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
|
.text
.align 32, 0x90
.globl __gmpn_sqr_diag_addlsh1
.def __gmpn_sqr_diag_addlsh1
.scl 2
.type 32
.endef
__gmpn_sqr_diag_addlsh1:
push %rdi
push %rsi
mov %rcx, %rdi
mov %rdx, %rsi
mov %r8, %rdx
mov %r9, %rcx
push %rbx
dec %rcx
shl %rcx
mov (%rdx), %rax
lea (%rdi,%rcx,8), %rdi
lea (%rsi,%rcx,8), %rsi
lea (%rdx,%rcx,4), %r11
neg %rcx
mul %rax
mov %rax, (%rdi,%rcx,8)
xor %ebx, %ebx
jmp Lmid
.align 16, 0x90
Ltop: add %r10, %r8
adc %rax, %r9
mov %r8, -8(%rdi,%rcx,8)
mov %r9, (%rdi,%rcx,8)
Lmid: mov 8(%r11,%rcx,4), %rax
mov (%rsi,%rcx,8), %r8
mov 8(%rsi,%rcx,8), %r9
adc %r8, %r8
adc %r9, %r9
lea (%rdx,%rbx), %r10
setc %bl
mul %rax
add $2, %rcx
js Ltop
Lend: add %r10, %r8
adc %rax, %r9
mov %r8, -8(%rdi)
mov %r9, (%rdi)
adc %rbx, %rdx
mov %rdx, 8(%rdi)
pop %rbx
pop %rsi
pop %rdi
ret
|
