Return to sqr_basecase.c CVS log

Up to [local] / OpenXM_contrib / gmp / mpn / generic

Annotation of OpenXM_contrib/gmp/mpn/generic/sqr_basecase.c, Revision 1.1.1.1

1.1       maekawa     1: /* mpn_sqr_basecase -- Internal routine to square two natural numbers
                      2:    of length m and n.
                      3:
                      4:    THIS IS AN INTERNAL FUNCTION WITH A MUTABLE INTERFACE.  IT IS ONLY
                      5:    SAFE TO REACH THIS FUNCTION THROUGH DOCUMENTED INTERFACES.
                      6:
                      7:
                      8: Copyright (C) 1991, 1992, 1993, 1994, 1996, 1997, 2000 Free Software
                      9: Foundation, Inc.
                     10:
                     11: This file is part of the GNU MP Library.
                     12:
                     13: The GNU MP Library is free software; you can redistribute it and/or modify
                     14: it under the terms of the GNU Lesser General Public License as published by
                     15: the Free Software Foundation; either version 2.1 of the License, or (at your
                     16: option) any later version.
                     17:
                     18: The GNU MP Library is distributed in the hope that it will be useful, but
                     19: WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
                     20: or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
                     21: License for more details.
                     22:
                     23: You should have received a copy of the GNU Lesser General Public License
                     24: along with the GNU MP Library; see the file COPYING.LIB.  If not, write to
                     25: the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
                     26: MA 02111-1307, USA. */
                     27:
                     28: #include "gmp.h"
                     29: #include "gmp-impl.h"
                     30: #include "longlong.h"
                     31:
                     32: void
                     33: #if __STDC__
                     34: mpn_sqr_basecase (mp_ptr prodp, mp_srcptr up, mp_size_t n)
                     35: #else
                     36: mpn_sqr_basecase (prodp, up, n)
                     37:      mp_ptr prodp;
                     38:      mp_srcptr up;
                     39:      mp_size_t n;
                     40: #endif
                     41: {
                     42:   mp_size_t i;
                     43:
                     44:   {
                     45:     /* N.B.!  We need the superfluous indirection through argh to work around
                     46:        a reloader bug in GCC 2.7.*.  */
                     47:     mp_limb_t x;
                     48:     mp_limb_t argh;
                     49:     x = up[0];
                     50:     umul_ppmm (argh, prodp[0], x, x);
                     51:     prodp[1] = argh;
                     52:   }
                     53:   if (n > 1)
                     54:     {
                     55:       mp_limb_t tarr[2 * KARATSUBA_SQR_THRESHOLD];
                     56:       mp_ptr tp = tarr;
                     57:       mp_limb_t cy;
                     58:
                     59:       /* must fit 2*n limbs in tarr */
                     60:       ASSERT (n <= KARATSUBA_SQR_THRESHOLD);
                     61:
                     62:       cy = mpn_mul_1 (tp, up + 1, n - 1, up[0]);
                     63:       tp[n - 1] = cy;
                     64:       for (i = 2; i < n; i++)
                     65:        {
                     66:          mp_limb_t cy;
                     67:          cy = mpn_addmul_1 (tp + 2 * i - 2, up + i, n - i, up[i - 1]);
                     68:          tp[n + i - 2] = cy;
                     69:        }
                     70:       for (i = 1; i < n; i++)
                     71:        {
                     72:          mp_limb_t x;
                     73:          x = up[i];
                     74:          umul_ppmm (prodp[2 * i + 1], prodp[2 * i], x, x);
                     75:        }
                     76:       {
                     77:        mp_limb_t cy;
                     78:        cy = mpn_lshift (tp, tp, 2 * n - 2, 1);
                     79:        cy += mpn_add_n (prodp + 1, prodp + 1, tp, 2 * n - 2);
                     80:        prodp[2 * n - 1] += cy;
                     81:       }
                     82:     }
                     83: }