1 dnl AMD64 mpn_addmul_2 -- Multiply an n-limb vector with a 2-limb vector and
2 dnl add the result to a third limb vector.
4 dnl Copyright 2008 Free Software Foundation, Inc.
6 dnl This file is part of the GNU MP Library.
8 dnl The GNU MP Library is free software; you can redistribute it and/or modify
9 dnl it under the terms of the GNU Lesser General Public License as published
10 dnl by the Free Software Foundation; either version 3 of the License, or (at
11 dnl your option) any later version.
13 dnl The GNU MP Library is distributed in the hope that it will be useful, but
14 dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
15 dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
16 dnl License for more details.
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/.
21 include(`../config.m4')
30 C This code is the result of running a code generation and optimization tool
31 C suite written by David Harvey and Torbjorn Granlund.
34 C * Work on feed-in and wind-down code.
35 C * Convert "mov $0" to "xor".
36 C * Adjust initial lea to save some bytes.
37 C * Perhaps adjust n from n_param&3 value?
42 define(`n_param',`%rdx')
56 PROLOGUE(mpn_addmul_2)
65 lea -32(up,n_param,8), up
66 lea -32(rp,n_param,8), rp
112 add w3, (rp,n,8) C 0 21
121 adc $0, R32(w2) C 6 30
123 add w0, 8(rp,n,8) C 3 27
134 add w1, 16(rp,n,8) C 9
146 add w2, 24(rp,n,8) C 15