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
314
315
316
317
318
319
320
321
322
323
324
|
.text
.align 6, 0x90
.globl ___gmpn_copyi
___gmpn_copyi:
cmp $7, %rdx
jbe Lbc
test $8, %dil
jz Lrp_aligned
movsq
dec %rdx
Lrp_aligned:
test $8, %sil
jnz Luent
jmp Lam
.align 4, 0x90
Latop:movdqa 0(%rsi), %xmm0
movdqa 16(%rsi), %xmm1
movdqa 32(%rsi), %xmm2
movdqa 48(%rsi), %xmm3
lea 64(%rsi), %rsi
movdqa %xmm0, (%rdi)
movdqa %xmm1, 16(%rdi)
movdqa %xmm2, 32(%rdi)
movdqa %xmm3, 48(%rdi)
lea 64(%rdi), %rdi
Lam: sub $8, %rdx
jnc Latop
test $4, %dl
jz 1f
movdqa (%rsi), %xmm0
movdqa 16(%rsi), %xmm1
lea 32(%rsi), %rsi
movdqa %xmm0, (%rdi)
movdqa %xmm1, 16(%rdi)
lea 32(%rdi), %rdi
1: test $2, %dl
jz 1f
movdqa (%rsi), %xmm0
lea 16(%rsi), %rsi
movdqa %xmm0, (%rdi)
lea 16(%rdi), %rdi
1: test $1, %dl
jz 1f
mov (%rsi), %r8
mov %r8, (%rdi)
1:
ret
Luent:
cmp $16, %rdx
jc Lued0
movaps 120(%rsi), %xmm7
movaps 104(%rsi), %xmm6
movaps 88(%rsi), %xmm5
movaps 72(%rsi), %xmm4
movaps 56(%rsi), %xmm3
movaps 40(%rsi), %xmm2
lea 128(%rsi), %rsi
sub $32, %rdx
jc Lued1
.align 4, 0x90
Lutop:movaps -104(%rsi), %xmm1
sub $16, %rdx
movaps -120(%rsi), %xmm0
.byte 0x66,0x0f,0x3a,0x0f,254,8
movaps -136(%rsi), %xmm8
movdqa %xmm7, 112(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,245,8
movaps 120(%rsi), %xmm7
movdqa %xmm6, 96(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,236,8
movaps 104(%rsi), %xmm6
movdqa %xmm5, 80(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,227,8
movaps 88(%rsi), %xmm5
movdqa %xmm4, 64(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,218,8
movaps 72(%rsi), %xmm4
movdqa %xmm3, 48(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,209,8
movaps 56(%rsi), %xmm3
movdqa %xmm2, 32(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,200,8
movaps 40(%rsi), %xmm2
movdqa %xmm1, 16(%rdi)
.byte 0x66,65,0x0f,0x3a,0x0f,192,8
lea 128(%rsi), %rsi
movdqa %xmm0, (%rdi)
lea 128(%rdi), %rdi
jnc Lutop
Lued1:movaps -104(%rsi), %xmm1
movaps -120(%rsi), %xmm0
movaps -136(%rsi), %xmm8
.byte 0x66,0x0f,0x3a,0x0f,254,8
movdqa %xmm7, 112(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,245,8
movdqa %xmm6, 96(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,236,8
movdqa %xmm5, 80(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,227,8
movdqa %xmm4, 64(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,218,8
movdqa %xmm3, 48(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,209,8
movdqa %xmm2, 32(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,200,8
movdqa %xmm1, 16(%rdi)
.byte 0x66,65,0x0f,0x3a,0x0f,192,8
movdqa %xmm0, (%rdi)
lea 128(%rdi), %rdi
Lued0:test $8, %dl
jz 1f
movaps 56(%rsi), %xmm3
movaps 40(%rsi), %xmm2
movaps 24(%rsi), %xmm1
movaps 8(%rsi), %xmm0
movaps -8(%rsi), %xmm4
.byte 0x66,0x0f,0x3a,0x0f,218,8
movdqa %xmm3, 48(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,209,8
movdqa %xmm2, 32(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,200,8
movdqa %xmm1, 16(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,196,8
lea 64(%rsi), %rsi
movdqa %xmm0, (%rdi)
lea 64(%rdi), %rdi
1: test $4, %dl
jz 1f
movaps 24(%rsi), %xmm1
movaps 8(%rsi), %xmm0
.byte 0x66,0x0f,0x3a,0x0f,200,8
movaps -8(%rsi), %xmm3
movdqa %xmm1, 16(%rdi)
.byte 0x66,0x0f,0x3a,0x0f,195,8
lea 32(%rsi), %rsi
movdqa %xmm0, (%rdi)
lea 32(%rdi), %rdi
1: test $2, %dl
jz 1f
movdqa 8(%rsi), %xmm0
movdqa -8(%rsi), %xmm3
.byte 0x66,0x0f,0x3a,0x0f,195,8
lea 16(%rsi), %rsi
movdqa %xmm0, (%rdi)
lea 16(%rdi), %rdi
1: test $1, %dl
jz 1f
mov (%rsi), %r8
mov %r8, (%rdi)
1:
ret
Lbc: lea -8(%rdi), %rdi
sub $4, %edx
jc Lend
.align 4, 0x90
Ltop: mov (%rsi), %r8
mov 8(%rsi), %r9
lea 32(%rdi), %rdi
mov 16(%rsi), %r10
mov 24(%rsi), %r11
lea 32(%rsi), %rsi
mov %r8, -24(%rdi)
mov %r9, -16(%rdi)
mov %r10, -8(%rdi)
mov %r11, (%rdi)
Lend: test $1, %dl
jz 1f
mov (%rsi), %r8
mov %r8, 8(%rdi)
lea 8(%rdi), %rdi
lea 8(%rsi), %rsi
1: test $2, %dl
jz 1f
mov (%rsi), %r8
mov 8(%rsi), %r9
mov %r8, 8(%rdi)
mov %r9, 16(%rdi)
1:
ret
|
