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
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
|
dnl Alpha mpn_add_n -- Add two limb vectors of the same length > 0 and
dnl store sum in a third limb vector.
dnl Copyright 1995, 1999, 2000, 2005, 2011 Free Software Foundation, Inc.
dnl This file is part of the GNU MP Library.
dnl
dnl The GNU MP Library is free software; you can redistribute it and/or modify
dnl it under the terms of either:
dnl
dnl * the GNU Lesser General Public License as published by the Free
dnl Software Foundation; either version 3 of the License, or (at your
dnl option) any later version.
dnl
dnl or
dnl
dnl * the GNU General Public License as published by the Free Software
dnl Foundation; either version 2 of the License, or (at your option) any
dnl later version.
dnl
dnl or both in parallel, as here.
dnl
dnl The GNU MP Library is distributed in the hope that it will be useful, but
dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
dnl for more details.
dnl
dnl You should have received copies of the GNU General Public License and the
dnl GNU Lesser General Public License along with the GNU MP Library. If not,
dnl see https://www.gnu.org/licenses/.
include(`../config.m4')
C cycles/limb
C EV4: ?
C EV5: 4.75
C EV6: 3
dnl INPUT PARAMETERS
dnl res_ptr r16
dnl s1_ptr r17
dnl s2_ptr r18
dnl size r19
ASM_START()
PROLOGUE(mpn_add_nc)
bis r20,r31,r25
br L(com)
EPILOGUE()
PROLOGUE(mpn_add_n)
bis r31,r31,r25 C clear cy
L(com): subq r19,4,r19 C decr loop cnt
blt r19,$Lend2 C if less than 4 limbs, goto 2nd loop
C Start software pipeline for 1st loop
ldq r0,0(r18)
ldq r4,0(r17)
ldq r1,8(r18)
ldq r5,8(r17)
addq r17,32,r17 C update s1_ptr
addq r0,r4,r28 C 1st main add
ldq r2,16(r18)
addq r25,r28,r20 C 1st carry add
ldq r3,24(r18)
cmpult r28,r4,r8 C compute cy from last add
ldq r6,-16(r17)
cmpult r20,r28,r25 C compute cy from last add
ldq r7,-8(r17)
bis r8,r25,r25 C combine cy from the two adds
subq r19,4,r19 C decr loop cnt
addq r1,r5,r28 C 2nd main add
addq r18,32,r18 C update s2_ptr
addq r28,r25,r21 C 2nd carry add
cmpult r28,r5,r8 C compute cy from last add
blt r19,$Lend1 C if less than 4 limbs remain, jump
C 1st loop handles groups of 4 limbs in a software pipeline
ALIGN(16)
$Loop: cmpult r21,r28,r25 C compute cy from last add
ldq r0,0(r18)
bis r8,r25,r25 C combine cy from the two adds
ldq r1,8(r18)
addq r2,r6,r28 C 3rd main add
ldq r4,0(r17)
addq r28,r25,r22 C 3rd carry add
ldq r5,8(r17)
cmpult r28,r6,r8 C compute cy from last add
cmpult r22,r28,r25 C compute cy from last add
stq r20,0(r16)
bis r8,r25,r25 C combine cy from the two adds
stq r21,8(r16)
addq r3,r7,r28 C 4th main add
addq r28,r25,r23 C 4th carry add
cmpult r28,r7,r8 C compute cy from last add
cmpult r23,r28,r25 C compute cy from last add
addq r17,32,r17 C update s1_ptr
bis r8,r25,r25 C combine cy from the two adds
addq r16,32,r16 C update res_ptr
addq r0,r4,r28 C 1st main add
ldq r2,16(r18)
addq r25,r28,r20 C 1st carry add
ldq r3,24(r18)
cmpult r28,r4,r8 C compute cy from last add
ldq r6,-16(r17)
cmpult r20,r28,r25 C compute cy from last add
ldq r7,-8(r17)
bis r8,r25,r25 C combine cy from the two adds
subq r19,4,r19 C decr loop cnt
stq r22,-16(r16)
addq r1,r5,r28 C 2nd main add
stq r23,-8(r16)
addq r25,r28,r21 C 2nd carry add
addq r18,32,r18 C update s2_ptr
cmpult r28,r5,r8 C compute cy from last add
bge r19,$Loop
C Finish software pipeline for 1st loop
$Lend1: cmpult r21,r28,r25 C compute cy from last add
bis r8,r25,r25 C combine cy from the two adds
addq r2,r6,r28 C 3rd main add
addq r28,r25,r22 C 3rd carry add
cmpult r28,r6,r8 C compute cy from last add
cmpult r22,r28,r25 C compute cy from last add
stq r20,0(r16)
bis r8,r25,r25 C combine cy from the two adds
stq r21,8(r16)
addq r3,r7,r28 C 4th main add
addq r28,r25,r23 C 4th carry add
cmpult r28,r7,r8 C compute cy from last add
cmpult r23,r28,r25 C compute cy from last add
bis r8,r25,r25 C combine cy from the two adds
addq r16,32,r16 C update res_ptr
stq r22,-16(r16)
stq r23,-8(r16)
$Lend2: addq r19,4,r19 C restore loop cnt
beq r19,$Lret
C Start software pipeline for 2nd loop
ldq r0,0(r18)
ldq r4,0(r17)
subq r19,1,r19
beq r19,$Lend0
C 2nd loop handles remaining 1-3 limbs
ALIGN(16)
$Loop0: addq r0,r4,r28 C main add
ldq r0,8(r18)
cmpult r28,r4,r8 C compute cy from last add
ldq r4,8(r17)
addq r28,r25,r20 C carry add
addq r18,8,r18
addq r17,8,r17
stq r20,0(r16)
cmpult r20,r28,r25 C compute cy from last add
subq r19,1,r19 C decr loop cnt
bis r8,r25,r25 C combine cy from the two adds
addq r16,8,r16
bne r19,$Loop0
$Lend0: addq r0,r4,r28 C main add
addq r28,r25,r20 C carry add
cmpult r28,r4,r8 C compute cy from last add
cmpult r20,r28,r25 C compute cy from last add
stq r20,0(r16)
bis r8,r25,r25 C combine cy from the two adds
$Lret: bis r25,r31,r0 C return cy
ret r31,(r26),1
EPILOGUE()
ASM_END()
|
