Debian Codegraph @

crypto_kem/8192128f/avx/transpose_64x256_sp_asm.q

raw
1 reg256 x0
2 reg256 x1
3 reg256 x2
4 reg256 x3
5 reg256 x4
6 reg256 x5
7 reg256 x6
8 reg256 x7
9 reg256 t0
10 reg256 t1
11 reg256 v00
12 reg256 v01
13 reg256 v10
14 reg256 v11
15 reg256 mask0
16 reg256 mask1
17 reg256 mask2
18 reg256 mask3
19 reg256 mask4
20 reg256 mask5
21
22 enter transpose_64x256_sp_asm
23
24 mask0 aligned= mem256[ MASK5_0 ]
25 mask1 aligned= mem256[ MASK5_1 ]
26 mask2 aligned= mem256[ MASK4_0 ]
27 mask3 aligned= mem256[ MASK4_1 ]
28 mask4 aligned= mem256[ MASK3_0 ]
29 mask5 aligned= mem256[ MASK3_1 ]
30 x0 = mem256[ input_0 + 0 ]
31 x1 = mem256[ input_0 + 256 ]
32 x2 = mem256[ input_0 + 512 ]
33 x3 = mem256[ input_0 + 768 ]
34 x4 = mem256[ input_0 + 1024 ]
35 x5 = mem256[ input_0 + 1280 ]
36 x6 = mem256[ input_0 + 1536 ]
37 x7 = mem256[ input_0 + 1792 ]
38 v00 = x0 & mask0
39 4x v10 = x4 << 32
40 4x v01 = x0 unsigned>> 32
41 v11 = x4 & mask1
42 x0 = v00 | v10
43 x4 = v01 | v11
44 v00 = x1 & mask0
45 4x v10 = x5 << 32
46 4x v01 = x1 unsigned>> 32
47 v11 = x5 & mask1
48 x1 = v00 | v10
49 x5 = v01 | v11
50 v00 = x2 & mask0
51 4x v10 = x6 << 32
52 4x v01 = x2 unsigned>> 32
53 v11 = x6 & mask1
54 x2 = v00 | v10
55 x6 = v01 | v11
56 v00 = x3 & mask0
57 4x v10 = x7 << 32
58 4x v01 = x3 unsigned>> 32
59 v11 = x7 & mask1
60 x3 = v00 | v10
61 x7 = v01 | v11
62 v00 = x0 & mask2
63 8x v10 = x2 << 16
64 8x v01 = x0 unsigned>> 16
65 v11 = x2 & mask3
66 x0 = v00 | v10
67 x2 = v01 | v11
68 v00 = x1 & mask2
69 8x v10 = x3 << 16
70 8x v01 = x1 unsigned>> 16
71 v11 = x3 & mask3
72 x1 = v00 | v10
73 x3 = v01 | v11
74 v00 = x4 & mask2
75 8x v10 = x6 << 16
76 8x v01 = x4 unsigned>> 16
77 v11 = x6 & mask3
78 x4 = v00 | v10
79 x6 = v01 | v11
80 v00 = x5 & mask2
81 8x v10 = x7 << 16
82 8x v01 = x5 unsigned>> 16
83 v11 = x7 & mask3
84 x5 = v00 | v10
85 x7 = v01 | v11
86 v00 = x0 & mask4
87 16x v10 = x1 << 8
88 16x v01 = x0 unsigned>> 8
89 v11 = x1 & mask5
90 x0 = v00 | v10
91 x1 = v01 | v11
92 v00 = x2 & mask4
93 16x v10 = x3 << 8
94 16x v01 = x2 unsigned>> 8
95 v11 = x3 & mask5
96 x2 = v00 | v10
97 x3 = v01 | v11
98 v00 = x4 & mask4
99 16x v10 = x5 << 8
100 16x v01 = x4 unsigned>> 8
101 v11 = x5 & mask5
102 x4 = v00 | v10
103 x5 = v01 | v11
104 v00 = x6 & mask4
105 16x v10 = x7 << 8
106 16x v01 = x6 unsigned>> 8
107 v11 = x7 & mask5
108 x6 = v00 | v10
109 x7 = v01 | v11
110 mem256[ input_0 + 0 ] = x0
111 mem256[ input_0 + 256 ] = x1
112 mem256[ input_0 + 512 ] = x2
113 mem256[ input_0 + 768 ] = x3
114 mem256[ input_0 + 1024 ] = x4
115 mem256[ input_0 + 1280 ] = x5
116 mem256[ input_0 + 1536 ] = x6
117 mem256[ input_0 + 1792 ] = x7
118
119 x0 = mem256[ input_0 + 32 ]
120 x1 = mem256[ input_0 + 288 ]
121 x2 = mem256[ input_0 + 544 ]
122 x3 = mem256[ input_0 + 800 ]
123 x4 = mem256[ input_0 + 1056 ]
124 x5 = mem256[ input_0 + 1312 ]
125 x6 = mem256[ input_0 + 1568 ]
126 x7 = mem256[ input_0 + 1824 ]
127 v00 = x0 & mask0
128 4x v10 = x4 << 32
129 4x v01 = x0 unsigned>> 32
130 v11 = x4 & mask1
131 x0 = v00 | v10
132 x4 = v01 | v11
133 v00 = x1 & mask0
134 4x v10 = x5 << 32
135 4x v01 = x1 unsigned>> 32
136 v11 = x5 & mask1
137 x1 = v00 | v10
138 x5 = v01 | v11
139 v00 = x2 & mask0
140 4x v10 = x6 << 32
141 4x v01 = x2 unsigned>> 32
142 v11 = x6 & mask1
143 x2 = v00 | v10
144 x6 = v01 | v11
145 v00 = x3 & mask0
146 4x v10 = x7 << 32
147 4x v01 = x3 unsigned>> 32
148 v11 = x7 & mask1
149 x3 = v00 | v10
150 x7 = v01 | v11
151 v00 = x0 & mask2
152 8x v10 = x2 << 16
153 8x v01 = x0 unsigned>> 16
154 v11 = x2 & mask3
155 x0 = v00 | v10
156 x2 = v01 | v11
157 v00 = x1 & mask2
158 8x v10 = x3 << 16
159 8x v01 = x1 unsigned>> 16
160 v11 = x3 & mask3
161 x1 = v00 | v10
162 x3 = v01 | v11
163 v00 = x4 & mask2
164 8x v10 = x6 << 16
165 8x v01 = x4 unsigned>> 16
166 v11 = x6 & mask3
167 x4 = v00 | v10
168 x6 = v01 | v11
169 v00 = x5 & mask2
170 8x v10 = x7 << 16
171 8x v01 = x5 unsigned>> 16
172 v11 = x7 & mask3
173 x5 = v00 | v10
174 x7 = v01 | v11
175 v00 = x0 & mask4
176 16x v10 = x1 << 8
177 16x v01 = x0 unsigned>> 8
178 v11 = x1 & mask5
179 x0 = v00 | v10
180 x1 = v01 | v11
181 v00 = x2 & mask4
182 16x v10 = x3 << 8
183 16x v01 = x2 unsigned>> 8
184 v11 = x3 & mask5
185 x2 = v00 | v10
186 x3 = v01 | v11
187 v00 = x4 & mask4
188 16x v10 = x5 << 8
189 16x v01 = x4 unsigned>> 8
190 v11 = x5 & mask5
191 x4 = v00 | v10
192 x5 = v01 | v11
193 v00 = x6 & mask4
194 16x v10 = x7 << 8
195 16x v01 = x6 unsigned>> 8
196 v11 = x7 & mask5
197 x6 = v00 | v10
198 x7 = v01 | v11
199 mem256[ input_0 + 32 ] = x0
200 mem256[ input_0 + 288 ] = x1
201 mem256[ input_0 + 544 ] = x2
202 mem256[ input_0 + 800 ] = x3
203 mem256[ input_0 + 1056 ] = x4
204 mem256[ input_0 + 1312 ] = x5
205 mem256[ input_0 + 1568 ] = x6
206 mem256[ input_0 + 1824 ] = x7
207
208 x0 = mem256[ input_0 + 64 ]
209 x1 = mem256[ input_0 + 320 ]
210 x2 = mem256[ input_0 + 576 ]
211 x3 = mem256[ input_0 + 832 ]
212 x4 = mem256[ input_0 + 1088 ]
213 x5 = mem256[ input_0 + 1344 ]
214 x6 = mem256[ input_0 + 1600 ]
215 x7 = mem256[ input_0 + 1856 ]
216 v00 = x0 & mask0
217 4x v10 = x4 << 32
218 4x v01 = x0 unsigned>> 32
219 v11 = x4 & mask1
220 x0 = v00 | v10
221 x4 = v01 | v11
222 v00 = x1 & mask0
223 4x v10 = x5 << 32
224 4x v01 = x1 unsigned>> 32
225 v11 = x5 & mask1
226 x1 = v00 | v10
227 x5 = v01 | v11
228 v00 = x2 & mask0
229 4x v10 = x6 << 32
230 4x v01 = x2 unsigned>> 32
231 v11 = x6 & mask1
232 x2 = v00 | v10
233 x6 = v01 | v11
234 v00 = x3 & mask0
235 4x v10 = x7 << 32
236 4x v01 = x3 unsigned>> 32
237 v11 = x7 & mask1
238 x3 = v00 | v10
239 x7 = v01 | v11
240 v00 = x0 & mask2
241 8x v10 = x2 << 16
242 8x v01 = x0 unsigned>> 16
243 v11 = x2 & mask3
244 x0 = v00 | v10
245 x2 = v01 | v11
246 v00 = x1 & mask2
247 8x v10 = x3 << 16
248 8x v01 = x1 unsigned>> 16
249 v11 = x3 & mask3
250 x1 = v00 | v10
251 x3 = v01 | v11
252 v00 = x4 & mask2
253 8x v10 = x6 << 16
254 8x v01 = x4 unsigned>> 16
255 v11 = x6 & mask3
256 x4 = v00 | v10
257 x6 = v01 | v11
258 v00 = x5 & mask2
259 8x v10 = x7 << 16
260 8x v01 = x5 unsigned>> 16
261 v11 = x7 & mask3
262 x5 = v00 | v10
263 x7 = v01 | v11
264 v00 = x0 & mask4
265 16x v10 = x1 << 8
266 16x v01 = x0 unsigned>> 8
267 v11 = x1 & mask5
268 x0 = v00 | v10
269 x1 = v01 | v11
270 v00 = x2 & mask4
271 16x v10 = x3 << 8
272 16x v01 = x2 unsigned>> 8
273 v11 = x3 & mask5
274 x2 = v00 | v10
275 x3 = v01 | v11
276 v00 = x4 & mask4
277 16x v10 = x5 << 8
278 16x v01 = x4 unsigned>> 8
279 v11 = x5 & mask5
280 x4 = v00 | v10
281 x5 = v01 | v11
282 v00 = x6 & mask4
283 16x v10 = x7 << 8
284 16x v01 = x6 unsigned>> 8
285 v11 = x7 & mask5
286 x6 = v00 | v10
287 x7 = v01 | v11
288 mem256[ input_0 + 64 ] = x0
289 mem256[ input_0 + 320 ] = x1
290 mem256[ input_0 + 576 ] = x2
291 mem256[ input_0 + 832 ] = x3
292 mem256[ input_0 + 1088 ] = x4
293 mem256[ input_0 + 1344 ] = x5
294 mem256[ input_0 + 1600 ] = x6
295 mem256[ input_0 + 1856 ] = x7
296
297 x0 = mem256[ input_0 + 96 ]
298 x1 = mem256[ input_0 + 352 ]
299 x2 = mem256[ input_0 + 608 ]
300 x3 = mem256[ input_0 + 864 ]
301 x4 = mem256[ input_0 + 1120 ]
302 x5 = mem256[ input_0 + 1376 ]
303 x6 = mem256[ input_0 + 1632 ]
304 x7 = mem256[ input_0 + 1888 ]
305 v00 = x0 & mask0
306 4x v10 = x4 << 32
307 4x v01 = x0 unsigned>> 32
308 v11 = x4 & mask1
309 x0 = v00 | v10
310 x4 = v01 | v11
311 v00 = x1 & mask0
312 4x v10 = x5 << 32
313 4x v01 = x1 unsigned>> 32
314 v11 = x5 & mask1
315 x1 = v00 | v10
316 x5 = v01 | v11
317 v00 = x2 & mask0
318 4x v10 = x6 << 32
319 4x v01 = x2 unsigned>> 32
320 v11 = x6 & mask1
321 x2 = v00 | v10
322 x6 = v01 | v11
323 v00 = x3 & mask0
324 4x v10 = x7 << 32
325 4x v01 = x3 unsigned>> 32
326 v11 = x7 & mask1
327 x3 = v00 | v10
328 x7 = v01 | v11
329 v00 = x0 & mask2
330 8x v10 = x2 << 16
331 8x v01 = x0 unsigned>> 16
332 v11 = x2 & mask3
333 x0 = v00 | v10
334 x2 = v01 | v11
335 v00 = x1 & mask2
336 8x v10 = x3 << 16
337 8x v01 = x1 unsigned>> 16
338 v11 = x3 & mask3
339 x1 = v00 | v10
340 x3 = v01 | v11
341 v00 = x4 & mask2
342 8x v10 = x6 << 16
343 8x v01 = x4 unsigned>> 16
344 v11 = x6 & mask3
345 x4 = v00 | v10
346 x6 = v01 | v11
347 v00 = x5 & mask2
348 8x v10 = x7 << 16
349 8x v01 = x5 unsigned>> 16
350 v11 = x7 & mask3
351 x5 = v00 | v10
352 x7 = v01 | v11
353 v00 = x0 & mask4
354 16x v10 = x1 << 8
355 16x v01 = x0 unsigned>> 8
356 v11 = x1 & mask5
357 x0 = v00 | v10
358 x1 = v01 | v11
359 v00 = x2 & mask4
360 16x v10 = x3 << 8
361 16x v01 = x2 unsigned>> 8
362 v11 = x3 & mask5
363 x2 = v00 | v10
364 x3 = v01 | v11
365 v00 = x4 & mask4
366 16x v10 = x5 << 8
367 16x v01 = x4 unsigned>> 8
368 v11 = x5 & mask5
369 x4 = v00 | v10
370 x5 = v01 | v11
371 v00 = x6 & mask4
372 16x v10 = x7 << 8
373 16x v01 = x6 unsigned>> 8
374 v11 = x7 & mask5
375 x6 = v00 | v10
376 x7 = v01 | v11
377 mem256[ input_0 + 96 ] = x0
378 mem256[ input_0 + 352 ] = x1
379 mem256[ input_0 + 608 ] = x2
380 mem256[ input_0 + 864 ] = x3
381 mem256[ input_0 + 1120 ] = x4
382 mem256[ input_0 + 1376 ] = x5
383 mem256[ input_0 + 1632 ] = x6
384 mem256[ input_0 + 1888 ] = x7
385
386 x0 = mem256[ input_0 + 128 ]
387 x1 = mem256[ input_0 + 384 ]
388 x2 = mem256[ input_0 + 640 ]
389 x3 = mem256[ input_0 + 896 ]
390 x4 = mem256[ input_0 + 1152 ]
391 x5 = mem256[ input_0 + 1408 ]
392 x6 = mem256[ input_0 + 1664 ]
393 x7 = mem256[ input_0 + 1920 ]
394 v00 = x0 & mask0
395 4x v10 = x4 << 32
396 4x v01 = x0 unsigned>> 32
397 v11 = x4 & mask1
398 x0 = v00 | v10
399 x4 = v01 | v11
400 v00 = x1 & mask0
401 4x v10 = x5 << 32
402 4x v01 = x1 unsigned>> 32
403 v11 = x5 & mask1
404 x1 = v00 | v10
405 x5 = v01 | v11
406 v00 = x2 & mask0
407 4x v10 = x6 << 32
408 4x v01 = x2 unsigned>> 32
409 v11 = x6 & mask1
410 x2 = v00 | v10
411 x6 = v01 | v11
412 v00 = x3 & mask0
413 4x v10 = x7 << 32
414 4x v01 = x3 unsigned>> 32
415 v11 = x7 & mask1
416 x3 = v00 | v10
417 x7 = v01 | v11
418 v00 = x0 & mask2
419 8x v10 = x2 << 16
420 8x v01 = x0 unsigned>> 16
421 v11 = x2 & mask3
422 x0 = v00 | v10
423 x2 = v01 | v11
424 v00 = x1 & mask2
425 8x v10 = x3 << 16
426 8x v01 = x1 unsigned>> 16
427 v11 = x3 & mask3
428 x1 = v00 | v10
429 x3 = v01 | v11
430 v00 = x4 & mask2
431 8x v10 = x6 << 16
432 8x v01 = x4 unsigned>> 16
433 v11 = x6 & mask3
434 x4 = v00 | v10
435 x6 = v01 | v11
436 v00 = x5 & mask2
437 8x v10 = x7 << 16
438 8x v01 = x5 unsigned>> 16
439 v11 = x7 & mask3
440 x5 = v00 | v10
441 x7 = v01 | v11
442 v00 = x0 & mask4
443 16x v10 = x1 << 8
444 16x v01 = x0 unsigned>> 8
445 v11 = x1 & mask5
446 x0 = v00 | v10
447 x1 = v01 | v11
448 v00 = x2 & mask4
449 16x v10 = x3 << 8
450 16x v01 = x2 unsigned>> 8
451 v11 = x3 & mask5
452 x2 = v00 | v10
453 x3 = v01 | v11
454 v00 = x4 & mask4
455 16x v10 = x5 << 8
456 16x v01 = x4 unsigned>> 8
457 v11 = x5 & mask5
458 x4 = v00 | v10
459 x5 = v01 | v11
460 v00 = x6 & mask4
461 16x v10 = x7 << 8
462 16x v01 = x6 unsigned>> 8
463 v11 = x7 & mask5
464 x6 = v00 | v10
465 x7 = v01 | v11
466 mem256[ input_0 + 128 ] = x0
467 mem256[ input_0 + 384 ] = x1
468 mem256[ input_0 + 640 ] = x2
469 mem256[ input_0 + 896 ] = x3
470 mem256[ input_0 + 1152 ] = x4
471 mem256[ input_0 + 1408 ] = x5
472 mem256[ input_0 + 1664 ] = x6
473 mem256[ input_0 + 1920 ] = x7
474
475 x0 = mem256[ input_0 + 160 ]
476 x1 = mem256[ input_0 + 416 ]
477 x2 = mem256[ input_0 + 672 ]
478 x3 = mem256[ input_0 + 928 ]
479 x4 = mem256[ input_0 + 1184 ]
480 x5 = mem256[ input_0 + 1440 ]
481 x6 = mem256[ input_0 + 1696 ]
482 x7 = mem256[ input_0 + 1952 ]
483 v00 = x0 & mask0
484 4x v10 = x4 << 32
485 4x v01 = x0 unsigned>> 32
486 v11 = x4 & mask1
487 x0 = v00 | v10
488 x4 = v01 | v11
489 v00 = x1 & mask0
490 4x v10 = x5 << 32
491 4x v01 = x1 unsigned>> 32
492 v11 = x5 & mask1
493 x1 = v00 | v10
494 x5 = v01 | v11
495 v00 = x2 & mask0
496 4x v10 = x6 << 32
497 4x v01 = x2 unsigned>> 32
498 v11 = x6 & mask1
499 x2 = v00 | v10
500 x6 = v01 | v11
501 v00 = x3 & mask0
502 4x v10 = x7 << 32
503 4x v01 = x3 unsigned>> 32
504 v11 = x7 & mask1
505 x3 = v00 | v10
506 x7 = v01 | v11
507 v00 = x0 & mask2
508 8x v10 = x2 << 16
509 8x v01 = x0 unsigned>> 16
510 v11 = x2 & mask3
511 x0 = v00 | v10
512 x2 = v01 | v11
513 v00 = x1 & mask2
514 8x v10 = x3 << 16
515 8x v01 = x1 unsigned>> 16
516 v11 = x3 & mask3
517 x1 = v00 | v10
518 x3 = v01 | v11
519 v00 = x4 & mask2
520 8x v10 = x6 << 16
521 8x v01 = x4 unsigned>> 16
522 v11 = x6 & mask3
523 x4 = v00 | v10
524 x6 = v01 | v11
525 v00 = x5 & mask2
526 8x v10 = x7 << 16
527 8x v01 = x5 unsigned>> 16
528 v11 = x7 & mask3
529 x5 = v00 | v10
530 x7 = v01 | v11
531 v00 = x0 & mask4
532 16x v10 = x1 << 8
533 16x v01 = x0 unsigned>> 8
534 v11 = x1 & mask5
535 x0 = v00 | v10
536 x1 = v01 | v11
537 v00 = x2 & mask4
538 16x v10 = x3 << 8
539 16x v01 = x2 unsigned>> 8
540 v11 = x3 & mask5
541 x2 = v00 | v10
542 x3 = v01 | v11
543 v00 = x4 & mask4
544 16x v10 = x5 << 8
545 16x v01 = x4 unsigned>> 8
546 v11 = x5 & mask5
547 x4 = v00 | v10
548 x5 = v01 | v11
549 v00 = x6 & mask4
550 16x v10 = x7 << 8
551 16x v01 = x6 unsigned>> 8
552 v11 = x7 & mask5
553 x6 = v00 | v10
554 x7 = v01 | v11
555 mem256[ input_0 + 160 ] = x0
556 mem256[ input_0 + 416 ] = x1
557 mem256[ input_0 + 672 ] = x2
558 mem256[ input_0 + 928 ] = x3
559 mem256[ input_0 + 1184 ] = x4
560 mem256[ input_0 + 1440 ] = x5
561 mem256[ input_0 + 1696 ] = x6
562 mem256[ input_0 + 1952 ] = x7
563
564 x0 = mem256[ input_0 + 192 ]
565 x1 = mem256[ input_0 + 448 ]
566 x2 = mem256[ input_0 + 704 ]
567 x3 = mem256[ input_0 + 960 ]
568 x4 = mem256[ input_0 + 1216 ]
569 x5 = mem256[ input_0 + 1472 ]
570 x6 = mem256[ input_0 + 1728 ]
571 x7 = mem256[ input_0 + 1984 ]
572 v00 = x0 & mask0
573 4x v10 = x4 << 32
574 4x v01 = x0 unsigned>> 32
575 v11 = x4 & mask1
576 x0 = v00 | v10
577 x4 = v01 | v11
578 v00 = x1 & mask0
579 4x v10 = x5 << 32
580 4x v01 = x1 unsigned>> 32
581 v11 = x5 & mask1
582 x1 = v00 | v10
583 x5 = v01 | v11
584 v00 = x2 & mask0
585 4x v10 = x6 << 32
586 4x v01 = x2 unsigned>> 32
587 v11 = x6 & mask1
588 x2 = v00 | v10
589 x6 = v01 | v11
590 v00 = x3 & mask0
591 4x v10 = x7 << 32
592 4x v01 = x3 unsigned>> 32
593 v11 = x7 & mask1
594 x3 = v00 | v10
595 x7 = v01 | v11
596 v00 = x0 & mask2
597 8x v10 = x2 << 16
598 8x v01 = x0 unsigned>> 16
599 v11 = x2 & mask3
600 x0 = v00 | v10
601 x2 = v01 | v11
602 v00 = x1 & mask2
603 8x v10 = x3 << 16
604 8x v01 = x1 unsigned>> 16
605 v11 = x3 & mask3
606 x1 = v00 | v10
607 x3 = v01 | v11
608 v00 = x4 & mask2
609 8x v10 = x6 << 16
610 8x v01 = x4 unsigned>> 16
611 v11 = x6 & mask3
612 x4 = v00 | v10
613 x6 = v01 | v11
614 v00 = x5 & mask2
615 8x v10 = x7 << 16
616 8x v01 = x5 unsigned>> 16
617 v11 = x7 & mask3
618 x5 = v00 | v10
619 x7 = v01 | v11
620 v00 = x0 & mask4
621 16x v10 = x1 << 8
622 16x v01 = x0 unsigned>> 8
623 v11 = x1 & mask5
624 x0 = v00 | v10
625 x1 = v01 | v11
626 v00 = x2 & mask4
627 16x v10 = x3 << 8
628 16x v01 = x2 unsigned>> 8
629 v11 = x3 & mask5
630 x2 = v00 | v10
631 x3 = v01 | v11
632 v00 = x4 & mask4
633 16x v10 = x5 << 8
634 16x v01 = x4 unsigned>> 8
635 v11 = x5 & mask5
636 x4 = v00 | v10
637 x5 = v01 | v11
638 v00 = x6 & mask4
639 16x v10 = x7 << 8
640 16x v01 = x6 unsigned>> 8
641 v11 = x7 & mask5
642 x6 = v00 | v10
643 x7 = v01 | v11
644 mem256[ input_0 + 192 ] = x0
645 mem256[ input_0 + 448 ] = x1
646 mem256[ input_0 + 704 ] = x2
647 mem256[ input_0 + 960 ] = x3
648 mem256[ input_0 + 1216 ] = x4
649 mem256[ input_0 + 1472 ] = x5
650 mem256[ input_0 + 1728 ] = x6
651 mem256[ input_0 + 1984 ] = x7
652
653 x0 = mem256[ input_0 + 224 ]
654 x1 = mem256[ input_0 + 480 ]
655 x2 = mem256[ input_0 + 736 ]
656 x3 = mem256[ input_0 + 992 ]
657 x4 = mem256[ input_0 + 1248 ]
658 x5 = mem256[ input_0 + 1504 ]
659 x6 = mem256[ input_0 + 1760 ]
660 x7 = mem256[ input_0 + 2016 ]
661 v00 = x0 & mask0
662 4x v10 = x4 << 32
663 4x v01 = x0 unsigned>> 32
664 v11 = x4 & mask1
665 x0 = v00 | v10
666 x4 = v01 | v11
667 v00 = x1 & mask0
668 4x v10 = x5 << 32
669 4x v01 = x1 unsigned>> 32
670 v11 = x5 & mask1
671 x1 = v00 | v10
672 x5 = v01 | v11
673 v00 = x2 & mask0
674 4x v10 = x6 << 32
675 4x v01 = x2 unsigned>> 32
676 v11 = x6 & mask1
677 x2 = v00 | v10
678 x6 = v01 | v11
679 v00 = x3 & mask0
680 4x v10 = x7 << 32
681 4x v01 = x3 unsigned>> 32
682 v11 = x7 & mask1
683 x3 = v00 | v10
684 x7 = v01 | v11
685 v00 = x0 & mask2
686 8x v10 = x2 << 16
687 8x v01 = x0 unsigned>> 16
688 v11 = x2 & mask3
689 x0 = v00 | v10
690 x2 = v01 | v11
691 v00 = x1 & mask2
692 8x v10 = x3 << 16
693 8x v01 = x1 unsigned>> 16
694 v11 = x3 & mask3
695 x1 = v00 | v10
696 x3 = v01 | v11
697 v00 = x4 & mask2
698 8x v10 = x6 << 16
699 8x v01 = x4 unsigned>> 16
700 v11 = x6 & mask3
701 x4 = v00 | v10
702 x6 = v01 | v11
703 v00 = x5 & mask2
704 8x v10 = x7 << 16
705 8x v01 = x5 unsigned>> 16
706 v11 = x7 & mask3
707 x5 = v00 | v10
708 x7 = v01 | v11
709 v00 = x0 & mask4
710 16x v10 = x1 << 8
711 16x v01 = x0 unsigned>> 8
712 v11 = x1 & mask5
713 x0 = v00 | v10
714 x1 = v01 | v11
715 v00 = x2 & mask4
716 16x v10 = x3 << 8
717 16x v01 = x2 unsigned>> 8
718 v11 = x3 & mask5
719 x2 = v00 | v10
720 x3 = v01 | v11
721 v00 = x4 & mask4
722 16x v10 = x5 << 8
723 16x v01 = x4 unsigned>> 8
724 v11 = x5 & mask5
725 x4 = v00 | v10
726 x5 = v01 | v11
727 v00 = x6 & mask4
728 16x v10 = x7 << 8
729 16x v01 = x6 unsigned>> 8
730 v11 = x7 & mask5
731 x6 = v00 | v10
732 x7 = v01 | v11
733 mem256[ input_0 + 224 ] = x0
734 mem256[ input_0 + 480 ] = x1
735 mem256[ input_0 + 736 ] = x2
736 mem256[ input_0 + 992 ] = x3
737 mem256[ input_0 + 1248 ] = x4
738 mem256[ input_0 + 1504 ] = x5
739 mem256[ input_0 + 1760 ] = x6
740 mem256[ input_0 + 2016 ] = x7
741
742 mask0 aligned= mem256[ MASK2_0 ]
743 mask1 aligned= mem256[ MASK2_1 ]
744 mask2 aligned= mem256[ MASK1_0 ]
745 mask3 aligned= mem256[ MASK1_1 ]
746 mask4 aligned= mem256[ MASK0_0 ]
747 mask5 aligned= mem256[ MASK0_1 ]
748 x0 = mem256[ input_0 + 0 ]
749 x1 = mem256[ input_0 + 32 ]
750 x2 = mem256[ input_0 + 64 ]
751 x3 = mem256[ input_0 + 96 ]
752 x4 = mem256[ input_0 + 128 ]
753 x5 = mem256[ input_0 + 160 ]
754 x6 = mem256[ input_0 + 192 ]
755 x7 = mem256[ input_0 + 224 ]
756 v00 = x0 & mask0
757 v10 = x4 & mask0
758 4x v10 <<= 4
759 v01 = x0 & mask1
760 v11 = x4 & mask1
761 4x v01 unsigned>>= 4
762 x0 = v00 | v10
763 x4 = v01 | v11
764 v00 = x1 & mask0
765 v10 = x5 & mask0
766 4x v10 <<= 4
767 v01 = x1 & mask1
768 v11 = x5 & mask1
769 4x v01 unsigned>>= 4
770 x1 = v00 | v10
771 x5 = v01 | v11
772 v00 = x2 & mask0
773 v10 = x6 & mask0
774 4x v10 <<= 4
775 v01 = x2 & mask1
776 v11 = x6 & mask1
777 4x v01 unsigned>>= 4
778 x2 = v00 | v10
779 x6 = v01 | v11
780 v00 = x3 & mask0
781 v10 = x7 & mask0
782 4x v10 <<= 4
783 v01 = x3 & mask1
784 v11 = x7 & mask1
785 4x v01 unsigned>>= 4
786 x3 = v00 | v10
787 x7 = v01 | v11
788 v00 = x0 & mask2
789 v10 = x2 & mask2
790 4x v10 <<= 2
791 v01 = x0 & mask3
792 v11 = x2 & mask3
793 4x v01 unsigned>>= 2
794 x0 = v00 | v10
795 x2 = v01 | v11
796 v00 = x1 & mask2
797 v10 = x3 & mask2
798 4x v10 <<= 2
799 v01 = x1 & mask3
800 v11 = x3 & mask3
801 4x v01 unsigned>>= 2
802 x1 = v00 | v10
803 x3 = v01 | v11
804 v00 = x4 & mask2
805 v10 = x6 & mask2
806 4x v10 <<= 2
807 v01 = x4 & mask3
808 v11 = x6 & mask3
809 4x v01 unsigned>>= 2
810 x4 = v00 | v10
811 x6 = v01 | v11
812 v00 = x5 & mask2
813 v10 = x7 & mask2
814 4x v10 <<= 2
815 v01 = x5 & mask3
816 v11 = x7 & mask3
817 4x v01 unsigned>>= 2
818 x5 = v00 | v10
819 x7 = v01 | v11
820 v00 = x0 & mask4
821 v10 = x1 & mask4
822 4x v10 <<= 1
823 v01 = x0 & mask5
824 v11 = x1 & mask5
825 4x v01 unsigned>>= 1
826 x0 = v00 | v10
827 x1 = v01 | v11
828 v00 = x2 & mask4
829 v10 = x3 & mask4
830 4x v10 <<= 1
831 v01 = x2 & mask5
832 v11 = x3 & mask5
833 4x v01 unsigned>>= 1
834 x2 = v00 | v10
835 x3 = v01 | v11
836 v00 = x4 & mask4
837 v10 = x5 & mask4
838 4x v10 <<= 1
839 v01 = x4 & mask5
840 v11 = x5 & mask5
841 4x v01 unsigned>>= 1
842 x4 = v00 | v10
843 x5 = v01 | v11
844 v00 = x6 & mask4
845 v10 = x7 & mask4
846 4x v10 <<= 1
847 v01 = x6 & mask5
848 v11 = x7 & mask5
849 4x v01 unsigned>>= 1
850 x6 = v00 | v10
851 x7 = v01 | v11
852 mem256[ input_0 + 0 ] = x0
853 mem256[ input_0 + 32 ] = x1
854 mem256[ input_0 + 64 ] = x2
855 mem256[ input_0 + 96 ] = x3
856 mem256[ input_0 + 128 ] = x4
857 mem256[ input_0 + 160 ] = x5
858 mem256[ input_0 + 192 ] = x6
859 mem256[ input_0 + 224 ] = x7
860
861 x0 = mem256[ input_0 + 256 ]
862 x1 = mem256[ input_0 + 288 ]
863 x2 = mem256[ input_0 + 320 ]
864 x3 = mem256[ input_0 + 352 ]
865 x4 = mem256[ input_0 + 384 ]
866 x5 = mem256[ input_0 + 416 ]
867 x6 = mem256[ input_0 + 448 ]
868 x7 = mem256[ input_0 + 480 ]
869 v00 = x0 & mask0
870 v10 = x4 & mask0
871 4x v10 <<= 4
872 v01 = x0 & mask1
873 v11 = x4 & mask1
874 4x v01 unsigned>>= 4
875 x0 = v00 | v10
876 x4 = v01 | v11
877 v00 = x1 & mask0
878 v10 = x5 & mask0
879 4x v10 <<= 4
880 v01 = x1 & mask1
881 v11 = x5 & mask1
882 4x v01 unsigned>>= 4
883 x1 = v00 | v10
884 x5 = v01 | v11
885 v00 = x2 & mask0
886 v10 = x6 & mask0
887 4x v10 <<= 4
888 v01 = x2 & mask1
889 v11 = x6 & mask1
890 4x v01 unsigned>>= 4
891 x2 = v00 | v10
892 x6 = v01 | v11
893 v00 = x3 & mask0
894 v10 = x7 & mask0
895 4x v10 <<= 4
896 v01 = x3 & mask1
897 v11 = x7 & mask1
898 4x v01 unsigned>>= 4
899 x3 = v00 | v10
900 x7 = v01 | v11
901 v00 = x0 & mask2
902 v10 = x2 & mask2
903 4x v10 <<= 2
904 v01 = x0 & mask3
905 v11 = x2 & mask3
906 4x v01 unsigned>>= 2
907 x0 = v00 | v10
908 x2 = v01 | v11
909 v00 = x1 & mask2
910 v10 = x3 & mask2
911 4x v10 <<= 2
912 v01 = x1 & mask3
913 v11 = x3 & mask3
914 4x v01 unsigned>>= 2
915 x1 = v00 | v10
916 x3 = v01 | v11
917 v00 = x4 & mask2
918 v10 = x6 & mask2
919 4x v10 <<= 2
920 v01 = x4 & mask3
921 v11 = x6 & mask3
922 4x v01 unsigned>>= 2
923 x4 = v00 | v10
924 x6 = v01 | v11
925 v00 = x5 & mask2
926 v10 = x7 & mask2
927 4x v10 <<= 2
928 v01 = x5 & mask3
929 v11 = x7 & mask3
930 4x v01 unsigned>>= 2
931 x5 = v00 | v10
932 x7 = v01 | v11
933 v00 = x0 & mask4
934 v10 = x1 & mask4
935 4x v10 <<= 1
936 v01 = x0 & mask5
937 v11 = x1 & mask5
938 4x v01 unsigned>>= 1
939 x0 = v00 | v10
940 x1 = v01 | v11
941 v00 = x2 & mask4
942 v10 = x3 & mask4
943 4x v10 <<= 1
944 v01 = x2 & mask5
945 v11 = x3 & mask5
946 4x v01 unsigned>>= 1
947 x2 = v00 | v10
948 x3 = v01 | v11
949 v00 = x4 & mask4
950 v10 = x5 & mask4
951 4x v10 <<= 1
952 v01 = x4 & mask5
953 v11 = x5 & mask5
954 4x v01 unsigned>>= 1
955 x4 = v00 | v10
956 x5 = v01 | v11
957 v00 = x6 & mask4
958 v10 = x7 & mask4
959 4x v10 <<= 1
960 v01 = x6 & mask5
961 v11 = x7 & mask5
962 4x v01 unsigned>>= 1
963 x6 = v00 | v10
964 x7 = v01 | v11
965 mem256[ input_0 + 256 ] = x0
966 mem256[ input_0 + 288 ] = x1
967 mem256[ input_0 + 320 ] = x2
968 mem256[ input_0 + 352 ] = x3
969 mem256[ input_0 + 384 ] = x4
970 mem256[ input_0 + 416 ] = x5
971 mem256[ input_0 + 448 ] = x6
972 mem256[ input_0 + 480 ] = x7
973
974 x0 = mem256[ input_0 + 512 ]
975 x1 = mem256[ input_0 + 544 ]
976 x2 = mem256[ input_0 + 576 ]
977 x3 = mem256[ input_0 + 608 ]
978 x4 = mem256[ input_0 + 640 ]
979 x5 = mem256[ input_0 + 672 ]
980 x6 = mem256[ input_0 + 704 ]
981 x7 = mem256[ input_0 + 736 ]
982 v00 = x0 & mask0
983 v10 = x4 & mask0
984 4x v10 <<= 4
985 v01 = x0 & mask1
986 v11 = x4 & mask1
987 4x v01 unsigned>>= 4
988 x0 = v00 | v10
989 x4 = v01 | v11
990 v00 = x1 & mask0
991 v10 = x5 & mask0
992 4x v10 <<= 4
993 v01 = x1 & mask1
994 v11 = x5 & mask1
995 4x v01 unsigned>>= 4
996 x1 = v00 | v10
997 x5 = v01 | v11
998 v00 = x2 & mask0
999 v10 = x6 & mask0
1000 4x v10 <<= 4
1001 v01 = x2 & mask1
1002 v11 = x6 & mask1
1003 4x v01 unsigned>>= 4
1004 x2 = v00 | v10
1005 x6 = v01 | v11
1006 v00 = x3 & mask0
1007 v10 = x7 & mask0
1008 4x v10 <<= 4
1009 v01 = x3 & mask1
1010 v11 = x7 & mask1
1011 4x v01 unsigned>>= 4
1012 x3 = v00 | v10
1013 x7 = v01 | v11
1014 v00 = x0 & mask2
1015 v10 = x2 & mask2
1016 4x v10 <<= 2
1017 v01 = x0 & mask3
1018 v11 = x2 & mask3
1019 4x v01 unsigned>>= 2
1020 x0 = v00 | v10
1021 x2 = v01 | v11
1022 v00 = x1 & mask2
1023 v10 = x3 & mask2
1024 4x v10 <<= 2
1025 v01 = x1 & mask3
1026 v11 = x3 & mask3
1027 4x v01 unsigned>>= 2
1028 x1 = v00 | v10
1029 x3 = v01 | v11
1030 v00 = x4 & mask2
1031 v10 = x6 & mask2
1032 4x v10 <<= 2
1033 v01 = x4 & mask3
1034 v11 = x6 & mask3
1035 4x v01 unsigned>>= 2
1036 x4 = v00 | v10
1037 x6 = v01 | v11
1038 v00 = x5 & mask2
1039 v10 = x7 & mask2
1040 4x v10 <<= 2
1041 v01 = x5 & mask3
1042 v11 = x7 & mask3
1043 4x v01 unsigned>>= 2
1044 x5 = v00 | v10
1045 x7 = v01 | v11
1046 v00 = x0 & mask4
1047 v10 = x1 & mask4
1048 4x v10 <<= 1
1049 v01 = x0 & mask5
1050 v11 = x1 & mask5
1051 4x v01 unsigned>>= 1
1052 x0 = v00 | v10
1053 x1 = v01 | v11
1054 v00 = x2 & mask4
1055 v10 = x3 & mask4
1056 4x v10 <<= 1
1057 v01 = x2 & mask5
1058 v11 = x3 & mask5
1059 4x v01 unsigned>>= 1
1060 x2 = v00 | v10
1061 x3 = v01 | v11
1062 v00 = x4 & mask4
1063 v10 = x5 & mask4
1064 4x v10 <<= 1
1065 v01 = x4 & mask5
1066 v11 = x5 & mask5
1067 4x v01 unsigned>>= 1
1068 x4 = v00 | v10
1069 x5 = v01 | v11
1070 v00 = x6 & mask4
1071 v10 = x7 & mask4
1072 4x v10 <<= 1
1073 v01 = x6 & mask5
1074 v11 = x7 & mask5
1075 4x v01 unsigned>>= 1
1076 x6 = v00 | v10
1077 x7 = v01 | v11
1078 mem256[ input_0 + 512 ] = x0
1079 mem256[ input_0 + 544 ] = x1
1080 mem256[ input_0 + 576 ] = x2
1081 mem256[ input_0 + 608 ] = x3
1082 mem256[ input_0 + 640 ] = x4
1083 mem256[ input_0 + 672 ] = x5
1084 mem256[ input_0 + 704 ] = x6
1085 mem256[ input_0 + 736 ] = x7
1086
1087 x0 = mem256[ input_0 + 768 ]
1088 x1 = mem256[ input_0 + 800 ]
1089 x2 = mem256[ input_0 + 832 ]
1090 x3 = mem256[ input_0 + 864 ]
1091 x4 = mem256[ input_0 + 896 ]
1092 x5 = mem256[ input_0 + 928 ]
1093 x6 = mem256[ input_0 + 960 ]
1094 x7 = mem256[ input_0 + 992 ]
1095 v00 = x0 & mask0
1096 v10 = x4 & mask0
1097 4x v10 <<= 4
1098 v01 = x0 & mask1
1099 v11 = x4 & mask1
1100 4x v01 unsigned>>= 4
1101 x0 = v00 | v10
1102 x4 = v01 | v11
1103 v00 = x1 & mask0
1104 v10 = x5 & mask0
1105 4x v10 <<= 4
1106 v01 = x1 & mask1
1107 v11 = x5 & mask1
1108 4x v01 unsigned>>= 4
1109 x1 = v00 | v10
1110 x5 = v01 | v11
1111 v00 = x2 & mask0
1112 v10 = x6 & mask0
1113 4x v10 <<= 4
1114 v01 = x2 & mask1
1115 v11 = x6 & mask1
1116 4x v01 unsigned>>= 4
1117 x2 = v00 | v10
1118 x6 = v01 | v11
1119 v00 = x3 & mask0
1120 v10 = x7 & mask0
1121 4x v10 <<= 4
1122 v01 = x3 & mask1
1123 v11 = x7 & mask1
1124 4x v01 unsigned>>= 4
1125 x3 = v00 | v10
1126 x7 = v01 | v11
1127 v00 = x0 & mask2
1128 v10 = x2 & mask2
1129 4x v10 <<= 2
1130 v01 = x0 & mask3
1131 v11 = x2 & mask3
1132 4x v01 unsigned>>= 2
1133 x0 = v00 | v10
1134 x2 = v01 | v11
1135 v00 = x1 & mask2
1136 v10 = x3 & mask2
1137 4x v10 <<= 2
1138 v01 = x1 & mask3
1139 v11 = x3 & mask3
1140 4x v01 unsigned>>= 2
1141 x1 = v00 | v10
1142 x3 = v01 | v11
1143 v00 = x4 & mask2
1144 v10 = x6 & mask2
1145 4x v10 <<= 2
1146 v01 = x4 & mask3
1147 v11 = x6 & mask3
1148 4x v01 unsigned>>= 2
1149 x4 = v00 | v10
1150 x6 = v01 | v11
1151 v00 = x5 & mask2
1152 v10 = x7 & mask2
1153 4x v10 <<= 2
1154 v01 = x5 & mask3
1155 v11 = x7 & mask3
1156 4x v01 unsigned>>= 2
1157 x5 = v00 | v10
1158 x7 = v01 | v11
1159 v00 = x0 & mask4
1160 v10 = x1 & mask4
1161 4x v10 <<= 1
1162 v01 = x0 & mask5
1163 v11 = x1 & mask5
1164 4x v01 unsigned>>= 1
1165 x0 = v00 | v10
1166 x1 = v01 | v11
1167 v00 = x2 & mask4
1168 v10 = x3 & mask4
1169 4x v10 <<= 1
1170 v01 = x2 & mask5
1171 v11 = x3 & mask5
1172 4x v01 unsigned>>= 1
1173 x2 = v00 | v10
1174 x3 = v01 | v11
1175 v00 = x4 & mask4
1176 v10 = x5 & mask4
1177 4x v10 <<= 1
1178 v01 = x4 & mask5
1179 v11 = x5 & mask5
1180 4x v01 unsigned>>= 1
1181 x4 = v00 | v10
1182 x5 = v01 | v11
1183 v00 = x6 & mask4
1184 v10 = x7 & mask4
1185 4x v10 <<= 1
1186 v01 = x6 & mask5
1187 v11 = x7 & mask5
1188 4x v01 unsigned>>= 1
1189 x6 = v00 | v10
1190 x7 = v01 | v11
1191 mem256[ input_0 + 768 ] = x0
1192 mem256[ input_0 + 800 ] = x1
1193 mem256[ input_0 + 832 ] = x2
1194 mem256[ input_0 + 864 ] = x3
1195 mem256[ input_0 + 896 ] = x4
1196 mem256[ input_0 + 928 ] = x5
1197 mem256[ input_0 + 960 ] = x6
1198 mem256[ input_0 + 992 ] = x7
1199
1200 x0 = mem256[ input_0 + 1024 ]
1201 x1 = mem256[ input_0 + 1056 ]
1202 x2 = mem256[ input_0 + 1088 ]
1203 x3 = mem256[ input_0 + 1120 ]
1204 x4 = mem256[ input_0 + 1152 ]
1205 x5 = mem256[ input_0 + 1184 ]
1206 x6 = mem256[ input_0 + 1216 ]
1207 x7 = mem256[ input_0 + 1248 ]
1208 v00 = x0 & mask0
1209 v10 = x4 & mask0
1210 4x v10 <<= 4
1211 v01 = x0 & mask1
1212 v11 = x4 & mask1
1213 4x v01 unsigned>>= 4
1214 x0 = v00 | v10
1215 x4 = v01 | v11
1216 v00 = x1 & mask0
1217 v10 = x5 & mask0
1218 4x v10 <<= 4
1219 v01 = x1 & mask1
1220 v11 = x5 & mask1
1221 4x v01 unsigned>>= 4
1222 x1 = v00 | v10
1223 x5 = v01 | v11
1224 v00 = x2 & mask0
1225 v10 = x6 & mask0
1226 4x v10 <<= 4
1227 v01 = x2 & mask1
1228 v11 = x6 & mask1
1229 4x v01 unsigned>>= 4
1230 x2 = v00 | v10
1231 x6 = v01 | v11
1232 v00 = x3 & mask0
1233 v10 = x7 & mask0
1234 4x v10 <<= 4
1235 v01 = x3 & mask1
1236 v11 = x7 & mask1
1237 4x v01 unsigned>>= 4
1238 x3 = v00 | v10
1239 x7 = v01 | v11
1240 v00 = x0 & mask2
1241 v10 = x2 & mask2
1242 4x v10 <<= 2
1243 v01 = x0 & mask3
1244 v11 = x2 & mask3
1245 4x v01 unsigned>>= 2
1246 x0 = v00 | v10
1247 x2 = v01 | v11
1248 v00 = x1 & mask2
1249 v10 = x3 & mask2
1250 4x v10 <<= 2
1251 v01 = x1 & mask3
1252 v11 = x3 & mask3
1253 4x v01 unsigned>>= 2
1254 x1 = v00 | v10
1255 x3 = v01 | v11
1256 v00 = x4 & mask2
1257 v10 = x6 & mask2
1258 4x v10 <<= 2
1259 v01 = x4 & mask3
1260 v11 = x6 & mask3
1261 4x v01 unsigned>>= 2
1262 x4 = v00 | v10
1263 x6 = v01 | v11
1264 v00 = x5 & mask2
1265 v10 = x7 & mask2
1266 4x v10 <<= 2
1267 v01 = x5 & mask3
1268 v11 = x7 & mask3
1269 4x v01 unsigned>>= 2
1270 x5 = v00 | v10
1271 x7 = v01 | v11
1272 v00 = x0 & mask4
1273 v10 = x1 & mask4
1274 4x v10 <<= 1
1275 v01 = x0 & mask5
1276 v11 = x1 & mask5
1277 4x v01 unsigned>>= 1
1278 x0 = v00 | v10
1279 x1 = v01 | v11
1280 v00 = x2 & mask4
1281 v10 = x3 & mask4
1282 4x v10 <<= 1
1283 v01 = x2 & mask5
1284 v11 = x3 & mask5
1285 4x v01 unsigned>>= 1
1286 x2 = v00 | v10
1287 x3 = v01 | v11
1288 v00 = x4 & mask4
1289 v10 = x5 & mask4
1290 4x v10 <<= 1
1291 v01 = x4 & mask5
1292 v11 = x5 & mask5
1293 4x v01 unsigned>>= 1
1294 x4 = v00 | v10
1295 x5 = v01 | v11
1296 v00 = x6 & mask4
1297 v10 = x7 & mask4
1298 4x v10 <<= 1
1299 v01 = x6 & mask5
1300 v11 = x7 & mask5
1301 4x v01 unsigned>>= 1
1302 x6 = v00 | v10
1303 x7 = v01 | v11
1304 mem256[ input_0 + 1024 ] = x0
1305 mem256[ input_0 + 1056 ] = x1
1306 mem256[ input_0 + 1088 ] = x2
1307 mem256[ input_0 + 1120 ] = x3
1308 mem256[ input_0 + 1152 ] = x4
1309 mem256[ input_0 + 1184 ] = x5
1310 mem256[ input_0 + 1216 ] = x6
1311 mem256[ input_0 + 1248 ] = x7
1312
1313 x0 = mem256[ input_0 + 1280 ]
1314 x1 = mem256[ input_0 + 1312 ]
1315 x2 = mem256[ input_0 + 1344 ]
1316 x3 = mem256[ input_0 + 1376 ]
1317 x4 = mem256[ input_0 + 1408 ]
1318 x5 = mem256[ input_0 + 1440 ]
1319 x6 = mem256[ input_0 + 1472 ]
1320 x7 = mem256[ input_0 + 1504 ]
1321 v00 = x0 & mask0
1322 v10 = x4 & mask0
1323 4x v10 <<= 4
1324 v01 = x0 & mask1
1325 v11 = x4 & mask1
1326 4x v01 unsigned>>= 4
1327 x0 = v00 | v10
1328 x4 = v01 | v11
1329 v00 = x1 & mask0
1330 v10 = x5 & mask0
1331 4x v10 <<= 4
1332 v01 = x1 & mask1
1333 v11 = x5 & mask1
1334 4x v01 unsigned>>= 4
1335 x1 = v00 | v10
1336 x5 = v01 | v11
1337 v00 = x2 & mask0
1338 v10 = x6 & mask0
1339 4x v10 <<= 4
1340 v01 = x2 & mask1
1341 v11 = x6 & mask1
1342 4x v01 unsigned>>= 4
1343 x2 = v00 | v10
1344 x6 = v01 | v11
1345 v00 = x3 & mask0
1346 v10 = x7 & mask0
1347 4x v10 <<= 4
1348 v01 = x3 & mask1
1349 v11 = x7 & mask1
1350 4x v01 unsigned>>= 4
1351 x3 = v00 | v10
1352 x7 = v01 | v11
1353 v00 = x0 & mask2
1354 v10 = x2 & mask2
1355 4x v10 <<= 2
1356 v01 = x0 & mask3
1357 v11 = x2 & mask3
1358 4x v01 unsigned>>= 2
1359 x0 = v00 | v10
1360 x2 = v01 | v11
1361 v00 = x1 & mask2
1362 v10 = x3 & mask2
1363 4x v10 <<= 2
1364 v01 = x1 & mask3
1365 v11 = x3 & mask3
1366 4x v01 unsigned>>= 2
1367 x1 = v00 | v10
1368 x3 = v01 | v11
1369 v00 = x4 & mask2
1370 v10 = x6 & mask2
1371 4x v10 <<= 2
1372 v01 = x4 & mask3
1373 v11 = x6 & mask3
1374 4x v01 unsigned>>= 2
1375 x4 = v00 | v10
1376 x6 = v01 | v11
1377 v00 = x5 & mask2
1378 v10 = x7 & mask2
1379 4x v10 <<= 2
1380 v01 = x5 & mask3
1381 v11 = x7 & mask3
1382 4x v01 unsigned>>= 2
1383 x5 = v00 | v10
1384 x7 = v01 | v11
1385 v00 = x0 & mask4
1386 v10 = x1 & mask4
1387 4x v10 <<= 1
1388 v01 = x0 & mask5
1389 v11 = x1 & mask5
1390 4x v01 unsigned>>= 1
1391 x0 = v00 | v10
1392 x1 = v01 | v11
1393 v00 = x2 & mask4
1394 v10 = x3 & mask4
1395 4x v10 <<= 1
1396 v01 = x2 & mask5
1397 v11 = x3 & mask5
1398 4x v01 unsigned>>= 1
1399 x2 = v00 | v10
1400 x3 = v01 | v11
1401 v00 = x4 & mask4
1402 v10 = x5 & mask4
1403 4x v10 <<= 1
1404 v01 = x4 & mask5
1405 v11 = x5 & mask5
1406 4x v01 unsigned>>= 1
1407 x4 = v00 | v10
1408 x5 = v01 | v11
1409 v00 = x6 & mask4
1410 v10 = x7 & mask4
1411 4x v10 <<= 1
1412 v01 = x6 & mask5
1413 v11 = x7 & mask5
1414 4x v01 unsigned>>= 1
1415 x6 = v00 | v10
1416 x7 = v01 | v11
1417 mem256[ input_0 + 1280 ] = x0
1418 mem256[ input_0 + 1312 ] = x1
1419 mem256[ input_0 + 1344 ] = x2
1420 mem256[ input_0 + 1376 ] = x3
1421 mem256[ input_0 + 1408 ] = x4
1422 mem256[ input_0 + 1440 ] = x5
1423 mem256[ input_0 + 1472 ] = x6
1424 mem256[ input_0 + 1504 ] = x7
1425
1426 x0 = mem256[ input_0 + 1536 ]
1427 x1 = mem256[ input_0 + 1568 ]
1428 x2 = mem256[ input_0 + 1600 ]
1429 x3 = mem256[ input_0 + 1632 ]
1430 x4 = mem256[ input_0 + 1664 ]
1431 x5 = mem256[ input_0 + 1696 ]
1432 x6 = mem256[ input_0 + 1728 ]
1433 x7 = mem256[ input_0 + 1760 ]
1434 v00 = x0 & mask0
1435 v10 = x4 & mask0
1436 4x v10 <<= 4
1437 v01 = x0 & mask1
1438 v11 = x4 & mask1
1439 4x v01 unsigned>>= 4
1440 x0 = v00 | v10
1441 x4 = v01 | v11
1442 v00 = x1 & mask0
1443 v10 = x5 & mask0
1444 4x v10 <<= 4
1445 v01 = x1 & mask1
1446 v11 = x5 & mask1
1447 4x v01 unsigned>>= 4
1448 x1 = v00 | v10
1449 x5 = v01 | v11
1450 v00 = x2 & mask0
1451 v10 = x6 & mask0
1452 4x v10 <<= 4
1453 v01 = x2 & mask1
1454 v11 = x6 & mask1
1455 4x v01 unsigned>>= 4
1456 x2 = v00 | v10
1457 x6 = v01 | v11
1458 v00 = x3 & mask0
1459 v10 = x7 & mask0
1460 4x v10 <<= 4
1461 v01 = x3 & mask1
1462 v11 = x7 & mask1
1463 4x v01 unsigned>>= 4
1464 x3 = v00 | v10
1465 x7 = v01 | v11
1466 v00 = x0 & mask2
1467 v10 = x2 & mask2
1468 4x v10 <<= 2
1469 v01 = x0 & mask3
1470 v11 = x2 & mask3
1471 4x v01 unsigned>>= 2
1472 x0 = v00 | v10
1473 x2 = v01 | v11
1474 v00 = x1 & mask2
1475 v10 = x3 & mask2
1476 4x v10 <<= 2
1477 v01 = x1 & mask3
1478 v11 = x3 & mask3
1479 4x v01 unsigned>>= 2
1480 x1 = v00 | v10
1481 x3 = v01 | v11
1482 v00 = x4 & mask2
1483 v10 = x6 & mask2
1484 4x v10 <<= 2
1485 v01 = x4 & mask3
1486 v11 = x6 & mask3
1487 4x v01 unsigned>>= 2
1488 x4 = v00 | v10
1489 x6 = v01 | v11
1490 v00 = x5 & mask2
1491 v10 = x7 & mask2
1492 4x v10 <<= 2
1493 v01 = x5 & mask3
1494 v11 = x7 & mask3
1495 4x v01 unsigned>>= 2
1496 x5 = v00 | v10
1497 x7 = v01 | v11
1498 v00 = x0 & mask4
1499 v10 = x1 & mask4
1500 4x v10 <<= 1
1501 v01 = x0 & mask5
1502 v11 = x1 & mask5
1503 4x v01 unsigned>>= 1
1504 x0 = v00 | v10
1505 x1 = v01 | v11
1506 v00 = x2 & mask4
1507 v10 = x3 & mask4
1508 4x v10 <<= 1
1509 v01 = x2 & mask5
1510 v11 = x3 & mask5
1511 4x v01 unsigned>>= 1
1512 x2 = v00 | v10
1513 x3 = v01 | v11
1514 v00 = x4 & mask4
1515 v10 = x5 & mask4
1516 4x v10 <<= 1
1517 v01 = x4 & mask5
1518 v11 = x5 & mask5
1519 4x v01 unsigned>>= 1
1520 x4 = v00 | v10
1521 x5 = v01 | v11
1522 v00 = x6 & mask4
1523 v10 = x7 & mask4
1524 4x v10 <<= 1
1525 v01 = x6 & mask5
1526 v11 = x7 & mask5
1527 4x v01 unsigned>>= 1
1528 x6 = v00 | v10
1529 x7 = v01 | v11
1530 mem256[ input_0 + 1536 ] = x0
1531 mem256[ input_0 + 1568 ] = x1
1532 mem256[ input_0 + 1600 ] = x2
1533 mem256[ input_0 + 1632 ] = x3
1534 mem256[ input_0 + 1664 ] = x4
1535 mem256[ input_0 + 1696 ] = x5
1536 mem256[ input_0 + 1728 ] = x6
1537 mem256[ input_0 + 1760 ] = x7
1538
1539 x0 = mem256[ input_0 + 1792 ]
1540 x1 = mem256[ input_0 + 1824 ]
1541 x2 = mem256[ input_0 + 1856 ]
1542 x3 = mem256[ input_0 + 1888 ]
1543 x4 = mem256[ input_0 + 1920 ]
1544 x5 = mem256[ input_0 + 1952 ]
1545 x6 = mem256[ input_0 + 1984 ]
1546 x7 = mem256[ input_0 + 2016 ]
1547 v00 = x0 & mask0
1548 v10 = x4 & mask0
1549 4x v10 <<= 4
1550 v01 = x0 & mask1
1551 v11 = x4 & mask1
1552 4x v01 unsigned>>= 4
1553 x0 = v00 | v10
1554 x4 = v01 | v11
1555 v00 = x1 & mask0
1556 v10 = x5 & mask0
1557 4x v10 <<= 4
1558 v01 = x1 & mask1
1559 v11 = x5 & mask1
1560 4x v01 unsigned>>= 4
1561 x1 = v00 | v10
1562 x5 = v01 | v11
1563 v00 = x2 & mask0
1564 v10 = x6 & mask0
1565 4x v10 <<= 4
1566 v01 = x2 & mask1
1567 v11 = x6 & mask1
1568 4x v01 unsigned>>= 4
1569 x2 = v00 | v10
1570 x6 = v01 | v11
1571 v00 = x3 & mask0
1572 v10 = x7 & mask0
1573 4x v10 <<= 4
1574 v01 = x3 & mask1
1575 v11 = x7 & mask1
1576 4x v01 unsigned>>= 4
1577 x3 = v00 | v10
1578 x7 = v01 | v11
1579 v00 = x0 & mask2
1580 v10 = x2 & mask2
1581 4x v10 <<= 2
1582 v01 = x0 & mask3
1583 v11 = x2 & mask3
1584 4x v01 unsigned>>= 2
1585 x0 = v00 | v10
1586 x2 = v01 | v11
1587 v00 = x1 & mask2
1588 v10 = x3 & mask2
1589 4x v10 <<= 2
1590 v01 = x1 & mask3
1591 v11 = x3 & mask3
1592 4x v01 unsigned>>= 2
1593 x1 = v00 | v10
1594 x3 = v01 | v11
1595 v00 = x4 & mask2
1596 v10 = x6 & mask2
1597 4x v10 <<= 2
1598 v01 = x4 & mask3
1599 v11 = x6 & mask3
1600 4x v01 unsigned>>= 2
1601 x4 = v00 | v10
1602 x6 = v01 | v11
1603 v00 = x5 & mask2
1604 v10 = x7 & mask2
1605 4x v10 <<= 2
1606 v01 = x5 & mask3
1607 v11 = x7 & mask3
1608 4x v01 unsigned>>= 2
1609 x5 = v00 | v10
1610 x7 = v01 | v11
1611 v00 = x0 & mask4
1612 v10 = x1 & mask4
1613 4x v10 <<= 1
1614 v01 = x0 & mask5
1615 v11 = x1 & mask5
1616 4x v01 unsigned>>= 1
1617 x0 = v00 | v10
1618 x1 = v01 | v11
1619 v00 = x2 & mask4
1620 v10 = x3 & mask4
1621 4x v10 <<= 1
1622 v01 = x2 & mask5
1623 v11 = x3 & mask5
1624 4x v01 unsigned>>= 1
1625 x2 = v00 | v10
1626 x3 = v01 | v11
1627 v00 = x4 & mask4
1628 v10 = x5 & mask4
1629 4x v10 <<= 1
1630 v01 = x4 & mask5
1631 v11 = x5 & mask5
1632 4x v01 unsigned>>= 1
1633 x4 = v00 | v10
1634 x5 = v01 | v11
1635 v00 = x6 & mask4
1636 v10 = x7 & mask4
1637 4x v10 <<= 1
1638 v01 = x6 & mask5
1639 v11 = x7 & mask5
1640 4x v01 unsigned>>= 1
1641 x6 = v00 | v10
1642 x7 = v01 | v11
1643 mem256[ input_0 + 1792 ] = x0
1644 mem256[ input_0 + 1824 ] = x1
1645 mem256[ input_0 + 1856 ] = x2
1646 mem256[ input_0 + 1888 ] = x3
1647 mem256[ input_0 + 1920 ] = x4
1648 mem256[ input_0 + 1952 ] = x5
1649 mem256[ input_0 + 1984 ] = x6
1650 mem256[ input_0 + 2016 ] = x7
1651
1652 return