-
Notifications
You must be signed in to change notification settings - Fork 0
/
fp2e_conjugate.s
252 lines (191 loc) · 6.21 KB
/
fp2e_conjugate.s
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
# File: dclxvi-20130329/fp2e_conjugate.s
# Author: Ruben Niederhagen, Peter Schwabe
# Public Domain
# qhasm: enter fp2e_conjugate_qhasm
.text
.p2align 5
.globl _fp2e_conjugate_qhasm
.globl fp2e_conjugate_qhasm
_fp2e_conjugate_qhasm:
fp2e_conjugate_qhasm:
push %rbp
mov %rsp,%r11
and $31,%r11
add $0,%r11
sub %r11,%rsp
# qhasm: int64 0rop
# qhasm: int64 0op
# qhasm: input 0rop
# qhasm: input 0op
# qhasm: int6464 0r0
# qhasm: int6464 0r1
# qhasm: int6464 0r2
# qhasm: int6464 0r3
# qhasm: int6464 0r4
# qhasm: int6464 0r5
# qhasm: int6464 0r6
# qhasm: int6464 0r7
# qhasm: int6464 0r8
# qhasm: int6464 0r9
# qhasm: int6464 0r10
# qhasm: int6464 0r11
# qhasm: int6464 0t0
# qhasm: int6464 0t1
# qhasm: int6464 0t2
# qhasm: int6464 0t3
# qhasm: 0r0 = *(int128 *)(0op + 0)
# asm 1: movdqa 0(<0op=int64#2),>0r0=int6464#1
# asm 2: movdqa 0(<0op=%rsi),>0r0=%xmm0
movdqa 0(%rsi),%xmm0
# qhasm: 0r1 = *(int128 *)(0op + 16)
# asm 1: movdqa 16(<0op=int64#2),>0r1=int6464#2
# asm 2: movdqa 16(<0op=%rsi),>0r1=%xmm1
movdqa 16(%rsi),%xmm1
# qhasm: 0r2 = *(int128 *)(0op + 32)
# asm 1: movdqa 32(<0op=int64#2),>0r2=int6464#3
# asm 2: movdqa 32(<0op=%rsi),>0r2=%xmm2
movdqa 32(%rsi),%xmm2
# qhasm: 0r3 = *(int128 *)(0op + 48)
# asm 1: movdqa 48(<0op=int64#2),>0r3=int6464#4
# asm 2: movdqa 48(<0op=%rsi),>0r3=%xmm3
movdqa 48(%rsi),%xmm3
# qhasm: 0r4 = *(int128 *)(0op + 64)
# asm 1: movdqa 64(<0op=int64#2),>0r4=int6464#5
# asm 2: movdqa 64(<0op=%rsi),>0r4=%xmm4
movdqa 64(%rsi),%xmm4
# qhasm: 0r5 = *(int128 *)(0op + 80)
# asm 1: movdqa 80(<0op=int64#2),>0r5=int6464#6
# asm 2: movdqa 80(<0op=%rsi),>0r5=%xmm5
movdqa 80(%rsi),%xmm5
# qhasm: 0r6 = *(int128 *)(0op + 96)
# asm 1: movdqa 96(<0op=int64#2),>0r6=int6464#7
# asm 2: movdqa 96(<0op=%rsi),>0r6=%xmm6
movdqa 96(%rsi),%xmm6
# qhasm: 0r7 = *(int128 *)(0op + 112)
# asm 1: movdqa 112(<0op=int64#2),>0r7=int6464#8
# asm 2: movdqa 112(<0op=%rsi),>0r7=%xmm7
movdqa 112(%rsi),%xmm7
# qhasm: 0r8 = *(int128 *)(0op + 128)
# asm 1: movdqa 128(<0op=int64#2),>0r8=int6464#9
# asm 2: movdqa 128(<0op=%rsi),>0r8=%xmm8
movdqa 128(%rsi),%xmm8
# qhasm: 0r9 = *(int128 *)(0op + 144)
# asm 1: movdqa 144(<0op=int64#2),>0r9=int6464#10
# asm 2: movdqa 144(<0op=%rsi),>0r9=%xmm9
movdqa 144(%rsi),%xmm9
# qhasm: 0r10 = *(int128 *)(0op + 160)
# asm 1: movdqa 160(<0op=int64#2),>0r10=int6464#11
# asm 2: movdqa 160(<0op=%rsi),>0r10=%xmm10
movdqa 160(%rsi),%xmm10
# qhasm: 0r11 = *(int128 *)(0op + 176)
# asm 1: movdqa 176(<0op=int64#2),>0r11=int6464#12
# asm 2: movdqa 176(<0op=%rsi),>0r11=%xmm11
movdqa 176(%rsi),%xmm11
# qhasm: int6464 1t0
# qhasm: 1t0 = ONE_MINUSONE
# asm 1: movdqa ONE_MINUSONE,<1t0=int6464#13
# asm 2: movdqa ONE_MINUSONE,<1t0=%xmm12
mov ONE_MINUSONE@GOTPCREL(%rip), %rbp
movdqa (%rbp),%xmm12
# qhasm: float6464 0r0 *= 1t0
# asm 1: mulpd <1t0=int6464#13,<0r0=int6464#1
# asm 2: mulpd <1t0=%xmm12,<0r0=%xmm0
mulpd %xmm12,%xmm0
# qhasm: float6464 0r1 *= 1t0
# asm 1: mulpd <1t0=int6464#13,<0r1=int6464#2
# asm 2: mulpd <1t0=%xmm12,<0r1=%xmm1
mulpd %xmm12,%xmm1
# qhasm: float6464 0r2 *= 1t0
# asm 1: mulpd <1t0=int6464#13,<0r2=int6464#3
# asm 2: mulpd <1t0=%xmm12,<0r2=%xmm2
mulpd %xmm12,%xmm2
# qhasm: float6464 0r3 *= 1t0
# asm 1: mulpd <1t0=int6464#13,<0r3=int6464#4
# asm 2: mulpd <1t0=%xmm12,<0r3=%xmm3
mulpd %xmm12,%xmm3
# qhasm: float6464 0r4 *= 1t0
# asm 1: mulpd <1t0=int6464#13,<0r4=int6464#5
# asm 2: mulpd <1t0=%xmm12,<0r4=%xmm4
mulpd %xmm12,%xmm4
# qhasm: float6464 0r5 *= 1t0
# asm 1: mulpd <1t0=int6464#13,<0r5=int6464#6
# asm 2: mulpd <1t0=%xmm12,<0r5=%xmm5
mulpd %xmm12,%xmm5
# qhasm: float6464 0r6 *= 1t0
# asm 1: mulpd <1t0=int6464#13,<0r6=int6464#7
# asm 2: mulpd <1t0=%xmm12,<0r6=%xmm6
mulpd %xmm12,%xmm6
# qhasm: float6464 0r7 *= 1t0
# asm 1: mulpd <1t0=int6464#13,<0r7=int6464#8
# asm 2: mulpd <1t0=%xmm12,<0r7=%xmm7
mulpd %xmm12,%xmm7
# qhasm: float6464 0r8 *= 1t0
# asm 1: mulpd <1t0=int6464#13,<0r8=int6464#9
# asm 2: mulpd <1t0=%xmm12,<0r8=%xmm8
mulpd %xmm12,%xmm8
# qhasm: float6464 0r9 *= 1t0
# asm 1: mulpd <1t0=int6464#13,<0r9=int6464#10
# asm 2: mulpd <1t0=%xmm12,<0r9=%xmm9
mulpd %xmm12,%xmm9
# qhasm: float6464 0r10 *= 1t0
# asm 1: mulpd <1t0=int6464#13,<0r10=int6464#11
# asm 2: mulpd <1t0=%xmm12,<0r10=%xmm10
mulpd %xmm12,%xmm10
# qhasm: float6464 0r11 *= 1t0
# asm 1: mulpd <1t0=int6464#13,<0r11=int6464#12
# asm 2: mulpd <1t0=%xmm12,<0r11=%xmm11
mulpd %xmm12,%xmm11
# qhasm: *(int128 *)(0rop + 0) = 0r0
# asm 1: movdqa <0r0=int6464#1,0(<0rop=int64#1)
# asm 2: movdqa <0r0=%xmm0,0(<0rop=%rdi)
movdqa %xmm0,0(%rdi)
# qhasm: *(int128 *)(0rop + 16) = 0r1
# asm 1: movdqa <0r1=int6464#2,16(<0rop=int64#1)
# asm 2: movdqa <0r1=%xmm1,16(<0rop=%rdi)
movdqa %xmm1,16(%rdi)
# qhasm: *(int128 *)(0rop + 32) = 0r2
# asm 1: movdqa <0r2=int6464#3,32(<0rop=int64#1)
# asm 2: movdqa <0r2=%xmm2,32(<0rop=%rdi)
movdqa %xmm2,32(%rdi)
# qhasm: *(int128 *)(0rop + 48) = 0r3
# asm 1: movdqa <0r3=int6464#4,48(<0rop=int64#1)
# asm 2: movdqa <0r3=%xmm3,48(<0rop=%rdi)
movdqa %xmm3,48(%rdi)
# qhasm: *(int128 *)(0rop + 64) = 0r4
# asm 1: movdqa <0r4=int6464#5,64(<0rop=int64#1)
# asm 2: movdqa <0r4=%xmm4,64(<0rop=%rdi)
movdqa %xmm4,64(%rdi)
# qhasm: *(int128 *)(0rop + 80) = 0r5
# asm 1: movdqa <0r5=int6464#6,80(<0rop=int64#1)
# asm 2: movdqa <0r5=%xmm5,80(<0rop=%rdi)
movdqa %xmm5,80(%rdi)
# qhasm: *(int128 *)(0rop + 96) = 0r6
# asm 1: movdqa <0r6=int6464#7,96(<0rop=int64#1)
# asm 2: movdqa <0r6=%xmm6,96(<0rop=%rdi)
movdqa %xmm6,96(%rdi)
# qhasm: *(int128 *)(0rop + 112) = 0r7
# asm 1: movdqa <0r7=int6464#8,112(<0rop=int64#1)
# asm 2: movdqa <0r7=%xmm7,112(<0rop=%rdi)
movdqa %xmm7,112(%rdi)
# qhasm: *(int128 *)(0rop + 128) = 0r8
# asm 1: movdqa <0r8=int6464#9,128(<0rop=int64#1)
# asm 2: movdqa <0r8=%xmm8,128(<0rop=%rdi)
movdqa %xmm8,128(%rdi)
# qhasm: *(int128 *)(0rop + 144) = 0r9
# asm 1: movdqa <0r9=int6464#10,144(<0rop=int64#1)
# asm 2: movdqa <0r9=%xmm9,144(<0rop=%rdi)
movdqa %xmm9,144(%rdi)
# qhasm: *(int128 *)(0rop + 160) = 0r10
# asm 1: movdqa <0r10=int6464#11,160(<0rop=int64#1)
# asm 2: movdqa <0r10=%xmm10,160(<0rop=%rdi)
movdqa %xmm10,160(%rdi)
# qhasm: *(int128 *)(0rop + 176) = 0r11
# asm 1: movdqa <0r11=int6464#12,176(<0rop=int64#1)
# asm 2: movdqa <0r11=%xmm11,176(<0rop=%rdi)
movdqa %xmm11,176(%rdi)
# qhasm: leave
add %r11,%rsp
mov %rdi,%rax
mov %rsi,%rdx
pop %rbp
ret