7 @@ int fast_s_mp_sqr (mp_int * a, mp_int * b)
       }
 
       /* store it */
-      W[ix] = _W;
+      W[ix] = (mp_digit)(_W & MP_MASK);
 
       /* make next carry */
       W1 = _W >> ((mp_word)DIGIT_BIT);
@@ -2467,21 +2444,29 @@ int mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
 #endif
   }
 
+/* modified diminished radix reduction */
+#if defined(BN_MP_REDUCE_IS_2K_L_C) && defined(BN_MP_REDUCE_2K_L_C)
+  if (mp_reduce_is_2k_l(P) == MP_YES) {
+     return s_mp_exptmod(G, X, P, Y, 1);
+  }
+#endif
+
 #ifdef BN_MP_DR_IS_MODULUS_C
   /* is it a DR modulus? */
   dr = mp_dr_is_modulus(P);
 #else
+  /* default to no */
   dr = 0;
 #endif
 
 #ifdef BN_MP_REDUCE_IS_2K_C
-  /* if not, is it a uDR modulus? */
+  /* if not, is it a unrestricted DR modulus? */
   if (dr == 0) {
      dr = mp_reduce_is_2k(P) << 1;
   }
 #endif
     
-  /* if the modulus is odd or dr != 0 use the fast method */
+  /* if the modulus is odd or dr != 0 use the montgomery method */
 #ifdef BN_MP_EXPTMOD_FAST_C
   if (mp_isodd (P) == 1 || dr !=  0) {
     return mp_exptmod_fast (G, X, P, Y, dr);
@@ -2489,7 +2474,7 @@ int mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
 #endif
 #ifdef BN_S_MP_EXPTMOD_C
     /* otherwise use the generic Barrett reduction technique */
-    return s_mp_exptmod (G, X, P, Y);
+    return s_mp_exptmod (G, X, P, Y, 0);
 #else
     /* no exptmod for evens */
     return MP_VAL;
@@ -2535,8 +2520,7 @@ int mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
    #define TAB_SIZE 256
 #endif
 
-int
-mp_exptmod_fast (mp_int * G, mp_int * X, mp_int * P, mp_int * Y, int redmode)
+int mp_exptmod_fast (mp_int * G, mp_int * X, mp_int * P, mp_int * Y, int redmode)
 {
   mp_int  M[TAB_SIZE], res;
   mp_digit buf, mp;
@@ -2887,6 +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; }
    }
 
+   /* make sure U3 >= 0 */
+   if (u3.sign == MP_NEG) {
+      mp_neg(&u1, &u1);
+      mp_neg(&u2, &u2);
+      mp_neg(&u3, &u3);
+   }
+
    /* copy result out */
    if (U1 != NULL) { mp_exch(U1, &u1); }
    if (U2 != NULL) { mp_exch(U2, &u2); }
@@ -3561,8 +3552,8 @@ int mp_invmod_slow (mp_int * a, mp_int * b, mp_int * c)
   }
 
   /* x = a, y = b */
-  if ((res = mp_copy (a, &x)) != MP_OKAY) {
-    goto LBL_ERR;
+  if ((res = mp_mod(a, b, &x)) != MP_OKAY) {
+      goto LBL_ERR;
   }
   if ((res = mp_copy (b, &y)) != MP_OKAY) {
     goto LBL_ERR;
@@ -4490,7 +4481,6 @@ int mp_montgomery_calc_normalization (mp_int * a, mp_int * b)
   /* how many bits of last digit does b use */
   bits = mp_count_bits (b) % DIGIT_BIT;
 
-
   if (b->used > 1) {
      if ((res = mp_2expt (a, (b->used - 1) * DIGIT_BIT + bits - 1)) != MP_OKAY) {
         return res;
@@ -4989,8 +4979,9 @@ mp_mul_d (mp_int * a, mp_digit b, mp_int * c)
     u       = (mp_digit) (r >> ((mp_word) DIGIT_BIT));
   }
 
-  /* store final carry [if any] */
+  /* store final carry [if any] and increment ix offset  */
   *tmpc++ = u;
+  ++ix;
 
   /* now zero digits above the top */
   while (ix++ < olduse) {
@@ -5202,12 +5193,18 @@ LBL_T1:mp_clear (&t1);
 int mp_neg (mp_int * a, mp_int * b)
 {
   int     res;
-  if ((res = mp_copy (a, b)) != MP_OKAY) {
-    return res;
+  if (a != b) {
+     if ((res = mp_copy (a, b)) != MP_OKAY) {
+        return res;
+     }
   }
+
   if (mp_iszero(b) != MP_YES) {
      b->sign = (a->sign == MP_ZPOS) ? MP_NEG : MP_ZPOS;
+  } else {
+     b->sign = MP_ZPOS;
   }
+
   return MP_OKAY;
 }
 #endif
@@ -5847,7 +5844,7 @@ int mp_prime_random_ex(mp_int *a, int t, int size, int flags, ltm_prime_callback
 
    /* calc the maskOR_msb */
    maskOR_msb        = 0;
-   maskOR_msb_offset = (size - 2) >> 3;
+   maskOR_msb_offset = ((size & 7) == 1) ? 1 : 0;
    if (flags & LTM_PRIME_2MSB_ON) {
       maskOR_msb     |= 1 << ((size - 2) & 7);
    } else if (flags & LTM_PRIME_2MSB_OFF) {
@@ -5855,7 +5852,7 @@ int mp_prime_random_ex(mp_int *a, int t, int size, int flags, ltm_prime_callback
    } 
 
    /* get the maskOR_lsb */
-   maskOR_lsb         = 0;
+   maskOR_lsb         = 1;
    if (flags & LTM_PRIME_BBS) {
       maskOR_lsb     |= 3;
    }
@@ -5949,22 +5946,29 @@ int mp_radix_size (mp_int * a, int radix, int *size)
     return MP_VAL;
   }
 
-  /* init a copy of the input */
-  if ((res = mp_init_copy (&t, a)) != MP_OKAY) {
-    return res;
+  if (mp_iszero(a) == MP_YES) {
+     *size = 2;
+    return MP_OKAY;
   }
 
   /* digs is the digit count */
   digs = 0;
 
   /* if it's negative add one for the sign */
-  if (t.sign == MP_NEG) {
+  if (a->sign == MP_NEG) {
     ++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 */
-  while (mp_iszero (&t) == 0) {
+  while (mp_iszero (&t) == MP_NO) {
     if ((res = mp_div_d (&t, (mp_digit) radix, &t, &d)) != MP_OKAY) {
       mp_clear (&t);
       return res;
@@ -6038,14 +6042,14 @@ mp_rand (mp_int * a, int digits)
 
   /* first place a random non-zero digit */
   do {
-    d = ((mp_digit) abs (rand ()));
+    d = ((mp_digit) abs (rand ())) & MP_MASK;
   } while (d == 0);
 
   if ((res = mp_add_d (a, d, a)) != MP_OKAY) {
     return res;
   }
 
-  while (digits-- > 0) {
+  while (--digits > 0) {
     if ((res = mp_lshd (a, 1)) != MP_OKAY) {
       return res;
     }
@@ -6080,7 +6084,7 @@ mp_rand (mp_int * a, int digits)
  */
 
 /* read a string [ASCII] in a given radix */
-int mp_read_radix (mp_int * a, char *str, int radix)
+int mp_read_radix (mp_int * a, const char *str, int radix)
 {
   int     y, res, neg;
   char    ch;
@@ -6263,8 +6267,7 @@ mp_read_unsigned_bin (mp_int * a, unsigned char *b, int c)
  * precomputed via mp_reduce_setup.
  * From HAC pp.604 Algorithm 14.42
  */
-int
-mp_reduce (mp_int * x, mp_int * m, mp_int * mu)
+int mp_reduce (mp_int * x, mp_int * m, mp_int * mu)
 {
   mp_int  q;
   int     res, um = m->used;
@@ -6284,11 +6287,11 @@ mp_reduce (mp_int * x, mp_int * m, mp_int * mu)
     }
   } else {
 #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;
     }
 #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;
     }
 #else 
@@ -6361,8 +6364,7 @@ CLEANUP:
  */
 
 /* reduces a modulo n where n is of the form 2**p - d */
-int
-mp_reduce_2k(mp_int *a, mp_int *n, mp_digit d)
+int mp_reduce_2k(mp_int *a, mp_int *n, mp_digit d)
 {
    mp_int q;
    int    p, res;
@@ -6404,6 +6406,68 @@ ERR:
 
 /* End: bn_mp_reduce_2k.c */
 
+/* Start: bn_mp_reduce_2k_l.c */
+#include <tommath.h>
+#ifdef BN_MP_REDUCE_2K_L_C
+/* LibTomMath, multiple-precision integer library -- Tom St Denis
+ *
+ * LibTomMath is a library that provides multiple-precision
+ * integer arithmetic as well as number theoretic functionality.
+ *
+ * The library was designed directly after the MPI library by
+ * Michael Fromberger but has been written from scratch with
+ * additional optimizations in place.
+ *
+ * The library is free for all purposes without any express
+ * guarantee it works.
+ *
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
+ */
+
+/* reduces a modulo n where n is of the form 2**p - d 
+   This differs from reduce_2k since "d" can be larger
+   than a single digit.
+*/
+int mp_reduce_2k_l(mp_int *a, mp_int *n, mp_int *d)
+{
+   mp_int q;
+   int    p, res;
+   
+   if ((res = mp_init(&q)) != MP_OKAY) {
+      return res;
+   }
+   
+   p = mp_count_bits(n);    
+top:
+   /* q = a/2**p, a = a mod 2**p */
+   if ((res = mp_div_2d(a, p, &q, a)) != MP_OKAY) {
+      goto ERR;
+   }
+   
+   /* q = q * d */
+   if ((res = mp_mul(&q, d, &q)) != MP_OKAY) { 
+      goto ERR;
+   }
+   
+   /* a = a + q */
+   if ((res = s_mp_add(a, &q, a)) != MP_OKAY) {
+      goto ERR;
+   }
+   
+   if (mp_cmp_mag(a, n) != MP_LT) {
+      s_mp_sub(a, n, a);
+      goto top;
+   }
+   
+ERR:
+   mp_clear(&q);
+   return res;
+}
+
+#endif
+
+/* End: bn_mp_reduce_2k_l.c */
+
 /* Start: bn_mp_reduce_2k_setup.c */
 #include <tommath.h>
 #ifdef BN_MP_REDUCE_2K_SETUP_C
@@ -6423,8 +6487,7 @@ ERR:
  */
 
 /* determines the setup value */
-int 
-mp_reduce_2k_setup(mp_int *a, mp_digit *d)
+int mp_reduce_2k_setup(mp_int *a, mp_digit *d)
 {
    int res, p;
    mp_int tmp;
@@ -6452,6 +6515,50 @@ mp_reduce_2k_setup(mp_int *a, mp_digit *d)
 
 /* End: bn_mp_reduce_2k_setup.c */
 
+/* Start: bn_mp_reduce_2k_setup_l.c */
+#include <tommath.h>
+#ifdef BN_MP_REDUCE_2K_SETUP_L_C
+/* LibTomMath, multiple-precision integer library -- Tom St Denis
+ *
+ * LibTomMath is a library that provides multiple-precision
+ * integer arithmetic as well as number theoretic functionality.
+ *
+ * The library was designed directly after the MPI library by
+ * Michael Fromberger but has been written from scratch with
+ * additional optimizations in place.
+ *
+ * The library is free for all purposes without any express
+ * guarantee it works.
+ *
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
+ */
+
+/* determines the setup value */
+int mp_reduce_2k_setup_l(mp_int *a, mp_int *d)
+{
+   int    res;
+   mp_int tmp;
+   
+   if ((res = mp_init(&tmp)) != MP_OKAY) {
+      return res;
+   }
+   
+   if ((res = mp_2expt(&tmp, mp_count_bits(a))) != MP_OKAY) {
+      goto ERR;
+   }
+   
+   if ((res = s_mp_sub(&tmp, a, d)) != MP_OKAY) {
+      goto ERR;
+   }
+   
+ERR:
+   mp_clear(&tmp);
+   return res;
+}
+#endif
+
+/* End: bn_mp_reduce_2k_setup_l.c */
+
 /* Start: bn_mp_reduce_is_2k.c */
 #include <tommath.h>
 #ifdef BN_MP_REDUCE_IS_2K_C
@@ -6477,9 +6584,9 @@ int mp_reduce_is_2k(mp_int *a)
    mp_digit iz;
    
    if (a->used == 0) {
-      return 0;
+      return MP_NO;
    } else if (a->used == 1) {
-      return 1;
+      return MP_YES;
    } else if (a->used > 1) {
       iy = mp_count_bits(a);
       iz = 1;
@@ -6488,7 +6595,7 @@ int mp_reduce_is_2k(mp_int *a)
       /* Test every bit from the second digit up, must be 1 */
       for (ix = DIGIT_BIT; ix < iy; ix++) {
           if ((a->dp[iw] & iz) == 0) {
-             return 0;
+             return MP_NO;
           }
           iz <<= 1;
           if (iz > (mp_digit)MP_MASK) {
@@ -6497,13 +6604,57 @@ int mp_reduce_is_2k(mp_int *a)
           }
       }
    }
-   return 1;
+   return MP_YES;
 }
 
 #endif
 
 /* End: bn_mp_reduce_is_2k.c */
 
+/* Start: bn_mp_reduce_is_2k_l.c */
+#include <tommath.h>
+#ifdef BN_MP_REDUCE_IS_2K_L_C
+/* LibTomMath, multiple-precision integer library -- Tom St Denis
+ *
+ * LibTomMath is a library that provides multiple-precision
+ * integer arithmetic as well as number theoretic functionality.
+ *
+ * The library was designed directly after the MPI library by
+ * Michael Fromberger but has been written from scratch with
+ * additional optimizations in place.
+ *
+ * The library is free for all purposes without any express
+ * guarantee it works.
+ *
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
+ */
+
+/* determines if reduce_2k_l can be used */
+int mp_reduce_is_2k_l(mp_int *a)
+{
+   int ix, iy;
+   
+   if (a->used == 0) {
+      return MP_NO;
+   } else if (a->used == 1) {
+      return MP_YES;
+   } else if (a->used > 1) {
+      /* if more than half of the digits are -1 we're sold */
+      for (iy = ix = 0; ix < a->used; ix++) {
+          if (a->dp[ix] == MP_MASK) {
+              ++iy;
+          }
+      }
+      return (iy >= (a->used/2)) ? MP_YES : MP_NO;
+      
+   }
+   return MP_NO;
+}
+
+#endif
+
+/* End: bn_mp_reduce_is_2k_l.c */
+
 /* Start: bn_mp_reduce_setup.c */
 #include <tommath.h>
 #ifdef BN_MP_REDUCE_SETUP_C
@@ -7138,8 +7289,7 @@ mp_submod (mp_int * a, mp_int * b, mp_int * c, mp_int * d)
  */
 
 /* store in signed [big endian] format */
-int
-mp_to_signed_bin (mp_int * a, unsigned char *b)
+int mp_to_signed_bin (mp_int * a, unsigned char *b)
 {
   int     res;
 
@@ -7153,6 +7303,37 @@ mp_to_signed_bin (mp_int * a, unsigned char *b)
 
 /* End: bn_mp_to_signed_bin.c */
 
+/* Start: bn_mp_to_signed_bin_n.c */
+#include <tommath.h>
+#ifdef BN_MP_TO_SIGNED_BIN_N_C
+/* LibTomMath, multiple-precision integer library -- Tom St Denis
+ *
+ * LibTomMath is a library that provides multiple-precision
+ * integer arithmetic as well as number theoretic functionality.
+ *
+ * The library was designed directly after the MPI library by
+ * Michael Fromberger but has been written from scratch with
+ * additional optimizations in place.
+ *
+ * The library is free for all purposes without any express
+ * guarantee it works.
+ *
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
+ */
+
+/* store in signed [big endian] format */
+int mp_to_signed_bin_n (mp_int * a, unsigned char *b, unsigned long *outlen)
+{
+   if (*outlen < (unsigned long)mp_signed_bin_size(a)) {
+      return MP_VAL;
+   }
+   *outlen = mp_signed_bin_size(a);
+   return mp_to_signed_bin(a, b);
+}
+#endif
+
+/* End: bn_mp_to_signed_bin_n.c */
+
 /* Start: bn_mp_to_unsigned_bin.c */
 #include <tommath.h>
 #ifdef BN_MP_TO_UNSIGNED_BIN_C
@@ -7172,8 +7353,7 @@ mp_to_signed_bin (mp_int * a, unsigned char *b)
  */
 
 /* store in unsigned [big endian] format */
-int
-mp_to_unsigned_bin (mp_int * a, unsigned char *b)
+int mp_to_unsigned_bin (mp_int * a, unsigned char *b)
 {
   int     x, res;
   mp_int  t;
@@ -7202,6 +7382,37 @@ mp_to_unsigned_bin (mp_int * a, unsigned char *b)
 
 /* End: bn_mp_to_unsigned_bin.c */
 
+/* Start: bn_mp_to_unsigned_bin_n.c */
+#include <tommath.h>
+#ifdef BN_MP_TO_UNSIGNED_BIN_N_C
+/* LibTomMath, multiple-precision integer library -- Tom St Denis
+ *
+ * LibTomMath is a library that provides multiple-precision
+ * integer arithmetic as well as number theoretic functionality.
+ *
+ * The library was designed directly after the MPI library by
+ * Michael Fromberger but has been written from scratch with
+ * additional optimizations in place.
+ *
+ * The library is free for all purposes without any express
+ * guarantee it works.
+ *
+ * Tom St Denis, tomstdenis@iahu.ca, http://math.libtomcrypt.org
+ */
+
+/* store in unsigned [big endian] format */
+int mp_to_unsigned_bin_n (mp_int * a, unsigned char *b, unsigned long *outlen)
+{
+   if (*outlen < (unsigned long)mp_unsigned_bin_size(a)) {
+      return MP_VAL;
+   }
+   *outlen = mp_unsigned_bin_size(a);
+   return mp_to_unsigned_bin(a, b);
+}
+#endif
+
+/* End: bn_mp_to_unsigned_bin_n.c */
+
 /* Start: bn_mp_toom_mul.c */
 #include <tommath.h>
 #ifdef BN_MP_TOOM_MUL_C
@@ -7222,9 +7433,10 @@ mp_to_unsigned_bin (mp_int * a, unsigned char *b)
 
 /* multiplication using the Toom-Cook 3-way algorithm 
  *
- * Much more complicated than Karatsuba but has a lower asymptotic running time of 
- * O(N**1.464).  This algorithm is only particularly useful on VERY large
- * inputs (we're talking 1000s of digits here...).
+ * Much more complicated than Karatsuba but has a lower 
+ * asymptotic running time of O(N**1.464).  This algorithm is 
+ * 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)
 {
@@ -7894,8 +8106,7 @@ int mp_toradix_n(mp_int * a, char *str, int radix, int maxlen)
  */
 
 /* get the size for an unsigned equivalent */
-int
-mp_unsigned_bin_size (mp_int * a)
+int mp_unsigned_bin_size (mp_int * a)
 {
   int     size = mp_count_bits (a);
   return (size / 8 + ((size & 7) != 0 ? 1 : 0));
@@ -7944,7 +8155,7 @@ mp_xor (mp_int * a, mp_int * b, mp_int * c)
   }
 
   for (ix = 0; ix < px; ix++) {
-
+     t.dp[ix] ^= x->dp[ix];
   }
   mp_clamp (&t);
   mp_exch (c, &t);
@@ -7974,12 +8185,18 @@ mp_xor (mp_int * a, mp_int * b, mp_int * c)
  */
 
 /* set to zero */
-void
-mp_zero (mp_int * a)
+void mp_zero (mp_int * a)
 {
+  int       n;
+  mp_digit *tmp;
+
   a->sign = MP_ZPOS;
   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
 
@@ -8218,11 +8435,12 @@ s_mp_add (mp_int * a, mp_int * b, mp_int * c)
    #define TAB_SIZE 256
 #endif
 
-int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
+int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y, int redmode)
 {
   mp_int  M[TAB_SIZE], res, mu;
   mp_digit buf;
   int     err, bitbuf, bitcpy, bitcnt, mode, digidx, x, y, winsize;
+  int (*redux)(mp_int*,mp_int*,mp_int*);
 
   /* find window size */
   x = mp_count_bits (X);
@@ -8269,9 +8487,18 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
   if ((err = mp_init (&mu)) != MP_OKAY) {
     goto LBL_M;
   }
-  if ((err = mp_reduce_setup (&mu, P)) != MP_OKAY) {
-    goto LBL_MU;
-  }
+  
+  if (redmode == 0) {
+     if ((err = mp_reduce_setup (&mu, P)) != MP_OKAY) {
+        goto LBL_MU;
+     }
+     redux = mp_reduce;
+  } else {
+     if ((err = mp_reduce_2k_setup_l (P, &mu)) != MP_OKAY) {
+        goto LBL_MU;
+     }
+     redux = mp_reduce_2k_l;
+  }    
 
   /* create M table
    *
@@ -8293,11 +8520,14 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
   }
 
   for (x = 0; x < (winsize - 1); x++) {
+    /* square it */
     if ((err = mp_sqr (&M[1 << (winsize - 1)], 
                        &M[1 << (winsize - 1)])) != MP_OKAY) {
       goto LBL_MU;
     }
-    if ((err = mp_reduce (&M[1 << (winsize - 1)], P, &mu)) != MP_OKAY) {
+
+    /* reduce modulo P */
+    if ((err = redux (&M[1 << (winsize - 1)], P, &mu)) != MP_OKAY) {
       goto LBL_MU;
     }
   }
@@ -8309,7 +8539,7 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
     if ((err = mp_mul (&M[x - 1], &M[1], &M[x])) != MP_OKAY) {
       goto LBL_MU;
     }
-    if ((err = mp_reduce (&M[x], P, &mu)) != MP_OKAY) {
+    if ((err = redux (&M[x], P, &mu)) != MP_OKAY) {
       goto LBL_MU;
     }
   }
@@ -8358,7 +8588,7 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
       if ((err = mp_sqr (&res, &res)) != MP_OKAY) {
         goto LBL_RES;
       }
-      if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) {
+      if ((err = redux (&res, P, &mu)) != MP_OKAY) {
         goto LBL_RES;
       }
       continue;
@@ -8375,7 +8605,7 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
         if ((err = mp_sqr (&res, &res)) != MP_OKAY) {
           goto LBL_RES;
         }
-        if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) {
+        if ((err = redux (&res, P, &mu)) != MP_OKAY) {
           goto LBL_RES;
         }
       }
@@ -8384,7 +8614,7 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
       if ((err = mp_mul (&res, &M[bitbuf], &res)) != MP_OKAY) {
         goto LBL_RES;
       }
-      if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) {
+      if ((err = redux (&res, P, &mu)) != MP_OKAY) {
         goto LBL_RES;
       }
 
@@ -8402,7 +8632,7 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
       if ((err = mp_sqr (&res, &res)) != MP_OKAY) {
         goto LBL_RES;
       }
-      if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) {
+      if ((err = redux (&res, P, &mu)) != MP_OKAY) {
         goto LBL_RES;
       }
 
@@ -8412,7 +8642,7 @@ int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
         if ((err = mp_mul (&res, &M[1], &res)) != MP_OKAY) {
           goto LBL_RES;
         }
-        if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) {
+        if ((err = redux (&res, P, &mu)) != MP_OKAY) {
           goto LBL_RES;
         }
       }
@@ -8456,8 +8686,7 @@ LBL_M:
  * HAC pp. 595, Algorithm 14.12  Modified so you can control how 
  * many digits of output are created.
  */
-int
-s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
+int s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
 {
   mp_int  t;
   int     res, pa, pb, ix, iy;
@@ -8625,8 +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 */
-int
-s_mp_sqr (mp_int * a, mp_int * b)
+int s_mp_sqr (mp_int * a, mp_int * b)
 {
   mp_int  t;
   int     res, ix, iy, pa;
@@ -8803,11 +9031,12 @@ s_mp_sub (mp_int * a, mp_int * b, mp_int * c)
  CPU                    /Compiler     /MUL CUTOFF/SQR CUTOFF
 -------------------------------------------------------------
  Intel P4 Northwood     /GCC v3.4.1   /        88/       128/LTM 0.32 ;-)
+ AMD Athlon64           /GCC v3.4.4   /        74/       124/LTM 0.34
  
 */
 
-int     KARATSUBA_MUL_CUTOFF = 88,      /* Min. number of digits before Karatsuba multiplication is used. */
-        KARATSUBA_SQR_CUTOFF = 128,     /* Min. number of digits before Karatsuba squaring is used. */
+int     KARATSUBA_MUL_CUTOFF = 74,      /* Min. number of digits before Karatsuba multiplication is used. */
+        KARATSUBA_SQR_CUTOFF = 124,     /* Min. number of digits before Karatsuba squaring is used. */
         
         TOOM_MUL_CUTOFF      = 350,      /* no optimal values of these are known yet so set em high */
         TOOM_SQR_CUTOFF      = 400; 
diff --git a/libtommath/tommath.h b/libtommath/tommath.h
index 7cc92c2..bcb9d86 100644
--- a/libtommath/tommath.h
+++ b/libtommath/tommath.h
@@ -429,6 +429,15 @@ int mp_reduce_2k_setup(mp_int *a, mp_digit *d);
 /* reduces a modulo b where b is of the form 2**p - k [0 <= a] */
 int mp_reduce_2k(mp_int *a, mp_int *n, mp_digit d);
 
+/* returns true if a can be reduced with mp_reduce_2k_l */
+int mp_reduce_is_2k_l(mp_int *a);
+
+/* determines k value for 2k reduction */
+int mp_reduce_2k_setup_l(mp_int *a, mp_int *d);
+
+/* reduces a modulo b where b is of the form 2**p - k [0 <= a] */
+int mp_reduce_2k_l(mp_int *a, mp_int *n, mp_int *d);
+
 /* d = a**b (mod c) */
 int mp_exptmod(mp_int *a, mp_int *b, mp_int *c, mp_int *d);
 
@@ -511,12 +520,14 @@ int mp_count_bits(mp_int *a);
 int mp_unsigned_bin_size(mp_int *a);
 int mp_read_unsigned_bin(mp_int *a, unsigned char *b, int c);
 int mp_to_unsigned_bin(mp_int *a, unsigned char *b);
+int mp_to_unsigned_bin_n (mp_int * a, unsigned char *b, unsigned long *outlen);
 
 int mp_signed_bin_size(mp_int *a);
 int mp_read_signed_bin(mp_int *a, unsigned char *b, int c);
 int mp_to_signed_bin(mp_int *a, unsigned char *b);
+int mp_to_signed_bin_n (mp_int * a, unsigned char *b, unsigned long *outlen);
 
-int mp_read_radix(mp_int *a, char *str, int radix);
+int mp_read_radix(mp_int *a, const char *str, int radix);
 int mp_toradix(mp_int *a, char *str, int radix);
 int mp_toradix_n(mp_int * a, char *str, int radix, int maxlen);
 int mp_radix_size(mp_int *a, int radix, int *size);
@@ -554,7 +565,7 @@ int fast_mp_invmod(mp_int *a, mp_int *b, mp_int *c);
 int mp_invmod_slow (mp_int * a, mp_int * b, mp_int * c);
 int fast_mp_montgomery_reduce(mp_int *a, mp_int *m, mp_digit mp);
 int mp_exptmod_fast(mp_int *G, mp_int *X, mp_int *P, mp_int *Y, int mode);
-int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y);
+int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y, int mode);
 void bn_reverse(unsigned char *s, int len);
 
 extern const char *mp_s_rmap;
diff --git a/libtommath/tommath.pdf b/libtommath/tommath.pdf
index 88e2dc7..c486d29 100644
--- a/libtommath/tommath.pdf
+++ b/libtommath/tommath.pdf
diff --git a/libtommath/tommath.src b/libtommath/tommath.src
index 6ee842d..7a53860 100644
--- a/libtommath/tommath.src
+++ b/libtommath/tommath.src
@@ -49,7 +49,7 @@
 \begin{document}
 \frontmatter
 \pagestyle{empty}
-\title{Implementing Multiple Precision Arithmetic \\ ~ \\ Draft Edition }
+\title{Multi--Precision Math}
 \author{\mbox{
 %\begin{small}
 \begin{tabular}{c}
@@ -66,7 +66,7 @@ QUALCOMM Australia \\
 }
 }
 \maketitle
-This text has been placed in the public domain.  This text corresponds to the v0.30 release of the 
+This text has been placed in the public domain.  This text corresponds to the v0.35 release of the 
 LibTomMath project.
 
 \begin{alltt}
@@ -85,66 +85,32 @@ This text is formatted to the international B5 paper size of 176mm wide by 250mm
 
 \tableofcontents
 \listoffigures
-\chapter*{Prefaces to the Draft Edition}
-I started this text in April 2003 to complement my LibTomMath library.  That is, explain how to implement the functions
-contained in LibTomMath.  The goal is to have a textbook that any Computer Science student can use when implementing their
-own multiple precision arithmetic.  The plan I wanted to follow was flesh out all the
-ideas and concepts I had floating around in my head and then work on it afterwards refining a little bit at a time.  Chance
-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
-text.  
-
-Choosing to not waste any time I dove right into the project even before my spring semester was finished.  I wrote a bit
-off and on at first.  The moment my exams were finished I jumped into long 12 to 16 hour days.  The result after only
-a couple of months was a ten chapter, three hundred page draft that I quickly had distributed to anyone who wanted
-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
-managed to grab a certain level of attention having people from around the world ask me for copies of the text was certain
-rewarding.
-
-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.  
-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
-finished yet.  I haven't given up on the project, only had some setbacks.  First O'Reilly declined to publish the text then
-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
-onto finishing the book not securing a contract.
-
-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.  
-Even the simplest introductory material has to be lined with references and figures.  A lot of the text has to be re-written
-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
-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.
+\chapter*{Prefaces}
+When I tell people about my LibTom projects and that I release them as public domain they are often puzzled.  
+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.''  
+Which seems odd and perhaps too terse for adult conversation. I often qualify it with ``I am able, I am willing.'' which 
+perhaps explains it better.  I am the first to admit there is not anything that special with what I have done.  Perhaps
+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 
+back to society in the form of tools and knowledge that can help others in their endeavours.
+
+I started writing this book because it was the most logical task to further my goal of open academia.  The LibTomMath source
+code itself was written to be easy to follow and learn from.  There are times, however, where pure C source code does not
+explain the algorithms properly.  Hence this book.  The book literally starts with the foundation of the library and works
+itself outwards to the more complicated algorithms.  The use of both pseudo--code and verbatim source code provides a duality
+of ``theory'' and ``practice'' that the computer science students of the world shall appreciate.  I never deviate too far
+from relatively straightforward algebra and I hope that this book can be a valuable learning asset.
+
+This book and indeed much of the LibTom projects would not exist in their current form if it was not for a plethora
+of kind people donating their time, resources and kind words to help support my work.  Writing a text of significant
+length (along with the source code) is a tiresome and lengthy process.  Currently the LibTom project is four years old,
+comprises of literally thousands of users and over 100,000 lines of source code, TeX and other material.  People like Mads and Greg 
+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.  
+
+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
+honour your kind gestures with this project.
+
+Open Source.  Open Academia.  Open Minds.
 
 \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
 
-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}
 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
 the absolute value of an mp\_int.
 
-\newpage\begin{figure}[here]
+\begin{figure}[here]
 \begin{center}
 \begin{tabular}{l}
 \hline Algorithm \textbf{mp\_abs}. \\
@@ -1335,6 +1301,9 @@ logic to handle it.
 
 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}
 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.
@@ -1368,11 +1337,15 @@ zero as negative.
 
 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}
 \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.
 
-\begin{figure}[here]
+\newpage\begin{figure}[here]
 \begin{center}
 \begin{tabular}{l}
 \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
 
-Line @21,mp_zero@ calls mp\_zero() to clear the mp\_int and reset the sign.  Line @22,MP_MASK@ copies the digit 
-into the least significant location.  Note the usage of a new constant \textbf{MP\_MASK}.  This constant is used to quickly
-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 
-$MP\_MASK = 2^k - 1$ to perform the reduction.  Finally line @23,a->used@ will set the \textbf{used} member with respect to the 
-digit actually set. This function will always make the integer positive.
+First we zero (line @21,mp_zero@) the mp\_int to make sure that the other members are initialized for a 
+small positive constant.  mp\_zero() ensures that the \textbf{sign} is positive and the \textbf{used} count
+is zero.  Next we set the digit and reduce it modulo $\beta$ (line @22,MP_MASK@).  After this step we have to 
+check if the resulting digit is zero or not.  If it is not then we set the \textbf{used} count to one, otherwise
+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 
 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
 
-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
-are compared since it is a very cheap test to perform and can potentially save considerable time.  The implementation given is also not valid 
-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 
-array of digits.
+The two if statements (lines @24,if@ and @28,if@) compare the number of digits in the two inputs.  These two are 
+performed before all of the digits are compared since it is a very cheap test to perform and can potentially save 
+considerable time.  The implementation given is also not valid 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 array of digits.
+
+
 
 \subsection{Signed Comparisons}
 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
 
-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
-has the positive sign is larger.   At line @30,if@, the inputs are compared based on magnitudes.  If the signs were both negative then 
-the unsigned comparison is performed in the opposite direction (\textit{line @31,mp_cmp_mag@}).  Otherwise, the signs are assumed to 
+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.   The inputs are compared (line @30,if@) based on magnitudes.  If the signs were both 
+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.
 
 \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
 
-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 
-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 
-accomodate the result of the addition. 
+We first sort (lines @27,if@ to @35,}@) the inputs based on magnitude and determine the $min$ and $max$ variables.
+Note that $x$ is a pointer to an mp\_int assigned to the largest input, in effect it is a local alias.  Next we
+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 
 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.
 
-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 
-implementation.  The initial addition loop begins on line @66,for@ and ends on line @75,}@.  Similarly the conditional addition loop
-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++@.  
-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
-for the next loop on lines @97,for@ to @99,}@ which set any old upper digits to zero.
+The initial carry $u$ will be cleared (line @65,u = 0@), note that $u$ is of type mp\_digit which ensures type 
+compatibility within the implementation.  The initial addition (line @66,for@ to @75,}@) adds digits from
+both inputs until the smallest input runs out of digits.  Similarly the conditional addition loop
+(line @81,for@ to @90,}@) adds the remaining digits from the larger of the two inputs.  The addition is finished 
+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}
 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 $2^{\gamma} > \beta$}).  
 
 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]
 \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
 
-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 
-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 
-$a$, $b$ and $c$ respectively.
+Like low level addition we ``sort'' the inputs.  Except in this case the sorting is hardcoded 
+(lines @24,min@ and @25,max@).  In reality the $min$ and $max$ variables are only aliases and are only 
+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 addition loop.  As remarked earlier there is an implementation reason for using the ``awkward'' method of extracting the carry 
-(\textit{see line @57, >>@}).  The traditional method for extracting the carry would be to shift by $lg(\beta)$ positions and logically AND 
-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
-occurs from subtraction.  This carry extraction requires two relatively cheap operations to extract the carry.  The other method is to simply 
-shift the 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.
+The first subtraction loop (lines @47,u = 0@ through @61,}@) subtract digits from both inputs until the smaller of
+the two inputs has been exhausted.  As remarked earlier there is an implementation reason for using the ``awkward'' 
+method of extracting the carry (line @57, >>@).  The traditional method for extracting the carry would be to shift 
+by $lg(\beta)$ positions and logically AND 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 occurs from subtraction.  This carry 
+extraction requires two relatively cheap operations to extract the carry.  The other method is to simply shift the 
+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
-$a$ and copy the result to $c$.  
+If $a$ has a larger magnitude than $b$ an additional loop (lines @64,for@ through @73,}@) is required to propagate 
+the carry through $a$ and copy the result to $c$.  
 
 \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
@@ -2098,10 +2081,11 @@ FIGU,sliding_window,Sliding Window Movement
 
 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 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
-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
-over the input.  
+The if statement (line @24,if@) ensures that the $b$ variable is greater than zero since we do not interpret negative
+shift counts properly.  The \textbf{used} count is incremented by $b$ before the copy loop begins.  This elminates 
+the need for an additional variable in the for loop.  The variable $top$ (line @42,top@) is an alias
+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 $x$}
 
@@ -2151,9 +2135,9 @@ Once the window copy is complete the upper digits must be zeroed and the \textbf
 
 EXAM,bn_mp_rshd.c
 
-The only noteworthy element of this routine is the lack of a return type.  
-
--- Will update later to give it a return type...Tom
+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
+the upper digits of the input to make sure the result is correct.
 
 \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
 
-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}
 
@@ -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
 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}
 
@@ -2306,7 +2299,13 @@ is copied to $b$, leading digits are removed and the remaining leading digit is
 
 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}
 \begin{tabular}{cl}
@@ -2464,33 +2463,46 @@ exceed the precision requested.
 
 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
-the number of digits of output is less than \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.
+First we determine (line @30,if@) if the Comba method can be used first since it's faster.  The conditions for 
+sing the Comba routine are that min$(a.used, b.used) < \delta$ and the number of digits of output is less than 
+\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.
+
+If we cannot use the Comba method we proceed to setup the baseline routine.  We allocate the the destination mp\_int
+$t$ (line @36,init@) to the exact size of the output to avoid further re--allocations.  At this point we now 
+begin the $O(n^2)$ loop.
 
-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
-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 
-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 
-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 
-example, the instruction ``MUL'' on the x86 processor can multiply two 32-bit values and produce a 64-bit result.  
+This implementation of multiplication has the caveat that it can be trimmed to only produce a variable number of
+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}
 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
-makes the nested loop very sequential and hard to unroll and implement in parallel.  The ``Comba'' \cite{COMBA} method is named after little known 
-(\textit{in cryptographic venues}) Paul G. Comba who described a method of implementing fast multipliers that do not require nested 
-carry fixup operations.  As an interesting aside it seems that Paul Barrett describes a similar technique in
-his 1986 paper \cite{BARRETT} written five years before.
+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 makes the nested loop very sequential and hard to unroll and implement 
+in parallel.  The ``Comba'' \cite{COMBA} method is named after little known (\textit{in cryptographic venues}) Paul G. 
+Comba who described a method of implementing fast multipliers that do not require nested carry fixup operations.  As an 
+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
-the columns of the result are produced.  In the standard long-hand algorithm rows of products 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.  
+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 the columns of the result are produced.  In the standard long-hand algorithm rows of products 
+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 
-simple multiplication and addition step is performed.  The carries of the columns are propagated 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. 
+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 simple multiplication and addition step is performed.  The carries of the columns are propagated 
+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}
 \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{Output}.  $c \leftarrow \vert a \vert \cdot \vert b \vert \mbox{ (mod }\beta^{digs}\mbox{)}$. \\
 \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}) \\
 2.  If step 1 failed return(\textit{MP\_MEM}).\\
 \\
-Zero the temporary array $\hat W$. \\
-3.  for $n$ from $0$ to $digs - 1$ do \\
-\hspace{3mm}3.1  $\hat W_n \leftarrow 0$ \\
+3.  $pa \leftarrow \mbox{MIN}(digs, a.used + b.used)$ \\
 \\
-Compute the columns. \\
-4.  for $ix$ from $0$ to $a.used - 1$ do \\
-\hspace{3mm}4.1  $pb \leftarrow \mbox{min}(b.used, digs - ix)$ \\
-\hspace{3mm}4.2  If $pb < 1$ then goto step 5. \\
-\hspace{3mm}4.3  for $iy$ from $0$ to $pb - 1$ do \\
-\hspace{6mm}4.3.1  $\hat W_{ix+iy} \leftarrow \hat W_{ix+iy} + a_{ix}b_{iy}$ \\
+4.  $\_ \hat W \leftarrow 0$ \\
+5.  for $ix$ from 0 to $pa - 1$ do \\
+\hspace{3mm}5.1  $ty \leftarrow \mbox{MIN}(b.used - 1, ix)$ \\
+\hspace{3mm}5.2  $tx \leftarrow ix - ty$ \\
+\hspace{3mm}5.3  $iy \leftarrow \mbox{MIN}(a.used - tx, ty + 1)$ \\
+\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. \\
-5.  $oldused \leftarrow c.used$ \\
-6.  $c.used \leftarrow digs$ \\
-7.  If $digs > 1$ then do \\
-\hspace{3mm}7.1.  for $ix$ from $1$ to $digs - 1$ do \\
-\hspace{6mm}7.1.1  $\hat W_{ix} \leftarrow \hat W_{ix} + \lfloor \hat W_{ix-1} / \beta \rfloor$ \\
-\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.  $c_{ix} \leftarrow \hat W_{ix} \mbox{ (mod }\beta\mbox{)}$ \\
+7.  $oldused \leftarrow c.used$ \\
+8.  $c.used \leftarrow digs$ \\
+9.  for $ix$ from $0$ to $pa$ do \\
+\hspace{3mm}9.1  $c_{ix} \leftarrow W_{ix}$ \\
+10.  for $ix$ from $pa + 1$ to $oldused - 1$ do \\
+\hspace{3mm}10.1 $c_{ix} \leftarrow 0$ \\
 \\
-Zero excess digits. \\
-10.  If $digs < oldused$ then do \\
-\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}). \\
+11.  Clamp $c$. \\
+12.  Return MP\_OKAY. \\
 \hline
 \end{tabular}
 \end{center}
@@ -2625,15 +2631,24 @@ Zero excess digits. \\
 \end{figure}
 
 \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
-essentially peforms the same calculation as algorithm s\_mp\_mul\_digs, just much faster.
+This algorithm performs the unsigned multiplication of $a$ and $b$ using the Comba method limited to $digs$ digits of precision.
+
+The outer loop of this algorithm is more complicated than that of the baseline multiplier.  This is because on the inside of the 
+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 $ty$ variable is set to the minimum count of $ix$ or the number of digits in $b$.  That way if $a$ has more digits than
+$b$ this will be limited to $b.used - 1$.  The $tx$ variable is set to the to the distance past $b.used$ the variable
+$ix$ is.  This is used for the immediately subsequent statement where we find $iy$.  
 
-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 
-unlike algorithm s\_mp\_mul\_digs no temporary mp\_int is required since the result is calculated directly in $\hat W$.  
+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.
 
-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
-a carry variable or propagation in this loop allows the loop to be performed with only single precision multiplication and additions.  Now that each
-iteration of the inner loop can be performed independent of the others the inner loop can be performed with a high level of parallelism.
+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 
 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
 
-The memset on line @47,memset@ clears the initial $\hat W$ array to zero in a single step. Like the slower baseline multiplication
-implementation a series of aliases (\textit{lines @67, tmpx@, @70, tmpy@ and @75,_W@}) are used to simplify the inner $O(n^2)$ loop.  
-In this case a new alias $\_\hat W$ has been added which refers to the double precision columns offset by $ix$ in each pass.  
+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
+to produce the individual columns of the product.  We use the two aliases $tmpx$ and $tmpy$ (lines @61,tmpx@, @62,tmpy@) to point
+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 
-stripped to the bones of any extra baggage\footnote{Hence the pointer aliases.}.  On x86 processors the multiplication and additions amount to at the 
-very least five instructions (\textit{two loads, two additions, one multiply}) while on the ARMv4 processors they amount to only three 
-(\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 
-and scheduling the instructions so there are very few dependency stalls.
+The inner loop (lines @70,for@ to @72,}@) of this implementation is where the tradeoff come into play.  Originally this comba 
+implementation was ``row--major'' which means it adds to each of the columns in each pass.  After the outer loop it would then fix 
+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 
+one mp\_word per iteration.  On processors such as the Athlon XP and P4 this did not matter much since the cache bandwidth 
+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
-baseline method there are dependency stalls as the algorithm must wait for the multiplier to finish before propagating the carry to the next 
-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.  
+After the inner loop we store the current accumulator in $W$ and shift $\_ \hat W$ (lines @75,W[ix]@, @78,>>@) to forward it as 
+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.  
 
 \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
@@ -2976,13 +2991,26 @@ result $a \cdot b$ is produced.
 
 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}
 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.  
 
-\newpage\begin{figure}[!here]
+\begin{figure}[!here]
 \begin{small}
 \begin{center}
 \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
 will not handle.  
 
-\newpage\begin{figure}[!here]
+\begin{figure}[!here]
 \begin{small}
 \begin{center}
 \begin{tabular}{l}
@@ -3121,9 +3149,14 @@ results calculated so far.  This involves expensive carry propagation which will
 
 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
-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
-additions (\textit{see line @57,r + r@}) since it is usually faster than shifting,if not at least as fast.  
+Inside the outer loop (line @32,for@) the square term is calculated on line @35,r =@.  The carry (line @42,>>@) has been
+extracted from the mp\_word accumulator using a right shift.  Aliases for $a_{ix}$ and $t_{ix+iy}$ are initialized 
+(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}
 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,
 $ab + ba + ac + ca = 2ab + 2ac = 2(ab + ac)$.  
 
-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
-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 
-moved to a $O(n)$ work level outside the $O(n^2)$ level.  
+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 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 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]
 \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{Output}.  $b \leftarrow a^2$ \\
 \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}). \\
 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.\\
-\hspace{3mm}4.2  for $iy$ from $ix + 1$ to $a.used - 1$ do \\
-\hspace{6mm}4.2.1  $\hat W_{ix+iy} \leftarrow \hat W_{ix+iy} + a_{ix}a_{iy}$ \\
-5.  $oldused \leftarrow b.used$ \\
-6.  $b.used \leftarrow 2a.used + 1$ \\
+3.  $pa \leftarrow 2 \cdot a.used$ \\
+4.  $\hat W1 \leftarrow 0$ \\
+5.  for $ix$ from $0$ to $pa - 1$ do \\
+\hspace{3mm}5.1  $\_ \hat W \leftarrow 0$ \\
+\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. \\
-7.  $\hat W_0 \leftarrow 2 \hat W_0 + \hat {X}_0$ \\
-8.  for $ix$ from $1$ to $2a.used$ do \\
-\hspace{3mm}8.1 $\hat W_{ix} \leftarrow 2 \hat W_{ix} + \hat {X}_{ix}$ \\
-\hspace{3mm}8.2 $\hat W_{ix} \leftarrow \hat W_{ix} + \lfloor \hat W_{ix - 1} / \beta \rfloor$ \\
-\hspace{3mm}8.3 $b_{ix-1} \leftarrow W_{ix-1} \mbox{ (mod }\beta\mbox{)}$ \\
-9.  $b_{2a.used} \leftarrow \hat W_{2a.used} \mbox{ (mod }\beta\mbox{)}$ \\
-10.  if $2a.used + 1 < oldused$ then do \\
-\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}). \\ 
+6.  $oldused \leftarrow b.used$ \\
+7.  $b.used \leftarrow 2 \cdot a.used$ \\
+8.  for $ix$ from $0$ to $pa - 1$ do \\
+\hspace{3mm}8.1  $b_{ix} \leftarrow W_{ix}$ \\
+9.  for $ix$ from $pa$ to $oldused - 1$ do \\
+\hspace{3mm}9.1  $b_{ix} \leftarrow 0$ \\
+10.  Clamp excess digits from $b$.  (\textit{mp\_clamp}) \\
+11.  Return(\textit{MP\_OKAY}). \\ 
 \hline
 \end{tabular}
 \end{center}
@@ -3183,24 +3216,24 @@ Double the products and propagate the carries simultaneously. \\
 \end{figure}
 
 \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
-the number of input digits is less than \textbf{MP\_WARRAY} and less than $\delta \over 2$.  
+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 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
-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 
-processors to simply make it a full size array.
+First, we have an accumulator and carry variables $\_ \hat W$ and $\hat W1$ respectively.  This is because the inner loop
+products are to be doubled.  If we had added the previous carry in we would be doubling too much.  Next we perform an
+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 
-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
-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.  
+Finally the last difference is the addition of the ``square'' term outside the inner loop (step 5.8).  We add in the square
+only to even outputs and it is the square of the term at the $\lfloor ix / 2 \rfloor$ position.
 
 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}
 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
 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
-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}
+This routine uses the same error trap coding style as mp\_karatsuba\_sqr.  As the temporary variables are initialized errors are 
+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.
 
 \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
-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.  
 
 \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 \\
                       & 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. \\
                       & \\                      
-$\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 [ 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 \\
                       & 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}
 
 \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 
 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 
-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 
 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.  
@@ -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
 future use so that the Barrett algorithm can be used without delay.  
 
-\begin{figure}[!here]
+\newpage\begin{figure}[!here]
 \begin{small}
 \begin{center}
 \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
 equivalent to equation \ref{eqn:legendre}.
 
+\textit{-- Tom, don't be an ass, cite your source here...!}
+
 \begin{equation}
 a^{(p-1)/2} \equiv \begin{array}{rl}
                               -1 &  \mbox{if }a\mbox{ is a quadratic non-residue.} \\
diff --git a/libtommath/tommath.tex b/libtommath/tommath.tex
index 9c4dc82..b016010 100644
--- a/libtommath/tommath.tex
+++ b/libtommath/tommath.tex
@@ -49,7 +49,7 @@
 \begin{document}
 \frontmatter
 \pagestyle{empty}
-\title{Implementing Multiple Precision Arithmetic \\ ~ \\ Draft Edition }
+\title{Multi--Precision Math}
 \author{\mbox{
 %\begin{small}
 \begin{tabular}{c}
@@ -66,7 +66,7 @@ QUALCOMM Australia \\
 }
 }
 \maketitle
-This text has been placed in the public domain.  This text corresponds to the v0.30 release of the 
+This text has been placed in the public domain.  This text corresponds to the v0.35 release of the 
 LibTomMath project.
 
 \begin{alltt}
@@ -85,66 +85,32 @@ This text is formatted to the international B5 paper size of 176mm wide by 250mm
 
 \tableofcontents
 \listoffigures
-\chapter*{Prefaces to the Draft Edition}
-I started this text in April 2003 to complement my LibTomMath library.  That is, explain how to implement the functions
-contained in LibTomMath.  The goal is to have a textbook that any Computer Science student can use when implementing their
-own multiple precision arithmetic.  The plan I wanted to follow was flesh out all the
-ideas and concepts I had floating around in my head and then work on it afterwards refining a little bit at a time.  Chance
-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
-text.  
-
-Choosing to not waste any time I dove right into the project even before my spring semester was finished.  I wrote a bit
-off and on at first.  The moment my exams were finished I jumped into long 12 to 16 hour days.  The result after only
-a couple of months was a ten chapter, three hundred page draft that I quickly had distributed to anyone who wanted
-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
-managed to grab a certain level of attention having people from around the world ask me for copies of the text was certain
-rewarding.
-
-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.  
-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
-finished yet.  I haven't given up on the project, only had some setbacks.  First O'Reilly declined to publish the text then
-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
-onto finishing the book not securing a contract.
-
-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.  
-Even the simplest introductory material has to be lined with references and figures.  A lot of the text has to be re-written
-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
-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.
+\chapter*{Prefaces}
+When I tell people about my LibTom projects and that I release them as public domain they are often puzzled.  
+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.''  
+Which seems odd and perhaps too terse for adult conversation. I often qualify it with ``I am able, I am willing.'' which 
+perhaps explains it better.  I am the first to admit there is not anything that special with what I have done.  Perhaps
+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 
+back to society in the form of tools and knowledge that can help others in their endeavours.
+
+I started writing this book because it was the most logical task to further my goal of open academia.  The LibTomMath source
+code itself was written to be easy to follow and learn from.  There are times, however, where pure C source code does not
+explain the algorithms properly.  Hence this book.  The book literally starts with the foundation of the library and works
+itself outwards to the more complicated algorithms.  The use of both pseudo--code and verbatim source code provides a duality
+of ``theory'' and ``practice'' that the computer science students of the world shall appreciate.  I never deviate too far
+from relatively straightforward algebra and I hope that this book can be a valuable learning asset.
+
+This book and indeed much of the LibTom projects would not exist in their current form if it was not for a plethora
+of kind people donating their time, resources and kind words to help support my work.  Writing a text of significant
+length (along with the source code) is a tiresome and lengthy process.  Currently the LibTom project is four years old,
+comprises of literally thousands of users and over 100,000 lines of source code, TeX and other material.  People like Mads and Greg 
+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.  
+
+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
+honour your kind gestures with this project.
+
+Open Source.  Open Academia.  Open Minds.
 
 \begin{flushright} Tom St Denis \end{flushright}
 
@@ -1045,7 +1011,7 @@ assumed to contain undefined values they are initially set to zero.
 \end{alltt}
 \end{small}
 
-A quick optimization is to first determine if a memory re-allocation is required at all.  The if statement (line 23) checks
+A quick optimization is to first determine if a memory re-allocation is required at all.  The if statement (line 24) 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}
 the function skips the re-allocation part thus saving time.
 
@@ -1590,14 +1556,20 @@ This algorithm simply resets a mp\_int to the default state.
 \begin{alltt}
 016   
 017   /* set to zero */
-018   void
-019   mp_zero (mp_int * a)
-020   \{
-021     a->sign = MP_ZPOS;
-022     a->used = 0;
-023     memset (a->dp, 0, sizeof (mp_digit) * a->alloc);
-024   \}
-025   #endif
+018   void mp_zero (mp_int * a)
+019   \{
+020     int       n;
+021     mp_digit *tmp;
+022   
+023     a->sign = MP_ZPOS;
+024     a->used = 0;
+025   
+026     tmp = a->dp;
+027     for (n = 0; n < a->alloc; n++) \{
+028        *tmp++ = 0;
+029     \}
+030   \}
+031   #endif
 \end{alltt}
 \end{small}
 
@@ -1609,7 +1581,7 @@ 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
 the absolute value of an mp\_int.
 
-\newpage\begin{figure}[here]
+\begin{figure}[here]
 \begin{center}
 \begin{tabular}{l}
 \hline Algorithm \textbf{mp\_abs}. \\
@@ -1662,6 +1634,9 @@ logic to handle it.
 \end{alltt}
 \end{small}
 
+This fairly trivial algorithm first eliminates non--required duplications (line 27) and then sets the
+\textbf{sign} flag to \textbf{MP\_ZPOS}.
+
 \subsection{Integer Negation}
 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.
@@ -1702,23 +1677,33 @@ zero as negative.
 018   int mp_neg (mp_int * a, mp_int * b)
 019   \{
 020     int     res;
-021     if ((res = mp_copy (a, b)) != MP_OKAY) \{
-022       return res;
-023     \}
-024     if (mp_iszero(b) != MP_YES) \{
-025        b->sign = (a->sign == MP_ZPOS) ? MP_NEG : MP_ZPOS;
-026     \}
-027     return MP_OKAY;
-028   \}
-029   #endif
+021     if (a != b) \{
+022        if ((res = mp_copy (a, b)) != MP_OKAY) \{
+023           return res;
+024        \}
+025     \}
+026   
+027     if (mp_iszero(b) != MP_YES) \{
+028        b->sign = (a->sign == MP_ZPOS) ? MP_NEG : MP_ZPOS;
+029     \} else \{
+030        b->sign = MP_ZPOS;
+031     \}
+032   
+033     return MP_OKAY;
+034   \}
+035   #endif
 \end{alltt}
 \end{small}
 
+Like mp\_abs() this function avoids non--required duplications (line 21) 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}
 \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.
 
-\begin{figure}[here]
+\newpage\begin{figure}[here]
 \begin{center}
 \begin{tabular}{l}
 \hline Algorithm \textbf{mp\_set}. \\
@@ -1757,11 +1742,14 @@ single digit is set (\textit{modulo $\beta$}) and the \textbf{used} count is adj
 \end{alltt}
 \end{small}
 
-Line 20 calls mp\_zero() to clear the mp\_int and reset the sign.  Line 21 copies the digit 
-into the least significant location.  Note the usage of a new constant \textbf{MP\_MASK}.  This constant is used to quickly
-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 
-$MP\_MASK = 2^k - 1$ to perform the reduction.  Finally line 22 will set the \textbf{used} member with respect to the 
-digit actually set. This function will always make the integer positive.
+First we zero (line 20) the mp\_int to make sure that the other members are initialized for a 
+small positive constant.  mp\_zero() ensures that the \textbf{sign} is positive and the \textbf{used} count
+is zero.  Next we set the digit and reduce it modulo $\beta$ (line 21).  After this step we have to 
+check if the resulting digit is zero or not.  If it is not then we set the \textbf{used} count to one, otherwise
+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 
 this function should take that into account.  Only trivially small constants can be set using this function.
@@ -1936,10 +1924,12 @@ the zero'th digit.  If after all of the digits have been compared, no difference
 \end{alltt}
 \end{small}
 
-The two if statements on lines 24 and 28 compare the number of digits in the two inputs.  These two are performed before all of the digits
-are compared since it is a very cheap test to perform and can potentially save considerable time.  The implementation given is also not valid 
-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 
-array of digits.
+The two if statements (lines 24 and 28) compare the number of digits in the two inputs.  These two are 
+performed before all of the digits are compared since it is a very cheap test to perform and can potentially save 
+considerable time.  The implementation given is also not valid 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 array of digits.
+
+
 
 \subsection{Signed Comparisons}
 Comparing with sign considerations is also fairly critical in several routines (\textit{division for example}).  Based on an unsigned magnitude 
@@ -2000,9 +1990,9 @@ $\vert a \vert < \vert b \vert$.  Step number four will compare the two when the
 \end{alltt}
 \end{small}
 
-The two if statements on lines 22 and 23 perform the initial sign comparison.  If the signs are not the equal then which ever
-has the positive sign is larger.   At line 31, the inputs are compared based on magnitudes.  If the signs were both negative then 
-the unsigned comparison is performed in the opposite direction (\textit{line 33}).  Otherwise, the signs are assumed to 
+The two if statements (lines 22 and 23) perform the initial sign comparison.  If the signs are not the equal then which ever
+has the positive sign is larger.   The inputs are compared (line 31) based on magnitudes.  If the signs were both 
+negative then the unsigned comparison is performed in the opposite direction (line 33).  Otherwise, the signs are assumed to 
 be both positive and a forward direction unsigned comparison is performed.
 
 \section*{Exercises}
@@ -2218,19 +2208,21 @@ The final carry is stored in $c_{max}$ and digits above $max$ upto $oldused$ are
 \end{alltt}
 \end{small}
 
-Lines 27 to 35 perform the initial sorting of the inputs and determine the $min$ and $max$ variables.  Note that $x$ is a pointer to a 
-mp\_int assigned to the largest input, in effect it is a local alias.  Lines 37 to 42 ensure that the destination is grown to 
-accomodate the result of the addition. 
+We first sort (lines 27 to 35) the inputs based on magnitude and determine the $min$ and $max$ variables.
+Note that $x$ is a pointer to an mp\_int assigned to the largest input, in effect it is a local alias.  Next we
+grow the destination (37 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 
 lines 55, 58 and 61 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.
 
-The initial carry $u$ is cleared on line 64, note that $u$ is of type mp\_digit which ensures type compatibility within the 
-implementation.  The initial addition loop begins on line 65 and ends on line 74.  Similarly the conditional addition loop
-begins on line 80 and ends on line 90.  The addition is finished with the final carry being stored in $tmpc$ on line 93.  
-Note the ``++'' operator on the same line.  After line 93 $tmpc$ will point to the $c.used$'th digit of the mp\_int $c$.  This is useful
-for the next loop on lines 96 to 99 which set any old upper digits to zero.
+The initial carry $u$ will be cleared (line 64), note that $u$ is of type mp\_digit which ensures type 
+compatibility within the implementation.  The initial addition (line 65 to 74) adds digits from
+both inputs until the smallest input runs out of digits.  Similarly the conditional addition loop
+(line 80 to 90) adds the remaining digits from the larger of the two inputs.  The addition is finished 
+with the final carry being stored in $tmpc$ (line 93).  Note the ``++'' operator within the same expression.
+After line 93, $tmpc$ will point to the $c.used$'th digit of the mp\_int $c$.  This is useful
+for the next loop (line 96 to 99) which set any old upper digits to zero.
 
 \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
@@ -2245,7 +2237,7 @@ this algorithm we will assume that the variable $\gamma$ represents the number o
 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''
-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]
 \begin{center}
@@ -2387,20 +2379,23 @@ If $b$ has a smaller magnitude than $a$ then step 9 will force the carry and cop
 \end{alltt}
 \end{small}
 
-Line 24 and 25 perform the initial hardcoded sorting of the inputs.  In reality the $min$ and $max$ variables are only aliases and are only 
-used to make the source code easier to read.  Again the pointer alias optimization is used within this algorithm.  Lines 41, 42 and 43 initialize the aliases for 
-$a$, $b$ and $c$ respectively.
+Like low level addition we ``sort'' the inputs.  Except in this case the sorting is hardcoded 
+(lines 24 and 25).  In reality the $min$ and $max$ variables are only aliases and are only 
+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 41, 42 and 43) for $a$, $b$ and $c$ respectively.
 
-The first subtraction loop occurs on lines 46 through 60.  The theory behind the subtraction loop is exactly the same as that for
-the addition loop.  As remarked earlier there is an implementation reason for using the ``awkward'' method of extracting the carry 
-(\textit{see line 56}).  The traditional method for extracting the carry would be to shift by $lg(\beta)$ positions and logically AND 
-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
-occurs from subtraction.  This carry extraction requires two relatively cheap operations to extract the carry.  The other method is to simply 
-shift the 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.
+The first subtraction loop (lines 46 through 60) subtract digits from both inputs until the smaller of
+the two inputs has been exhausted.  As remarked earlier there is an implementation reason for using the ``awkward'' 
+method of extracting the carry (line 56).  The traditional method for extracting the carry would be to shift 
+by $lg(\beta)$ positions and logically AND 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 occurs from subtraction.  This carry 
+extraction requires two relatively cheap operations to extract the carry.  The other method is to simply shift the 
+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 63 through 72}) is required to propagate the carry through
-$a$ and copy the result to $c$.  
+If $a$ has a larger magnitude than $b$ an additional loop (lines 63 through 72) is required to propagate 
+the carry through $a$ and copy the result to $c$.  
 
 \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
@@ -2985,10 +2980,11 @@ step 8 sets the lower $b$ digits to zero.
 \end{alltt}
 \end{small}
 
-The if statement on line 23 ensures that the $b$ variable is greater than zero.  The \textbf{used} count is incremented by $b$ before
-the copy loop begins.  This elminates the need for an additional variable in the for loop.  The variable $top$ on line 41 is an alias
-for the leading digit while $bottom$ on line 44 is an alias for the trailing edge.  The aliases form a window of exactly $b$ digits
-over the input.  
+The if statement (line 23) ensures that the $b$ variable is greater than zero since we do not interpret negative
+shift counts properly.  The \textbf{used} count is incremented by $b$ before the copy loop begins.  This elminates 
+the need for an additional variable in the for loop.  The variable $top$ (line 41) is an alias
+for the leading digit while $bottom$ (line 44) is an alias for the trailing edge.  The aliases form a 
+window of exactly $b$ digits over the input.  
 
 \subsection{Division by $x$}
 
@@ -3095,9 +3091,9 @@ Once the window copy is complete the upper digits must be zeroed and the \textbf
 \end{alltt}
 \end{small}
 
-The only noteworthy element of this routine is the lack of a return type.  
-
--- Will update later to give it a return type...Tom
+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) we then zero
+the upper digits of the input to make sure the result is correct.
 
 \section{Powers of Two}
 
@@ -3228,7 +3224,15 @@ complete.  It is possible to optimize this algorithm down to a $O(n)$ algorithm
 \end{alltt}
 \end{small}
 
-Notes to be revised when code is updated. -- Tom
+The shifting is performed in--place which means the first step (line 24) 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) 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 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}
 
@@ -3361,7 +3365,8 @@ 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
 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}
 
@@ -3446,7 +3451,13 @@ is copied to $b$, leading digits are removed and the remaining leading digit is
 \end{alltt}
 \end{small}
 
--- 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).  Next we reduce the 
+leading digit of both (line 45) and then mp\_clamp().
 
 \section*{Exercises}
 \begin{tabular}{cl}
@@ -3611,101 +3622,113 @@ exceed the precision requested.
 018    * HAC pp. 595, Algorithm 14.12  Modified so you can control how 
 019    * many digits of output are created.
 020    */
-021   int
-022   s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
-023   \{
-024     mp_int  t;
-025     int     res, pa, pb, ix, iy;
-026     mp_digit u;
-027     mp_word r;
-028     mp_digit tmpx, *tmpt, *tmpy;
-029   
-030     /* can we use the fast multiplier? */
-031     if (((digs) < MP_WARRAY) &&
-032         MIN (a->used, b->used) < 
-033             (1 << ((CHAR_BIT * sizeof (mp_word)) - (2 * DIGIT_BIT)))) \{
-034       return fast_s_mp_mul_digs (a, b, c, digs);
-035     \}
-036   
-037     if ((res = mp_init_size (&t, digs)) != MP_OKAY) \{
-038       return res;
-039     \}
-040     t.used = digs;
-041   
-042     /* compute the digits of the product directly */
-043     pa = a->used;
-044     for (ix = 0; ix < pa; ix++) \{
-045       /* set the carry to zero */
-046       u = 0;
-047   
-048       /* limit ourselves to making digs digits of output */
-049       pb = MIN (b->used, digs - ix);
-050   
-051       /* setup some aliases */
-052       /* copy of the digit from a used within the nested loop */
-053       tmpx = a->dp[ix];
-054       
-055       /* an alias for the destination shifted ix places */
-056       tmpt = t.dp + ix;
-057       
-058       /* an alias for the digits of b */
-059       tmpy = b->dp;
-060   
-061       /* compute the columns of the output and propagate the carry */
-062       for (iy = 0; iy < pb; iy++) \{
-063         /* compute the column as a mp_word */
-064         r       = ((mp_word)*tmpt) +
-065                   ((mp_word)tmpx) * ((mp_word)*tmpy++) +
-066                   ((mp_word) u);
-067   
-068         /* the new column is the lower part of the result */
-069         *tmpt++ = (mp_digit) (r & ((mp_word) MP_MASK));
-070   
-071         /* get the carry word from the result */
-072         u       = (mp_digit) (r >> ((mp_word) DIGIT_BIT));
-073       \}
-074       /* set carry if it is placed below digs */
-075       if (ix + iy < digs) \{
-076         *tmpt = u;
-077       \}
-078     \}
-079   
-080     mp_clamp (&t);
-081     mp_exch (&t, c);
-082   
-083     mp_clear (&t);
-084     return MP_OKAY;
-085   \}
-086   #endif
+021   int s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
+022   \{
+023     mp_int  t;
+024     int     res, pa, pb, ix, iy;
+025     mp_digit u;
+026     mp_word r;
+027     mp_digit tmpx, *tmpt, *tmpy;
+028   
+029     /* can we use the fast multiplier? */
+030     if (((digs) < MP_WARRAY) &&
+031         MIN (a->used, b->used) < 
+032             (1 << ((CHAR_BIT * sizeof (mp_word)) - (2 * DIGIT_BIT)))) \{
+033       return fast_s_mp_mul_digs (a, b, c, digs);
+034     \}
+035   
+036     if ((res = mp_init_size (&t, digs)) != MP_OKAY) \{
+037       return res;
+038     \}
+039     t.used = digs;
+040   
+041     /* compute the digits of the product directly */
+042     pa = a->used;
+043     for (ix = 0; ix < pa; ix++) \{
+044       /* set the carry to zero */
+045       u = 0;
+046   
+047       /* limit ourselves to making digs digits of output */
+048       pb = MIN (b->used, digs - ix);
+049   
+050       /* setup some aliases */
+051       /* copy of the digit from a used within the nested loop */
+052       tmpx = a->dp[ix];
+053       
+054       /* an alias for the destination shifted ix places */
+055       tmpt = t.dp + ix;
+056       
+057       /* an alias for the digits of b */
+058       tmpy = b->dp;
+059   
+060       /* compute the columns of the output and propagate the carry */
+061       for (iy = 0; iy < pb; iy++) \{
+062         /* compute the column as a mp_word */
+063         r       = ((mp_word)*tmpt) +
+064                   ((mp_word)tmpx) * ((mp_word)*tmpy++) +
+065                   ((mp_word) u);
+066   
+067         /* the new column is the lower part of the result */
+068         *tmpt++ = (mp_digit) (r & ((mp_word) MP_MASK));
+069   
+070         /* get the carry word from the result */
+071         u       = (mp_digit) (r >> ((mp_word) DIGIT_BIT));
+072       \}
+073       /* set carry if it is placed below digs */
+074       if (ix + iy < digs) \{
+075         *tmpt = u;
+076       \}
+077     \}
+078   
+079     mp_clamp (&t);
+080     mp_exch (&t, c);
+081   
+082     mp_clear (&t);
+083     return MP_OKAY;
+084   \}
+085   #endif
 \end{alltt}
 \end{small}
 
-Lines 31 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
-the number of digits of output is less than \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.
+First we determine (line 30) if the Comba method can be used first since it's faster.  The conditions for 
+sing the Comba routine are that min$(a.used, b.used) < \delta$ and the number of digits of output is less than 
+\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.
+
+If we cannot use the Comba method we proceed to setup the baseline routine.  We allocate the the destination mp\_int
+$t$ (line 36) to the exact size of the output to avoid further re--allocations.  At this point we now 
+begin the $O(n^2)$ loop.
 
-Of particular importance is the calculation of the $ix+iy$'th column on lines 64, 65 and 66.  Note how all of the
-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 
-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 
-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 
-example, the instruction ``MUL'' on the x86 processor can multiply two 32-bit values and produce a 64-bit result.  
+This implementation of multiplication has the caveat that it can be trimmed to only produce a variable number of
+digits as output.  In each iteration of the outer loop the $pb$ variable is set (line 48) 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) and the carry propagated (line 71) to the 
+next iteration.
 
 \subsection{Faster Multiplication by the ``Comba'' Method}
 
-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
-makes the nested loop very sequential and hard to unroll and implement in parallel.  The ``Comba'' \cite{COMBA} method is named after little known 
-(\textit{in cryptographic venues}) Paul G. Comba who described a method of implementing fast multipliers that do not require nested 
-carry fixup operations.  As an interesting aside it seems that Paul Barrett describes a similar technique in
-his 1986 paper \cite{BARRETT} written five years before.
+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 makes the nested loop very sequential and hard to unroll and implement 
+in parallel.  The ``Comba'' \cite{COMBA} method is named after little known (\textit{in cryptographic venues}) Paul G. 
+Comba who described a method of implementing fast multipliers that do not require nested carry fixup operations.  As an 
+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
-the columns of the result are produced.  In the standard long-hand algorithm rows of products 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.  
+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 the columns of the result are produced.  In the standard long-hand algorithm rows of products 
+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 
-simple multiplication and addition step is performed.  The carries of the columns are propagated 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. 
+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 simple multiplication and addition step is performed.  The carries of the columns are propagated 
+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}
 \vec x_n = \sum_{i+j = n} a_ib_j, \forall n \in \lbrace 0, 1, 2, \ldots, i + j \rbrace
@@ -3799,38 +3822,32 @@ $256$ 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{Output}.  $c \leftarrow \vert a \vert \cdot \vert b \vert \mbox{ (mod }\beta^{digs}\mbox{)}$. \\
 \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}) \\
 2.  If step 1 failed return(\textit{MP\_MEM}).\\
 \\
-Zero the temporary array $\hat W$. \\
-3.  for $n$ from $0$ to $digs - 1$ do \\
-\hspace{3mm}3.1  $\hat W_n \leftarrow 0$ \\
+3.  $pa \leftarrow \mbox{MIN}(digs, a.used + b.used)$ \\
 \\
-Compute the columns. \\
-4.  for $ix$ from $0$ to $a.used - 1$ do \\
-\hspace{3mm}4.1  $pb \leftarrow \mbox{min}(b.used, digs - ix)$ \\
-\hspace{3mm}4.2  If $pb < 1$ then goto step 5. \\
-\hspace{3mm}4.3  for $iy$ from $0$ to $pb - 1$ do \\
-\hspace{6mm}4.3.1  $\hat W_{ix+iy} \leftarrow \hat W_{ix+iy} + a_{ix}b_{iy}$ \\
+4.  $\_ \hat W \leftarrow 0$ \\
+5.  for $ix$ from 0 to $pa - 1$ do \\
+\hspace{3mm}5.1  $ty \leftarrow \mbox{MIN}(b.used - 1, ix)$ \\
+\hspace{3mm}5.2  $tx \leftarrow ix - ty$ \\
+\hspace{3mm}5.3  $iy \leftarrow \mbox{MIN}(a.used - tx, ty + 1)$ \\
+\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. \\
-5.  $oldused \leftarrow c.used$ \\
-6.  $c.used \leftarrow digs$ \\
-7.  If $digs > 1$ then do \\
-\hspace{3mm}7.1.  for $ix$ from $1$ to $digs - 1$ do \\
-\hspace{6mm}7.1.1  $\hat W_{ix} \leftarrow \hat W_{ix} + \lfloor \hat W_{ix-1} / \beta \rfloor$ \\
-\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.  $c_{ix} \leftarrow \hat W_{ix} \mbox{ (mod }\beta\mbox{)}$ \\
+7.  $oldused \leftarrow c.used$ \\
+8.  $c.used \leftarrow digs$ \\
+9.  for $ix$ from $0$ to $pa$ do \\
+\hspace{3mm}9.1  $c_{ix} \leftarrow W_{ix}$ \\
+10.  for $ix$ from $pa + 1$ to $oldused - 1$ do \\
+\hspace{3mm}10.1 $c_{ix} \leftarrow 0$ \\
 \\
-Zero excess digits. \\
-10.  If $digs < oldused$ then do \\
-\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}). \\
+11.  Clamp $c$. \\
+12.  Return MP\_OKAY. \\
 \hline
 \end{tabular}
 \end{center}
@@ -3840,15 +3857,24 @@ Zero excess digits. \\
 \end{figure}
 
 \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
-essentially peforms the same calculation as algorithm s\_mp\_mul\_digs, just much faster.
+This algorithm performs the unsigned multiplication of $a$ and $b$ using the Comba method limited to $digs$ digits of precision.
+
+The outer loop of this algorithm is more complicated than that of the baseline multiplier.  This is because on the inside of the 
+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 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 
-unlike algorithm s\_mp\_mul\_digs no temporary mp\_int is required since the result is calculated directly in $\hat W$.  
+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
+$b$ this will be limited to $b.used - 1$.  The $tx$ variable is set to the to the distance past $b.used$ the variable
+$ix$ is.  This is used for the immediately subsequent statement where we find $iy$.  
 
-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
-a carry variable or propagation in this loop allows the loop to be performed with only single precision multiplication and additions.  Now that each
-iteration of the inner loop can be performed independent of the others the inner loop can be performed with a high level of parallelism.
+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 
 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 
@@ -3877,97 +3903,95 @@ and addition operations in the nested loop in parallel.
 030    * Based on Algorithm 14.12 on pp.595 of HAC.
 031    *
 032    */
-033   int
-034   fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
-035   \{
-036     int     olduse, res, pa, ix, iz;
-037     mp_digit W[MP_WARRAY];
-038     register mp_word  _W;
-039   
-040     /* grow the destination as required */
-041     if (c->alloc < digs) \{
-042       if ((res = mp_grow (c, digs)) != MP_OKAY) \{
-043         return res;
-044       \}
-045     \}
-046   
-047     /* number of output digits to produce */
-048     pa = MIN(digs, a->used + b->used);
-049   
-050     /* clear the carry */
-051     _W = 0;
-052     for (ix = 0; ix < pa; ix++) \{ 
-053         int      tx, ty;
-054         int      iy;
-055         mp_digit *tmpx, *tmpy;
-056   
-057         /* get offsets into the two bignums */
-058         ty = MIN(b->used-1, ix);
-059         tx = ix - ty;
-060   
-061         /* setup temp aliases */
-062         tmpx = a->dp + tx;
-063         tmpy = b->dp + ty;
-064   
-065         /* this is the number of times the loop will iterrate, essentially its
-       
-066            while (tx++ < a->used && ty-- >= 0) \{ ... \}
-067          */
-068         iy = MIN(a->used-tx, ty+1);
-069   
-070         /* execute loop */
-071         for (iz = 0; iz < iy; ++iz) \{
-072            _W += ((mp_word)*tmpx++)*((mp_word)*tmpy--);
-073         \}
-074   
-075         /* store term */
-076         W[ix] = ((mp_digit)_W) & MP_MASK;
-077   
-078         /* make next carry */
-079         _W = _W >> ((mp_word)DIGIT_BIT);
-080     \}
-081   
-082     /* store final carry */
-083     W[ix] = _W;
-084   
-085     /* setup dest */
-086     olduse  = c->used;
-087     c->used = digs;
-088   
-089     \{
-090       register mp_digit *tmpc;
-091       tmpc = c->dp;
-092       for (ix = 0; ix < digs; ix++) \{
-093         /* now extract the previous digit [below the carry] */
-094         *tmpc++ = W[ix];
-095       \}
-096   
-097       /* clear unused digits [that existed in the old copy of c] */
-098       for (; ix < olduse; ix++) \{
-099         *tmpc++ = 0;
-100       \}
-101     \}
-102     mp_clamp (c);
-103     return MP_OKAY;
-104   \}
-105   #endif
+033   int fast_s_mp_mul_digs (mp_int * a, mp_int * b, mp_int * c, int digs)
+034   \{
+035     int     olduse, res, pa, ix, iz;
+036     mp_digit W[MP_WARRAY];
+037     register mp_word  _W;
+038   
+039     /* grow the destination as required */
+040     if (c->alloc < digs) \{
+041       if ((res = mp_grow (c, digs)) != MP_OKAY) \{
+042         return res;
+043       \}
+044     \}
+045   
+046     /* number of output digits to produce */
+047     pa = MIN(digs, a->used + b->used);
+048   
+049     /* clear the carry */
+050     _W = 0;
+051     for (ix = 0; ix < pa; ix++) \{ 
+052         int      tx, ty;
+053         int      iy;
+054         mp_digit *tmpx, *tmpy;
+055   
+056         /* get offsets into the two bignums */
+057         ty = MIN(b->used-1, ix);
+058         tx = ix - ty;
+059   
+060         /* setup temp aliases */
+061         tmpx = a->dp + tx;
+062         tmpy = b->dp + ty;
+063   
+064         /* this is the number of times the loop will iterrate, essentially 
+065            while (tx++ < a->used && ty-- >= 0) \{ ... \}
+066          */
+067         iy = MIN(a->used-tx, ty+1);
+068   
+069         /* execute loop */
+070         for (iz = 0; iz < iy; ++iz) \{
+071            _W += ((mp_word)*tmpx++)*((mp_word)*tmpy--);
+072         \}
+073   
+074         /* store term */
+075         W[ix] = ((mp_digit)_W) & MP_MASK;
+076   
+077         /* make next carry */
+078         _W = _W >> ((mp_word)DIGIT_BIT);
+079     \}
+080   
+081     /* store final carry */
+082     W[ix] = (mp_digit)(_W & MP_MASK);
+083   
+084     /* setup dest */
+085     olduse  = c->used;
+086     c->used = pa;
+087   
+088     \{
+089       register mp_digit *tmpc;
+090       tmpc = c->dp;
+091       for (ix = 0; ix < pa+1; ix++) \{
+092         /* now extract the previous digit [below the carry] */
+093         *tmpc++ = W[ix];
+094       \}
+095   
+096       /* clear unused digits [that existed in the old copy of c] */
+097       for (; ix < olduse; ix++) \{
+098         *tmpc++ = 0;
+099       \}
+100     \}
+101     mp_clamp (c);
+102     return MP_OKAY;
+103   \}
+104   #endif
 \end{alltt}
 \end{small}
 
-The memset on line @47,memset@ clears the initial $\hat W$ array to zero in a single step. Like the slower baseline multiplication
-implementation a series of aliases (\textit{lines 62, 63 and 76}) are used to simplify the inner $O(n^2)$ loop.  
-In this case a new alias $\_\hat W$ has been added which refers to the double precision columns offset by $ix$ in each pass.  
+As per the pseudo--code we first calculate $pa$ (line 47) as the number of digits to output.  Next we begin the outer loop
+to produce the individual columns of the product.  We use the two aliases $tmpx$ and $tmpy$ (lines 61, 62) to point
+inside the two multiplicands quickly.  
 
-The inner loop on lines 92, 79 and 80 is where the algorithm will spend the majority of the time, which is why it has been 
-stripped to the bones of any extra baggage\footnote{Hence the pointer aliases.}.  On x86 processors the multiplication and additions amount to at the 
-very least five instructions (\textit{two loads, two additions, one multiply}) while on the ARMv4 processors they amount to only three 
-(\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 
-and scheduling the instructions so there are very few dependency stalls.
+The inner loop (lines 70 to 72) of this implementation is where the tradeoff come into play.  Originally this comba 
+implementation was ``row--major'' which means it adds to each of the columns in each pass.  After the outer loop it would then fix 
+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 
+one mp\_word per iteration.  On processors such as the Athlon XP and P4 this did not matter much since the cache bandwidth 
+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
-baseline method there are dependency stalls as the algorithm must wait for the multiplier to finish before propagating the carry to the next 
-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.  
+After the inner loop we store the current accumulator in $W$ and shift $\_ \hat W$ (lines 75, 78) to forward it as 
+a carry for the next pass.  After the outer loop we use the final carry (line 82) as the last digit of the product.  
 
 \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
@@ -4444,277 +4468,290 @@ result $a \cdot b$ is produced.
 016   
 017   /* multiplication using the Toom-Cook 3-way algorithm 
 018    *
-019    * Much more complicated than Karatsuba but has a lower asymptotic running t
-      ime of 
-020    * O(N**1.464).  This algorithm is only particularly useful on VERY large
-021    * inputs (we're talking 1000s of digits here...).
-022   */
-023   int mp_toom_mul(mp_int *a, mp_int *b, mp_int *c)
-024   \{
-025       mp_int w0, w1, w2, w3, w4, tmp1, tmp2, a0, a1, a2, b0, b1, b2;
-026       int res, B;
-027           
-028       /* init temps */
-029       if ((res = mp_init_multi(&w0, &w1, &w2, &w3, &w4, 
-030                                &a0, &a1, &a2, &b0, &b1, 
-031                                &b2, &tmp1, &tmp2, NULL)) != MP_OKAY) \{
-032          return res;
-033       \}
-034       
-035       /* B */
-036       B = MIN(a->used, b->used) / 3;
-037       
-038       /* a = a2 * B**2 + a1 * B + a0 */
-039       if ((res = mp_mod_2d(a, DIGIT_BIT * B, &a0)) != MP_OKAY) \{
-040          goto ERR;
-041       \}
-042   
-043       if ((res = mp_copy(a, &a1)) != MP_OKAY) \{
-044          goto ERR;
-045       \}
-046       mp_rshd(&a1, B);
-047       mp_mod_2d(&a1, DIGIT_BIT * B, &a1);
-048   
-049       if ((res = mp_copy(a, &a2)) != MP_OKAY) \{
-050          goto ERR;
-051       \}
-052       mp_rshd(&a2, B*2);
-053       
-054       /* b = b2 * B**2 + b1 * B + b0 */
-055       if ((res = mp_mod_2d(b, DIGIT_BIT * B, &b0)) != MP_OKAY) \{
-056          goto ERR;
-057       \}
-058   
-059       if ((res = mp_copy(b, &b1)) != MP_OKAY) \{
-060          goto ERR;
-061       \}
-062       mp_rshd(&b1, B);
-063       mp_mod_2d(&b1, DIGIT_BIT * B, &b1);
-064   
-065       if ((res = mp_copy(b, &b2)) != MP_OKAY) \{
-066          goto ERR;
-067       \}
-068       mp_rshd(&b2, B*2);
-069       
-070       /* w0 = a0*b0 */
-071       if ((res = mp_mul(&a0, &b0, &w0)) != MP_OKAY) \{
-072          goto ERR;
-073       \}
-074       
-075       /* w4 = a2 * b2 */
-076       if ((res = mp_mul(&a2, &b2, &w4)) != MP_OKAY) \{
-077          goto ERR;
-078       \}
-079       
-080       /* w1 = (a2 + 2(a1 + 2a0))(b2 + 2(b1 + 2b0)) */
-081       if ((res = mp_mul_2(&a0, &tmp1)) != MP_OKAY) \{
-082          goto ERR;
-083       \}
-084       if ((res = mp_add(&tmp1, &a1, &tmp1)) != MP_OKAY) \{
-085          goto ERR;
-086       \}
-087       if ((res = mp_mul_2(&tmp1, &tmp1)) != MP_OKAY) \{
-088          goto ERR;
-089       \}
-090       if ((res = mp_add(&tmp1, &a2, &tmp1)) != MP_OKAY) \{
-091          goto ERR;
-092       \}
-093       
-094       if ((res = mp_mul_2(&b0, &tmp2)) != MP_OKAY) \{
-095          goto ERR;
-096       \}
-097       if ((res = mp_add(&tmp2, &b1, &tmp2)) != MP_OKAY) \{
-098          goto ERR;
-099       \}
-100       if ((res = mp_mul_2(&tmp2, &tmp2)) != MP_OKAY) \{
-101          goto ERR;
-102       \}
-103       if ((res = mp_add(&tmp2, &b2, &tmp2)) != MP_OKAY) \{
-104          goto ERR;
-105       \}
-106       
-107       if ((res = mp_mul(&tmp1, &tmp2, &w1)) != MP_OKAY) \{
-108          goto ERR;
-109       \}
-110       
-111       /* w3 = (a0 + 2(a1 + 2a2))(b0 + 2(b1 + 2b2)) */
-112       if ((res = mp_mul_2(&a2, &tmp1)) != MP_OKAY) \{
-113          goto ERR;
-114       \}
-115       if ((res = mp_add(&tmp1, &a1, &tmp1)) != MP_OKAY) \{
-116          goto ERR;
-117       \}
-118       if ((res = mp_mul_2(&tmp1, &tmp1)) != MP_OKAY) \{
-119          goto ERR;
-120       \}
-121       if ((res = mp_add(&tmp1, &a0, &tmp1)) != MP_OKAY) \{
-122          goto ERR;
-123       \}
-124       
-125       if ((res = mp_mul_2(&b2, &tmp2)) != MP_OKAY) \{
-126          goto ERR;
-127       \}
-128       if ((res = mp_add(&tmp2, &b1, &tmp2)) != MP_OKAY) \{
-129          goto ERR;
-130       \}
-131       if ((res = mp_mul_2(&tmp2, &tmp2)) != MP_OKAY) \{
-132          goto ERR;
-133       \}
-134       if ((res = mp_add(&tmp2, &b0, &tmp2)) != MP_OKAY) \{
-135          goto ERR;
-136       \}
-137       
-138       if ((res = mp_mul(&tmp1, &tmp2, &w3)) != MP_OKAY) \{
-139          goto ERR;
-140       \}
-141       
-142   
-143       /* w2 = (a2 + a1 + a0)(b2 + b1 + b0) */
-144       if ((res = mp_add(&a2, &a1, &tmp1)) != MP_OKAY) \{
-145          goto ERR;
-146       \}
-147       if ((res = mp_add(&tmp1, &a0, &tmp1)) != MP_OKAY) \{
-148          goto ERR;
-149       \}
-150       if ((res = mp_add(&b2, &b1, &tmp2)) != MP_OKAY) \{
-151          goto ERR;
-152       \}
-153       if ((res = mp_add(&tmp2, &b0, &tmp2)) != MP_OKAY) \{
-154          goto ERR;
-155       \}
-156       if ((res = mp_mul(&tmp1, &tmp2, &w2)) != MP_OKAY) \{
-157          goto ERR;
-158       \}
-159       
-160       /* now solve the matrix 
-161       
-162          0  0  0  0  1
-163          1  2  4  8  16
-164          1  1  1  1  1
-165          16 8  4  2  1
-166          1  0  0  0  0
-167          
-168          using 12 subtractions, 4 shifts, 
-169                 2 small divisions and 1 small multiplication 
-170        */
-171        
-172        /* r1 - r4 */
-173        if ((res = mp_sub(&w1, &w4, &w1)) != MP_OKAY) \{
-174           goto ERR;
-175        \}
-176        /* r3 - r0 */
-177        if ((res = mp_sub(&w3, &w0, &w3)) != MP_OKAY) \{
-178           goto ERR;
-179        \}
-180        /* r1/2 */
-181        if ((res = mp_div_2(&w1, &w1)) != MP_OKAY) \{
-182           goto ERR;
-183        \}
-184        /* r3/2 */
-185        if ((res = mp_div_2(&w3, &w3)) != MP_OKAY) \{
-186           goto ERR;
-187        \}
-188        /* r2 - r0 - r4 */
-189        if ((res = mp_sub(&w2, &w0, &w2)) != MP_OKAY) \{
-190           goto ERR;
-191        \}
-192        if ((res = mp_sub(&w2, &w4, &w2)) != MP_OKAY) \{
-193           goto ERR;
-194        \}
-195        /* r1 - r2 */
-196        if ((res = mp_sub(&w1, &w2, &w1)) != MP_OKAY) \{
-197           goto ERR;
-198        \}
-199        /* r3 - r2 */
-200        if ((res = mp_sub(&w3, &w2, &w3)) != MP_OKAY) \{
-201           goto ERR;
-202        \}
-203        /* r1 - 8r0 */
-204        if ((res = mp_mul_2d(&w0, 3, &tmp1)) != MP_OKAY) \{
-205           goto ERR;
-206        \}
-207        if ((res = mp_sub(&w1, &tmp1, &w1)) != MP_OKAY) \{
-208           goto ERR;
-209        \}
-210        /* r3 - 8r4 */
-211        if ((res = mp_mul_2d(&w4, 3, &tmp1)) != MP_OKAY) \{
-212           goto ERR;
-213        \}
-214        if ((res = mp_sub(&w3, &tmp1, &w3)) != MP_OKAY) \{
-215           goto ERR;
-216        \}
-217        /* 3r2 - r1 - r3 */
-218        if ((res = mp_mul_d(&w2, 3, &w2)) != MP_OKAY) \{
-219           goto ERR;
-220        \}
-221        if ((res = mp_sub(&w2, &w1, &w2)) != MP_OKAY) \{
-222           goto ERR;
-223        \}
-224        if ((res = mp_sub(&w2, &w3, &w2)) != MP_OKAY) \{
-225           goto ERR;
-226        \}
-227        /* r1 - r2 */
-228        if ((res = mp_sub(&w1, &w2, &w1)) != MP_OKAY) \{
-229           goto ERR;
-230        \}
-231        /* r3 - r2 */
-232        if ((res = mp_sub(&w3, &w2, &w3)) != MP_OKAY) \{
-233           goto ERR;
-234        \}
-235        /* r1/3 */
-236        if ((res = mp_div_3(&w1, &w1, NULL)) != MP_OKAY) \{
-237           goto ERR;
-238        \}
-239        /* r3/3 */
-240        if ((res = mp_div_3(&w3, &w3, NULL)) != MP_OKAY) \{
-241           goto ERR;
-242        \}
-243        
-244        /* at this point shift W[n] by B*n */
-245        if ((res = mp_lshd(&w1, 1*B)) != MP_OKAY) \{
-246           goto ERR;
-247        \}
-248        if ((res = mp_lshd(&w2, 2*B)) != MP_OKAY) \{
-249           goto ERR;
-250        \}
-251        if ((res = mp_lshd(&w3, 3*B)) != MP_OKAY) \{
-252           goto ERR;
-253        \}
-254        if ((res = mp_lshd(&w4, 4*B)) != MP_OKAY) \{
-255           goto ERR;
-256        \}     
-257        
-258        if ((res = mp_add(&w0, &w1, c)) != MP_OKAY) \{
-259           goto ERR;
-260        \}
-261        if ((res = mp_add(&w2, &w3, &tmp1)) != MP_OKAY) \{
-262           goto ERR;
-263        \}
-264        if ((res = mp_add(&w4, &tmp1, &tmp1)) != MP_OKAY) \{
-265           goto ERR;
-266        \}
-267        if ((res = mp_add(&tmp1, c, c)) != MP_OKAY) \{
-268           goto ERR;
-269        \}     
-270        
-271   ERR:
-272        mp_clear_multi(&w0, &w1, &w2, &w3, &w4, 
-273                       &a0, &a1, &a2, &b0, &b1, 
-274                       &b2, &tmp1, &tmp2, NULL);
-275        return res;
-276   \}     
-277        
-278   #endif
+019    * Much more complicated than Karatsuba but has a lower 
+020    * asymptotic running time of O(N**1.464).  This algorithm is 
+021    * only particularly useful on VERY large inputs 
+022    * (we're talking 1000s of digits here...).
+023   */
+024   int mp_toom_mul(mp_int *a, mp_int *b, mp_int *c)
+025   \{
+026       mp_int w0, w1, w2, w3, w4, tmp1, tmp2, a0, a1, a2, b0, b1, b2;
+027       int res, B;
+028           
+029       /* init temps */
+030       if ((res = mp_init_multi(&w0, &w1, &w2, &w3, &w4, 
+031                                &a0, &a1, &a2, &b0, &b1, 
+032                                &b2, &tmp1, &tmp2, NULL)) != MP_OKAY) \{
+033          return res;
+034       \}
+035       
+036       /* B */
+037       B = MIN(a->used, b->used) / 3;
+038       
+039       /* a = a2 * B**2 + a1 * B + a0 */
+040       if ((res = mp_mod_2d(a, DIGIT_BIT * B, &a0)) != MP_OKAY) \{
+041          goto ERR;
+042       \}
+043   
+044       if ((res = mp_copy(a, &a1)) != MP_OKAY) \{
+045          goto ERR;
+046       \}
+047       mp_rshd(&a1, B);
+048       mp_mod_2d(&a1, DIGIT_BIT * B, &a1);
+049   
+050       if ((res = mp_copy(a, &a2)) != MP_OKAY) \{
+051          goto ERR;
+052       \}
+053       mp_rshd(&a2, B*2);
+054       
+055       /* b = b2 * B**2 + b1 * B + b0 */
+056       if ((res = mp_mod_2d(b, DIGIT_BIT * B, &b0)) != MP_OKAY) \{
+057          goto ERR;
+058       \}
+059   
+060       if ((res = mp_copy(b, &b1)) != MP_OKAY) \{
+061          goto ERR;
+062       \}
+063       mp_rshd(&b1, B);
+064       mp_mod_2d(&b1, DIGIT_BIT * B, &b1);
+065   
+066       if ((res = mp_copy(b, &b2)) != MP_OKAY) \{
+067          goto ERR;
+068       \}
+069       mp_rshd(&b2, B*2);
+070       
+071       /* w0 = a0*b0 */
+072       if ((res = mp_mul(&a0, &b0, &w0)) != MP_OKAY) \{
+073          goto ERR;
+074       \}
+075       
+076       /* w4 = a2 * b2 */
+077       if ((res = mp_mul(&a2, &b2, &w4)) != MP_OKAY) \{
+078          goto ERR;
+079       \}
+080       
+081       /* w1 = (a2 + 2(a1 + 2a0))(b2 + 2(b1 + 2b0)) */
+082       if ((res = mp_mul_2(&a0, &tmp1)) != MP_OKAY) \{
+083          goto ERR;
+084       \}
+085       if ((res = mp_add(&tmp1, &a1, &tmp1)) != MP_OKAY) \{
+086          goto ERR;
+087       \}
+088       if ((res = mp_mul_2(&tmp1, &tmp1)) != MP_OKAY) \{
+089          goto ERR;
+090       \}
+091       if ((res = mp_add(&tmp1, &a2, &tmp1)) != MP_OKAY) \{
+092          goto ERR;
+093       \}
+094       
+095       if ((res = mp_mul_2(&b0, &tmp2)) != MP_OKAY) \{
+096          goto ERR;
+097       \}
+098       if ((res = mp_add(&tmp2, &b1, &tmp2)) != MP_OKAY) \{
+099          goto ERR;
+100       \}
+101       if ((res = mp_mul_2(&tmp2, &tmp2)) != MP_OKAY) \{
+102          goto ERR;
+103       \}
+104       if ((res = mp_add(&tmp2, &b2, &tmp2)) != MP_OKAY) \{
+105          goto ERR;
+106       \}
+107       
+108       if ((res = mp_mul(&tmp1, &tmp2, &w1)) != MP_OKAY) \{
+109          goto ERR;
+110       \}
+111       
+112       /* w3 = (a0 + 2(a1 + 2a2))(b0 + 2(b1 + 2b2)) */
+113       if ((res = mp_mul_2(&a2, &tmp1)) != MP_OKAY) \{
+114          goto ERR;
+115       \}
+116       if ((res = mp_add(&tmp1, &a1, &tmp1)) != MP_OKAY) \{
+117          goto ERR;
+118       \}
+119       if ((res = mp_mul_2(&tmp1, &tmp1)) != MP_OKAY) \{
+120          goto ERR;
+121       \}
+122       if ((res = mp_add(&tmp1, &a0, &tmp1)) != MP_OKAY) \{
+123          goto ERR;
+124       \}
+125       
+126       if ((res = mp_mul_2(&b2, &tmp2)) != MP_OKAY) \{
+127          goto ERR;
+128       \}
+129       if ((res = mp_add(&tmp2, &b1, &tmp2)) != MP_OKAY) \{
+130          goto ERR;
+131       \}
+132       if ((res = mp_mul_2(&tmp2, &tmp2)) != MP_OKAY) \{
+133          goto ERR;
+134       \}
+135       if ((res = mp_add(&tmp2, &b0, &tmp2)) != MP_OKAY) \{
+136          goto ERR;
+137       \}
+138       
+139       if ((res = mp_mul(&tmp1, &tmp2, &w3)) != MP_OKAY) \{
+140          goto ERR;
+141       \}
+142       
+143   
+144       /* w2 = (a2 + a1 + a0)(b2 + b1 + b0) */
+145       if ((res = mp_add(&a2, &a1, &tmp1)) != MP_OKAY) \{
+146          goto ERR;
+147       \}
+148       if ((res = mp_add(&tmp1, &a0, &tmp1)) != MP_OKAY) \{
+149          goto ERR;
+150       \}
+151       if ((res = mp_add(&b2, &b1, &tmp2)) != MP_OKAY) \{
+152          goto ERR;
+153       \}
+154       if ((res = mp_add(&tmp2, &b0, &tmp2)) != MP_OKAY) \{
+155          goto ERR;
+156       \}
+157       if ((res = mp_mul(&tmp1, &tmp2, &w2)) != MP_OKAY) \{
+158          goto ERR;
+159       \}
+160       
+161       /* now solve the matrix 
+162       
+163          0  0  0  0  1
+164          1  2  4  8  16
+165          1  1  1  1  1
+166          16 8  4  2  1
+167          1  0  0  0  0
+168          
+169          using 12 subtractions, 4 shifts, 
+170                 2 small divisions and 1 small multiplication 
+171        */
+172        
+173        /* r1 - r4 */
+174        if ((res = mp_sub(&w1, &w4, &w1)) != MP_OKAY) \{
+175           goto ERR;
+176        \}
+177        /* r3 - r0 */
+178        if ((res = mp_sub(&w3, &w0, &w3)) != MP_OKAY) \{
+179           goto ERR;
+180        \}
+181        /* r1/2 */
+182        if ((res = mp_div_2(&w1, &w1)) != MP_OKAY) \{
+183           goto ERR;
+184        \}
+185        /* r3/2 */
+186        if ((res = mp_div_2(&w3, &w3)) != MP_OKAY) \{
+187           goto ERR;
+188        \}
+189        /* r2 - r0 - r4 */
+190        if ((res = mp_sub(&w2, &w0, &w2)) != MP_OKAY) \{
+191           goto ERR;
+192        \}
+193        if ((res = mp_sub(&w2, &w4, &w2)) != MP_OKAY) \{
+194           goto ERR;
+195        \}
+196        /* r1 - r2 */
+197        if ((res = mp_sub(&w1, &w2, &w1)) != MP_OKAY) \{
+198           goto ERR;
+199        \}
+200        /* r3 - r2 */
+201        if ((res = mp_sub(&w3, &w2, &w3)) != MP_OKAY) \{
+202           goto ERR;
+203        \}
+204        /* r1 - 8r0 */
+205        if ((res = mp_mul_2d(&w0, 3, &tmp1)) != MP_OKAY) \{
+206           goto ERR;
+207        \}
+208        if ((res = mp_sub(&w1, &tmp1, &w1)) != MP_OKAY) \{
+209           goto ERR;
+210        \}
+211        /* r3 - 8r4 */
+212        if ((res = mp_mul_2d(&w4, 3, &tmp1)) != MP_OKAY) \{
+213           goto ERR;
+214        \}
+215        if ((res = mp_sub(&w3, &tmp1, &w3)) != MP_OKAY) \{
+216           goto ERR;
+217        \}
+218        /* 3r2 - r1 - r3 */
+219        if ((res = mp_mul_d(&w2, 3, &w2)) != MP_OKAY) \{
+220           goto ERR;
+221        \}
+222        if ((res = mp_sub(&w2, &w1, &w2)) != MP_OKAY) \{
+223           goto ERR;
+224        \}
+225        if ((res = mp_sub(&w2, &w3, &w2)) != MP_OKAY) \{
+226           goto ERR;
+227        \}
+228        /* r1 - r2 */
+229        if ((res = mp_sub(&w1, &w2, &w1)) != MP_OKAY) \{
+230           goto ERR;
+231        \}
+232        /* r3 - r2 */
+233        if ((res = mp_sub(&w3, &w2, &w3)) != MP_OKAY) \{
+234           goto ERR;
+235        \}
+236        /* r1/3 */
+237        if ((res = mp_div_3(&w1, &w1, NULL)) != MP_OKAY) \{
+238           goto ERR;
+239        \}
+240        /* r3/3 */
+241        if ((res = mp_div_3(&w3, &w3, NULL)) != MP_OKAY) \{
+242           goto ERR;
+243        \}
+244        
+245        /* at this point shift W[n] by B*n */
+246        if ((res = mp_lshd(&w1, 1*B)) != MP_OKAY) \{
+247           goto ERR;
+248        \}
+249        if ((res = mp_lshd(&w2, 2*B)) != MP_OKAY) \{
+250           goto ERR;
+251        \}
+252        if ((res = mp_lshd(&w3, 3*B)) != MP_OKAY) \{
+253           goto ERR;
+254        \}
+255        if ((res = mp_lshd(&w4, 4*B)) != MP_OKAY) \{
+256           goto ERR;
+257        \}     
+258        
+259        if ((res = mp_add(&w0, &w1, c)) != MP_OKAY) \{
+260           goto ERR;
+261        \}
+262        if ((res = mp_add(&w2, &w3, &tmp1)) != MP_OKAY) \{
+263           goto ERR;
+264        \}
+265        if ((res = mp_add(&w4, &tmp1, &tmp1)) != MP_OKAY) \{
+266           goto ERR;
+267        \}
+268        if ((res = mp_add(&tmp1, c, c)) != MP_OKAY) \{
+269           goto ERR;
+270        \}     
+271        
+272   ERR:
+273        mp_clear_multi(&w0, &w1, &w2, &w3, &w4, 
+274                       &a0, &a1, &a2, &b0, &b1, 
+275                       &b2, &tmp1, &tmp2, NULL);
+276        return res;
+277   \}     
+278        
+279   #endif
 \end{alltt}
 \end{small}
 
--- 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 to 69) 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 and 77).  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}
 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.  
 
-\newpage\begin{figure}[!here]
+\begin{figure}[!here]
 \begin{small}
 \begin{center}
 \begin{tabular}{l}
@@ -4847,7 +4884,7 @@ 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
 will not handle.  
 
-\newpage\begin{figure}[!here]
+\begin{figure}[!here]
 \begin{small}
 \begin{center}
 \begin{tabular}{l}
@@ -4907,75 +4944,79 @@ results calculated so far.  This involves expensive carry propagation which will
 \begin{alltt}
 016   
 017   /* low level squaring, b = a*a, HAC pp.596-597, Algorithm 14.16 */
-018   int
-019   s_mp_sqr (mp_int * a, mp_int * b)
-020   \{
-021     mp_int  t;
-022     int     res, ix, iy, pa;
-023     mp_word r;
-024     mp_digit u, tmpx, *tmpt;
-025   
-026     pa = a->used;
-027     if ((res = mp_init_size (&t, 2*pa + 1)) != MP_OKAY) \{
-028       return res;
-029     \}
-030   
-031     /* default used is maximum possible size */
-032     t.used = 2*pa + 1;
-033   
-034     for (ix = 0; ix < pa; ix++) \{
-035       /* first calculate the digit at 2*ix */
-036       /* calculate double precision result */
-037       r = ((mp_word) t.dp[2*ix]) +
-038           ((mp_word)a->dp[ix])*((mp_word)a->dp[ix]);
-039   
-040       /* store lower part in result */
-041       t.dp[ix+ix] = (mp_digit) (r & ((mp_word) MP_MASK));
-042   
-043       /* get the carry */
-044       u           = (mp_digit)(r >> ((mp_word) DIGIT_BIT));
-045   
-046       /* left hand side of A[ix] * A[iy] */
-047       tmpx        = a->dp[ix];
-048   
-049       /* alias for where to store the results */
-050       tmpt        = t.dp + (2*ix + 1);
-051       
-052       for (iy = ix + 1; iy < pa; iy++) \{
-053         /* first calculate the product */
-054         r       = ((mp_word)tmpx) * ((mp_word)a->dp[iy]);
-055   
-056         /* now calculate the double precision result, note we use
-057          * addition instead of *2 since it's easier to optimize
-058          */
-059         r       = ((mp_word) *tmpt) + r + r + ((mp_word) u);
-060   
-061         /* store lower part */
-062         *tmpt++ = (mp_digit) (r & ((mp_word) MP_MASK));
-063   
-064         /* get carry */
-065         u       = (mp_digit)(r >> ((mp_word) DIGIT_BIT));
-066       \}
-067       /* propagate upwards */
-068       while (u != ((mp_digit) 0)) \{
-069         r       = ((mp_word) *tmpt) + ((mp_word) u);
-070         *tmpt++ = (mp_digit) (r & ((mp_word) MP_MASK));
-071         u       = (mp_digit)(r >> ((mp_word) DIGIT_BIT));
-072       \}
-073     \}
-074   
-075     mp_clamp (&t);
-076     mp_exch (&t, b);
-077     mp_clear (&t);
-078     return MP_OKAY;
-079   \}
-080   #endif
+018   int s_mp_sqr (mp_int * a, mp_int * b)
+019   \{
+020     mp_int  t;
+021     int     res, ix, iy, pa;
+022     mp_word r;
+023     mp_digit u, tmpx, *tmpt;
+024   
+025     pa = a->used;
+026     if ((res = mp_init_size (&t, 2*pa + 1)) != MP_OKAY) \{
+027       return res;
+028     \}
+029   
+030     /* default used is maximum possible size */
+031     t.used = 2*pa + 1;
+032   
+033     for (ix = 0; ix < pa; ix++) \{
+034       /* first calculate the digit at 2*ix */
+035       /* calculate double precision result */
+036       r = ((mp_word) t.dp[2*ix]) +
+037           ((mp_word)a->dp[ix])*((mp_word)a->dp[ix]);
+038   
+039       /* store lower part in result */
+040       t.dp[ix+ix] = (mp_digit) (r & ((mp_word) MP_MASK));
+041   
+042       /* get the carry */
+043       u           = (mp_digit)(r >> ((mp_word) DIGIT_BIT));
+044   
+045       /* left hand side of A[ix] * A[iy] */
+046       tmpx        = a->dp[ix];
+047   
+048       /* alias for where to store the results */
+049       tmpt        = t.dp + (2*ix + 1);
+050       
+051       for (iy = ix + 1; iy < pa; iy++) \{
+052         /* first calculate the product */
+053         r       = ((mp_word)tmpx) * ((mp_word)a->dp[iy]);
+054   
+055         /* now calculate the double precision result, note we use
+056          * addition instead of *2 since it's easier to optimize
+057          */
+058         r       = ((mp_word) *tmpt) + r + r + ((mp_word) u);
+059   
+060         /* store lower part */
+061         *tmpt++ = (mp_digit) (r & ((mp_word) MP_MASK));
+062   
+063         /* get carry */
+064         u       = (mp_digit)(r >> ((mp_word) DIGIT_BIT));
+065       \}
+066       /* propagate upwards */
+067       while (u != ((mp_digit) 0)) \{
+068         r       = ((mp_word) *tmpt) + ((mp_word) u);
+069         *tmpt++ = (mp_digit) (r & ((mp_word) MP_MASK));
+070         u       = (mp_digit)(r >> ((mp_word) DIGIT_BIT));
+071       \}
+072     \}
+073   
+074     mp_clamp (&t);
+075     mp_exch (&t, b);
+076     mp_clear (&t);
+077     return MP_OKAY;
+078   \}
+079   #endif
 \end{alltt}
 \end{small}
 
-Inside the outer loop (\textit{see line 34}) the square term is calculated on line 37.  Line 44 extracts the carry from the square
-term.  Aliases for $a_{ix}$ and $t_{ix+iy}$ are initialized on lines 47 and 50 respectively.  The doubling is performed using two
-additions (\textit{see line 59}) since it is usually faster than shifting,if not at least as fast.  
+Inside the outer loop (line 33) the square term is calculated on line 36.  The carry (line 43) has been
+extracted from the mp\_word accumulator using a right shift.  Aliases for $a_{ix}$ and $t_{ix+iy}$ are initialized 
+(lines 46 and 49) to simplify the inner loop.  The doubling is performed using two
+additions (line 58) 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}
 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
@@ -4987,9 +5028,9 @@ 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,
 $ab + ba + ac + ca = 2ab + 2ac = 2(ab + ac)$.  
 
-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
-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 
-moved to a $O(n)$ work level outside the $O(n^2)$ level.  
+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 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 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]
 \begin{small}
@@ -4999,34 +5040,34 @@ moved to a $O(n)$ work level outside the $O(n^2)$ level.
 \textbf{Input}.   mp\_int $a$ \\
 \textbf{Output}.  $b \leftarrow a^2$ \\
 \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}). \\
 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.\\
-\hspace{3mm}4.2  for $iy$ from $ix + 1$ to $a.used - 1$ do \\
-\hspace{6mm}4.2.1  $\hat W_{ix+iy} \leftarrow \hat W_{ix+iy} + a_{ix}a_{iy}$ \\
-5.  $oldused \leftarrow b.used$ \\
-6.  $b.used \leftarrow 2a.used + 1$ \\
+3.  $pa \leftarrow 2 \cdot a.used$ \\
+4.  $\hat W1 \leftarrow 0$ \\
+5.  for $ix$ from $0$ to $pa - 1$ do \\
+\hspace{3mm}5.1  $\_ \hat W \leftarrow 0$ \\
+\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. \\
-7.  $\hat W_0 \leftarrow 2 \hat W_0 + \hat {X}_0$ \\
-8.  for $ix$ from $1$ to $2a.used$ do \\
-\hspace{3mm}8.1 $\hat W_{ix} \leftarrow 2 \hat W_{ix} + \hat {X}_{ix}$ \\
-\hspace{3mm}8.2 $\hat W_{ix} \leftarrow \hat W_{ix} + \lfloor \hat W_{ix - 1} / \beta \rfloor$ \\
-\hspace{3mm}8.3 $b_{ix-1} \leftarrow W_{ix-1} \mbox{ (mod }\beta\mbox{)}$ \\
-9.  $b_{2a.used} \leftarrow \hat W_{2a.used} \mbox{ (mod }\beta\mbox{)}$ \\
-10.  if $2a.used + 1 < oldused$ then do \\
-\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}). \\ 
+6.  $oldused \leftarrow b.used$ \\
+7.  $b.used \leftarrow 2 \cdot a.used$ \\
+8.  for $ix$ from $0$ to $pa - 1$ do \\
+\hspace{3mm}8.1  $b_{ix} \leftarrow W_{ix}$ \\
+9.  for $ix$ from $pa$ to $oldused - 1$ do \\
+\hspace{3mm}9.1  $b_{ix} \leftarrow 0$ \\
+10.  Clamp excess digits from $b$.  (\textit{mp\_clamp}) \\
+11.  Return(\textit{MP\_OKAY}). \\ 
 \hline
 \end{tabular}
 \end{center}
@@ -5035,146 +5076,123 @@ Double the products and propagate the carries simultaneously. \\
 \end{figure}
 
 \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
-the number of input digits is less than \textbf{MP\_WARRAY} and less than $\delta \over 2$.  
+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 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
-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 
-processors to simply make it a full size array.
+First, we have an accumulator and carry variables $\_ \hat W$ and $\hat W1$ respectively.  This is because the inner loop
+products are to be doubled.  If we had added the previous carry in we would be doubling too much.  Next we perform an
+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 
-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
-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.  
+Finally the last difference is the addition of the ``square'' term outside the inner loop (step 5.8).  We add in the square
+only to even outputs and it is the square of the term at the $\lfloor ix / 2 \rfloor$ position.
 
 \vspace{+3mm}\begin{small}
 \hspace{-5.1mm}{\bf File}: bn\_fast\_s\_mp\_sqr.c
 \vspace{-3mm}
 \begin{alltt}
 016   
-017   /* fast squaring
-018    *
-019    * This is the comba method where the columns of the product
-020    * are computed first then the carries are computed.  This
-021    * has the effect of making a very simple inner loop that
-022    * is executed the most
-023    *
-024    * W2 represents the outer products and W the inner.
-025    *
-026    * A further optimizations is made because the inner
-027    * products are of the form "A * B * 2".  The *2 part does
-028    * not need to be computed until the end which is good
-029    * because 64-bit shifts are slow!
-030    *
-031    * Based on Algorithm 14.16 on pp.597 of HAC.
-032    *
-033    */
-034   /* the jist of squaring...
-035   
-036   you do like mult except the offset of the tmpx [one that starts closer to ze
-      ro]
-037   can't equal the offset of tmpy.  So basically you set up iy like before then
-       you min it with
-038   (ty-tx) so that it never happens.  You double all those you add in the inner
-       loop
-039   
-040   After that loop you do the squares and add them in.
-041   
-042   Remove W2 and don't memset W
-043   
-044   */
-045   
-046   int fast_s_mp_sqr (mp_int * a, mp_int * b)
-047   \{
-048     int       olduse, res, pa, ix, iz;
-049     mp_digit   W[MP_WARRAY], *tmpx;
-050     mp_word   W1;
-051   
-052     /* grow the destination as required */
-053     pa = a->used + a->used;
-054     if (b->alloc < pa) \{
-055       if ((res = mp_grow (b, pa)) != MP_OKAY) \{
-056         return res;
-057       \}
-058     \}
-059   
-060     /* number of output digits to produce */
-061     W1 = 0;
-062     for (ix = 0; ix < pa; ix++) \{ 
-063         int      tx, ty, iy;
-064         mp_word  _W;
-065         mp_digit *tmpy;
-066   
-067         /* clear counter */
-068         _W = 0;
+017   /* the jist of squaring...
+018    * you do like mult except the offset of the tmpx [one that 
+019    * starts closer to zero] can't equal the offset of tmpy.  
+020    * So basically you set up iy like before then you min it with
+021    * (ty-tx) so that it never happens.  You double all those 
+022    * you add in the inner loop
+023   
+024   After that loop you do the squares and add them in.
+025   */
+026   
+027   int fast_s_mp_sqr (mp_int * a, mp_int * b)
+028   \{
+029     int       olduse, res, pa, ix, iz;
+030     mp_digit   W[MP_WARRAY], *tmpx;
+031     mp_word   W1;
+032   
+033     /* grow the destination as required */
+034     pa = a->used + a->used;
+035     if (b->alloc < pa) \{
+036       if ((res = mp_grow (b, pa)) != MP_OKAY) \{
+037         return res;
+038       \}
+039     \}
+040   
+041     /* number of output digits to produce */
+042     W1 = 0;
+043     for (ix = 0; ix < pa; ix++) \{ 
+044         int      tx, ty, iy;
+045         mp_word  _W;
+046         mp_digit *tmpy;
+047   
+048         /* clear counter */
+049         _W = 0;
+050   
+051         /* get offsets into the two bignums */
+052         ty = MIN(a->used-1, ix);
+053         tx = ix - ty;
+054   
+055         /* setup temp aliases */
+056         tmpx = a->dp + tx;
+057         tmpy = a->dp + ty;
+058   
+059         /* this is the number of times the loop will iterrate, essentially
+060            while (tx++ < a->used && ty-- >= 0) \{ ... \}
+061          */
+062         iy = MIN(a->used-tx, ty+1);
+063   
+064         /* now for squaring tx can never equal ty 
+065          * we halve the distance since they approach at a rate of 2x
+066          * and we have to round because odd cases need to be executed
+067          */
+068         iy = MIN(iy, (ty-tx+1)>>1);
 069   
-070         /* get offsets into the two bignums */
-071         ty = MIN(a->used-1, ix);
-072         tx = ix - ty;
-073   
-074         /* setup temp aliases */
-075         tmpx = a->dp + tx;
-076         tmpy = a->dp + ty;
+070         /* execute loop */
+071         for (iz = 0; iz < iy; iz++) \{
+072            _W += ((mp_word)*tmpx++)*((mp_word)*tmpy--);
+073         \}
+074   
+075         /* double the inner product and add carry */
+076         _W = _W + _W + W1;
 077   
-078         /* this is the number of times the loop will iterrate, essentially its
-       
-079            while (tx++ < a->used && ty-- >= 0) \{ ... \}
-080          */
-081         iy = MIN(a->used-tx, ty+1);
+078         /* even columns have the square term in them */
+079         if ((ix&1) == 0) \{
+080            _W += ((mp_word)a->dp[ix>>1])*((mp_word)a->dp[ix>>1]);
+081         \}
 082   
-083         /* now for squaring tx can never equal ty 
-084          * we halve the distance since they approach at a rate of 2x
-085          * and we have to round because odd cases need to be executed
-086          */
-087         iy = MIN(iy, (ty-tx+1)>>1);
-088   
-089         /* execute loop */
-090         for (iz = 0; iz < iy; iz++) \{
-091            _W += ((mp_word)*tmpx++)*((mp_word)*tmpy--);
-092         \}
+083         /* store it */
+084         W[ix] = (mp_digit)(_W & MP_MASK);
+085   
+086         /* make next carry */
+087         W1 = _W >> ((mp_word)DIGIT_BIT);
+088     \}
+089   
+090     /* setup dest */
+091     olduse  = b->used;
+092     b->used = a->used+a->used;
 093   
-094         /* double the inner product and add carry */
-095         _W = _W + _W + W1;
-096   
-097         /* even columns have the square term in them */
-098         if ((ix&1) == 0) \{
-099            _W += ((mp_word)a->dp[ix>>1])*((mp_word)a->dp[ix>>1]);
-100         \}
-101   
-102         /* store it */
-103         W[ix] = _W;
-104   
-105         /* make next carry */
-106         W1 = _W >> ((mp_word)DIGIT_BIT);
-107     \}
-108   
-109     /* setup dest */
-110     olduse  = b->used;
-111     b->used = a->used+a->used;
-112   
-113     \{
-114       mp_digit *tmpb;
-115       tmpb = b->dp;
-116       for (ix = 0; ix < pa; ix++) \{
-117         *tmpb++ = W[ix] & MP_MASK;
-118       \}
-119   
-120       /* clear unused digits [that existed in the old copy of c] */
-121       for (; ix < olduse; ix++) \{
-122         *tmpb++ = 0;
-123       \}
-124     \}
-125     mp_clamp (b);
-126     return MP_OKAY;
-127   \}
-128   #endif
+094     \{
+095       mp_digit *tmpb;
+096       tmpb = b->dp;
+097       for (ix = 0; ix < pa; ix++) \{
+098         *tmpb++ = W[ix] & MP_MASK;
+099       \}
+100   
+101       /* clear unused digits [that existed in the old copy of c] */
+102       for (; ix < olduse; ix++) \{
+103         *tmpb++ = 0;
+104       \}
+105     \}
+106     mp_clamp (b);
+107     return MP_OKAY;
+108   \}
+109   #endif
 \end{alltt}
 \end{small}
 
--- 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}
 The same algorithm that performs optimal polynomial basis multiplication can be used to perform polynomial basis squaring.  The minor exception
@@ -5392,14 +5410,13 @@ 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
 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
-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}
+This routine uses the same error trap coding style as mp\_karatsuba\_sqr.  As the temporary variables are initialized errors are 
+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.
 
 \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
-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.  
 
 \subsection{High Level Squaring}
@@ -5485,12 +5502,9 @@ neither of the polynomial basis algorithms should be used then either the Comba
 $\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. \\
                       & \\
-$\left [ 3 \right ] $ & In section 5.3 the fact that every column of a squaring is made up \\
+$\left [ 2 \right ] $ & In section 5.3 the fact that every column of a squaring is made up \\
                       & 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 [ 1 \right ] $ & Prove that Karatsuba squaring requires $O \left (n^{lg(3)} \right )$ time. \\
@@ -5498,6 +5512,14 @@ $\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 \\
                       & 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}
 
 \chapter{Modular Reduction}
@@ -5516,7 +5538,7 @@ 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 
 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 
-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 
 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.  
@@ -5730,95 +5752,94 @@ performed at most twice, and on average once. However, if $a \ge b^2$ than it wi
 018    * precomputed via mp_reduce_setup.
 019    * From HAC pp.604 Algorithm 14.42
 020    */
-021   int
-022   mp_reduce (mp_int * x, mp_int * m, mp_int * mu)
-023   \{
-024     mp_int  q;
-025     int     res, um = m->used;
-026   
-027     /* q = x */
-028     if ((res = mp_init_copy (&q, x)) != MP_OKAY) \{
-029       return res;
-030     \}
-031   
-032     /* q1 = x / b**(k-1)  */
-033     mp_rshd (&q, um - 1);         
-034   
-035     /* according to HAC this optimization is ok */
-036     if (((unsigned long) um) > (((mp_digit)1) << (DIGIT_BIT - 1))) \{
-037       if ((res = mp_mul (&q, mu, &q)) != MP_OKAY) \{
-038         goto CLEANUP;
-039       \}
-040     \} else \{
-041   #ifdef BN_S_MP_MUL_HIGH_DIGS_C
-042       if ((res = s_mp_mul_high_digs (&q, mu, &q, um - 1)) != MP_OKAY) \{
-043         goto CLEANUP;
-044       \}
-045   #elif defined(BN_FAST_S_MP_MUL_HIGH_DIGS_C)
-046       if ((res = fast_s_mp_mul_high_digs (&q, mu, &q, um - 1)) != MP_OKAY) \{
-047         goto CLEANUP;
-048       \}
-049   #else 
-050       \{ 
-051         res = MP_VAL;
-052         goto CLEANUP;
-053       \}
-054   #endif
-055     \}
-056   
-057     /* q3 = q2 / b**(k+1) */
-058     mp_rshd (&q, um + 1);         
-059   
-060     /* x = x mod b**(k+1), quick (no division) */
-061     if ((res = mp_mod_2d (x, DIGIT_BIT * (um + 1), x)) != MP_OKAY) \{
-062       goto CLEANUP;
-063     \}
-064   
-065     /* q = q * m mod b**(k+1), quick (no division) */
-066     if ((res = s_mp_mul_digs (&q, m, &q, um + 1)) != MP_OKAY) \{
-067       goto CLEANUP;
-068     \}
-069   
-070     /* x = x - q */
-071     if ((res = mp_sub (x, &q, x)) != MP_OKAY) \{
-072       goto CLEANUP;
-073     \}
-074   
-075     /* If x < 0, add b**(k+1) to it */
-076     if (mp_cmp_d (x, 0) == MP_LT) \{
-077       mp_set (&q, 1);
-078       if ((res = mp_lshd (&q, um + 1)) != MP_OKAY)
-079         goto CLEANUP;
-080       if ((res = mp_add (x, &q, x)) != MP_OKAY)
-081         goto CLEANUP;
-082     \}
-083   
-084     /* Back off if it's too big */
-085     while (mp_cmp (x, m) != MP_LT) \{
-086       if ((res = s_mp_sub (x, m, x)) != MP_OKAY) \{
-087         goto CLEANUP;
-088       \}
-089     \}
-090     
-091   CLEANUP:
-092     mp_clear (&q);
-093   
-094     return res;
-095   \}
-096   #endif
+021   int mp_reduce (mp_int * x, mp_int * m, mp_int * mu)
+022   \{
+023     mp_int  q;
+024     int     res, um = m->used;
+025   
+026     /* q = x */
+027     if ((res = mp_init_copy (&q, x)) != MP_OKAY) \{
+028       return res;
+029     \}
+030   
+031     /* q1 = x / b**(k-1)  */
+032     mp_rshd (&q, um - 1);         
+033   
+034     /* according to HAC this optimization is ok */
+035     if (((unsigned long) um) > (((mp_digit)1) << (DIGIT_BIT - 1))) \{
+036       if ((res = mp_mul (&q, mu, &q)) != MP_OKAY) \{
+037         goto CLEANUP;
+038       \}
+039     \} else \{
+040   #ifdef BN_S_MP_MUL_HIGH_DIGS_C
+041       if ((res = s_mp_mul_high_digs (&q, mu, &q, um)) != MP_OKAY) \{
+042         goto CLEANUP;
+043       \}
+044   #elif defined(BN_FAST_S_MP_MUL_HIGH_DIGS_C)
+045       if ((res = fast_s_mp_mul_high_digs (&q, mu, &q, um)) != MP_OKAY) \{
+046         goto CLEANUP;
+047       \}
+048   #else 
+049       \{ 
+050         res = MP_VAL;
+051         goto CLEANUP;
+052       \}
+053   #endif
+054     \}
+055   
+056     /* q3 = q2 / b**(k+1) */
+057     mp_rshd (&q, um + 1);         
+058   
+059     /* x = x mod b**(k+1), quick (no division) */
+060     if ((res = mp_mod_2d (x, DIGIT_BIT * (um + 1), x)) != MP_OKAY) \{
+061       goto CLEANUP;
+062     \}
+063   
+064     /* q = q * m mod b**(k+1), quick (no division) */
+065     if ((res = s_mp_mul_digs (&q, m, &q, um + 1)) != MP_OKAY) \{
+066       goto CLEANUP;
+067     \}
+068   
+069     /* x = x - q */
+070     if ((res = mp_sub (x, &q, x)) != MP_OKAY) \{
+071       goto CLEANUP;
+072     \}
+073   
+074     /* If x < 0, add b**(k+1) to it */
+075     if (mp_cmp_d (x, 0) == MP_LT) \{
+076       mp_set (&q, 1);
+077       if ((res = mp_lshd (&q, um + 1)) != MP_OKAY)
+078         goto CLEANUP;
+079       if ((res = mp_add (x, &q, x)) != MP_OKAY)
+080         goto CLEANUP;
+081     \}
+082   
+083     /* Back off if it's too big */
+084     while (mp_cmp (x, m) != MP_LT) \{
+085       if ((res = s_mp_sub (x, m, x)) != MP_OKAY) \{
+086         goto CLEANUP;
+087       \}
+088     \}
+089     
+090   CLEANUP:
+091     mp_clear (&q);
+092   
+093     return res;
+094   \}
+095   #endif
 \end{alltt}
 \end{small}
 
 The first multiplication that determines the quotient can be performed by only producing the digits from $m - 1$ and up.  This essentially halves
 the number of single precision multiplications required.  However, the optimization is only safe if $\beta$ is much larger than the number of digits
-in the modulus.  In the source code this is evaluated on lines 36 to 44 where algorithm s\_mp\_mul\_high\_digs is used when it is
+in the modulus.  In the source code this is evaluated on lines 36 to 43 where algorithm s\_mp\_mul\_high\_digs is used when it is
 safe to do so.  
 
 \subsection{The Barrett Setup Algorithm}
 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.  
 
-\begin{figure}[!here]
+\newpage\begin{figure}[!here]
 \begin{small}
 \begin{center}
 \begin{tabular}{l}
@@ -6314,161 +6335,160 @@ stored in the destination $x$.
 022    *
 023    * Based on Algorithm 14.32 on pp.601 of HAC.
 024   */
-025   int
-026   fast_mp_montgomery_reduce (mp_int * x, mp_int * n, mp_digit rho)
-027   \{
-028     int     ix, res, olduse;
-029     mp_word W[MP_WARRAY];
-030   
-031     /* get old used count */
-032     olduse = x->used;
-033   
-034     /* grow a as required */
-035     if (x->alloc < n->used + 1) \{
-036       if ((res = mp_grow (x, n->used + 1)) != MP_OKAY) \{
-037         return res;
-038       \}
-039     \}
-040   
-041     /* first we have to get the digits of the input into
-042      * an array of double precision words W[...]
-043      */
-044     \{
-045       register mp_word *_W;
-046       register mp_digit *tmpx;
-047   
-048       /* alias for the W[] array */
-049       _W   = W;
-050   
-051       /* alias for the digits of  x*/
-052       tmpx = x->dp;
-053   
-054       /* copy the digits of a into W[0..a->used-1] */
-055       for (ix = 0; ix < x->used; ix++) \{
-056         *_W++ = *tmpx++;
-057       \}
-058   
-059       /* zero the high words of W[a->used..m->used*2] */
-060       for (; ix < n->used * 2 + 1; ix++) \{
-061         *_W++ = 0;
-062       \}
-063     \}
-064   
-065     /* now we proceed to zero successive digits
-066      * from the least significant upwards
-067      */
-068     for (ix = 0; ix < n->used; ix++) \{
-069       /* mu = ai * m' mod b
-070        *
-071        * We avoid a double precision multiplication (which isn't required)
-072        * by casting the value down to a mp_digit.  Note this requires
-073        * that W[ix-1] have  the carry cleared (see after the inner loop)
-074        */
-075       register mp_digit mu;
-076       mu = (mp_digit) (((W[ix] & MP_MASK) * rho) & MP_MASK);
-077   
-078       /* a = a + mu * m * b**i
-079        *
-080        * This is computed in place and on the fly.  The multiplication
-081        * by b**i is handled by offseting which columns the results
-082        * are added to.
-083        *
-084        * Note the comba method normally doesn't handle carries in the
-085        * inner loop In this case we fix the carry from the previous
-086        * column since the Montgomery reduction requires digits of the
-087        * result (so far) [see above] to work.  This is
-088        * handled by fixing up one carry after the inner loop.  The
-089        * carry fixups are done in order so after these loops the
-090        * first m->used words of W[] have the carries fixed
-091        */
-092       \{
-093         register int iy;
-094         register mp_digit *tmpn;
-095         register mp_word *_W;
-096   
-097         /* alias for the digits of the modulus */
-098         tmpn = n->dp;
-099   
-100         /* Alias for the columns set by an offset of ix */
-101         _W = W + ix;
-102   
-103         /* inner loop */
-104         for (iy = 0; iy < n->used; iy++) \{
-105             *_W++ += ((mp_word)mu) * ((mp_word)*tmpn++);
-106         \}
-107       \}
-108   
-109       /* now fix carry for next digit, W[ix+1] */
-110       W[ix + 1] += W[ix] >> ((mp_word) DIGIT_BIT);
-111     \}
-112   
-113     /* now we have to propagate the carries and
-114      * shift the words downward [all those least
-115      * significant digits we zeroed].
-116      */
-117     \{
-118       register mp_digit *tmpx;
-119       register mp_word *_W, *_W1;
-120   
-121       /* nox fix rest of carries */
-122   
-123       /* alias for current word */
-124       _W1 = W + ix;
-125   
-126       /* alias for next word, where the carry goes */
-127       _W = W + ++ix;
-128   
-129       for (; ix <= n->used * 2 + 1; ix++) \{
-130         *_W++ += *_W1++ >> ((mp_word) DIGIT_BIT);
-131       \}
-132   
-133       /* copy out, A = A/b**n
-134        *
-135        * The result is A/b**n but instead of converting from an
-136        * array of mp_word to mp_digit than calling mp_rshd
-137        * we just copy them in the right order
-138        */
-139   
-140       /* alias for destination word */
-141       tmpx = x->dp;
-142   
-143       /* alias for shifted double precision result */
-144       _W = W + n->used;
-145   
-146       for (ix = 0; ix < n->used + 1; ix++) \{
-147         *tmpx++ = (mp_digit)(*_W++ & ((mp_word) MP_MASK));
-148       \}
-149   
-150       /* zero oldused digits, if the input a was larger than
-151        * m->used+1 we'll have to clear the digits
-152        */
-153       for (; ix < olduse; ix++) \{
-154         *tmpx++ = 0;
-155       \}
-156     \}
-157   
-158     /* set the max used and clamp */
-159     x->used = n->used + 1;
-160     mp_clamp (x);
-161   
-162     /* if A >= m then A = A - m */
-163     if (mp_cmp_mag (x, n) != MP_LT) \{
-164       return s_mp_sub (x, n, x);
-165     \}
-166     return MP_OKAY;
-167   \}
-168   #endif
+025   int fast_mp_montgomery_reduce (mp_int * x, mp_int * n, mp_digit rho)
+026   \{
+027     int     ix, res, olduse;
+028     mp_word W[MP_WARRAY];
+029   
+030     /* get old used count */
+031     olduse = x->used;
+032   
+033     /* grow a as required */
+034     if (x->alloc < n->used + 1) \{
+035       if ((res = mp_grow (x, n->used + 1)) != MP_OKAY) \{
+036         return res;
+037       \}
+038     \}
+039   
+040     /* first we have to get the digits of the input into
+041      * an array of double precision words W[...]
+042      */
+043     \{
+044       register mp_word *_W;
+045       register mp_digit *tmpx;
+046   
+047       /* alias for the W[] array */
+048       _W   = W;
+049   
+050       /* alias for the digits of  x*/
+051       tmpx = x->dp;
+052   
+053       /* copy the digits of a into W[0..a->used-1] */
+054       for (ix = 0; ix < x->used; ix++) \{
+055         *_W++ = *tmpx++;
+056       \}
+057   
+058       /* zero the high words of W[a->used..m->used*2] */
+059       for (; ix < n->used * 2 + 1; ix++) \{
+060         *_W++ = 0;
+061       \}
+062     \}
+063   
+064     /* now we proceed to zero successive digits
+065      * from the least significant upwards
+066      */
+067     for (ix = 0; ix < n->used; ix++) \{
+068       /* mu = ai * m' mod b
+069        *
+070        * We avoid a double precision multiplication (which isn't required)
+071        * by casting the value down to a mp_digit.  Note this requires
+072        * that W[ix-1] have  the carry cleared (see after the inner loop)
+073        */
+074       register mp_digit mu;
+075       mu = (mp_digit) (((W[ix] & MP_MASK) * rho) & MP_MASK);
+076   
+077       /* a = a + mu * m * b**i
+078        *
+079        * This is computed in place and on the fly.  The multiplication
+080        * by b**i is handled by offseting which columns the results
+081        * are added to.
+082        *
+083        * Note the comba method normally doesn't handle carries in the
+084        * inner loop In this case we fix the carry from the previous
+085        * column since the Montgomery reduction requires digits of the
+086        * result (so far) [see above] to work.  This is
+087        * handled by fixing up one carry after the inner loop.  The
+088        * carry fixups are done in order so after these loops the
+089        * first m->used words of W[] have the carries fixed
+090        */
+091       \{
+092         register int iy;
+093         register mp_digit *tmpn;
+094         register mp_word *_W;
+095   
+096         /* alias for the digits of the modulus */
+097         tmpn = n->dp;
+098   
+099         /* Alias for the columns set by an offset of ix */
+100         _W = W + ix;
+101   
+102         /* inner loop */
+103         for (iy = 0; iy < n->used; iy++) \{
+104             *_W++ += ((mp_word)mu) * ((mp_word)*tmpn++);
+105         \}
+106       \}
+107   
+108       /* now fix carry for next digit, W[ix+1] */
+109       W[ix + 1] += W[ix] >> ((mp_word) DIGIT_BIT);
+110     \}
+111   
+112     /* now we have to propagate the carries and
+113      * shift the words downward [all those least
+114      * significant digits we zeroed].
+115      */
+116     \{
+117       register mp_digit *tmpx;
+118       register mp_word *_W, *_W1;
+119   
+120       /* nox fix rest of carries */
+121   
+122       /* alias for current word */
+123       _W1 = W + ix;
+124   
+125       /* alias for next word, where the carry goes */
+126       _W = W + ++ix;
+127   
+128       for (; ix <= n->used * 2 + 1; ix++) \{
+129         *_W++ += *_W1++ >> ((mp_word) DIGIT_BIT);
+130       \}
+131   
+132       /* copy out, A = A/b**n
+133        *
+134        * The result is A/b**n but instead of converting from an
+135        * array of mp_word to mp_digit than calling mp_rshd
+136        * we just copy them in the right order
+137        */
+138   
+139       /* alias for destination word */
+140       tmpx = x->dp;
+141   
+142       /* alias for shifted double precision result */
+143       _W = W + n->used;
+144   
+145       for (ix = 0; ix < n->used + 1; ix++) \{
+146         *tmpx++ = (mp_digit)(*_W++ & ((mp_word) MP_MASK));
+147       \}
+148   
+149       /* zero oldused digits, if the input a was larger than
+150        * m->used+1 we'll have to clear the digits
+151        */
+152       for (; ix < olduse; ix++) \{
+153         *tmpx++ = 0;
+154       \}
+155     \}
+156   
+157     /* set the max used and clamp */
+158     x->used = n->used + 1;
+159     mp_clamp (x);
+160   
+161     /* if A >= m then A = A - m */
+162     if (mp_cmp_mag (x, n) != MP_LT) \{
+163       return s_mp_sub (x, n, x);
+164     \}
+165     return MP_OKAY;
+166   \}
+167   #endif
 \end{alltt}
 \end{small}
 
-The $\hat W$ array is first filled with digits of $x$ on line 48 then the rest of the digits are zeroed on line 55.  Both loops share
+The $\hat W$ array is first filled with digits of $x$ on line 50 then the rest of the digits are zeroed on line 54.  Both loops share
 the same alias variables to make the code easier to read.  
 
 The value of $\mu$ is calculated in an interesting fashion.  First the value $\hat W_{ix}$ is reduced modulo $\beta$ and cast to a mp\_digit.  This
-forces the compiler to use a single precision multiplication and prevents any concerns about loss of precision.   Line 110 fixes the carry 
+forces the compiler to use a single precision multiplication and prevents any concerns about loss of precision.   Line 109 fixes the carry 
 for the next iteration of the loop by propagating the carry from $\hat W_{ix}$ to $\hat W_{ix+1}$.
 
-The for loop on line 109 propagates the rest of the carries upwards through the columns.  The for loop on line 126 reduces the columns
+The for loop on line 108 propagates the rest of the carries upwards through the columns.  The for loop on line 125 reduces the columns
 modulo $\beta$ and shifts them $k$ places at the same time.  The alias $\_ \hat W$ actually refers to the array $\hat W$ starting at the $n.used$'th
 digit, that is $\_ \hat W_{t} = \hat W_{n.used + t}$.  
 
@@ -6968,51 +6988,50 @@ shift which makes the algorithm fairly inexpensive to use.
 \begin{alltt}
 016   
 017   /* reduces a modulo n where n is of the form 2**p - d */
-018   int
-019   mp_reduce_2k(mp_int *a, mp_int *n, mp_digit d)
-020   \{
-021      mp_int q;
-022      int    p, res;
-023      
-024      if ((res = mp_init(&q)) != MP_OKAY) \{
-025         return res;
-026      \}
-027      
-028      p = mp_count_bits(n);    
-029   top:
-030      /* q = a/2**p, a = a mod 2**p */
-031      if ((res = mp_div_2d(a, p, &q, a)) != MP_OKAY) \{
-032         goto ERR;
-033      \}
-034      
-035      if (d != 1) \{
-036         /* q = q * d */
-037         if ((res = mp_mul_d(&q, d, &q)) != MP_OKAY) \{ 
-038            goto ERR;
-039         \}
-040      \}
-041      
-042      /* a = a + q */
-043      if ((res = s_mp_add(a, &q, a)) != MP_OKAY) \{
-044         goto ERR;
-045      \}
-046      
-047      if (mp_cmp_mag(a, n) != MP_LT) \{
-048         s_mp_sub(a, n, a);
-049         goto top;
-050      \}
-051      
-052   ERR:
-053      mp_clear(&q);
-054      return res;
-055   \}
-056   
-057   #endif
+018   int mp_reduce_2k(mp_int *a, mp_int *n, mp_digit d)
+019   \{
+020      mp_int q;
+021      int    p, res;
+022      
+023      if ((res = mp_init(&q)) != MP_OKAY) \{
+024         return res;
+025      \}
+026      
+027      p = mp_count_bits(n);    
+028   top:
+029      /* q = a/2**p, a = a mod 2**p */
+030      if ((res = mp_div_2d(a, p, &q, a)) != MP_OKAY) \{
+031         goto ERR;
+032      \}
+033      
+034      if (d != 1) \{
+035         /* q = q * d */
+036         if ((res = mp_mul_d(&q, d, &q)) != MP_OKAY) \{ 
+037            goto ERR;
+038         \}
+039      \}
+040      
+041      /* a = a + q */
+042      if ((res = s_mp_add(a, &q, a)) != MP_OKAY) \{
+043         goto ERR;
+044      \}
+045      
+046      if (mp_cmp_mag(a, n) != MP_LT) \{
+047         s_mp_sub(a, n, a);
+048         goto top;
+049      \}
+050      
+051   ERR:
+052      mp_clear(&q);
+053      return res;
+054   \}
+055   
+056   #endif
 \end{alltt}
 \end{small}
 
 The algorithm mp\_count\_bits calculates the number of bits in an mp\_int which is used to find the initial value of $p$.  The call to mp\_div\_2d
-on line 31 calculates both the quotient $q$ and the remainder $a$ required.  By doing both in a single function call the code size
+on line 30 calculates both the quotient $q$ and the remainder $a$ required.  By doing both in a single function call the code size
 is kept fairly small.  The multiplication by $k$ is only performed if $k > 1$. This allows reductions modulo $2^p - 1$ to be performed without
 any multiplications.  
 
@@ -7052,32 +7071,31 @@ is sufficient to solve for $k$.  Alternatively if $n$ has more than one digit th
 \begin{alltt}
 016   
 017   /* determines the setup value */
-018   int 
-019   mp_reduce_2k_setup(mp_int *a, mp_digit *d)
-020   \{
-021      int res, p;
-022      mp_int tmp;
-023      
-024      if ((res = mp_init(&tmp)) != MP_OKAY) \{
-025         return res;
-026      \}
-027      
-028      p = mp_count_bits(a);
-029      if ((res = mp_2expt(&tmp, p)) != MP_OKAY) \{
-030         mp_clear(&tmp);
-031         return res;
-032      \}
-033      
-034      if ((res = s_mp_sub(&tmp, a, &tmp)) != MP_OKAY) \{
-035         mp_clear(&tmp);
-036         return res;
-037      \}
-038      
-039      *d = tmp.dp[0];
-040      mp_clear(&tmp);
-041      return MP_OKAY;
-042   \}
-043   #endif
+018   int mp_reduce_2k_setup(mp_int *a, mp_digit *d)
+019   \{
+020      int res, p;
+021      mp_int tmp;
+022      
+023      if ((res = mp_init(&tmp)) != MP_OKAY) \{
+024         return res;
+025      \}
+026      
+027      p = mp_count_bits(a);
+028      if ((res = mp_2expt(&tmp, p)) != MP_OKAY) \{
+029         mp_clear(&tmp);
+030         return res;
+031      \}
+032      
+033      if ((res = s_mp_sub(&tmp, a, &tmp)) != MP_OKAY) \{
+034         mp_clear(&tmp);
+035         return res;
+036      \}
+037      
+038      *d = tmp.dp[0];
+039      mp_clear(&tmp);
+040      return MP_OKAY;
+041   \}
+042   #endif
 \end{alltt}
 \end{small}
 
@@ -7130,9 +7148,9 @@ This algorithm quickly determines if a modulus is of the form required for algor
 021      mp_digit iz;
 022      
 023      if (a->used == 0) \{
-024         return 0;
+024         return MP_NO;
 025      \} else if (a->used == 1) \{
-026         return 1;
+026         return MP_YES;
 027      \} else if (a->used > 1) \{
 028         iy = mp_count_bits(a);
 029         iz = 1;
@@ -7141,7 +7159,7 @@ This algorithm quickly determines if a modulus is of the form required for algor
 032         /* Test every bit from the second digit up, must be 1 */
 033         for (ix = DIGIT_BIT; ix < iy; ix++) \{
 034             if ((a->dp[iw] & iz) == 0) \{
-035                return 0;
+035                return MP_NO;
 036             \}
 037             iz <<= 1;
 038             if (iz > (mp_digit)MP_MASK) \{
@@ -7150,7 +7168,7 @@ This algorithm quickly determines if a modulus is of the form required for algor
 041             \}
 042         \}
 043      \}
-044      return 1;
+044      return MP_YES;
 045   \}
 046   
 047   #endif
@@ -7601,39 +7619,47 @@ algorithm since their arguments are essentially the same (\textit{two mp\_ints a
 064   #endif
 065     \}
 066   
-067   #ifdef BN_MP_DR_IS_MODULUS_C
-068     /* is it a DR modulus? */
-069     dr = mp_dr_is_modulus(P);
-070   #else
-071     dr = 0;
+067   /* modified diminished radix reduction */
+068   #if defined(BN_MP_REDUCE_IS_2K_L_C) && defined(BN_MP_REDUCE_2K_L_C)
+069     if (mp_reduce_is_2k_l(P) == MP_YES) \{
+070        return s_mp_exptmod(G, X, P, Y, 1);
+071     \}
 072   #endif
 073   
-074   #ifdef BN_MP_REDUCE_IS_2K_C
-075     /* if not, is it a uDR modulus? */
-076     if (dr == 0) \{
-077        dr = mp_reduce_is_2k(P) << 1;
-078     \}
-079   #endif
-080       
-081     /* if the modulus is odd or dr != 0 use the fast method */
-082   #ifdef BN_MP_EXPTMOD_FAST_C
-083     if (mp_isodd (P) == 1 || dr !=  0) \{
-084       return mp_exptmod_fast (G, X, P, Y, dr);
-085     \} else \{
-086   #endif
-087   #ifdef BN_S_MP_EXPTMOD_C
-088       /* otherwise use the generic Barrett reduction technique */
-089       return s_mp_exptmod (G, X, P, Y);
-090   #else
-091       /* no exptmod for evens */
-092       return MP_VAL;
-093   #endif
-094   #ifdef BN_MP_EXPTMOD_FAST_C
-095     \}
-096   #endif
-097   \}
-098   
-099   #endif
+074   #ifdef BN_MP_DR_IS_MODULUS_C
+075     /* is it a DR modulus? */
+076     dr = mp_dr_is_modulus(P);
+077   #else
+078     /* default to no */
+079     dr = 0;
+080   #endif
+081   
+082   #ifdef BN_MP_REDUCE_IS_2K_C
+083     /* if not, is it a unrestricted DR modulus? */
+084     if (dr == 0) \{
+085        dr = mp_reduce_is_2k(P) << 1;
+086     \}
+087   #endif
+088       
+089     /* if the modulus is odd or dr != 0 use the montgomery method */
+090   #ifdef BN_MP_EXPTMOD_FAST_C
+091     if (mp_isodd (P) == 1 || dr !=  0) \{
+092       return mp_exptmod_fast (G, X, P, Y, dr);
+093     \} else \{
+094   #endif
+095   #ifdef BN_S_MP_EXPTMOD_C
+096       /* otherwise use the generic Barrett reduction technique */
+097       return s_mp_exptmod (G, X, P, Y, 0);
+098   #else
+099       /* no exptmod for evens */
+100       return MP_VAL;
+101   #endif
+102   #ifdef BN_MP_EXPTMOD_FAST_C
+103     \}
+104   #endif
+105   \}
+106   
+107   #endif
 \end{alltt}
 \end{small}
 
@@ -7642,8 +7668,8 @@ negative the algorithm tries to perform a modular exponentiation with the modula
 the modular inverse of $G$ and $tmpX$ is assigned the absolute value of $X$.  The algorithm will recuse with these new values with a positive
 exponent.
 
-If the exponent is positive the algorithm resumes the exponentiation.  Line 69 determines if the modulus is of the restricted Diminished Radix 
-form.  If it is not line 77 attempts to determine if it is of a unrestricted Diminished Radix form.  The integer $dr$ will take on one
+If the exponent is positive the algorithm resumes the exponentiation.  Line 76 determines if the modulus is of the restricted Diminished Radix 
+form.  If it is not line 69 attempts to determine if it is of a unrestricted Diminished Radix form.  The integer $dr$ will take on one
 of three values.
 
 \begin{enumerate}
@@ -7652,7 +7678,7 @@ of three values.
 \item $dr = 2$ means that the modulus is of unrestricted Diminished Radix form.
 \end{enumerate}
 
-Line 67 determines if the fast modular exponentiation algorithm can be used.  It is allowed if $dr \ne 0$ or if the modulus is odd.  Otherwise,
+Line 69 determines if the fast modular exponentiation algorithm can be used.  It is allowed if $dr \ne 0$ or if the modulus is odd.  Otherwise,
 the slower s\_mp\_exptmod algorithm is used which uses Barrett reduction.  
 
 \subsection{Barrett Modular Exponentiation}
@@ -7820,230 +7846,244 @@ a Left-to-Right algorithm is used to process the remaining few bits.
 020      #define TAB_SIZE 256
 021   #endif
 022   
-023   int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y)
+023   int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y, int redmod
+      e)
 024   \{
 025     mp_int  M[TAB_SIZE], res, mu;
 026     mp_digit buf;
 027     int     err, bitbuf, bitcpy, bitcnt, mode, digidx, x, y, winsize;
-028   
-029     /* find window size */
-030     x = mp_count_bits (X);
-031     if (x <= 7) \{
-032       winsize = 2;
-033     \} else if (x <= 36) \{
-034       winsize = 3;
-035     \} else if (x <= 140) \{
-036       winsize = 4;
-037     \} else if (x <= 450) \{
-038       winsize = 5;
-039     \} else if (x <= 1303) \{
-040       winsize = 6;
-041     \} else if (x <= 3529) \{
-042       winsize = 7;
-043     \} else \{
-044       winsize = 8;
-045     \}
-046   
-047   #ifdef MP_LOW_MEM
-048       if (winsize > 5) \{
-049          winsize = 5;
-050       \}
-051   #endif
-052   
-053     /* init M array */
-054     /* init first cell */
-055     if ((err = mp_init(&M[1])) != MP_OKAY) \{
-056        return err; 
-057     \}
-058   
-059     /* now init the second half of the array */
-060     for (x = 1<<(winsize-1); x < (1 << winsize); x++) \{
-061       if ((err = mp_init(&M[x])) != MP_OKAY) \{
-062         for (y = 1<<(winsize-1); y < x; y++) \{
-063           mp_clear (&M[y]);
-064         \}
-065         mp_clear(&M[1]);
-066         return err;
-067       \}
-068     \}
-069   
-070     /* create mu, used for Barrett reduction */
-071     if ((err = mp_init (&mu)) != MP_OKAY) \{
-072       goto LBL_M;
-073     \}
-074     if ((err = mp_reduce_setup (&mu, P)) != MP_OKAY) \{
-075       goto LBL_MU;
-076     \}
-077   
-078     /* create M table
-079      *
-080      * The M table contains powers of the base, 
-081      * e.g. M[x] = G**x mod P
-082      *
-083      * The first half of the table is not 
-084      * computed though accept for M[0] and M[1]
-085      */
-086     if ((err = mp_mod (G, P, &M[1])) != MP_OKAY) \{
-087       goto LBL_MU;
-088     \}
-089   
-090     /* compute the value at M[1<<(winsize-1)] by squaring 
-091      * M[1] (winsize-1) times 
-092      */
-093     if ((err = mp_copy (&M[1], &M[1 << (winsize - 1)])) != MP_OKAY) \{
-094       goto LBL_MU;
-095     \}
-096   
-097     for (x = 0; x < (winsize - 1); x++) \{
-098       if ((err = mp_sqr (&M[1 << (winsize - 1)], 
-099                          &M[1 << (winsize - 1)])) != MP_OKAY) \{
-100         goto LBL_MU;
-101       \}
-102       if ((err = mp_reduce (&M[1 << (winsize - 1)], P, &mu)) != MP_OKAY) \{
-103         goto LBL_MU;
-104       \}
+028     int (*redux)(mp_int*,mp_int*,mp_int*);
+029   
+030     /* find window size */
+031     x = mp_count_bits (X);
+032     if (x <= 7) \{
+033       winsize = 2;
+034     \} else if (x <= 36) \{
+035       winsize = 3;
+036     \} else if (x <= 140) \{
+037       winsize = 4;
+038     \} else if (x <= 450) \{
+039       winsize = 5;
+040     \} else if (x <= 1303) \{
+041       winsize = 6;
+042     \} else if (x <= 3529) \{
+043       winsize = 7;
+044     \} else \{
+045       winsize = 8;
+046     \}
+047   
+048   #ifdef MP_LOW_MEM
+049       if (winsize > 5) \{
+050          winsize = 5;
+051       \}
+052   #endif
+053   
+054     /* init M array */
+055     /* init first cell */
+056     if ((err = mp_init(&M[1])) != MP_OKAY) \{
+057        return err; 
+058     \}
+059   
+060     /* now init the second half of the array */
+061     for (x = 1<<(winsize-1); x < (1 << winsize); x++) \{
+062       if ((err = mp_init(&M[x])) != MP_OKAY) \{
+063         for (y = 1<<(winsize-1); y < x; y++) \{
+064           mp_clear (&M[y]);
+065         \}
+066         mp_clear(&M[1]);
+067         return err;
+068       \}
+069     \}
+070   
+071     /* create mu, used for Barrett reduction */
+072     if ((err = mp_init (&mu)) != MP_OKAY) \{
+073       goto LBL_M;
+074     \}
+075     
+076     if (redmode == 0) \{
+077        if ((err = mp_reduce_setup (&mu, P)) != MP_OKAY) \{
+078           goto LBL_MU;
+079        \}
+080        redux = mp_reduce;
+081     \} else \{
+082        if ((err = mp_reduce_2k_setup_l (P, &mu)) != MP_OKAY) \{
+083           goto LBL_MU;
+084        \}
+085        redux = mp_reduce_2k_l;
+086     \}    
+087   
+088     /* create M table
+089      *
+090      * The M table contains powers of the base, 
+091      * e.g. M[x] = G**x mod P
+092      *
+093      * The first half of the table is not 
+094      * computed though accept for M[0] and M[1]
+095      */
+096     if ((err = mp_mod (G, P, &M[1])) != MP_OKAY) \{
+097       goto LBL_MU;
+098     \}
+099   
+100     /* compute the value at M[1<<(winsize-1)] by squaring 
+101      * M[1] (winsize-1) times 
+102      */
+103     if ((err = mp_copy (&M[1], &M[1 << (winsize - 1)])) != MP_OKAY) \{
+104       goto LBL_MU;
 105     \}
 106   
-107     /* create upper table, that is M[x] = M[x-1] * M[1] (mod P)
-108      * for x = (2**(winsize - 1) + 1) to (2**winsize - 1)
-109      */
-110     for (x = (1 << (winsize - 1)) + 1; x < (1 << winsize); x++) \{
-111       if ((err = mp_mul (&M[x - 1], &M[1], &M[x])) != MP_OKAY) \{
-112         goto LBL_MU;
-113       \}
-114       if ((err = mp_reduce (&M[x], P, &mu)) != MP_OKAY) \{
-115         goto LBL_MU;
-116       \}
-117     \}
-118   
-119     /* setup result */
-120     if ((err = mp_init (&res)) != MP_OKAY) \{
-121       goto LBL_MU;
-122     \}
-123     mp_set (&res, 1);
-124   
-125     /* set initial mode and bit cnt */
-126     mode   = 0;
-127     bitcnt = 1;
-128     buf    = 0;
-129     digidx = X->used - 1;
-130     bitcpy = 0;
-131     bitbuf = 0;
-132   
-133     for (;;) \{
-134       /* grab next digit as required */
-135       if (--bitcnt == 0) \{
-136         /* if digidx == -1 we are out of digits */
-137         if (digidx == -1) \{
-138           break;
-139         \}
-140         /* read next digit and reset the bitcnt */
-141         buf    = X->dp[digidx--];
-142         bitcnt = (int) DIGIT_BIT;
-143       \}
-144   
-145       /* grab the next msb from the exponent */
-146       y     = (buf >> (mp_digit)(DIGIT_BIT - 1)) & 1;
-147       buf <<= (mp_digit)1;
-148   
-149       /* if the bit is zero and mode == 0 then we ignore it
-150        * These represent the leading zero bits before the first 1 bit
-151        * in the exponent.  Technically this opt is not required but it
-152        * does lower the # of trivial squaring/reductions used
-153        */
-154       if (mode == 0 && y == 0) \{
-155         continue;
+107     for (x = 0; x < (winsize - 1); x++) \{
+108       /* square it */
+109       if ((err = mp_sqr (&M[1 << (winsize - 1)], 
+110                          &M[1 << (winsize - 1)])) != MP_OKAY) \{
+111         goto LBL_MU;
+112       \}
+113   
+114       /* reduce modulo P */
+115       if ((err = redux (&M[1 << (winsize - 1)], P, &mu)) != MP_OKAY) \{
+116         goto LBL_MU;
+117       \}
+118     \}
+119   
+120     /* create upper table, that is M[x] = M[x-1] * M[1] (mod P)
+121      * for x = (2**(winsize - 1) + 1) to (2**winsize - 1)
+122      */
+123     for (x = (1 << (winsize - 1)) + 1; x < (1 << winsize); x++) \{
+124       if ((err = mp_mul (&M[x - 1], &M[1], &M[x])) != MP_OKAY) \{
+125         goto LBL_MU;
+126       \}
+127       if ((err = redux (&M[x], P, &mu)) != MP_OKAY) \{
+128         goto LBL_MU;
+129       \}
+130     \}
+131   
+132     /* setup result */
+133     if ((err = mp_init (&res)) != MP_OKAY) \{
+134       goto LBL_MU;
+135     \}
+136     mp_set (&res, 1);
+137   
+138     /* set initial mode and bit cnt */
+139     mode   = 0;
+140     bitcnt = 1;
+141     buf    = 0;
+142     digidx = X->used - 1;
+143     bitcpy = 0;
+144     bitbuf = 0;
+145   
+146     for (;;) \{
+147       /* grab next digit as required */
+148       if (--bitcnt == 0) \{
+149         /* if digidx == -1 we are out of digits */
+150         if (digidx == -1) \{
+151           break;
+152         \}
+153         /* read next digit and reset the bitcnt */
+154         buf    = X->dp[digidx--];
+155         bitcnt = (int) DIGIT_BIT;
 156       \}
 157   
-158       /* if the bit is zero and mode == 1 then we square */
-159       if (mode == 1 && y == 0) \{
-160         if ((err = mp_sqr (&res, &res)) != MP_OKAY) \{
-161           goto LBL_RES;
-162         \}
-163         if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) \{
-164           goto LBL_RES;
-165         \}
-166         continue;
-167       \}
-168   
-169       /* else we add it to the window */
-170       bitbuf |= (y << (winsize - ++bitcpy));
-171       mode    = 2;
-172   
-173       if (bitcpy == winsize) \{
-174         /* ok window is filled so square as required and multiply  */
-175         /* square first */
-176         for (x = 0; x < winsize; x++) \{
-177           if ((err = mp_sqr (&res, &res)) != MP_OKAY) \{
-178             goto LBL_RES;
-179           \}
-180           if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) \{
-181             goto LBL_RES;
-182           \}
-183         \}
-184   
-185         /* then multiply */
-186         if ((err = mp_mul (&res, &M[bitbuf], &res)) != MP_OKAY) \{
-187           goto LBL_RES;
-188         \}
-189         if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) \{
-190           goto LBL_RES;
-191         \}
-192   
-193         /* empty window and reset */
-194         bitcpy = 0;
-195         bitbuf = 0;
-196         mode   = 1;
-197       \}
-198     \}
-199   
-200     /* if bits remain then square/multiply */
-201     if (mode == 2 && bitcpy > 0) \{
-202       /* square then multiply if the bit is set */
-203       for (x = 0; x < bitcpy; x++) \{
-204         if ((err = mp_sqr (&res, &res)) != MP_OKAY) \{
-205           goto LBL_RES;
-206         \}
-207         if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) \{
-208           goto LBL_RES;
-209         \}
-210   
-211         bitbuf <<= 1;
-212         if ((bitbuf & (1 << winsize)) != 0) \{
-213           /* then multiply */
-214           if ((err = mp_mul (&res, &M[1], &res)) != MP_OKAY) \{
-215             goto LBL_RES;
-216           \}
-217           if ((err = mp_reduce (&res, P, &mu)) != MP_OKAY) \{
-218             goto LBL_RES;
-219           \}
-220         \}
-221       \}
-222     \}
+158       /* grab the next msb from the exponent */
+159       y     = (buf >> (mp_digit)(DIGIT_BIT - 1)) & 1;
+160       buf <<= (mp_digit)1;
+161   
+162       /* if the bit is zero and mode == 0 then we ignore it
+163        * These represent the leading zero bits before the first 1 bit
+164        * in the exponent.  Technically this opt is not required but it
+165        * does lower the # of trivial squaring/reductions used
+166        */
+167       if (mode == 0 && y == 0) \{
+168         continue;
+169       \}
+170   
+171       /* if the bit is zero and mode == 1 then we square */
+172       if (mode == 1 && y == 0) \{
+173         if ((err = mp_sqr (&res, &res)) != MP_OKAY) \{
+174           goto LBL_RES;
+175         \}
+176         if ((err = redux (&res, P, &mu)) != MP_OKAY) \{
+177           goto LBL_RES;
+178         \}
+179         continue;
+180       \}
+181   
+182       /* else we add it to the window */
+183       bitbuf |= (y << (winsize - ++bitcpy));
+184       mode    = 2;
+185   
+186       if (bitcpy == winsize) \{
+187         /* ok window is filled so square as required and multiply  */
+188         /* square first */
+189         for (x = 0; x < winsize; x++) \{
+190           if ((err = mp_sqr (&res, &res)) != MP_OKAY) \{
+191             goto LBL_RES;
+192           \}
+193           if ((err = redux (&res, P, &mu)) != MP_OKAY) \{
+194             goto LBL_RES;
+195           \}
+196         \}
+197   
+198         /* then multiply */
+199         if ((err = mp_mul (&res, &M[bitbuf], &res)) != MP_OKAY) \{
+200           goto LBL_RES;
+201         \}
+202         if ((err = redux (&res, P, &mu)) != MP_OKAY) \{
+203           goto LBL_RES;
+204         \}
+205   
+206         /* empty window and reset */
+207         bitcpy = 0;
+208         bitbuf = 0;
+209         mode   = 1;
+210       \}
+211     \}
+212   
+213     /* if bits remain then square/multiply */
+214     if (mode == 2 && bitcpy > 0) \{
+215       /* square then multiply if the bit is set */
+216       for (x = 0; x < bitcpy; x++) \{
+217         if ((err = mp_sqr (&res, &res)) != MP_OKAY) \{
+218           goto LBL_RES;
+219         \}
+220         if ((err = redux (&res, P, &mu)) != MP_OKAY) \{
+221           goto LBL_RES;
+222         \}
 223   
-224     mp_exch (&res, Y);
-225     err = MP_OKAY;
-226   LBL_RES:mp_clear (&res);
-227   LBL_MU:mp_clear (&mu);
-228   LBL_M:
-229     mp_clear(&M[1]);
-230     for (x = 1<<(winsize-1); x < (1 << winsize); x++) \{
-231       mp_clear (&M[x]);
-232     \}
-233     return err;
-234   \}
-235   #endif
+224         bitbuf <<= 1;
+225         if ((bitbuf & (1 << winsize)) != 0) \{
+226           /* then multiply */
+227           if ((err = mp_mul (&res, &M[1], &res)) != MP_OKAY) \{
+228             goto LBL_RES;
+229           \}
+230           if ((err = redux (&res, P, &mu)) != MP_OKAY) \{
+231             goto LBL_RES;
+232           \}
+233         \}
+234       \}
+235     \}
+236   
+237     mp_exch (&res, Y);
+238     err = MP_OKAY;
+239   LBL_RES:mp_clear (&res);
+240   LBL_MU:mp_clear (&mu);
+241   LBL_M:
+242     mp_clear(&M[1]);
+243     for (x = 1<<(winsize-1); x < (1 << winsize); x++) \{
+244       mp_clear (&M[x]);
+245     \}
+246     return err;
+247   \}
+248   #endif
 \end{alltt}
 \end{small}
 
-Lines 31 through 41 determine the optimal window size based on the length of the exponent in bits.  The window divisions are sorted
+Lines 21 through 40 determine the optimal window size based on the length of the exponent in bits.  The window divisions are sorted
 from smallest to greatest so that in each \textbf{if} statement only one condition must be tested.  For example, by the \textbf{if} statement 
-on line 33 the value of $x$ is already known to be greater than $140$.  
+on line 32 the value of $x$ is already known to be greater than $140$.  
 
-The conditional piece of code beginning on line 47 allows the window size to be restricted to five bits.  This logic is used to ensure
+The conditional piece of code beginning on line 48 allows the window size to be restricted to five bits.  This logic is used to ensure
 the table of precomputed powers of $G$ remains relatively small.  
 
-The for loop on line 60 initializes the $M$ array while lines 61 and 74 compute the value of $\mu$ required for
+The for loop on line 61 initializes the $M$ array while lines 62 and 77 compute the value of $\mu$ required for
 Barrett reduction.  
 
 -- More later.
@@ -8873,21 +8913,22 @@ Unlike the full multiplication algorithms this algorithm does not require any si
 056       u       = (mp_digit) (r >> ((mp_word) DIGIT_BIT));
 057     \}
 058   
-059     /* store final carry [if any] */
+059     /* store final carry [if any] and increment ix offset  */
 060     *tmpc++ = u;
-061   
-062     /* now zero digits above the top */
-063     while (ix++ < olduse) \{
-064        *tmpc++ = 0;
-065     \}
-066   
-067     /* set used count */
-068     c->used = a->used + 1;
-069     mp_clamp(c);
-070   
-071     return MP_OKAY;
-072   \}
-073   #endif
+061     ++ix;
+062   
+063     /* now zero digits above the top */
+064     while (ix++ < olduse) \{
+065        *tmpc++ = 0;
+066     \}
+067   
+068     /* set used count */
+069     c->used = a->used + 1;
+070     mp_clamp(c);
+071   
+072     return MP_OKAY;
+073   \}
+074   #endif
 \end{alltt}
 \end{small}
 
@@ -9275,14 +9316,14 @@ the integers from $0$ to $\beta - 1$.
 028   
 029     /* first place a random non-zero digit */
 030     do \{
-031       d = ((mp_digit) abs (rand ()));
+031       d = ((mp_digit) abs (rand ())) & MP_MASK;
 032     \} while (d == 0);
 033   
 034     if ((res = mp_add_d (a, d, a)) != MP_OKAY) \{
 035       return res;
 036     \}
 037   
-038     while (digits-- > 0) \{
+038     while (--digits > 0) \{
 039       if ((res = mp_lshd (a, 1)) != MP_OKAY) \{
 040         return res;
 041       \}
@@ -9379,7 +9420,7 @@ as part of larger input without any significant problem.
 \begin{alltt}
 016   
 017   /* read a string [ASCII] in a given radix */
-018   int mp_read_radix (mp_int * a, char *str, int radix)
+018   int mp_read_radix (mp_int * a, const char *str, int radix)
 019   \{
 020     int     y, res, neg;
 021     char    ch;
@@ -9941,6 +9982,8 @@ 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
 equivalent to equation \ref{eqn:legendre}.
 
+\textit{-- Tom, don't be an ass, cite your source here...!}
+
 \begin{equation}
 a^{(p-1)/2} \equiv \begin{array}{rl}
                               -1 &  \mbox{if }a\mbox{ is a quadratic non-residue.} \\
diff --git a/libtommath/tommath_class.h b/libtommath/tommath_class.h
index 53bfa31..6d05b7b 100644
--- a/libtommath/tommath_class.h
+++ b/libtommath/tommath_class.h
@@ -90,8 +90,11 @@
 #define BN_MP_READ_UNSIGNED_BIN_C
 #define BN_MP_REDUCE_C
 #define BN_MP_REDUCE_2K_C
+#define BN_MP_REDUCE_2K_L_C
 #define BN_MP_REDUCE_2K_SETUP_C
+#define BN_MP_REDUCE_2K_SETUP_L_C
 #define BN_MP_REDUCE_IS_2K_C
+#define BN_MP_REDUCE_IS_2K_L_C
 #define BN_MP_REDUCE_SETUP_C
 #define BN_MP_RSHD_C
 #define BN_MP_SET_C
@@ -105,7 +108,9 @@
 #define BN_MP_SUB_D_C
 #define BN_MP_SUBMOD_C
 #define BN_MP_TO_SIGNED_BIN_C
+#define BN_MP_TO_SIGNED_BIN_N_C
 #define BN_MP_TO_UNSIGNED_BIN_C
+#define BN_MP_TO_UNSIGNED_BIN_N_C
 #define BN_MP_TOOM_MUL_C
 #define BN_MP_TOOM_SQR_C
 #define BN_MP_TORADIX_C
@@ -132,7 +137,7 @@
    #define BN_MP_ISEVEN_C
    #define BN_MP_INIT_MULTI_C
    #define BN_MP_COPY_C
-   #define BN_MP_ABS_C
+   #define BN_MP_MOD_C
    #define BN_MP_SET_C
    #define BN_MP_DIV_2_C
    #define BN_MP_ISODD_C
@@ -324,11 +329,12 @@
    #define BN_MP_CLEAR_C
    #define BN_MP_ABS_C
    #define BN_MP_CLEAR_MULTI_C
+   #define BN_MP_REDUCE_IS_2K_L_C
+   #define BN_S_MP_EXPTMOD_C
    #define BN_MP_DR_IS_MODULUS_C
    #define BN_MP_REDUCE_IS_2K_C
    #define BN_MP_ISODD_C
    #define BN_MP_EXPTMOD_FAST_C
-   #define BN_S_MP_EXPTMOD_C
 #endif
 
 #if defined(BN_MP_EXPTMOD_FAST_C)
@@ -360,6 +366,7 @@
    #define BN_MP_DIV_C
    #define BN_MP_MUL_C
    #define BN_MP_SUB_C
+   #define BN_MP_NEG_C
    #define BN_MP_EXCH_C
    #define BN_MP_CLEAR_MULTI_C
 #endif
@@ -434,6 +441,7 @@
 #if defined(BN_MP_INVMOD_SLOW_C)
    #define BN_MP_ISZERO_C
    #define BN_MP_INIT_MULTI_C
+   #define BN_MP_MOD_C
    #define BN_MP_COPY_C
    #define BN_MP_ISEVEN_C
    #define BN_MP_SET_C
@@ -725,6 +733,17 @@
    #define BN_MP_CLEAR_C
 #endif
 
+#if defined(BN_MP_REDUCE_2K_L_C)
+   #define BN_MP_INIT_C
+   #define BN_MP_COUNT_BITS_C
+   #define BN_MP_DIV_2D_C
+   #define BN_MP_MUL_C
+   #define BN_S_MP_ADD_C
+   #define BN_MP_CMP_MAG_C
+   #define BN_S_MP_SUB_C
+   #define BN_MP_CLEAR_C
+#endif
+
 #if defined(BN_MP_REDUCE_2K_SETUP_C)
    #define BN_MP_INIT_C
    #define BN_MP_COUNT_BITS_C
@@ -733,11 +752,22 @@
    #define BN_S_MP_SUB_C
 #endif
 
+#if defined(BN_MP_REDUCE_2K_SETUP_L_C)
+   #define BN_MP_INIT_C
+   #define BN_MP_2EXPT_C
+   #define BN_MP_COUNT_BITS_C
+   #define BN_S_MP_SUB_C
+   #define BN_MP_CLEAR_C
+#endif
+
 #if defined(BN_MP_REDUCE_IS_2K_C)
    #define BN_MP_REDUCE_2K_C
    #define BN_MP_COUNT_BITS_C
 #endif
 
+#if defined(BN_MP_REDUCE_IS_2K_L_C)
+#endif
+
 #if defined(BN_MP_REDUCE_SETUP_C)
    #define BN_MP_2EXPT_C
    #define BN_MP_DIV_C
@@ -815,6 +845,11 @@
    #define BN_MP_TO_UNSIGNED_BIN_C
 #endif
 
+#if defined(BN_MP_TO_SIGNED_BIN_N_C)
+   #define BN_MP_SIGNED_BIN_SIZE_C
+   #define BN_MP_TO_SIGNED_BIN_C
+#endif
+
 #if defined(BN_MP_TO_UNSIGNED_BIN_C)
    #define BN_MP_INIT_COPY_C
    #define BN_MP_ISZERO_C
@@ -822,6 +857,11 @@
    #define BN_MP_CLEAR_C
 #endif
 
+#if defined(BN_MP_TO_UNSIGNED_BIN_N_C)
+   #define BN_MP_UNSIGNED_BIN_SIZE_C
+   #define BN_MP_TO_UNSIGNED_BIN_C
+#endif
+
 #if defined(BN_MP_TOOM_MUL_C)
    #define BN_MP_INIT_MULTI_C
    #define BN_MP_MOD_2D_C
@@ -902,10 +942,12 @@
    #define BN_MP_INIT_C
    #define BN_MP_CLEAR_C
    #define BN_MP_REDUCE_SETUP_C
+   #define BN_MP_REDUCE_C
+   #define BN_MP_REDUCE_2K_SETUP_L_C
+   #define BN_MP_REDUCE_2K_L_C
    #define BN_MP_MOD_C
    #define BN_MP_COPY_C
    #define BN_MP_SQR_C
-   #define BN_MP_REDUCE_C
    #define BN_MP_MUL_C
    #define BN_MP_SET_C
    #define BN_MP_EXCH_C