1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
|
! SPARC v8 __mpn_addmul_1 -- Multiply a limb vector with a limb and
! add the result to a second limb vector.
! Copyright (C) 1992, 1993, 1994 Free Software Foundation, Inc.
! This file is part of the GNU MP Library.
! The GNU MP Library is free software; you can redistribute it and/or modify
! it under the terms of the GNU Library General Public License as published by
! the Free Software Foundation; either version 2 of the License, or (at your
! option) any later version.
! The GNU MP Library is distributed in the hope that it will be useful, but
! WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
! or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Library General Public
! License for more details.
! You should have received a copy of the GNU Library General Public License
! along with the GNU MP Library; see the file COPYING.LIB. If not, write to
! the Free Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
! INPUT PARAMETERS
! res_ptr o0
! s1_ptr o1
! size o2
! s2_limb o3
#include "sysdep.h"
.text
.align 4
.global C_SYMBOL_NAME(__mpn_addmul_1)
C_SYMBOL_NAME(__mpn_addmul_1):
orcc %g0,%g0,%g2
ld [%o1+0],%o4 ! 1
sll %o2,4,%g1
and %g1,(4-1)<<4,%g1
sethi %hi(LL),%g3
or %g3,%lo(LL),%g3
jmp %g3+%g1
nop
LL:
LL00: add %o0,-4,%o0
b Loop00 /* 4, 8, 12, ... */
add %o1,-4,%o1
nop
LL01: b Loop01 /* 1, 5, 9, ... */
nop
nop
nop
LL10: add %o0,-12,%o0 /* 2, 6, 10, ... */
b Loop10
add %o1,4,%o1
nop
LL11: add %o0,-8,%o0 /* 3, 7, 11, ... */
b Loop11
add %o1,-8,%o1
nop
1: addcc %g3,%g2,%g3 ! 1
ld [%o1+4],%o4 ! 2
rd %y,%g2 ! 1
addx %g0,%g2,%g2
ld [%o0+0],%g1 ! 2
addcc %g1,%g3,%g3
st %g3,[%o0+0] ! 1
Loop00: umul %o4,%o3,%g3 ! 2
ld [%o0+4],%g1 ! 2
addxcc %g3,%g2,%g3 ! 2
ld [%o1+8],%o4 ! 3
rd %y,%g2 ! 2
addx %g0,%g2,%g2
nop
addcc %g1,%g3,%g3
st %g3,[%o0+4] ! 2
Loop11: umul %o4,%o3,%g3 ! 3
addxcc %g3,%g2,%g3 ! 3
ld [%o1+12],%o4 ! 4
rd %y,%g2 ! 3
add %o1,16,%o1
addx %g0,%g2,%g2
ld [%o0+8],%g1 ! 2
addcc %g1,%g3,%g3
st %g3,[%o0+8] ! 3
Loop10: umul %o4,%o3,%g3 ! 4
addxcc %g3,%g2,%g3 ! 4
ld [%o1+0],%o4 ! 1
rd %y,%g2 ! 4
addx %g0,%g2,%g2
ld [%o0+12],%g1 ! 2
addcc %g1,%g3,%g3
st %g3,[%o0+12] ! 4
add %o0,16,%o0
addx %g0,%g2,%g2
Loop01: addcc %o2,-4,%o2
bg 1b
umul %o4,%o3,%g3 ! 1
addcc %g3,%g2,%g3 ! 4
rd %y,%g2 ! 4
addx %g0,%g2,%g2
ld [%o0+0],%g1 ! 2
addcc %g1,%g3,%g3
st %g3,[%o0+0] ! 4
addx %g0,%g2,%o0
retl
nop
! umul, ld, addxcc, rd, st
! umul, ld, addxcc, rd, ld, addcc, st, addx
|
