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
165
166
167
168
169
170
171
172
|
dnl AMD64 mpn_addlshC_n -- rp[] = up[] + (vp[] << C)
dnl AMD64 mpn_rsblshC_n -- rp[] = (vp[] << C) - up[]
dnl Copyright 2009-2012 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/.
C cycles/limb
C AMD K8,K9 2.1
C AMD K10 2.0
C AMD bd1 ~2.7
C AMD bd2 ~2.7
C AMD bd3 ?
C AMD bd4 ?
C AMD zen 2.0
C AMD bt1 3.3
C AMD bt2 3.0
C Intel P4 ?
C Intel PNR 3.0
C Intel NHM 2.75
C Intel SBR 2.55
C Intel IBR 2.49
C Intel HWL 2.25
C Intel BWL 1.89
C Intel SKL 1.90
C Intel atom 8.4
C Intel SLM 4.0
C VIA nano ?
C INPUT PARAMETERS
define(`rp', `%rdi')
define(`up', `%rsi')
define(`vp', `%rdx')
define(`n', `%rcx')
define(M, eval(m4_lshift(1,LSH)))
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)
ASM_START()
TEXT
ALIGN(16)
PROLOGUE(func)
FUNC_ENTRY(4)
push %r12
push %r13
push %r14
push %r15
mov (vp), %r8
lea (,%r8,M), %r12
shr $RSH, %r8
mov R32(n), R32(%rax)
lea (rp,n,8), rp
lea (up,n,8), up
lea (vp,n,8), vp
neg n
and $3, R8(%rax)
je L(b00)
cmp $2, R8(%rax)
jc L(b01)
je L(b10)
L(b11): mov 8(vp,n,8), %r10
lea (%r8,%r10,M), %r14
shr $RSH, %r10
mov 16(vp,n,8), %r11
lea (%r10,%r11,M), %r15
shr $RSH, %r11
ADDSUB (up,n,8), %r12
ADCSBB 8(up,n,8), %r14
ADCSBB 16(up,n,8), %r15
sbb R32(%rax), R32(%rax) C save carry for next
mov %r12, (rp,n,8)
mov %r14, 8(rp,n,8)
mov %r15, 16(rp,n,8)
add $3, n
js L(top)
jmp L(end)
L(b01): mov %r8, %r11
ADDSUB (up,n,8), %r12
sbb R32(%rax), R32(%rax) C save carry for next
mov %r12, (rp,n,8)
add $1, n
js L(top)
jmp L(end)
L(b10): mov 8(vp,n,8), %r11
lea (%r8,%r11,M), %r15
shr $RSH, %r11
ADDSUB (up,n,8), %r12
ADCSBB 8(up,n,8), %r15
sbb R32(%rax), R32(%rax) C save carry for next
mov %r12, (rp,n,8)
mov %r15, 8(rp,n,8)
add $2, n
js L(top)
jmp L(end)
L(b00): mov 8(vp,n,8), %r9
mov 16(vp,n,8), %r10
jmp L(e00)
ALIGN(16)
L(top): mov 16(vp,n,8), %r10
mov (vp,n,8), %r8
mov 8(vp,n,8), %r9
lea (%r11,%r8,M), %r12
shr $RSH, %r8
L(e00): lea (%r8,%r9,M), %r13
shr $RSH, %r9
mov 24(vp,n,8), %r11
lea (%r9,%r10,M), %r14
shr $RSH, %r10
lea (%r10,%r11,M), %r15
shr $RSH, %r11
add R32(%rax), R32(%rax) C restore carry
ADCSBB (up,n,8), %r12
ADCSBB 8(up,n,8), %r13
ADCSBB 16(up,n,8), %r14
ADCSBB 24(up,n,8), %r15
mov %r12, (rp,n,8)
mov %r13, 8(rp,n,8)
mov %r14, 16(rp,n,8)
sbb R32(%rax), R32(%rax) C save carry for next
mov %r15, 24(rp,n,8)
add $4, n
js L(top)
L(end):
ifelse(ADDSUB,add,`
sub R32(%r11), R32(%rax)
neg R32(%rax)
',`
add R32(%r11), R32(%rax)
movslq R32(%rax), %rax
')
pop %r15
pop %r14
pop %r13
pop %r12
FUNC_EXIT()
ret
EPILOGUE()
|