File: mp32opt.i386.asm

package info (click to toggle)
beecrypt 2.2.0-pre1-5
  • links: PTS
  • area: main
  • in suites: sarge
  • size: 1,820 kB
  • ctags: 1,325
  • sloc: ansic: 12,215; sh: 9,073; asm: 2,715; makefile: 80
file content (299 lines) | stat: -rw-r--r-- 3,882 bytes parent folder | download | duplicates (3)
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
#
# mp32opt.i386.asm
#
# Assembler optimized multiprecision integer routines for Intel 386
#
# Compile target is MetroWerks CodeWarrior Pro 5 for Windows
#
# Copyright (c) 1998, 1999, 2000, 2001 Virtual Unlimited B.V.
#
# Author: Bob Deblier <bob@virtualunlimited.com>
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
#

	.text

	.align 8
	.globl _mp32zero
_mp32zero:
	push edi

	mov ecx,[esp+8]
	mov edi,[esp+12]

	xor eax,eax
	rep stosd

	pop edi
	ret


	.align 8
	.globl _mp32fill
_mp32fill:
	push edi

	mov ecx,[esp+8]
	mov edi,[esp+12]
	mov eax,[esp+16]

	rep stosd

	pop edi
	ret


	.align 8
	.globl _mp32odd
_mp32odd:
	mov ecx,[esp+4]
	mov eax,[esp+8]
	mov eax,[eax+ecx*4-4]
	and eax,1
	ret


	.align 8
	.globl _mp32even
_mp32even:
	mov ecx,[esp+4]
	mov eax,[esp+8]
	mov eax,[eax+ecx*4-4]
	not eax
	and eax,1
	ret


	.align 8
	.globl _mp32addw
_mp32addw:
	push edi

	mov ecx,[esp+8]
	mov edi,[esp+12]
	mov eax,[esp+16]

	lea edi,[edi+ecx*4-4]
	add [edi],eax
	dec ecx
	jz @mp32addw_end
	sub edi,4
	xor edx,edx

	.align 4
@mp32addw_loop:
	adc [edi],edx
	sub edi,4
	dec ecx
	jnz @mp32addw_loop
@mp32addw_end:
	sbb eax,eax
	neg eax

	pop edi
	ret


	.align 8
	.globl _mp32subw
_mp32subw:
	push edi

	mov ecx,[esp+8]
	mov edi,[esp+12]
	mov eax,[esp+16]

	lea edi,[edi+ecx*4-4]
	sub [edi],eax
	dec ecx
	jz @mp32subw_end
	sub edi,4
	xor edx,edx

	.align 4
@mp32subw_loop:
	sbb [edi],edx
	sub edi,4
	dec ecx
	jnz @mp32subw_loop
@mp32subw_end:
	sbb eax,eax
	neg eax

	pop edi
	ret


	.align 8
	.globl _mp32add
_mp32add:
	push edi
	push esi
	
	mov ecx,[esp+12]
	mov edi,[esp+16]
	mov esi,[esp+20]
	
	xor edx,edx
	dec ecx
		
@mp32add_loop:
	mov eax,[esi+ecx*4]
	adc [edi+ecx*4],eax
	dec ecx
	jns @mp32add_loop
	
	sbb eax,eax
	neg eax

	pop esi
	pop edi
	ret


	.align 8
	.globl _mp32sub
_mp32sub:
	push edi
	push esi
	
	mov ecx,[esp+12]
	mov edi,[esp+16]
	mov esi,[esp+20]
	
	xor edx,edx
	dec ecx
		
@mp32sub_loop:
	mov eax,[esi+ecx*4]
	sbb [edi+ecx*4],eax
	dec ecx
	jns @mp32sub_loop
	
	sbb eax,eax
	neg eax

	pop esi
	pop edi
	ret


	.align 8
	.globl _mp32setmul
_mp32setmul:
	push edi
	push esi
	push ebx
	push ebp

	mov ecx,[esp+20]
	mov edi,[esp+24]
	mov esi,[esp+28]
	mov ebp,[esp+32]

	xor edx,edx
	dec ecx
	
	.align 4
@mp32setmul_loop:
	mov ebx,edx
	mov eax,[esi+ecx*4]
	mul ebp
	add eax,ebx
	adc edx,0
	mov [edi+ecx*4],eax
	dec ecx
	jns @mp32setmul_loop

	mov eax,edx

	pop ebp
	pop ebx
	pop esi
	pop edi
	ret


	.align 8
	.globl _mp32addmul
_mp32addmul:
	push edi
	push esi
	push ebx
	push ebp

	mov ecx,[esp+20]
	mov edi,[esp+24]
	mov esi,[esp+28]
	mov ebp,[esp+32]

	xor edx,edx
	dec ecx
	
	.align 4
@mp32addmul_loop:
	mov ebx,edx
	mov eax,[esi+ecx*4]
	mul ebp
	add eax,ebx
	adc edx,0
	add [edi+ecx*4],eax
	adc edx,0
	dec ecx
	jns @mp32addmul_loop

	mov eax,edx

	pop ebp
	pop ebx
	pop esi
	pop edi
	ret


	.align 8
	.globl _mp32addsqrtrc
_mp32addsqrtrc:
	push edi
	push esi
	push ebx

	mov ecx,[esp+16]
	mov edi,[esp+20]
	mov esi,[esp+24]

	xor ebx,ebx
	dec ecx

	.align 4
@mp32addsqrtrc_loop:
	mov eax,[esi+ecx*4]
	mul eax
	add eax,ebx
	adc edx,0
	add [edi+ecx*8+4],eax
	adc [edi+ecx*8+0],edx
	sbb ebx,ebx
	neg ebx
	dec ecx
	jns @mp32addsqrtrc_loop

	mov eax,ebx

	pop ebx
	pop esi
	pop edi
	ret