Debian Codegraph @

crypto_kem/348864pcf/avx/vec_mul_asm.q

raw
1 reg256 s0
2 reg256 s1
3 reg256 s2
4 reg256 s3
5 reg256 s4
6 reg256 s5
7 reg256 t0
8 reg256 t1
9 reg256 t2
10 reg256 b0
11 reg256 b1
12 reg256 b2
13 reg256 b3
14 reg256 b4
15 reg256 b5
16 reg256 a0
17 reg256 a1
18 reg256 a2
19 reg256 a3
20 reg256 a4
21 reg256 a5
22 reg256 r0
23 reg256 r1
24 reg256 r2
25 reg256 r3
26 reg256 r4
27 reg256 r5
28 reg256 r6
29 reg256 r7
30 reg256 r8
31 reg256 r9
32 reg256 r10
33 reg256 r11
34 reg256 r12
35 reg256 r13
36 reg256 r14
37 reg256 r15
38 reg256 r16
39 reg256 r17
40 reg256 r18
41 reg256 r19
42 reg256 r20
43 reg256 r21
44 reg256 r22
45 reg256 r
46 int64 h0
47 int64 h1
48 int64 h2
49 int64 h3
50 int64 h4
51 int64 h5
52 int64 h6
53 int64 h7
54 int64 h8
55 int64 h9
56 int64 h10
57 int64 h11
58 int64 h12
59 int64 h13
60 int64 h14
61 int64 h15
62 int64 h16
63 int64 h17
64 int64 h18
65 int64 h19
66 int64 h20
67 int64 h21
68 int64 h22
69 stack4864 buf
70 int64 ptr
71 int64 tmp
72 stack64 r11_stack
73 stack64 r12_stack
74 stack64 r13_stack
75 stack64 r14_stack
76 stack64 r15_stack
77 stack64 rbx_stack
78 stack64 rbp_stack
79
80 enter vec_mul_asm
81
82 r11_stack = caller_r11
83 r12_stack = caller_r12
84 r13_stack = caller_r13
85 r14_stack = caller_r14
86 r15_stack = caller_r15
87 rbx_stack = caller_rbx
88 ptr = &buf
89 s0 = mem256[ input_1 + 0 ]
90 s1 = mem256[ input_1 + 32 ]
91 s2 = mem256[ input_1 + 64 ]
92 t0 = mem256[ input_2 + 0 ]
93 t1 = mem256[ input_2 + 32 ]
94 t2 = mem256[ input_2 + 64 ]
95 a5[0,1,2,3] = s2[2,2,3,3]
96 b5[0,1,2,3] = t2[2,3,2,3]
97 r10 = a5 & b5
98 mem256[ ptr + 320 ] = r10
99 b4[0,1,2,3] = t2[0,1,0,1]
100 r9 = a5 & b4
101 b3[0,1,2,3] = t1[2,3,2,3]
102 r8 = a5 & b3
103 b2[0,1,2,3] = t1[0,1,0,1]
104 r7 = a5 & b2
105 b1[0,1,2,3] = t0[2,3,2,3]
106 r6 = a5 & b1
107 b0[0,1,2,3] = t0[0,1,0,1]
108 r5 = a5 & b0
109 a4[0,1,2,3] = s2[0,0,1,1]
110 r = a4 & b5
111 r9 ^= r
112 mem256[ ptr + 288 ] = r9
113 r = a4 & b4
114 r8 ^= r
115 r = a4 & b3
116 r7 ^= r
117 r = a4 & b2
118 r6 ^= r
119 r = a4 & b1
120 r5 ^= r
121 r4 = a4 & b0
122 a3[0,1,2,3] = s1[2,2,3,3]
123 r = a3 & b5
124 r8 ^= r
125 mem256[ ptr + 256 ] = r8
126 r = a3 & b4
127 r7 ^= r
128 r = a3 & b3
129 r6 ^= r
130 r = a3 & b2
131 r5 ^= r
132 r = a3 & b1
133 r4 ^= r
134 r3 = a3 & b0
135 a2[0,1,2,3] = s1[0,0,1,1]
136 r = a2 & b5
137 r7 ^= r
138 mem256[ ptr + 224 ] = r7
139 r = a2 & b4
140 r6 ^= r
141 r = a2 & b3
142 r5 ^= r
143 r = a2 & b2
144 r4 ^= r
145 r = a2 & b1
146 r3 ^= r
147 r2 = a2 & b0
148 a1[0,1,2,3] = s0[2,2,3,3]
149 r = a1 & b5
150 r6 ^= r
151 mem256[ ptr + 192 ] = r6
152 r = a1 & b4
153 r5 ^= r
154 r = a1 & b3
155 r4 ^= r
156 r = a1 & b2
157 r3 ^= r
158 r = a1 & b1
159 r2 ^= r
160 r1 = a1 & b0
161 a0[0,1,2,3] = s0[0,0,1,1]
162 r = a0 & b5
163 r5 ^= r
164 mem256[ ptr + 160 ] = r5
165 r = a0 & b4
166 r4 ^= r
167 r = a0 & b3
168 r3 ^= r
169 r = a0 & b2
170 r2 ^= r
171 r = a0 & b1
172 r1 ^= r
173 r0 = a0 & b0
174 mem256[ ptr + 128 ] = r4
175 mem256[ ptr + 96 ] = r3
176 mem256[ ptr + 64 ] = r2
177 mem256[ ptr + 32 ] = r1
178 mem256[ ptr + 0 ] = r0
179 h22 = mem64[ ptr + 344 ]
180 h13 = h22
181 h10 = h22
182 h21 = mem64[ ptr + 336 ]
183 h21 ^= *(uint64 *) ( ptr + 328 )
184 h12 = h21
185 h9 = h21
186 h20 = mem64[ ptr + 312 ]
187 h20 ^= *(uint64 *) ( ptr + 320 )
188 h11 = h20
189 h8 = h20
190 h19 = mem64[ ptr + 304 ]
191 h19 ^= *(uint64 *) ( ptr + 296 )
192 h10 ^= h19
193 h7 = h19
194 h18 = mem64[ ptr + 280 ]
195 h18 ^= *(uint64 *) ( ptr + 288 )
196 h9 ^= h18
197 h6 = h18
198 h17 = mem64[ ptr + 272 ]
199 h17 ^= *(uint64 *) ( ptr + 264 )
200 h8 ^= h17
201 h5 = h17
202 h16 = mem64[ ptr + 248 ]
203 h16 ^= *(uint64 *) ( ptr + 256 )
204 h7 ^= h16
205 h4 = h16
206 h15 = mem64[ ptr + 240 ]
207 h15 ^= *(uint64 *) ( ptr + 232 )
208 h6 ^= h15
209 h3 = h15
210 h14 = mem64[ ptr + 216 ]
211 h14 ^= *(uint64 *) ( ptr + 224 )
212 h5 ^= h14
213 h2 = h14
214 h13 ^= *(uint64 *) ( ptr + 208 )
215 h13 ^= *(uint64 *) ( ptr + 200 )
216 h4 ^= h13
217 h1 = h13
218 h12 ^= *(uint64 *) ( ptr + 184 )
219 h12 ^= *(uint64 *) ( ptr + 192 )
220 h3 ^= h12
221 h0 = h12
222 h11 ^= *(uint64 *) ( ptr + 176 )
223 h11 ^= *(uint64 *) ( ptr + 168 )
224 mem64[ input_0 + 88 ] = h11
225 h10 ^= *(uint64 *) ( ptr + 152 )
226 h10 ^= *(uint64 *) ( ptr + 160 )
227 mem64[ input_0 + 80 ] = h10
228 h9 ^= *(uint64 *) ( ptr + 144 )
229 h9 ^= *(uint64 *) ( ptr + 136 )
230 mem64[ input_0 + 72 ] = h9
231 h8 ^= *(uint64 *) ( ptr + 120 )
232 h8 ^= *(uint64 *) ( ptr + 128 )
233 mem64[ input_0 + 64 ] = h8
234 h7 ^= *(uint64 *) ( ptr + 112 )
235 h7 ^= *(uint64 *) ( ptr + 104 )
236 mem64[ input_0 + 56 ] = h7
237 h6 ^= *(uint64 *) ( ptr + 88 )
238 h6 ^= *(uint64 *) ( ptr + 96 )
239 mem64[ input_0 + 48 ] = h6
240 h5 ^= *(uint64 *) ( ptr + 80 )
241 h5 ^= *(uint64 *) ( ptr + 72 )
242 mem64[ input_0 + 40 ] = h5
243 h4 ^= *(uint64 *) ( ptr + 56 )
244 h4 ^= *(uint64 *) ( ptr + 64 )
245 mem64[ input_0 + 32 ] = h4
246 h3 ^= *(uint64 *) ( ptr + 48 )
247 h3 ^= *(uint64 *) ( ptr + 40 )
248 mem64[ input_0 + 24 ] = h3
249 h2 ^= *(uint64 *) ( ptr + 24 )
250 h2 ^= *(uint64 *) ( ptr + 32 )
251 mem64[ input_0 + 16 ] = h2
252 h1 ^= *(uint64 *) ( ptr + 16 )
253 h1 ^= *(uint64 *) ( ptr + 8 )
254 mem64[ input_0 + 8 ] = h1
255 h0 ^= *(uint64 *) ( ptr + 0 )
256 mem64[ input_0 + 0 ] = h0
257 caller_r11 = r11_stack
258 caller_r12 = r12_stack
259 caller_r13 = r13_stack
260 caller_r14 = r14_stack
261 caller_r15 = r15_stack
262 caller_rbx = rbx_stack
263 return