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
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
|
/
/ This Source Code Form is subject to the terms of the Mozilla Public
/ License, v. 2.0. If a copy of the MPL was not distributed with this
/ file, You can obtain one at http://mozilla.org/MPL/2.0/.
.text
/ ebp - 36: caller's esi
/ ebp - 32: caller's edi
/ ebp - 28:
/ ebp - 24:
/ ebp - 20:
/ ebp - 16:
/ ebp - 12:
/ ebp - 8:
/ ebp - 4:
/ ebp + 0: caller's ebp
/ ebp + 4: return address
/ ebp + 8: a argument
/ ebp + 12: a_len argument
/ ebp + 16: b argument
/ ebp + 20: c argument
/ registers:
/ eax:
/ ebx: carry
/ ecx: a_len
/ edx:
/ esi: a ptr
/ edi: c ptr
.globl s_mpv_mul_d
.type s_mpv_mul_d,@function
s_mpv_mul_d:
push %ebp
mov %esp,%ebp
sub $28,%esp
push %edi
push %esi
push %ebx
movl $0,%ebx / carry = 0
mov 12(%ebp),%ecx / ecx = a_len
mov 20(%ebp),%edi
cmp $0,%ecx
je L2 / jmp if a_len == 0
mov 8(%ebp),%esi / esi = a
cld
L1:
lodsl / eax = [ds:esi]; esi += 4
mov 16(%ebp),%edx / edx = b
mull %edx / edx:eax = Phi:Plo = a_i * b
add %ebx,%eax / add carry (%ebx) to edx:eax
adc $0,%edx
mov %edx,%ebx / high half of product becomes next carry
stosl / [es:edi] = ax; edi += 4;
dec %ecx / --a_len
jnz L1 / jmp if a_len != 0
L2:
mov %ebx,0(%edi) / *c = carry
pop %ebx
pop %esi
pop %edi
leave
ret
nop
/ ebp - 36: caller's esi
/ ebp - 32: caller's edi
/ ebp - 28:
/ ebp - 24:
/ ebp - 20:
/ ebp - 16:
/ ebp - 12:
/ ebp - 8:
/ ebp - 4:
/ ebp + 0: caller's ebp
/ ebp + 4: return address
/ ebp + 8: a argument
/ ebp + 12: a_len argument
/ ebp + 16: b argument
/ ebp + 20: c argument
/ registers:
/ eax:
/ ebx: carry
/ ecx: a_len
/ edx:
/ esi: a ptr
/ edi: c ptr
.globl s_mpv_mul_d_add
.type s_mpv_mul_d_add,@function
s_mpv_mul_d_add:
push %ebp
mov %esp,%ebp
sub $28,%esp
push %edi
push %esi
push %ebx
movl $0,%ebx / carry = 0
mov 12(%ebp),%ecx / ecx = a_len
mov 20(%ebp),%edi
cmp $0,%ecx
je L4 / jmp if a_len == 0
mov 8(%ebp),%esi / esi = a
cld
L3:
lodsl / eax = [ds:esi]; esi += 4
mov 16(%ebp),%edx / edx = b
mull %edx / edx:eax = Phi:Plo = a_i * b
add %ebx,%eax / add carry (%ebx) to edx:eax
adc $0,%edx
mov 0(%edi),%ebx / add in current word from *c
add %ebx,%eax
adc $0,%edx
mov %edx,%ebx / high half of product becomes next carry
stosl / [es:edi] = ax; edi += 4;
dec %ecx / --a_len
jnz L3 / jmp if a_len != 0
L4:
mov %ebx,0(%edi) / *c = carry
pop %ebx
pop %esi
pop %edi
leave
ret
nop
/ ebp - 36: caller's esi
/ ebp - 32: caller's edi
/ ebp - 28:
/ ebp - 24:
/ ebp - 20:
/ ebp - 16:
/ ebp - 12:
/ ebp - 8:
/ ebp - 4:
/ ebp + 0: caller's ebp
/ ebp + 4: return address
/ ebp + 8: a argument
/ ebp + 12: a_len argument
/ ebp + 16: b argument
/ ebp + 20: c argument
/ registers:
/ eax:
/ ebx: carry
/ ecx: a_len
/ edx:
/ esi: a ptr
/ edi: c ptr
.globl s_mpv_mul_d_add_prop
.type s_mpv_mul_d_add_prop,@function
s_mpv_mul_d_add_prop:
push %ebp
mov %esp,%ebp
sub $28,%esp
push %edi
push %esi
push %ebx
movl $0,%ebx / carry = 0
mov 12(%ebp),%ecx / ecx = a_len
mov 20(%ebp),%edi
cmp $0,%ecx
je L6 / jmp if a_len == 0
cld
mov 8(%ebp),%esi / esi = a
L5:
lodsl / eax = [ds:esi]; esi += 4
mov 16(%ebp),%edx / edx = b
mull %edx / edx:eax = Phi:Plo = a_i * b
add %ebx,%eax / add carry (%ebx) to edx:eax
adc $0,%edx
mov 0(%edi),%ebx / add in current word from *c
add %ebx,%eax
adc $0,%edx
mov %edx,%ebx / high half of product becomes next carry
stosl / [es:edi] = ax; edi += 4;
dec %ecx / --a_len
jnz L5 / jmp if a_len != 0
L6:
cmp $0,%ebx / is carry zero?
jz L8
mov 0(%edi),%eax / add in current word from *c
add %ebx,%eax
stosl / [es:edi] = ax; edi += 4;
jnc L8
L7:
mov 0(%edi),%eax / add in current word from *c
adc $0,%eax
stosl / [es:edi] = ax; edi += 4;
jc L7
L8:
pop %ebx
pop %esi
pop %edi
leave
ret
nop
/ ebp - 20: caller's esi
/ ebp - 16: caller's edi
/ ebp - 12:
/ ebp - 8: carry
/ ebp - 4: a_len local
/ ebp + 0: caller's ebp
/ ebp + 4: return address
/ ebp + 8: pa argument
/ ebp + 12: a_len argument
/ ebp + 16: ps argument
/ ebp + 20:
/ registers:
/ eax:
/ ebx: carry
/ ecx: a_len
/ edx:
/ esi: a ptr
/ edi: c ptr
.globl s_mpv_sqr_add_prop
.type s_mpv_sqr_add_prop,@function
s_mpv_sqr_add_prop:
push %ebp
mov %esp,%ebp
sub $12,%esp
push %edi
push %esi
push %ebx
movl $0,%ebx / carry = 0
mov 12(%ebp),%ecx / a_len
mov 16(%ebp),%edi / edi = ps
cmp $0,%ecx
je L11 / jump if a_len == 0
cld
mov 8(%ebp),%esi / esi = pa
L10:
lodsl / %eax = [ds:si]; si += 4;
mull %eax
add %ebx,%eax / add "carry"
adc $0,%edx
mov 0(%edi),%ebx
add %ebx,%eax / add low word from result
mov 4(%edi),%ebx
stosl / [es:di] = %eax; di += 4;
adc %ebx,%edx / add high word from result
movl $0,%ebx
mov %edx,%eax
adc $0,%ebx
stosl / [es:di] = %eax; di += 4;
dec %ecx / --a_len
jnz L10 / jmp if a_len != 0
L11:
cmp $0,%ebx / is carry zero?
jz L14
mov 0(%edi),%eax / add in current word from *c
add %ebx,%eax
stosl / [es:edi] = ax; edi += 4;
jnc L14
L12:
mov 0(%edi),%eax / add in current word from *c
adc $0,%eax
stosl / [es:edi] = ax; edi += 4;
jc L12
L14:
pop %ebx
pop %esi
pop %edi
leave
ret
nop
/
/ Divide 64-bit (Nhi,Nlo) by 32-bit divisor, which must be normalized
/ so its high bit is 1. This code is from NSPR.
/
/ mp_err s_mpv_div_2dx1d(mp_digit Nhi, mp_digit Nlo, mp_digit divisor,
/ mp_digit *qp, mp_digit *rp)
/ esp + 0: Caller's ebx
/ esp + 4: return address
/ esp + 8: Nhi argument
/ esp + 12: Nlo argument
/ esp + 16: divisor argument
/ esp + 20: qp argument
/ esp + 24: rp argument
/ registers:
/ eax:
/ ebx: carry
/ ecx: a_len
/ edx:
/ esi: a ptr
/ edi: c ptr
/
.globl s_mpv_div_2dx1d
.type s_mpv_div_2dx1d,@function
s_mpv_div_2dx1d:
push %ebx
mov 8(%esp),%edx
mov 12(%esp),%eax
mov 16(%esp),%ebx
div %ebx
mov 20(%esp),%ebx
mov %eax,0(%ebx)
mov 24(%esp),%ebx
mov %edx,0(%ebx)
xor %eax,%eax / return zero
pop %ebx
ret
nop
|
