pentium4/sse2/divrem_1.asm

0 dnl  Intel Pentium-4 mpn_divrem_1 -- mpn by limb division.
3 dnl  Copyright 1999, 2000, 2001, 2002, 2003, 2004 Free Software Foundation,
4 dnl  Inc.
5 dnl
6 dnl  This file is part of the GNU MP Library.
7 dnl
8 dnl  The GNU MP Library is free software; you can redistribute it and/or
9 dnl  modify it under the terms of the GNU Lesser General Public License as
10 dnl  published by the Free Software Foundation; either version 3 of the
11 dnl  License, or (at your option) any later version.
12 dnl
13 dnl  The GNU MP Library is distributed in the hope that it will be useful,
14 dnl  but WITHOUT ANY WARRANTY; without even the implied warranty of
15 dnl  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
16 dnl  Lesser General Public License for more details.
17 dnl
18 dnl  You should have received a copy of the GNU Lesser General Public License
19 dnl  along with the GNU MP Library.  If not, see http://www.gnu.org/licenses/.
83 dnl  MUL_THRESHOLD is the value of xsize+size at which the multiply by
84 dnl  inverse method is used, rather than plain "divl"s.  Minimum value 1.
85 dnl
86 dnl  The inverse takes about 80-90 cycles to calculate, but after that the
87 dnl  multiply is 32 c/l versus division at about 58 c/l.
88 dnl
89 dnl  At 4 limbs the div is a touch faster than the mul (and of course
90 dnl  simpler), so start the mul from 5 limbs.
95 defframe(PARAM_PREINV_SHIFT,   28)  dnl mpn_preinv_divrem_1
96 defframe(PARAM_PREINV_INVERSE, 24)  dnl mpn_preinv_divrem_1
97 defframe(PARAM_CARRY,  24)          dnl mpn_divrem_1c
104 dnl  re-use parameter space