Debian Codegraph @

crypto_kem/348864pcf/avx/vec128_mul_asm.q

raw
1 reg256 b0
2 reg256 b1
3 reg256 b2
4 reg256 b3
5 reg256 b4
6 reg256 b5
7 reg256 b6
8 reg256 b7
9 reg256 b8
10 reg256 b9
11 reg256 b10
12 reg256 b11
13 reg256 a0
14 reg256 a1
15 reg256 a2
16 reg256 a3
17 reg256 a4
18 reg256 a5
19 reg256 r0
20 reg256 r1
21 reg256 r2
22 reg256 r3
23 reg256 r4
24 reg256 r5
25 reg256 r6
26 reg256 r7
27 reg256 r8
28 reg256 r9
29 reg256 r10
30 reg256 r11
31 reg256 r12
32 reg256 r13
33 reg256 r14
34 reg256 r15
35 reg256 r16
36 reg256 r17
37 reg256 r18
38 reg256 r19
39 reg256 r20
40 reg256 r21
41 reg256 r22
42 reg256 r
43 reg128 h0
44 reg128 h1
45 reg128 h2
46 reg128 h3
47 reg128 h4
48 reg128 h5
49 reg128 h6
50 reg128 h7
51 reg128 h8
52 reg128 h9
53 reg128 h10
54 reg128 h11
55 reg128 h12
56 reg128 h13
57 reg128 h14
58 reg128 h15
59 reg128 h16
60 reg128 h17
61 reg128 h18
62 reg128 h19
63 reg128 h20
64 reg128 h21
65 reg128 h22
66 stack4864 buf
67 int64 ptr
68 int64 tmp
69 enter vec128_mul_asm
70 ptr = &buf
71 b11 = mem128[ input_2 + 176 ] x2
72 a5[0] = mem128[ input_1 + 80 ]
73 a5[1] = mem128[ input_1 + 176 ]
74 r16 = b11 & a5
75 mem256[ ptr + 512 ] = r16
76 a4[0] = mem128[ input_1 + 64 ]
77 a4[1] = mem128[ input_1 + 160 ]
78 r15 = b11 & a4
79 a3[0] = mem128[ input_1 + 48 ]
80 a3[1] = mem128[ input_1 + 144 ]
81 r14 = b11 & a3
82 a2[0] = mem128[ input_1 + 32 ]
83 a2[1] = mem128[ input_1 + 128 ]
84 r13 = b11 & a2
85 a1[0] = mem128[ input_1 + 16 ]
86 a1[1] = mem128[ input_1 + 112 ]
87 r12 = b11 & a1
88 a0[0] = mem128[ input_1 + 0 ]
89 a0[1] = mem128[ input_1 + 96 ]
90 r11 = b11 & a0
91 b10 = mem128[ input_2 + 160 ] x2
92 r = b10 & a5
93 r15 ^= r
94 mem256[ ptr + 480 ] = r15
95 r = b10 & a4
96 r14 ^= r
97 r = b10 & a3
98 r13 ^= r
99 r = b10 & a2
100 r12 ^= r
101 r = b10 & a1
102 r11 ^= r
103 r10 = b10 & a0
104 b9 = mem128[ input_2 + 144 ] x2
105 r = b9 & a5
106 r14 ^= r
107 mem256[ ptr + 448 ] = r14
108 r = b9 & a4
109 r13 ^= r
110 r = b9 & a3
111 r12 ^= r
112 r = b9 & a2
113 r11 ^= r
114 r = b9 & a1
115 r10 ^= r
116 r9 = b9 & a0
117 b8 = mem128[ input_2 + 128 ] x2
118 r = b8 & a5
119 r13 ^= r
120 mem256[ ptr + 416 ] = r13
121 r = b8 & a4
122 r12 ^= r
123 r = b8 & a3
124 r11 ^= r
125 r = b8 & a2
126 r10 ^= r
127 r = b8 & a1
128 r9 ^= r
129 r8 = b8 & a0
130 b7 = mem128[ input_2 + 112 ] x2
131 r = b7 & a5
132 r12 ^= r
133 mem256[ ptr + 384 ] = r12
134 r = b7 & a4
135 r11 ^= r
136 r = b7 & a3
137 r10 ^= r
138 r = b7 & a2
139 r9 ^= r
140 r = b7 & a1
141 r8 ^= r
142 r7 = b7 & a0
143 b6 = mem128[ input_2 + 96 ] x2
144 r = b6 & a5
145 r11 ^= r
146 mem256[ ptr + 352 ] = r11
147 r = b6 & a4
148 r10 ^= r
149 r = b6 & a3
150 r9 ^= r
151 r = b6 & a2
152 r8 ^= r
153 r = b6 & a1
154 r7 ^= r
155 r6 = b6 & a0
156 b5 = mem128[ input_2 + 80 ] x2
157 r = b5 & a5
158 r10 ^= r
159 mem256[ ptr + 320 ] = r10
160 r = b5 & a4
161 r9 ^= r
162 r = b5 & a3
163 r8 ^= r
164 r = b5 & a2
165 r7 ^= r
166 r = b5 & a1
167 r6 ^= r
168 r5 = b5 & a0
169 b4 = mem128[ input_2 + 64 ] x2
170 r = b4 & a5
171 r9 ^= r
172 mem256[ ptr + 288 ] = r9
173 r = b4 & a4
174 r8 ^= r
175 r = b4 & a3
176 r7 ^= r
177 r = b4 & a2
178 r6 ^= r
179 r = b4 & a1
180 r5 ^= r
181 r4 = b4 & a0
182 b3 = mem128[ input_2 + 48 ] x2
183 r = b3 & a5
184 r8 ^= r
185 mem256[ ptr + 256 ] = r8
186 r = b3 & a4
187 r7 ^= r
188 r = b3 & a3
189 r6 ^= r
190 r = b3 & a2
191 r5 ^= r
192 r = b3 & a1
193 r4 ^= r
194 r3 = b3 & a0
195 b2 = mem128[ input_2 + 32 ] x2
196 r = b2 & a5
197 r7 ^= r
198 mem256[ ptr + 224 ] = r7
199 r = b2 & a4
200 r6 ^= r
201 r = b2 & a3
202 r5 ^= r
203 r = b2 & a2
204 r4 ^= r
205 r = b2 & a1
206 r3 ^= r
207 r2 = b2 & a0
208 b1 = mem128[ input_2 + 16 ] x2
209 r = b1 & a5
210 r6 ^= r
211 mem256[ ptr + 192 ] = r6
212 r = b1 & a4
213 r5 ^= r
214 r = b1 & a3
215 r4 ^= r
216 r = b1 & a2
217 r3 ^= r
218 r = b1 & a1
219 r2 ^= r
220 r1 = b1 & a0
221 b0 = mem128[ input_2 + 0 ] x2
222 r = b0 & a5
223 r5 ^= r
224 mem256[ ptr + 160 ] = r5
225 r = b0 & a4
226 r4 ^= r
227 r = b0 & a3
228 r3 ^= r
229 r = b0 & a2
230 r2 ^= r
231 r = b0 & a1
232 r1 ^= r
233 r0 = b0 & a0
234 mem256[ ptr + 128 ] = r4
235 mem256[ ptr + 96 ] = r3
236 mem256[ ptr + 64 ] = r2
237 mem256[ ptr + 32 ] = r1
238 mem256[ ptr + 0 ] = r0
239 vzeroupper
240 h22 = mem128[ ptr + 528 ]
241 h13 = h22
242 h10 = h22
243 h21 = mem128[ ptr + 496 ]
244 h12 = h21
245 h9 = h21
246 h20 = mem128[ ptr + 464 ]
247 h11 = h20
248 h8 = h20
249 h19 = mem128[ ptr + 432 ]
250 h10 = h10 ^ h19
251 h7 = h19
252 h18 = mem128[ ptr + 400 ]
253 h9 = h9 ^ h18
254 h6 = h18
255 h17 = mem128[ ptr + 368 ]
256 h8 = h8 ^ h17
257 h5 = h17
258 h16 = mem128[ ptr + 336 ]
259 h16 = h16 ^ mem128[ ptr + 512 ]
260 h7 = h7 ^ h16
261 h4 = h16
262 h15 = mem128[ ptr + 304 ]
263 h15 = h15 ^ mem128[ ptr + 480 ]
264 h6 = h6 ^ h15
265 h3 = h15
266 h14 = mem128[ ptr + 272 ]
267 h14 = h14 ^ mem128[ ptr + 448 ]
268 h5 = h5 ^ h14
269 h2 = h14
270 h13 = h13 ^ mem128[ ptr + 240 ]
271 h13 = h13 ^ mem128[ ptr + 416 ]
272 h4 = h4 ^ h13
273 h1 = h13
274 h12 = h12 ^ mem128[ ptr + 208 ]
275 h12 = h12 ^ mem128[ ptr + 384 ]
276 h3 = h3 ^ h12
277 h0 = h12
278 h11 = h11 ^ mem128[ ptr + 352 ]
279 h11 = h11 ^ mem128[ ptr + 176 ]
280 mem128[ input_0 + 176 ] = h11
281 h10 = h10 ^ mem128[ ptr + 320 ]
282 h10 = h10 ^ mem128[ ptr + 144 ]
283 mem128[ input_0 + 160 ] = h10
284 h9 = h9 ^ mem128[ ptr + 288 ]
285 h9 = h9 ^ mem128[ ptr + 112 ]
286 mem128[ input_0 + 144 ] = h9
287 h8 = h8 ^ mem128[ ptr + 256 ]
288 h8 = h8 ^ mem128[ ptr + 80 ]
289 mem128[ input_0 + 128 ] = h8
290 h7 = h7 ^ mem128[ ptr + 224 ]
291 h7 = h7 ^ mem128[ ptr + 48 ]
292 mem128[ input_0 + 112 ] = h7
293 h6 = h6 ^ mem128[ ptr + 192 ]
294 h6 = h6 ^ mem128[ ptr + 16 ]
295 mem128[ input_0 + 96 ] = h6
296 h5 = h5 ^ mem128[ ptr + 160 ]
297 mem128[ input_0 + 80 ] = h5
298 h4 = h4 ^ mem128[ ptr + 128 ]
299 mem128[ input_0 + 64 ] = h4
300 h3 = h3 ^ mem128[ ptr + 96 ]
301 mem128[ input_0 + 48 ] = h3
302 h2 = h2 ^ mem128[ ptr + 64 ]
303 mem128[ input_0 + 32 ] = h2
304 h1 = h1 ^ mem128[ ptr + 32 ]
305 mem128[ input_0 + 16 ] = h1
306 h0 = h0 ^ mem128[ ptr + 0 ]
307 mem128[ input_0 + 0 ] = h0
308 return