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
|
#define mul(a0,a1,a2,a3, rb, stack) \
MOVQ a0, AX \
MULQ 0+rb \
MOVQ AX, R8 \
MOVQ DX, R9 \
MOVQ a0, AX \
MULQ 8+rb \
ADDQ AX, R9 \
ADCQ $0, DX \
MOVQ DX, R10 \
MOVQ a0, AX \
MULQ 16+rb \
ADDQ AX, R10 \
ADCQ $0, DX \
MOVQ DX, R11 \
MOVQ a0, AX \
MULQ 24+rb \
ADDQ AX, R11 \
ADCQ $0, DX \
MOVQ DX, R12 \
\
storeBlock(R8,R9,R10,R11, 0+stack) \
MOVQ R12, 32+stack \
\
MOVQ a1, AX \
MULQ 0+rb \
MOVQ AX, R8 \
MOVQ DX, R9 \
MOVQ a1, AX \
MULQ 8+rb \
ADDQ AX, R9 \
ADCQ $0, DX \
MOVQ DX, R10 \
MOVQ a1, AX \
MULQ 16+rb \
ADDQ AX, R10 \
ADCQ $0, DX \
MOVQ DX, R11 \
MOVQ a1, AX \
MULQ 24+rb \
ADDQ AX, R11 \
ADCQ $0, DX \
MOVQ DX, R12 \
\
ADDQ 8+stack, R8 \
ADCQ 16+stack, R9 \
ADCQ 24+stack, R10 \
ADCQ 32+stack, R11 \
ADCQ $0, R12 \
storeBlock(R8,R9,R10,R11, 8+stack) \
MOVQ R12, 40+stack \
\
MOVQ a2, AX \
MULQ 0+rb \
MOVQ AX, R8 \
MOVQ DX, R9 \
MOVQ a2, AX \
MULQ 8+rb \
ADDQ AX, R9 \
ADCQ $0, DX \
MOVQ DX, R10 \
MOVQ a2, AX \
MULQ 16+rb \
ADDQ AX, R10 \
ADCQ $0, DX \
MOVQ DX, R11 \
MOVQ a2, AX \
MULQ 24+rb \
ADDQ AX, R11 \
ADCQ $0, DX \
MOVQ DX, R12 \
\
ADDQ 16+stack, R8 \
ADCQ 24+stack, R9 \
ADCQ 32+stack, R10 \
ADCQ 40+stack, R11 \
ADCQ $0, R12 \
storeBlock(R8,R9,R10,R11, 16+stack) \
MOVQ R12, 48+stack \
\
MOVQ a3, AX \
MULQ 0+rb \
MOVQ AX, R8 \
MOVQ DX, R9 \
MOVQ a3, AX \
MULQ 8+rb \
ADDQ AX, R9 \
ADCQ $0, DX \
MOVQ DX, R10 \
MOVQ a3, AX \
MULQ 16+rb \
ADDQ AX, R10 \
ADCQ $0, DX \
MOVQ DX, R11 \
MOVQ a3, AX \
MULQ 24+rb \
ADDQ AX, R11 \
ADCQ $0, DX \
MOVQ DX, R12 \
\
ADDQ 24+stack, R8 \
ADCQ 32+stack, R9 \
ADCQ 40+stack, R10 \
ADCQ 48+stack, R11 \
ADCQ $0, R12 \
storeBlock(R8,R9,R10,R11, 24+stack) \
MOVQ R12, 56+stack
#define gfpReduce(stack) \
\ // m = (T * N') mod R, store m in R8:R9:R10:R11
MOVQ ·np+0(SB), AX \
MULQ 0+stack \
MOVQ AX, R8 \
MOVQ DX, R9 \
MOVQ ·np+0(SB), AX \
MULQ 8+stack \
ADDQ AX, R9 \
ADCQ $0, DX \
MOVQ DX, R10 \
MOVQ ·np+0(SB), AX \
MULQ 16+stack \
ADDQ AX, R10 \
ADCQ $0, DX \
MOVQ DX, R11 \
MOVQ ·np+0(SB), AX \
MULQ 24+stack \
ADDQ AX, R11 \
\
MOVQ ·np+8(SB), AX \
MULQ 0+stack \
MOVQ AX, R12 \
MOVQ DX, R13 \
MOVQ ·np+8(SB), AX \
MULQ 8+stack \
ADDQ AX, R13 \
ADCQ $0, DX \
MOVQ DX, R14 \
MOVQ ·np+8(SB), AX \
MULQ 16+stack \
ADDQ AX, R14 \
\
ADDQ R12, R9 \
ADCQ R13, R10 \
ADCQ R14, R11 \
\
MOVQ ·np+16(SB), AX \
MULQ 0+stack \
MOVQ AX, R12 \
MOVQ DX, R13 \
MOVQ ·np+16(SB), AX \
MULQ 8+stack \
ADDQ AX, R13 \
\
ADDQ R12, R10 \
ADCQ R13, R11 \
\
MOVQ ·np+24(SB), AX \
MULQ 0+stack \
ADDQ AX, R11 \
\
storeBlock(R8,R9,R10,R11, 64+stack) \
\
\ // m * N
mul(·p2+0(SB),·p2+8(SB),·p2+16(SB),·p2+24(SB), 64+stack, 96+stack) \
\
\ // Add the 512-bit intermediate to m*N
loadBlock(96+stack, R8,R9,R10,R11) \
loadBlock(128+stack, R12,R13,R14,R15) \
\
MOVQ $0, AX \
ADDQ 0+stack, R8 \
ADCQ 8+stack, R9 \
ADCQ 16+stack, R10 \
ADCQ 24+stack, R11 \
ADCQ 32+stack, R12 \
ADCQ 40+stack, R13 \
ADCQ 48+stack, R14 \
ADCQ 56+stack, R15 \
ADCQ $0, AX \
\
gfpCarry(R12,R13,R14,R15,AX, R8,R9,R10,R11,BX)
|
