Debian Codegraph @

crypto_kem/348864pcf/avx/transpose_64x64_asm.q

raw
1 reg128 r0
2 reg128 r1
3 reg128 r2
4 reg128 r3
5 reg128 r4
6 reg128 r5
7 reg128 r6
8 reg128 r7
9 reg128 t0
10 reg128 t1
11 reg128 v00
12 reg128 v01
13 reg128 v10
14 reg128 v11
15 int64 buf
16 reg128 mask0
17 reg128 mask1
18 reg128 mask2
19 reg128 mask3
20 reg128 mask4
21 reg128 mask5
22
23 enter transpose_64x64_asm
24
25 mask0 aligned= mem128[ MASK5_0 ]
26 mask1 aligned= mem128[ MASK5_1 ]
27 mask2 aligned= mem128[ MASK4_0 ]
28 mask3 aligned= mem128[ MASK4_1 ]
29 mask4 aligned= mem128[ MASK3_0 ]
30 mask5 aligned= mem128[ MASK3_1 ]
31 r0 = mem64[ input_0 + 0 ] x2
32 r1 = mem64[ input_0 + 64 ] x2
33 r2 = mem64[ input_0 + 128 ] x2
34 r3 = mem64[ input_0 + 192 ] x2
35 r4 = mem64[ input_0 + 256 ] x2
36 r5 = mem64[ input_0 + 320 ] x2
37 r6 = mem64[ input_0 + 384 ] x2
38 r7 = mem64[ input_0 + 448 ] x2
39 v00 = r0 & mask0
40 2x v10 = r4 << 32
41 2x v01 = r0 unsigned>> 32
42 v11 = r4 & mask1
43 r0 = v00 | v10
44 r4 = v01 | v11
45 v00 = r1 & mask0
46 2x v10 = r5 << 32
47 2x v01 = r1 unsigned>> 32
48 v11 = r5 & mask1
49 r1 = v00 | v10
50 r5 = v01 | v11
51 v00 = r2 & mask0
52 2x v10 = r6 << 32
53 2x v01 = r2 unsigned>> 32
54 v11 = r6 & mask1
55 r2 = v00 | v10
56 r6 = v01 | v11
57 v00 = r3 & mask0
58 2x v10 = r7 << 32
59 2x v01 = r3 unsigned>> 32
60 v11 = r7 & mask1
61 r3 = v00 | v10
62 r7 = v01 | v11
63 v00 = r0 & mask2
64 4x v10 = r2 << 16
65 4x v01 = r0 unsigned>> 16
66 v11 = r2 & mask3
67 r0 = v00 | v10
68 r2 = v01 | v11
69 v00 = r1 & mask2
70 4x v10 = r3 << 16
71 4x v01 = r1 unsigned>> 16
72 v11 = r3 & mask3
73 r1 = v00 | v10
74 r3 = v01 | v11
75 v00 = r4 & mask2
76 4x v10 = r6 << 16
77 4x v01 = r4 unsigned>> 16
78 v11 = r6 & mask3
79 r4 = v00 | v10
80 r6 = v01 | v11
81 v00 = r5 & mask2
82 4x v10 = r7 << 16
83 4x v01 = r5 unsigned>> 16
84 v11 = r7 & mask3
85 r5 = v00 | v10
86 r7 = v01 | v11
87 v00 = r0 & mask4
88 8x v10 = r1 << 8
89 8x v01 = r0 unsigned>> 8
90 v11 = r1 & mask5
91 r0 = v00 | v10
92 r1 = v01 | v11
93 v00 = r2 & mask4
94 8x v10 = r3 << 8
95 8x v01 = r2 unsigned>> 8
96 v11 = r3 & mask5
97 r2 = v00 | v10
98 r3 = v01 | v11
99 v00 = r4 & mask4
100 8x v10 = r5 << 8
101 8x v01 = r4 unsigned>> 8
102 v11 = r5 & mask5
103 r4 = v00 | v10
104 r5 = v01 | v11
105 v00 = r6 & mask4
106 8x v10 = r7 << 8
107 8x v01 = r6 unsigned>> 8
108 v11 = r7 & mask5
109 r6 = v00 | v10
110 r7 = v01 | v11
111 buf = r0[0]
112 mem64[ input_0 + 0 ] = buf
113 buf = r1[0]
114 mem64[ input_0 + 64 ] = buf
115 buf = r2[0]
116 mem64[ input_0 + 128 ] = buf
117 buf = r3[0]
118 mem64[ input_0 + 192 ] = buf
119 buf = r4[0]
120 mem64[ input_0 + 256 ] = buf
121 buf = r5[0]
122 mem64[ input_0 + 320 ] = buf
123 buf = r6[0]
124 mem64[ input_0 + 384 ] = buf
125 buf = r7[0]
126 mem64[ input_0 + 448 ] = buf
127
128 r0 = mem64[ input_0 + 8 ] x2
129 r1 = mem64[ input_0 + 72 ] x2
130 r2 = mem64[ input_0 + 136 ] x2
131 r3 = mem64[ input_0 + 200 ] x2
132 r4 = mem64[ input_0 + 264 ] x2
133 r5 = mem64[ input_0 + 328 ] x2
134 r6 = mem64[ input_0 + 392 ] x2
135 r7 = mem64[ input_0 + 456 ] x2
136 v00 = r0 & mask0
137 2x v10 = r4 << 32
138 2x v01 = r0 unsigned>> 32
139 v11 = r4 & mask1
140 r0 = v00 | v10
141 r4 = v01 | v11
142 v00 = r1 & mask0
143 2x v10 = r5 << 32
144 2x v01 = r1 unsigned>> 32
145 v11 = r5 & mask1
146 r1 = v00 | v10
147 r5 = v01 | v11
148 v00 = r2 & mask0
149 2x v10 = r6 << 32
150 2x v01 = r2 unsigned>> 32
151 v11 = r6 & mask1
152 r2 = v00 | v10
153 r6 = v01 | v11
154 v00 = r3 & mask0
155 2x v10 = r7 << 32
156 2x v01 = r3 unsigned>> 32
157 v11 = r7 & mask1
158 r3 = v00 | v10
159 r7 = v01 | v11
160 v00 = r0 & mask2
161 4x v10 = r2 << 16
162 4x v01 = r0 unsigned>> 16
163 v11 = r2 & mask3
164 r0 = v00 | v10
165 r2 = v01 | v11
166 v00 = r1 & mask2
167 4x v10 = r3 << 16
168 4x v01 = r1 unsigned>> 16
169 v11 = r3 & mask3
170 r1 = v00 | v10
171 r3 = v01 | v11
172 v00 = r4 & mask2
173 4x v10 = r6 << 16
174 4x v01 = r4 unsigned>> 16
175 v11 = r6 & mask3
176 r4 = v00 | v10
177 r6 = v01 | v11
178 v00 = r5 & mask2
179 4x v10 = r7 << 16
180 4x v01 = r5 unsigned>> 16
181 v11 = r7 & mask3
182 r5 = v00 | v10
183 r7 = v01 | v11
184 v00 = r0 & mask4
185 8x v10 = r1 << 8
186 8x v01 = r0 unsigned>> 8
187 v11 = r1 & mask5
188 r0 = v00 | v10
189 r1 = v01 | v11
190 v00 = r2 & mask4
191 8x v10 = r3 << 8
192 8x v01 = r2 unsigned>> 8
193 v11 = r3 & mask5
194 r2 = v00 | v10
195 r3 = v01 | v11
196 v00 = r4 & mask4
197 8x v10 = r5 << 8
198 8x v01 = r4 unsigned>> 8
199 v11 = r5 & mask5
200 r4 = v00 | v10
201 r5 = v01 | v11
202 v00 = r6 & mask4
203 8x v10 = r7 << 8
204 8x v01 = r6 unsigned>> 8
205 v11 = r7 & mask5
206 r6 = v00 | v10
207 r7 = v01 | v11
208 buf = r0[0]
209 mem64[ input_0 + 8 ] = buf
210 buf = r1[0]
211 mem64[ input_0 + 72 ] = buf
212 buf = r2[0]
213 mem64[ input_0 + 136 ] = buf
214 buf = r3[0]
215 mem64[ input_0 + 200 ] = buf
216 buf = r4[0]
217 mem64[ input_0 + 264 ] = buf
218 buf = r5[0]
219 mem64[ input_0 + 328 ] = buf
220 buf = r6[0]
221 mem64[ input_0 + 392 ] = buf
222 buf = r7[0]
223 mem64[ input_0 + 456 ] = buf
224
225 r0 = mem64[ input_0 + 16 ] x2
226 r1 = mem64[ input_0 + 80 ] x2
227 r2 = mem64[ input_0 + 144 ] x2
228 r3 = mem64[ input_0 + 208 ] x2
229 r4 = mem64[ input_0 + 272 ] x2
230 r5 = mem64[ input_0 + 336 ] x2
231 r6 = mem64[ input_0 + 400 ] x2
232 r7 = mem64[ input_0 + 464 ] x2
233 v00 = r0 & mask0
234 2x v10 = r4 << 32
235 2x v01 = r0 unsigned>> 32
236 v11 = r4 & mask1
237 r0 = v00 | v10
238 r4 = v01 | v11
239 v00 = r1 & mask0
240 2x v10 = r5 << 32
241 2x v01 = r1 unsigned>> 32
242 v11 = r5 & mask1
243 r1 = v00 | v10
244 r5 = v01 | v11
245 v00 = r2 & mask0
246 2x v10 = r6 << 32
247 2x v01 = r2 unsigned>> 32
248 v11 = r6 & mask1
249 r2 = v00 | v10
250 r6 = v01 | v11
251 v00 = r3 & mask0
252 2x v10 = r7 << 32
253 2x v01 = r3 unsigned>> 32
254 v11 = r7 & mask1
255 r3 = v00 | v10
256 r7 = v01 | v11
257 v00 = r0 & mask2
258 4x v10 = r2 << 16
259 4x v01 = r0 unsigned>> 16
260 v11 = r2 & mask3
261 r0 = v00 | v10
262 r2 = v01 | v11
263 v00 = r1 & mask2
264 4x v10 = r3 << 16
265 4x v01 = r1 unsigned>> 16
266 v11 = r3 & mask3
267 r1 = v00 | v10
268 r3 = v01 | v11
269 v00 = r4 & mask2
270 4x v10 = r6 << 16
271 4x v01 = r4 unsigned>> 16
272 v11 = r6 & mask3
273 r4 = v00 | v10
274 r6 = v01 | v11
275 v00 = r5 & mask2
276 4x v10 = r7 << 16
277 4x v01 = r5 unsigned>> 16
278 v11 = r7 & mask3
279 r5 = v00 | v10
280 r7 = v01 | v11
281 v00 = r0 & mask4
282 8x v10 = r1 << 8
283 8x v01 = r0 unsigned>> 8
284 v11 = r1 & mask5
285 r0 = v00 | v10
286 r1 = v01 | v11
287 v00 = r2 & mask4
288 8x v10 = r3 << 8
289 8x v01 = r2 unsigned>> 8
290 v11 = r3 & mask5
291 r2 = v00 | v10
292 r3 = v01 | v11
293 v00 = r4 & mask4
294 8x v10 = r5 << 8
295 8x v01 = r4 unsigned>> 8
296 v11 = r5 & mask5
297 r4 = v00 | v10
298 r5 = v01 | v11
299 v00 = r6 & mask4
300 8x v10 = r7 << 8
301 8x v01 = r6 unsigned>> 8
302 v11 = r7 & mask5
303 r6 = v00 | v10
304 r7 = v01 | v11
305 buf = r0[0]
306 mem64[ input_0 + 16 ] = buf
307 buf = r1[0]
308 mem64[ input_0 + 80 ] = buf
309 buf = r2[0]
310 mem64[ input_0 + 144 ] = buf
311 buf = r3[0]
312 mem64[ input_0 + 208 ] = buf
313 buf = r4[0]
314 mem64[ input_0 + 272 ] = buf
315 buf = r5[0]
316 mem64[ input_0 + 336 ] = buf
317 buf = r6[0]
318 mem64[ input_0 + 400 ] = buf
319 buf = r7[0]
320 mem64[ input_0 + 464 ] = buf
321
322 r0 = mem64[ input_0 + 24 ] x2
323 r1 = mem64[ input_0 + 88 ] x2
324 r2 = mem64[ input_0 + 152 ] x2
325 r3 = mem64[ input_0 + 216 ] x2
326 r4 = mem64[ input_0 + 280 ] x2
327 r5 = mem64[ input_0 + 344 ] x2
328 r6 = mem64[ input_0 + 408 ] x2
329 r7 = mem64[ input_0 + 472 ] x2
330 v00 = r0 & mask0
331 2x v10 = r4 << 32
332 2x v01 = r0 unsigned>> 32
333 v11 = r4 & mask1
334 r0 = v00 | v10
335 r4 = v01 | v11
336 v00 = r1 & mask0
337 2x v10 = r5 << 32
338 2x v01 = r1 unsigned>> 32
339 v11 = r5 & mask1
340 r1 = v00 | v10
341 r5 = v01 | v11
342 v00 = r2 & mask0
343 2x v10 = r6 << 32
344 2x v01 = r2 unsigned>> 32
345 v11 = r6 & mask1
346 r2 = v00 | v10
347 r6 = v01 | v11
348 v00 = r3 & mask0
349 2x v10 = r7 << 32
350 2x v01 = r3 unsigned>> 32
351 v11 = r7 & mask1
352 r3 = v00 | v10
353 r7 = v01 | v11
354 v00 = r0 & mask2
355 4x v10 = r2 << 16
356 4x v01 = r0 unsigned>> 16
357 v11 = r2 & mask3
358 r0 = v00 | v10
359 r2 = v01 | v11
360 v00 = r1 & mask2
361 4x v10 = r3 << 16
362 4x v01 = r1 unsigned>> 16
363 v11 = r3 & mask3
364 r1 = v00 | v10
365 r3 = v01 | v11
366 v00 = r4 & mask2
367 4x v10 = r6 << 16
368 4x v01 = r4 unsigned>> 16
369 v11 = r6 & mask3
370 r4 = v00 | v10
371 r6 = v01 | v11
372 v00 = r5 & mask2
373 4x v10 = r7 << 16
374 4x v01 = r5 unsigned>> 16
375 v11 = r7 & mask3
376 r5 = v00 | v10
377 r7 = v01 | v11
378 v00 = r0 & mask4
379 8x v10 = r1 << 8
380 8x v01 = r0 unsigned>> 8
381 v11 = r1 & mask5
382 r0 = v00 | v10
383 r1 = v01 | v11
384 v00 = r2 & mask4
385 8x v10 = r3 << 8
386 8x v01 = r2 unsigned>> 8
387 v11 = r3 & mask5
388 r2 = v00 | v10
389 r3 = v01 | v11
390 v00 = r4 & mask4
391 8x v10 = r5 << 8
392 8x v01 = r4 unsigned>> 8
393 v11 = r5 & mask5
394 r4 = v00 | v10
395 r5 = v01 | v11
396 v00 = r6 & mask4
397 8x v10 = r7 << 8
398 8x v01 = r6 unsigned>> 8
399 v11 = r7 & mask5
400 r6 = v00 | v10
401 r7 = v01 | v11
402 buf = r0[0]
403 mem64[ input_0 + 24 ] = buf
404 buf = r1[0]
405 mem64[ input_0 + 88 ] = buf
406 buf = r2[0]
407 mem64[ input_0 + 152 ] = buf
408 buf = r3[0]
409 mem64[ input_0 + 216 ] = buf
410 buf = r4[0]
411 mem64[ input_0 + 280 ] = buf
412 buf = r5[0]
413 mem64[ input_0 + 344 ] = buf
414 buf = r6[0]
415 mem64[ input_0 + 408 ] = buf
416 buf = r7[0]
417 mem64[ input_0 + 472 ] = buf
418
419 r0 = mem64[ input_0 + 32 ] x2
420 r1 = mem64[ input_0 + 96 ] x2
421 r2 = mem64[ input_0 + 160 ] x2
422 r3 = mem64[ input_0 + 224 ] x2
423 r4 = mem64[ input_0 + 288 ] x2
424 r5 = mem64[ input_0 + 352 ] x2
425 r6 = mem64[ input_0 + 416 ] x2
426 r7 = mem64[ input_0 + 480 ] x2
427 v00 = r0 & mask0
428 2x v10 = r4 << 32
429 2x v01 = r0 unsigned>> 32
430 v11 = r4 & mask1
431 r0 = v00 | v10
432 r4 = v01 | v11
433 v00 = r1 & mask0
434 2x v10 = r5 << 32
435 2x v01 = r1 unsigned>> 32
436 v11 = r5 & mask1
437 r1 = v00 | v10
438 r5 = v01 | v11
439 v00 = r2 & mask0
440 2x v10 = r6 << 32
441 2x v01 = r2 unsigned>> 32
442 v11 = r6 & mask1
443 r2 = v00 | v10
444 r6 = v01 | v11
445 v00 = r3 & mask0
446 2x v10 = r7 << 32
447 2x v01 = r3 unsigned>> 32
448 v11 = r7 & mask1
449 r3 = v00 | v10
450 r7 = v01 | v11
451 v00 = r0 & mask2
452 4x v10 = r2 << 16
453 4x v01 = r0 unsigned>> 16
454 v11 = r2 & mask3
455 r0 = v00 | v10
456 r2 = v01 | v11
457 v00 = r1 & mask2
458 4x v10 = r3 << 16
459 4x v01 = r1 unsigned>> 16
460 v11 = r3 & mask3
461 r1 = v00 | v10
462 r3 = v01 | v11
463 v00 = r4 & mask2
464 4x v10 = r6 << 16
465 4x v01 = r4 unsigned>> 16
466 v11 = r6 & mask3
467 r4 = v00 | v10
468 r6 = v01 | v11
469 v00 = r5 & mask2
470 4x v10 = r7 << 16
471 4x v01 = r5 unsigned>> 16
472 v11 = r7 & mask3
473 r5 = v00 | v10
474 r7 = v01 | v11
475 v00 = r0 & mask4
476 8x v10 = r1 << 8
477 8x v01 = r0 unsigned>> 8
478 v11 = r1 & mask5
479 r0 = v00 | v10
480 r1 = v01 | v11
481 v00 = r2 & mask4
482 8x v10 = r3 << 8
483 8x v01 = r2 unsigned>> 8
484 v11 = r3 & mask5
485 r2 = v00 | v10
486 r3 = v01 | v11
487 v00 = r4 & mask4
488 8x v10 = r5 << 8
489 8x v01 = r4 unsigned>> 8
490 v11 = r5 & mask5
491 r4 = v00 | v10
492 r5 = v01 | v11
493 v00 = r6 & mask4
494 8x v10 = r7 << 8
495 8x v01 = r6 unsigned>> 8
496 v11 = r7 & mask5
497 r6 = v00 | v10
498 r7 = v01 | v11
499 buf = r0[0]
500 mem64[ input_0 + 32 ] = buf
501 buf = r1[0]
502 mem64[ input_0 + 96 ] = buf
503 buf = r2[0]
504 mem64[ input_0 + 160 ] = buf
505 buf = r3[0]
506 mem64[ input_0 + 224 ] = buf
507 buf = r4[0]
508 mem64[ input_0 + 288 ] = buf
509 buf = r5[0]
510 mem64[ input_0 + 352 ] = buf
511 buf = r6[0]
512 mem64[ input_0 + 416 ] = buf
513 buf = r7[0]
514 mem64[ input_0 + 480 ] = buf
515
516 r0 = mem64[ input_0 + 40 ] x2
517 r1 = mem64[ input_0 + 104 ] x2
518 r2 = mem64[ input_0 + 168 ] x2
519 r3 = mem64[ input_0 + 232 ] x2
520 r4 = mem64[ input_0 + 296 ] x2
521 r5 = mem64[ input_0 + 360 ] x2
522 r6 = mem64[ input_0 + 424 ] x2
523 r7 = mem64[ input_0 + 488 ] x2
524 v00 = r0 & mask0
525 2x v10 = r4 << 32
526 2x v01 = r0 unsigned>> 32
527 v11 = r4 & mask1
528 r0 = v00 | v10
529 r4 = v01 | v11
530 v00 = r1 & mask0
531 2x v10 = r5 << 32
532 2x v01 = r1 unsigned>> 32
533 v11 = r5 & mask1
534 r1 = v00 | v10
535 r5 = v01 | v11
536 v00 = r2 & mask0
537 2x v10 = r6 << 32
538 2x v01 = r2 unsigned>> 32
539 v11 = r6 & mask1
540 r2 = v00 | v10
541 r6 = v01 | v11
542 v00 = r3 & mask0
543 2x v10 = r7 << 32
544 2x v01 = r3 unsigned>> 32
545 v11 = r7 & mask1
546 r3 = v00 | v10
547 r7 = v01 | v11
548 v00 = r0 & mask2
549 4x v10 = r2 << 16
550 4x v01 = r0 unsigned>> 16
551 v11 = r2 & mask3
552 r0 = v00 | v10
553 r2 = v01 | v11
554 v00 = r1 & mask2
555 4x v10 = r3 << 16
556 4x v01 = r1 unsigned>> 16
557 v11 = r3 & mask3
558 r1 = v00 | v10
559 r3 = v01 | v11
560 v00 = r4 & mask2
561 4x v10 = r6 << 16
562 4x v01 = r4 unsigned>> 16
563 v11 = r6 & mask3
564 r4 = v00 | v10
565 r6 = v01 | v11
566 v00 = r5 & mask2
567 4x v10 = r7 << 16
568 4x v01 = r5 unsigned>> 16
569 v11 = r7 & mask3
570 r5 = v00 | v10
571 r7 = v01 | v11
572 v00 = r0 & mask4
573 8x v10 = r1 << 8
574 8x v01 = r0 unsigned>> 8
575 v11 = r1 & mask5
576 r0 = v00 | v10
577 r1 = v01 | v11
578 v00 = r2 & mask4
579 8x v10 = r3 << 8
580 8x v01 = r2 unsigned>> 8
581 v11 = r3 & mask5
582 r2 = v00 | v10
583 r3 = v01 | v11
584 v00 = r4 & mask4
585 8x v10 = r5 << 8
586 8x v01 = r4 unsigned>> 8
587 v11 = r5 & mask5
588 r4 = v00 | v10
589 r5 = v01 | v11
590 v00 = r6 & mask4
591 8x v10 = r7 << 8
592 8x v01 = r6 unsigned>> 8
593 v11 = r7 & mask5
594 r6 = v00 | v10
595 r7 = v01 | v11
596 buf = r0[0]
597 mem64[ input_0 + 40 ] = buf
598 buf = r1[0]
599 mem64[ input_0 + 104 ] = buf
600 buf = r2[0]
601 mem64[ input_0 + 168 ] = buf
602 buf = r3[0]
603 mem64[ input_0 + 232 ] = buf
604 buf = r4[0]
605 mem64[ input_0 + 296 ] = buf
606 buf = r5[0]
607 mem64[ input_0 + 360 ] = buf
608 buf = r6[0]
609 mem64[ input_0 + 424 ] = buf
610 buf = r7[0]
611 mem64[ input_0 + 488 ] = buf
612
613 r0 = mem64[ input_0 + 48 ] x2
614 r1 = mem64[ input_0 + 112 ] x2
615 r2 = mem64[ input_0 + 176 ] x2
616 r3 = mem64[ input_0 + 240 ] x2
617 r4 = mem64[ input_0 + 304 ] x2
618 r5 = mem64[ input_0 + 368 ] x2
619 r6 = mem64[ input_0 + 432 ] x2
620 r7 = mem64[ input_0 + 496 ] x2
621 v00 = r0 & mask0
622 2x v10 = r4 << 32
623 2x v01 = r0 unsigned>> 32
624 v11 = r4 & mask1
625 r0 = v00 | v10
626 r4 = v01 | v11
627 v00 = r1 & mask0
628 2x v10 = r5 << 32
629 2x v01 = r1 unsigned>> 32
630 v11 = r5 & mask1
631 r1 = v00 | v10
632 r5 = v01 | v11
633 v00 = r2 & mask0
634 2x v10 = r6 << 32
635 2x v01 = r2 unsigned>> 32
636 v11 = r6 & mask1
637 r2 = v00 | v10
638 r6 = v01 | v11
639 v00 = r3 & mask0
640 2x v10 = r7 << 32
641 2x v01 = r3 unsigned>> 32
642 v11 = r7 & mask1
643 r3 = v00 | v10
644 r7 = v01 | v11
645 v00 = r0 & mask2
646 4x v10 = r2 << 16
647 4x v01 = r0 unsigned>> 16
648 v11 = r2 & mask3
649 r0 = v00 | v10
650 r2 = v01 | v11
651 v00 = r1 & mask2
652 4x v10 = r3 << 16
653 4x v01 = r1 unsigned>> 16
654 v11 = r3 & mask3
655 r1 = v00 | v10
656 r3 = v01 | v11
657 v00 = r4 & mask2
658 4x v10 = r6 << 16
659 4x v01 = r4 unsigned>> 16
660 v11 = r6 & mask3
661 r4 = v00 | v10
662 r6 = v01 | v11
663 v00 = r5 & mask2
664 4x v10 = r7 << 16
665 4x v01 = r5 unsigned>> 16
666 v11 = r7 & mask3
667 r5 = v00 | v10
668 r7 = v01 | v11
669 v00 = r0 & mask4
670 8x v10 = r1 << 8
671 8x v01 = r0 unsigned>> 8
672 v11 = r1 & mask5
673 r0 = v00 | v10
674 r1 = v01 | v11
675 v00 = r2 & mask4
676 8x v10 = r3 << 8
677 8x v01 = r2 unsigned>> 8
678 v11 = r3 & mask5
679 r2 = v00 | v10
680 r3 = v01 | v11
681 v00 = r4 & mask4
682 8x v10 = r5 << 8
683 8x v01 = r4 unsigned>> 8
684 v11 = r5 & mask5
685 r4 = v00 | v10
686 r5 = v01 | v11
687 v00 = r6 & mask4
688 8x v10 = r7 << 8
689 8x v01 = r6 unsigned>> 8
690 v11 = r7 & mask5
691 r6 = v00 | v10
692 r7 = v01 | v11
693 buf = r0[0]
694 mem64[ input_0 + 48 ] = buf
695 buf = r1[0]
696 mem64[ input_0 + 112 ] = buf
697 buf = r2[0]
698 mem64[ input_0 + 176 ] = buf
699 buf = r3[0]
700 mem64[ input_0 + 240 ] = buf
701 buf = r4[0]
702 mem64[ input_0 + 304 ] = buf
703 buf = r5[0]
704 mem64[ input_0 + 368 ] = buf
705 buf = r6[0]
706 mem64[ input_0 + 432 ] = buf
707 buf = r7[0]
708 mem64[ input_0 + 496 ] = buf
709
710 r0 = mem64[ input_0 + 56 ] x2
711 r1 = mem64[ input_0 + 120 ] x2
712 r2 = mem64[ input_0 + 184 ] x2
713 r3 = mem64[ input_0 + 248 ] x2
714 r4 = mem64[ input_0 + 312 ] x2
715 r5 = mem64[ input_0 + 376 ] x2
716 r6 = mem64[ input_0 + 440 ] x2
717 r7 = mem64[ input_0 + 504 ] x2
718 v00 = r0 & mask0
719 2x v10 = r4 << 32
720 2x v01 = r0 unsigned>> 32
721 v11 = r4 & mask1
722 r0 = v00 | v10
723 r4 = v01 | v11
724 v00 = r1 & mask0
725 2x v10 = r5 << 32
726 2x v01 = r1 unsigned>> 32
727 v11 = r5 & mask1
728 r1 = v00 | v10
729 r5 = v01 | v11
730 v00 = r2 & mask0
731 2x v10 = r6 << 32
732 2x v01 = r2 unsigned>> 32
733 v11 = r6 & mask1
734 r2 = v00 | v10
735 r6 = v01 | v11
736 v00 = r3 & mask0
737 2x v10 = r7 << 32
738 2x v01 = r3 unsigned>> 32
739 v11 = r7 & mask1
740 r3 = v00 | v10
741 r7 = v01 | v11
742 v00 = r0 & mask2
743 4x v10 = r2 << 16
744 4x v01 = r0 unsigned>> 16
745 v11 = r2 & mask3
746 r0 = v00 | v10
747 r2 = v01 | v11
748 v00 = r1 & mask2
749 4x v10 = r3 << 16
750 4x v01 = r1 unsigned>> 16
751 v11 = r3 & mask3
752 r1 = v00 | v10
753 r3 = v01 | v11
754 v00 = r4 & mask2
755 4x v10 = r6 << 16
756 4x v01 = r4 unsigned>> 16
757 v11 = r6 & mask3
758 r4 = v00 | v10
759 r6 = v01 | v11
760 v00 = r5 & mask2
761 4x v10 = r7 << 16
762 4x v01 = r5 unsigned>> 16
763 v11 = r7 & mask3
764 r5 = v00 | v10
765 r7 = v01 | v11
766 v00 = r0 & mask4
767 8x v10 = r1 << 8
768 8x v01 = r0 unsigned>> 8
769 v11 = r1 & mask5
770 r0 = v00 | v10
771 r1 = v01 | v11
772 v00 = r2 & mask4
773 8x v10 = r3 << 8
774 8x v01 = r2 unsigned>> 8
775 v11 = r3 & mask5
776 r2 = v00 | v10
777 r3 = v01 | v11
778 v00 = r4 & mask4
779 8x v10 = r5 << 8
780 8x v01 = r4 unsigned>> 8
781 v11 = r5 & mask5
782 r4 = v00 | v10
783 r5 = v01 | v11
784 v00 = r6 & mask4
785 8x v10 = r7 << 8
786 8x v01 = r6 unsigned>> 8
787 v11 = r7 & mask5
788 r6 = v00 | v10
789 r7 = v01 | v11
790 buf = r0[0]
791 mem64[ input_0 + 56 ] = buf
792 buf = r1[0]
793 mem64[ input_0 + 120 ] = buf
794 buf = r2[0]
795 mem64[ input_0 + 184 ] = buf
796 buf = r3[0]
797 mem64[ input_0 + 248 ] = buf
798 buf = r4[0]
799 mem64[ input_0 + 312 ] = buf
800 buf = r5[0]
801 mem64[ input_0 + 376 ] = buf
802 buf = r6[0]
803 mem64[ input_0 + 440 ] = buf
804 buf = r7[0]
805 mem64[ input_0 + 504 ] = buf
806
807 mask0 aligned= mem128[ MASK2_0 ]
808 mask1 aligned= mem128[ MASK2_1 ]
809 mask2 aligned= mem128[ MASK1_0 ]
810 mask3 aligned= mem128[ MASK1_1 ]
811 mask4 aligned= mem128[ MASK0_0 ]
812 mask5 aligned= mem128[ MASK0_1 ]
813 r0 = mem64[ input_0 + 0 ] x2
814 r1 = mem64[ input_0 + 8 ] x2
815 r2 = mem64[ input_0 + 16 ] x2
816 r3 = mem64[ input_0 + 24 ] x2
817 r4 = mem64[ input_0 + 32 ] x2
818 r5 = mem64[ input_0 + 40 ] x2
819 r6 = mem64[ input_0 + 48 ] x2
820 r7 = mem64[ input_0 + 56 ] x2
821 v00 = r0 & mask0
822 v10 = r4 & mask0
823 2x v10 <<= 4
824 v01 = r0 & mask1
825 v11 = r4 & mask1
826 2x v01 unsigned>>= 4
827 r0 = v00 | v10
828 r4 = v01 | v11
829 v00 = r1 & mask0
830 v10 = r5 & mask0
831 2x v10 <<= 4
832 v01 = r1 & mask1
833 v11 = r5 & mask1
834 2x v01 unsigned>>= 4
835 r1 = v00 | v10
836 r5 = v01 | v11
837 v00 = r2 & mask0
838 v10 = r6 & mask0
839 2x v10 <<= 4
840 v01 = r2 & mask1
841 v11 = r6 & mask1
842 2x v01 unsigned>>= 4
843 r2 = v00 | v10
844 r6 = v01 | v11
845 v00 = r3 & mask0
846 v10 = r7 & mask0
847 2x v10 <<= 4
848 v01 = r3 & mask1
849 v11 = r7 & mask1
850 2x v01 unsigned>>= 4
851 r3 = v00 | v10
852 r7 = v01 | v11
853 v00 = r0 & mask2
854 v10 = r2 & mask2
855 2x v10 <<= 2
856 v01 = r0 & mask3
857 v11 = r2 & mask3
858 2x v01 unsigned>>= 2
859 r0 = v00 | v10
860 r2 = v01 | v11
861 v00 = r1 & mask2
862 v10 = r3 & mask2
863 2x v10 <<= 2
864 v01 = r1 & mask3
865 v11 = r3 & mask3
866 2x v01 unsigned>>= 2
867 r1 = v00 | v10
868 r3 = v01 | v11
869 v00 = r4 & mask2
870 v10 = r6 & mask2
871 2x v10 <<= 2
872 v01 = r4 & mask3
873 v11 = r6 & mask3
874 2x v01 unsigned>>= 2
875 r4 = v00 | v10
876 r6 = v01 | v11
877 v00 = r5 & mask2
878 v10 = r7 & mask2
879 2x v10 <<= 2
880 v01 = r5 & mask3
881 v11 = r7 & mask3
882 2x v01 unsigned>>= 2
883 r5 = v00 | v10
884 r7 = v01 | v11
885 v00 = r0 & mask4
886 v10 = r1 & mask4
887 2x v10 <<= 1
888 v01 = r0 & mask5
889 v11 = r1 & mask5
890 2x v01 unsigned>>= 1
891 r0 = v00 | v10
892 r1 = v01 | v11
893 v00 = r2 & mask4
894 v10 = r3 & mask4
895 2x v10 <<= 1
896 v01 = r2 & mask5
897 v11 = r3 & mask5
898 2x v01 unsigned>>= 1
899 r2 = v00 | v10
900 r3 = v01 | v11
901 v00 = r4 & mask4
902 v10 = r5 & mask4
903 2x v10 <<= 1
904 v01 = r4 & mask5
905 v11 = r5 & mask5
906 2x v01 unsigned>>= 1
907 r4 = v00 | v10
908 r5 = v01 | v11
909 v00 = r6 & mask4
910 v10 = r7 & mask4
911 2x v10 <<= 1
912 v01 = r6 & mask5
913 v11 = r7 & mask5
914 2x v01 unsigned>>= 1
915 r6 = v00 | v10
916 r7 = v01 | v11
917 t0 = r0[0]r1[0]
918 mem128[ input_0 + 0 ] = t0
919 t0 = r2[0]r3[0]
920 mem128[ input_0 + 16 ] = t0
921 t0 = r4[0]r5[0]
922 mem128[ input_0 + 32 ] = t0
923 t0 = r6[0]r7[0]
924 mem128[ input_0 + 48 ] = t0
925
926 r0 = mem64[ input_0 + 64 ] x2
927 r1 = mem64[ input_0 + 72 ] x2
928 r2 = mem64[ input_0 + 80 ] x2
929 r3 = mem64[ input_0 + 88 ] x2
930 r4 = mem64[ input_0 + 96 ] x2
931 r5 = mem64[ input_0 + 104 ] x2
932 r6 = mem64[ input_0 + 112 ] x2
933 r7 = mem64[ input_0 + 120 ] x2
934 v00 = r0 & mask0
935 v10 = r4 & mask0
936 2x v10 <<= 4
937 v01 = r0 & mask1
938 v11 = r4 & mask1
939 2x v01 unsigned>>= 4
940 r0 = v00 | v10
941 r4 = v01 | v11
942 v00 = r1 & mask0
943 v10 = r5 & mask0
944 2x v10 <<= 4
945 v01 = r1 & mask1
946 v11 = r5 & mask1
947 2x v01 unsigned>>= 4
948 r1 = v00 | v10
949 r5 = v01 | v11
950 v00 = r2 & mask0
951 v10 = r6 & mask0
952 2x v10 <<= 4
953 v01 = r2 & mask1
954 v11 = r6 & mask1
955 2x v01 unsigned>>= 4
956 r2 = v00 | v10
957 r6 = v01 | v11
958 v00 = r3 & mask0
959 v10 = r7 & mask0
960 2x v10 <<= 4
961 v01 = r3 & mask1
962 v11 = r7 & mask1
963 2x v01 unsigned>>= 4
964 r3 = v00 | v10
965 r7 = v01 | v11
966 v00 = r0 & mask2
967 v10 = r2 & mask2
968 2x v10 <<= 2
969 v01 = r0 & mask3
970 v11 = r2 & mask3
971 2x v01 unsigned>>= 2
972 r0 = v00 | v10
973 r2 = v01 | v11
974 v00 = r1 & mask2
975 v10 = r3 & mask2
976 2x v10 <<= 2
977 v01 = r1 & mask3
978 v11 = r3 & mask3
979 2x v01 unsigned>>= 2
980 r1 = v00 | v10
981 r3 = v01 | v11
982 v00 = r4 & mask2
983 v10 = r6 & mask2
984 2x v10 <<= 2
985 v01 = r4 & mask3
986 v11 = r6 & mask3
987 2x v01 unsigned>>= 2
988 r4 = v00 | v10
989 r6 = v01 | v11
990 v00 = r5 & mask2
991 v10 = r7 & mask2
992 2x v10 <<= 2
993 v01 = r5 & mask3
994 v11 = r7 & mask3
995 2x v01 unsigned>>= 2
996 r5 = v00 | v10
997 r7 = v01 | v11
998 v00 = r0 & mask4
999 v10 = r1 & mask4
1000 2x v10 <<= 1
1001 v01 = r0 & mask5
1002 v11 = r1 & mask5
1003 2x v01 unsigned>>= 1
1004 r0 = v00 | v10
1005 r1 = v01 | v11
1006 v00 = r2 & mask4
1007 v10 = r3 & mask4
1008 2x v10 <<= 1
1009 v01 = r2 & mask5
1010 v11 = r3 & mask5
1011 2x v01 unsigned>>= 1
1012 r2 = v00 | v10
1013 r3 = v01 | v11
1014 v00 = r4 & mask4
1015 v10 = r5 & mask4
1016 2x v10 <<= 1
1017 v01 = r4 & mask5
1018 v11 = r5 & mask5
1019 2x v01 unsigned>>= 1
1020 r4 = v00 | v10
1021 r5 = v01 | v11
1022 v00 = r6 & mask4
1023 v10 = r7 & mask4
1024 2x v10 <<= 1
1025 v01 = r6 & mask5
1026 v11 = r7 & mask5
1027 2x v01 unsigned>>= 1
1028 r6 = v00 | v10
1029 r7 = v01 | v11
1030 t0 = r0[0]r1[0]
1031 mem128[ input_0 + 64 ] = t0
1032 t0 = r2[0]r3[0]
1033 mem128[ input_0 + 80 ] = t0
1034 t0 = r4[0]r5[0]
1035 mem128[ input_0 + 96 ] = t0
1036 t0 = r6[0]r7[0]
1037 mem128[ input_0 + 112 ] = t0
1038
1039 r0 = mem64[ input_0 + 128 ] x2
1040 r1 = mem64[ input_0 + 136 ] x2
1041 r2 = mem64[ input_0 + 144 ] x2
1042 r3 = mem64[ input_0 + 152 ] x2
1043 r4 = mem64[ input_0 + 160 ] x2
1044 r5 = mem64[ input_0 + 168 ] x2
1045 r6 = mem64[ input_0 + 176 ] x2
1046 r7 = mem64[ input_0 + 184 ] x2
1047 v00 = r0 & mask0
1048 v10 = r4 & mask0
1049 2x v10 <<= 4
1050 v01 = r0 & mask1
1051 v11 = r4 & mask1
1052 2x v01 unsigned>>= 4
1053 r0 = v00 | v10
1054 r4 = v01 | v11
1055 v00 = r1 & mask0
1056 v10 = r5 & mask0
1057 2x v10 <<= 4
1058 v01 = r1 & mask1
1059 v11 = r5 & mask1
1060 2x v01 unsigned>>= 4
1061 r1 = v00 | v10
1062 r5 = v01 | v11
1063 v00 = r2 & mask0
1064 v10 = r6 & mask0
1065 2x v10 <<= 4
1066 v01 = r2 & mask1
1067 v11 = r6 & mask1
1068 2x v01 unsigned>>= 4
1069 r2 = v00 | v10
1070 r6 = v01 | v11
1071 v00 = r3 & mask0
1072 v10 = r7 & mask0
1073 2x v10 <<= 4
1074 v01 = r3 & mask1
1075 v11 = r7 & mask1
1076 2x v01 unsigned>>= 4
1077 r3 = v00 | v10
1078 r7 = v01 | v11
1079 v00 = r0 & mask2
1080 v10 = r2 & mask2
1081 2x v10 <<= 2
1082 v01 = r0 & mask3
1083 v11 = r2 & mask3
1084 2x v01 unsigned>>= 2
1085 r0 = v00 | v10
1086 r2 = v01 | v11
1087 v00 = r1 & mask2
1088 v10 = r3 & mask2
1089 2x v10 <<= 2
1090 v01 = r1 & mask3
1091 v11 = r3 & mask3
1092 2x v01 unsigned>>= 2
1093 r1 = v00 | v10
1094 r3 = v01 | v11
1095 v00 = r4 & mask2
1096 v10 = r6 & mask2
1097 2x v10 <<= 2
1098 v01 = r4 & mask3
1099 v11 = r6 & mask3
1100 2x v01 unsigned>>= 2
1101 r4 = v00 | v10
1102 r6 = v01 | v11
1103 v00 = r5 & mask2
1104 v10 = r7 & mask2
1105 2x v10 <<= 2
1106 v01 = r5 & mask3
1107 v11 = r7 & mask3
1108 2x v01 unsigned>>= 2
1109 r5 = v00 | v10
1110 r7 = v01 | v11
1111 v00 = r0 & mask4
1112 v10 = r1 & mask4
1113 2x v10 <<= 1
1114 v01 = r0 & mask5
1115 v11 = r1 & mask5
1116 2x v01 unsigned>>= 1
1117 r0 = v00 | v10
1118 r1 = v01 | v11
1119 v00 = r2 & mask4
1120 v10 = r3 & mask4
1121 2x v10 <<= 1
1122 v01 = r2 & mask5
1123 v11 = r3 & mask5
1124 2x v01 unsigned>>= 1
1125 r2 = v00 | v10
1126 r3 = v01 | v11
1127 v00 = r4 & mask4
1128 v10 = r5 & mask4
1129 2x v10 <<= 1
1130 v01 = r4 & mask5
1131 v11 = r5 & mask5
1132 2x v01 unsigned>>= 1
1133 r4 = v00 | v10
1134 r5 = v01 | v11
1135 v00 = r6 & mask4
1136 v10 = r7 & mask4
1137 2x v10 <<= 1
1138 v01 = r6 & mask5
1139 v11 = r7 & mask5
1140 2x v01 unsigned>>= 1
1141 r6 = v00 | v10
1142 r7 = v01 | v11
1143 t0 = r0[0]r1[0]
1144 mem128[ input_0 + 128 ] = t0
1145 t0 = r2[0]r3[0]
1146 mem128[ input_0 + 144 ] = t0
1147 t0 = r4[0]r5[0]
1148 mem128[ input_0 + 160 ] = t0
1149 t0 = r6[0]r7[0]
1150 mem128[ input_0 + 176 ] = t0
1151
1152 r0 = mem64[ input_0 + 192 ] x2
1153 r1 = mem64[ input_0 + 200 ] x2
1154 r2 = mem64[ input_0 + 208 ] x2
1155 r3 = mem64[ input_0 + 216 ] x2
1156 r4 = mem64[ input_0 + 224 ] x2
1157 r5 = mem64[ input_0 + 232 ] x2
1158 r6 = mem64[ input_0 + 240 ] x2
1159 r7 = mem64[ input_0 + 248 ] x2
1160 v00 = r0 & mask0
1161 v10 = r4 & mask0
1162 2x v10 <<= 4
1163 v01 = r0 & mask1
1164 v11 = r4 & mask1
1165 2x v01 unsigned>>= 4
1166 r0 = v00 | v10
1167 r4 = v01 | v11
1168 v00 = r1 & mask0
1169 v10 = r5 & mask0
1170 2x v10 <<= 4
1171 v01 = r1 & mask1
1172 v11 = r5 & mask1
1173 2x v01 unsigned>>= 4
1174 r1 = v00 | v10
1175 r5 = v01 | v11
1176 v00 = r2 & mask0
1177 v10 = r6 & mask0
1178 2x v10 <<= 4
1179 v01 = r2 & mask1
1180 v11 = r6 & mask1
1181 2x v01 unsigned>>= 4
1182 r2 = v00 | v10
1183 r6 = v01 | v11
1184 v00 = r3 & mask0
1185 v10 = r7 & mask0
1186 2x v10 <<= 4
1187 v01 = r3 & mask1
1188 v11 = r7 & mask1
1189 2x v01 unsigned>>= 4
1190 r3 = v00 | v10
1191 r7 = v01 | v11
1192 v00 = r0 & mask2
1193 v10 = r2 & mask2
1194 2x v10 <<= 2
1195 v01 = r0 & mask3
1196 v11 = r2 & mask3
1197 2x v01 unsigned>>= 2
1198 r0 = v00 | v10
1199 r2 = v01 | v11
1200 v00 = r1 & mask2
1201 v10 = r3 & mask2
1202 2x v10 <<= 2
1203 v01 = r1 & mask3
1204 v11 = r3 & mask3
1205 2x v01 unsigned>>= 2
1206 r1 = v00 | v10
1207 r3 = v01 | v11
1208 v00 = r4 & mask2
1209 v10 = r6 & mask2
1210 2x v10 <<= 2
1211 v01 = r4 & mask3
1212 v11 = r6 & mask3
1213 2x v01 unsigned>>= 2
1214 r4 = v00 | v10
1215 r6 = v01 | v11
1216 v00 = r5 & mask2
1217 v10 = r7 & mask2
1218 2x v10 <<= 2
1219 v01 = r5 & mask3
1220 v11 = r7 & mask3
1221 2x v01 unsigned>>= 2
1222 r5 = v00 | v10
1223 r7 = v01 | v11
1224 v00 = r0 & mask4
1225 v10 = r1 & mask4
1226 2x v10 <<= 1
1227 v01 = r0 & mask5
1228 v11 = r1 & mask5
1229 2x v01 unsigned>>= 1
1230 r0 = v00 | v10
1231 r1 = v01 | v11
1232 v00 = r2 & mask4
1233 v10 = r3 & mask4
1234 2x v10 <<= 1
1235 v01 = r2 & mask5
1236 v11 = r3 & mask5
1237 2x v01 unsigned>>= 1
1238 r2 = v00 | v10
1239 r3 = v01 | v11
1240 v00 = r4 & mask4
1241 v10 = r5 & mask4
1242 2x v10 <<= 1
1243 v01 = r4 & mask5
1244 v11 = r5 & mask5
1245 2x v01 unsigned>>= 1
1246 r4 = v00 | v10
1247 r5 = v01 | v11
1248 v00 = r6 & mask4
1249 v10 = r7 & mask4
1250 2x v10 <<= 1
1251 v01 = r6 & mask5
1252 v11 = r7 & mask5
1253 2x v01 unsigned>>= 1
1254 r6 = v00 | v10
1255 r7 = v01 | v11
1256 t0 = r0[0]r1[0]
1257 mem128[ input_0 + 192 ] = t0
1258 t0 = r2[0]r3[0]
1259 mem128[ input_0 + 208 ] = t0
1260 t0 = r4[0]r5[0]
1261 mem128[ input_0 + 224 ] = t0
1262 t0 = r6[0]r7[0]
1263 mem128[ input_0 + 240 ] = t0
1264
1265 r0 = mem64[ input_0 + 256 ] x2
1266 r1 = mem64[ input_0 + 264 ] x2
1267 r2 = mem64[ input_0 + 272 ] x2
1268 r3 = mem64[ input_0 + 280 ] x2
1269 r4 = mem64[ input_0 + 288 ] x2
1270 r5 = mem64[ input_0 + 296 ] x2
1271 r6 = mem64[ input_0 + 304 ] x2
1272 r7 = mem64[ input_0 + 312 ] x2
1273 v00 = r0 & mask0
1274 v10 = r4 & mask0
1275 2x v10 <<= 4
1276 v01 = r0 & mask1
1277 v11 = r4 & mask1
1278 2x v01 unsigned>>= 4
1279 r0 = v00 | v10
1280 r4 = v01 | v11
1281 v00 = r1 & mask0
1282 v10 = r5 & mask0
1283 2x v10 <<= 4
1284 v01 = r1 & mask1
1285 v11 = r5 & mask1
1286 2x v01 unsigned>>= 4
1287 r1 = v00 | v10
1288 r5 = v01 | v11
1289 v00 = r2 & mask0
1290 v10 = r6 & mask0
1291 2x v10 <<= 4
1292 v01 = r2 & mask1
1293 v11 = r6 & mask1
1294 2x v01 unsigned>>= 4
1295 r2 = v00 | v10
1296 r6 = v01 | v11
1297 v00 = r3 & mask0
1298 v10 = r7 & mask0
1299 2x v10 <<= 4
1300 v01 = r3 & mask1
1301 v11 = r7 & mask1
1302 2x v01 unsigned>>= 4
1303 r3 = v00 | v10
1304 r7 = v01 | v11
1305 v00 = r0 & mask2
1306 v10 = r2 & mask2
1307 2x v10 <<= 2
1308 v01 = r0 & mask3
1309 v11 = r2 & mask3
1310 2x v01 unsigned>>= 2
1311 r0 = v00 | v10
1312 r2 = v01 | v11
1313 v00 = r1 & mask2
1314 v10 = r3 & mask2
1315 2x v10 <<= 2
1316 v01 = r1 & mask3
1317 v11 = r3 & mask3
1318 2x v01 unsigned>>= 2
1319 r1 = v00 | v10
1320 r3 = v01 | v11
1321 v00 = r4 & mask2
1322 v10 = r6 & mask2
1323 2x v10 <<= 2
1324 v01 = r4 & mask3
1325 v11 = r6 & mask3
1326 2x v01 unsigned>>= 2
1327 r4 = v00 | v10
1328 r6 = v01 | v11
1329 v00 = r5 & mask2
1330 v10 = r7 & mask2
1331 2x v10 <<= 2
1332 v01 = r5 & mask3
1333 v11 = r7 & mask3
1334 2x v01 unsigned>>= 2
1335 r5 = v00 | v10
1336 r7 = v01 | v11
1337 v00 = r0 & mask4
1338 v10 = r1 & mask4
1339 2x v10 <<= 1
1340 v01 = r0 & mask5
1341 v11 = r1 & mask5
1342 2x v01 unsigned>>= 1
1343 r0 = v00 | v10
1344 r1 = v01 | v11
1345 v00 = r2 & mask4
1346 v10 = r3 & mask4
1347 2x v10 <<= 1
1348 v01 = r2 & mask5
1349 v11 = r3 & mask5
1350 2x v01 unsigned>>= 1
1351 r2 = v00 | v10
1352 r3 = v01 | v11
1353 v00 = r4 & mask4
1354 v10 = r5 & mask4
1355 2x v10 <<= 1
1356 v01 = r4 & mask5
1357 v11 = r5 & mask5
1358 2x v01 unsigned>>= 1
1359 r4 = v00 | v10
1360 r5 = v01 | v11
1361 v00 = r6 & mask4
1362 v10 = r7 & mask4
1363 2x v10 <<= 1
1364 v01 = r6 & mask5
1365 v11 = r7 & mask5
1366 2x v01 unsigned>>= 1
1367 r6 = v00 | v10
1368 r7 = v01 | v11
1369 t0 = r0[0]r1[0]
1370 mem128[ input_0 + 256 ] = t0
1371 t0 = r2[0]r3[0]
1372 mem128[ input_0 + 272 ] = t0
1373 t0 = r4[0]r5[0]
1374 mem128[ input_0 + 288 ] = t0
1375 t0 = r6[0]r7[0]
1376 mem128[ input_0 + 304 ] = t0
1377
1378 r0 = mem64[ input_0 + 320 ] x2
1379 r1 = mem64[ input_0 + 328 ] x2
1380 r2 = mem64[ input_0 + 336 ] x2
1381 r3 = mem64[ input_0 + 344 ] x2
1382 r4 = mem64[ input_0 + 352 ] x2
1383 r5 = mem64[ input_0 + 360 ] x2
1384 r6 = mem64[ input_0 + 368 ] x2
1385 r7 = mem64[ input_0 + 376 ] x2
1386 v00 = r0 & mask0
1387 v10 = r4 & mask0
1388 2x v10 <<= 4
1389 v01 = r0 & mask1
1390 v11 = r4 & mask1
1391 2x v01 unsigned>>= 4
1392 r0 = v00 | v10
1393 r4 = v01 | v11
1394 v00 = r1 & mask0
1395 v10 = r5 & mask0
1396 2x v10 <<= 4
1397 v01 = r1 & mask1
1398 v11 = r5 & mask1
1399 2x v01 unsigned>>= 4
1400 r1 = v00 | v10
1401 r5 = v01 | v11
1402 v00 = r2 & mask0
1403 v10 = r6 & mask0
1404 2x v10 <<= 4
1405 v01 = r2 & mask1
1406 v11 = r6 & mask1
1407 2x v01 unsigned>>= 4
1408 r2 = v00 | v10
1409 r6 = v01 | v11
1410 v00 = r3 & mask0
1411 v10 = r7 & mask0
1412 2x v10 <<= 4
1413 v01 = r3 & mask1
1414 v11 = r7 & mask1
1415 2x v01 unsigned>>= 4
1416 r3 = v00 | v10
1417 r7 = v01 | v11
1418 v00 = r0 & mask2
1419 v10 = r2 & mask2
1420 2x v10 <<= 2
1421 v01 = r0 & mask3
1422 v11 = r2 & mask3
1423 2x v01 unsigned>>= 2
1424 r0 = v00 | v10
1425 r2 = v01 | v11
1426 v00 = r1 & mask2
1427 v10 = r3 & mask2
1428 2x v10 <<= 2
1429 v01 = r1 & mask3
1430 v11 = r3 & mask3
1431 2x v01 unsigned>>= 2
1432 r1 = v00 | v10
1433 r3 = v01 | v11
1434 v00 = r4 & mask2
1435 v10 = r6 & mask2
1436 2x v10 <<= 2
1437 v01 = r4 & mask3
1438 v11 = r6 & mask3
1439 2x v01 unsigned>>= 2
1440 r4 = v00 | v10
1441 r6 = v01 | v11
1442 v00 = r5 & mask2
1443 v10 = r7 & mask2
1444 2x v10 <<= 2
1445 v01 = r5 & mask3
1446 v11 = r7 & mask3
1447 2x v01 unsigned>>= 2
1448 r5 = v00 | v10
1449 r7 = v01 | v11
1450 v00 = r0 & mask4
1451 v10 = r1 & mask4
1452 2x v10 <<= 1
1453 v01 = r0 & mask5
1454 v11 = r1 & mask5
1455 2x v01 unsigned>>= 1
1456 r0 = v00 | v10
1457 r1 = v01 | v11
1458 v00 = r2 & mask4
1459 v10 = r3 & mask4
1460 2x v10 <<= 1
1461 v01 = r2 & mask5
1462 v11 = r3 & mask5
1463 2x v01 unsigned>>= 1
1464 r2 = v00 | v10
1465 r3 = v01 | v11
1466 v00 = r4 & mask4
1467 v10 = r5 & mask4
1468 2x v10 <<= 1
1469 v01 = r4 & mask5
1470 v11 = r5 & mask5
1471 2x v01 unsigned>>= 1
1472 r4 = v00 | v10
1473 r5 = v01 | v11
1474 v00 = r6 & mask4
1475 v10 = r7 & mask4
1476 2x v10 <<= 1
1477 v01 = r6 & mask5
1478 v11 = r7 & mask5
1479 2x v01 unsigned>>= 1
1480 r6 = v00 | v10
1481 r7 = v01 | v11
1482 t0 = r0[0]r1[0]
1483 mem128[ input_0 + 320 ] = t0
1484 t0 = r2[0]r3[0]
1485 mem128[ input_0 + 336 ] = t0
1486 t0 = r4[0]r5[0]
1487 mem128[ input_0 + 352 ] = t0
1488 t0 = r6[0]r7[0]
1489 mem128[ input_0 + 368 ] = t0
1490
1491 r0 = mem64[ input_0 + 384 ] x2
1492 r1 = mem64[ input_0 + 392 ] x2
1493 r2 = mem64[ input_0 + 400 ] x2
1494 r3 = mem64[ input_0 + 408 ] x2
1495 r4 = mem64[ input_0 + 416 ] x2
1496 r5 = mem64[ input_0 + 424 ] x2
1497 r6 = mem64[ input_0 + 432 ] x2
1498 r7 = mem64[ input_0 + 440 ] x2
1499 v00 = r0 & mask0
1500 v10 = r4 & mask0
1501 2x v10 <<= 4
1502 v01 = r0 & mask1
1503 v11 = r4 & mask1
1504 2x v01 unsigned>>= 4
1505 r0 = v00 | v10
1506 r4 = v01 | v11
1507 v00 = r1 & mask0
1508 v10 = r5 & mask0
1509 2x v10 <<= 4
1510 v01 = r1 & mask1
1511 v11 = r5 & mask1
1512 2x v01 unsigned>>= 4
1513 r1 = v00 | v10
1514 r5 = v01 | v11
1515 v00 = r2 & mask0
1516 v10 = r6 & mask0
1517 2x v10 <<= 4
1518 v01 = r2 & mask1
1519 v11 = r6 & mask1
1520 2x v01 unsigned>>= 4
1521 r2 = v00 | v10
1522 r6 = v01 | v11
1523 v00 = r3 & mask0
1524 v10 = r7 & mask0
1525 2x v10 <<= 4
1526 v01 = r3 & mask1
1527 v11 = r7 & mask1
1528 2x v01 unsigned>>= 4
1529 r3 = v00 | v10
1530 r7 = v01 | v11
1531 v00 = r0 & mask2
1532 v10 = r2 & mask2
1533 2x v10 <<= 2
1534 v01 = r0 & mask3
1535 v11 = r2 & mask3
1536 2x v01 unsigned>>= 2
1537 r0 = v00 | v10
1538 r2 = v01 | v11
1539 v00 = r1 & mask2
1540 v10 = r3 & mask2
1541 2x v10 <<= 2
1542 v01 = r1 & mask3
1543 v11 = r3 & mask3
1544 2x v01 unsigned>>= 2
1545 r1 = v00 | v10
1546 r3 = v01 | v11
1547 v00 = r4 & mask2
1548 v10 = r6 & mask2
1549 2x v10 <<= 2
1550 v01 = r4 & mask3
1551 v11 = r6 & mask3
1552 2x v01 unsigned>>= 2
1553 r4 = v00 | v10
1554 r6 = v01 | v11
1555 v00 = r5 & mask2
1556 v10 = r7 & mask2
1557 2x v10 <<= 2
1558 v01 = r5 & mask3
1559 v11 = r7 & mask3
1560 2x v01 unsigned>>= 2
1561 r5 = v00 | v10
1562 r7 = v01 | v11
1563 v00 = r0 & mask4
1564 v10 = r1 & mask4
1565 2x v10 <<= 1
1566 v01 = r0 & mask5
1567 v11 = r1 & mask5
1568 2x v01 unsigned>>= 1
1569 r0 = v00 | v10
1570 r1 = v01 | v11
1571 v00 = r2 & mask4
1572 v10 = r3 & mask4
1573 2x v10 <<= 1
1574 v01 = r2 & mask5
1575 v11 = r3 & mask5
1576 2x v01 unsigned>>= 1
1577 r2 = v00 | v10
1578 r3 = v01 | v11
1579 v00 = r4 & mask4
1580 v10 = r5 & mask4
1581 2x v10 <<= 1
1582 v01 = r4 & mask5
1583 v11 = r5 & mask5
1584 2x v01 unsigned>>= 1
1585 r4 = v00 | v10
1586 r5 = v01 | v11
1587 v00 = r6 & mask4
1588 v10 = r7 & mask4
1589 2x v10 <<= 1
1590 v01 = r6 & mask5
1591 v11 = r7 & mask5
1592 2x v01 unsigned>>= 1
1593 r6 = v00 | v10
1594 r7 = v01 | v11
1595 t0 = r0[0]r1[0]
1596 mem128[ input_0 + 384 ] = t0
1597 t0 = r2[0]r3[0]
1598 mem128[ input_0 + 400 ] = t0
1599 t0 = r4[0]r5[0]
1600 mem128[ input_0 + 416 ] = t0
1601 t0 = r6[0]r7[0]
1602 mem128[ input_0 + 432 ] = t0
1603
1604 r0 = mem64[ input_0 + 448 ] x2
1605 r1 = mem64[ input_0 + 456 ] x2
1606 r2 = mem64[ input_0 + 464 ] x2
1607 r3 = mem64[ input_0 + 472 ] x2
1608 r4 = mem64[ input_0 + 480 ] x2
1609 r5 = mem64[ input_0 + 488 ] x2
1610 r6 = mem64[ input_0 + 496 ] x2
1611 r7 = mem64[ input_0 + 504 ] x2
1612 v00 = r0 & mask0
1613 v10 = r4 & mask0
1614 2x v10 <<= 4
1615 v01 = r0 & mask1
1616 v11 = r4 & mask1
1617 2x v01 unsigned>>= 4
1618 r0 = v00 | v10
1619 r4 = v01 | v11
1620 v00 = r1 & mask0
1621 v10 = r5 & mask0
1622 2x v10 <<= 4
1623 v01 = r1 & mask1
1624 v11 = r5 & mask1
1625 2x v01 unsigned>>= 4
1626 r1 = v00 | v10
1627 r5 = v01 | v11
1628 v00 = r2 & mask0
1629 v10 = r6 & mask0
1630 2x v10 <<= 4
1631 v01 = r2 & mask1
1632 v11 = r6 & mask1
1633 2x v01 unsigned>>= 4
1634 r2 = v00 | v10
1635 r6 = v01 | v11
1636 v00 = r3 & mask0
1637 v10 = r7 & mask0
1638 2x v10 <<= 4
1639 v01 = r3 & mask1
1640 v11 = r7 & mask1
1641 2x v01 unsigned>>= 4
1642 r3 = v00 | v10
1643 r7 = v01 | v11
1644 v00 = r0 & mask2
1645 v10 = r2 & mask2
1646 2x v10 <<= 2
1647 v01 = r0 & mask3
1648 v11 = r2 & mask3
1649 2x v01 unsigned>>= 2
1650 r0 = v00 | v10
1651 r2 = v01 | v11
1652 v00 = r1 & mask2
1653 v10 = r3 & mask2
1654 2x v10 <<= 2
1655 v01 = r1 & mask3
1656 v11 = r3 & mask3
1657 2x v01 unsigned>>= 2
1658 r1 = v00 | v10
1659 r3 = v01 | v11
1660 v00 = r4 & mask2
1661 v10 = r6 & mask2
1662 2x v10 <<= 2
1663 v01 = r4 & mask3
1664 v11 = r6 & mask3
1665 2x v01 unsigned>>= 2
1666 r4 = v00 | v10
1667 r6 = v01 | v11
1668 v00 = r5 & mask2
1669 v10 = r7 & mask2
1670 2x v10 <<= 2
1671 v01 = r5 & mask3
1672 v11 = r7 & mask3
1673 2x v01 unsigned>>= 2
1674 r5 = v00 | v10
1675 r7 = v01 | v11
1676 v00 = r0 & mask4
1677 v10 = r1 & mask4
1678 2x v10 <<= 1
1679 v01 = r0 & mask5
1680 v11 = r1 & mask5
1681 2x v01 unsigned>>= 1
1682 r0 = v00 | v10
1683 r1 = v01 | v11
1684 v00 = r2 & mask4
1685 v10 = r3 & mask4
1686 2x v10 <<= 1
1687 v01 = r2 & mask5
1688 v11 = r3 & mask5
1689 2x v01 unsigned>>= 1
1690 r2 = v00 | v10
1691 r3 = v01 | v11
1692 v00 = r4 & mask4
1693 v10 = r5 & mask4
1694 2x v10 <<= 1
1695 v01 = r4 & mask5
1696 v11 = r5 & mask5
1697 2x v01 unsigned>>= 1
1698 r4 = v00 | v10
1699 r5 = v01 | v11
1700 v00 = r6 & mask4
1701 v10 = r7 & mask4
1702 2x v10 <<= 1
1703 v01 = r6 & mask5
1704 v11 = r7 & mask5
1705 2x v01 unsigned>>= 1
1706 r6 = v00 | v10
1707 r7 = v01 | v11
1708 t0 = r0[0]r1[0]
1709 mem128[ input_0 + 448 ] = t0
1710 t0 = r2[0]r3[0]
1711 mem128[ input_0 + 464 ] = t0
1712 t0 = r4[0]r5[0]
1713 mem128[ input_0 + 480 ] = t0
1714 t0 = r6[0]r7[0]
1715 mem128[ input_0 + 496 ] = t0
1716
1717 return