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
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
|
dnl AMD64 mpn_addmul_1/mpn_submul_1 optimised for Intel Atom.
dnl Copyright 2003-2005, 2007, 2008, 2011-2013 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 AMD K8,K9 4.5
C AMD K10 4.5
C AMD bull 4.73
C AMD pile 4.60 4.80
C AMD steam
C AMD excavator
C AMD bobcat 5.48
C AMD jaguar 5.61
C Intel P4 16.6
C Intel core2 5.09
C Intel NHM 4.79
C Intel SBR 3.88
C Intel IBR 3.65
C Intel HWL 3.53
C Intel BWL 2.75
C Intel SKL 2.76
C Intel atom 19.4
C Intel SLM 8
C VIA nano
C The loop of this code is the result of running a code generation and
C optimisation tool suite written by David Harvey and Torbjorn Granlund.
define(`rp', `%rdi') C rcx
define(`up', `%rsi') C rdx
define(`n_param', `%rdx') C r8
define(`v0', `%rcx') C r9
define(`n', `%rbx')
ifdef(`OPERATION_addmul_1',`
define(`ADDSUB', `add')
define(`func', `mpn_addmul_1')
')
ifdef(`OPERATION_submul_1',`
define(`ADDSUB', `sub')
define(`func', `mpn_submul_1')
')
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)
MULFUNC_PROLOGUE(mpn_addmul_1 mpn_submul_1)
ASM_START()
TEXT
ALIGN(16)
PROLOGUE(func)
FUNC_ENTRY(4)
push %rbx
mov (up), %rax
lea -8(up,n_param,8), up
lea -16(rp,n_param,8), rp
test $1, R8(n_param)
jnz L(bx1)
L(bx0): test $2, R8(n_param)
jnz L(b10)
L(b00): mov $1, R32(n)
sub n_param, n
mul v0
mov %rax, %r11
mov 8(up,n,8), %rax
mov %rdx, %r10
mul v0
mov %rax, %r8
mov 16(up,n,8), %rax
jmp L(lo0)
L(b10): mov $3, R32(n)
sub n_param, n
mul v0
mov %rax, %r11
mov -8(up,n,8), %rax
mov %rdx, %r10
mul v0
test n, n
jns L(cj2)
mov %rax, %r8
mov (up,n,8), %rax
mov %rdx, %r9
jmp L(lo2)
L(bx1): test $2, R8(n_param)
jnz L(b11)
L(b01): mov $2, R32(n)
sub n_param, n
mul v0
test n, n
jns L(cj1)
mov %rax, %r8
mov (up,n,8), %rax
mov %rdx, %r9
mul v0
mov %rax, %r11
mov 8(up,n,8), %rax
mov %rdx, %r10
jmp L(lo1)
L(b11): xor R32(n), R32(n)
sub n_param, n
mul v0
mov %rax, %r8
mov 16(up,n,8), %rax
mov %rdx, %r9
mul v0
mov %rax, %r11
mov 24(up,n,8), %rax
jmp L(lo3)
ALIGN(16)
L(top): mul v0
ADDSUB %r8, -16(rp,n,8)
mov %rax, %r8
mov (up,n,8), %rax
adc %r9, %r11
mov %rdx, %r9
adc $0, %r10
L(lo2): mul v0
ADDSUB %r11, -8(rp,n,8)
mov %rax, %r11
mov 8(up,n,8), %rax
adc %r10, %r8
mov %rdx, %r10
adc $0, %r9
L(lo1): mul v0
ADDSUB %r8, (rp,n,8)
mov %rax, %r8
adc %r9, %r11
mov 16(up,n,8), %rax
adc $0, %r10
L(lo0): mov %rdx, %r9
mul v0
ADDSUB %r11, 8(rp,n,8)
mov %rax, %r11
adc %r10, %r8
mov 24(up,n,8), %rax
adc $0, %r9
L(lo3): add $4, n
mov %rdx, %r10
js L(top)
L(end): mul v0
ADDSUB %r8, -16(rp,n,8)
adc %r9, %r11
adc $0, %r10
L(cj2): ADDSUB %r11, -8(rp,n,8)
adc %r10, %rax
adc $0, %rdx
L(cj1): ADDSUB %rax, (rp,n,8)
mov $0, R32(%rax)
adc %rdx, %rax
pop %rbx
FUNC_EXIT()
ret
EPILOGUE()
ASM_END()
|
