Debian Codegraph @

crypto_kem/348864pcf/avx/vec_mul_sp_asm.q

raw
1 reg256 s0
2 reg256 s1
3 reg256 s2
4 reg256 s3
5 reg256 s4
6 reg256 s5
7 reg256 b0
8 reg256 b1
9 reg256 b2
10 reg256 b3
11 reg256 b4
12 reg256 b5
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 int64 h0
44 int64 h1
45 int64 h2
46 int64 h3
47 int64 h4
48 int64 h5
49 int64 h6
50 int64 h7
51 int64 h8
52 int64 h9
53 int64 h10
54 int64 h11
55 int64 h12
56 int64 h13
57 int64 h14
58 int64 h15
59 int64 h16
60 int64 h17
61 int64 h18
62 int64 h19
63 int64 h20
64 int64 h21
65 int64 h22
66 stack4864 buf
67 int64 ptr
68 int64 tmp
69 stack64 r11_stack
70 stack64 r12_stack
71 stack64 r13_stack
72 stack64 r14_stack
73 stack64 r15_stack
74 stack64 rbx_stack
75 stack64 rbp_stack
76
77 enter vec_mul_sp_asm
78
79 r11_stack = caller_r11
80 r12_stack = caller_r12
81 r13_stack = caller_r13
82 r14_stack = caller_r14
83 r15_stack = caller_r15
84 rbx_stack = caller_rbx
85 ptr = &buf
86 s0 = mem256[ input_1 + 0 ]
87 s1 = mem256[ input_1 + 32 ]
88 s2 = mem256[ input_1 + 64 ]
89 a5[0,1,2,3] = s2[2,2,3,3]
90 r = mem256[ input_2 + 160 ]
91 b5[0,1,2,3] = r[1,3,1,3]
92 r10 = a5 & b5
93 mem256[ ptr + 320 ] = r10
94 r = mem256[ input_2 + 128 ]
95 b4[0,1,2,3] = r[1,3,1,3]
96 r9 = a5 & b4
97 r = mem256[ input_2 + 96 ]
98 b3[0,1,2,3] = r[1,3,1,3]
99 r8 = a5 & b3
100 r = mem256[ input_2 + 64 ]
101 b2[0,1,2,3] = r[1,3,1,3]
102 r7 = a5 & b2
103 r = mem256[ input_2 + 32 ]
104 b1[0,1,2,3] = r[1,3,1,3]
105 r6 = a5 & b1
106 r = mem256[ input_2 + 0 ]
107 b0[0,1,2,3] = r[1,3,1,3]
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