1
dnl Alpha __gmpn_mul_1 -- Multiply a limb vector with a limb and store
2
dnl the result in a second limb vector.
4
dnl Copyright 1992, 1994, 1995, 2000, 2002 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 2.1 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; see the file COPYING.LIB. If not, write to
20
dnl the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
21
dnl MA 02111-1307, USA.
23
include(`../config.m4')
32
C This code runs at 42 cycles/limb on EV4, 18 cycles/limb on EV5, and 7
37
ldq r2,0(r17) C r2 = s1_limb
38
lda r18,-1(r18) C size--
39
mulq r2,r19,r3 C r3 = prod_low
40
umulh r2,r19,r4 C r4 = prod_high
41
beq r18,$Le1c C jump if size was == 1
42
ldq r2,8(r17) C r2 = s1_limb
43
lda r18,-1(r18) C size--
44
addq r3,r20,r3 C r3 = cy_limb + cl
46
cmpult r3,r20,r0 C r0 = carry from (cy_limb + cl)
47
bne r18,$Loop C jump if size was == 2
49
$Le1c: addq r3,r20,r3 C r3 = cy_limb + cl
50
cmpult r3,r20,r0 C r0 = carry from (cy_limb + cl)
57
ldq r2,0(r17) C r2 = s1_limb
58
lda r18,-1(r18) C size--
59
mulq r2,r19,r3 C r3 = prod_low
60
bic r31,r31,r0 C clear cy_limb
61
umulh r2,r19,r4 C r4 = prod_high
62
beq r18,$Le1 C jump if size was == 1
63
ldq r2,8(r17) C r2 = s1_limb
64
lda r18,-1(r18) C size--
66
beq r18,$Le2 C jump if size was == 2
69
$Loop: mulq r2,r19,r3 C r3 = prod_low
70
addq r4,r0,r0 C cy_limb = cy_limb + 'cy'
71
lda r18,-1(r18) C size--
72
umulh r2,r19,r4 C r4 = prod_high
73
ldq r2,16(r17) C r2 = s1_limb
74
lda r17,8(r17) C s1_ptr++
75
addq r3,r0,r3 C r3 = cy_limb + prod_low
77
cmpult r3,r0,r0 C r0 = carry from (cy_limb + prod_low)
78
lda r16,8(r16) C res_ptr++
81
$Le2: mulq r2,r19,r3 C r3 = prod_low
82
addq r4,r0,r0 C cy_limb = cy_limb + 'cy'
83
umulh r2,r19,r4 C r4 = prod_high
84
addq r3,r0,r3 C r3 = cy_limb + prod_low
85
cmpult r3,r0,r0 C r0 = carry from (cy_limb + prod_low)
87
addq r4,r0,r0 C cy_limb = prod_high + cy