--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bn_s_mp_sqr.c	Mon May 31 18:25:22 2004 +0000
@@ -0,0 +1,79 @@
+/* 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, [email protected], http://math.libtomcrypt.org
+ */
+#include <tommath.h>
+
+/* low level squaring, b = a*a, HAC pp.596-597, Algorithm 14.16 */
+int
+s_mp_sqr (mp_int * a, mp_int * b)
+{
+  mp_int  t;
+  int     res, ix, iy, pa;
+  mp_word r;
+  mp_digit u, tmpx, *tmpt;
+
+  pa = a->used;
+  if ((res = mp_init_size (&t, 2*pa + 1)) != MP_OKAY) {
+    return res;
+  }
+
+  /* default used is maximum possible size */
+  t.used = 2*pa + 1;
+
+  for (ix = 0; ix < pa; ix++) {
+    /* first calculate the digit at 2*ix */
+    /* calculate double precision result */
+    r = ((mp_word) t.dp[2*ix]) +
+        ((mp_word)a->dp[ix])*((mp_word)a->dp[ix]);
+
+    /* store lower part in result */
+    t.dp[ix+ix] = (mp_digit) (r & ((mp_word) MP_MASK));
+
+    /* get the carry */
+    u           = (mp_digit)(r >> ((mp_word) DIGIT_BIT));
+
+    /* left hand side of A[ix] * A[iy] */
+    tmpx        = a->dp[ix];
+
+    /* alias for where to store the results */
+    tmpt        = t.dp + (2*ix + 1);
+    
+    for (iy = ix + 1; iy < pa; iy++) {
+      /* first calculate the product */
+      r       = ((mp_word)tmpx) * ((mp_word)a->dp[iy]);
+
+      /* now calculate the double precision result, note we use
+       * addition instead of *2 since it's easier to optimize
+       */
+      r       = ((mp_word) *tmpt) + r + r + ((mp_word) u);
+
+      /* store lower part */
+      *tmpt++ = (mp_digit) (r & ((mp_word) MP_MASK));
+
+      /* get carry */
+      u       = (mp_digit)(r >> ((mp_word) DIGIT_BIT));
+    }
+    /* propagate upwards */
+    while (u != ((mp_digit) 0)) {
+      r       = ((mp_word) *tmpt) + ((mp_word) u);
+      *tmpt++ = (mp_digit) (r & ((mp_word) MP_MASK));
+      u       = (mp_digit)(r >> ((mp_word) DIGIT_BIT));
+    }
+  }
+
+  mp_clamp (&t);
+  mp_exch (&t, b);
+  mp_clear (&t);
+  return MP_OKAY;
+}