2 * Serpent Cipher 8-way parallel algorithm (x86_64/AVX)
4 * Copyright (C) 2012 Johannes Goetzfried
5 * <Johannes.Goetzfried@informatik.stud.uni-erlangen.de>
7 * Based on arch/x86/crypto/serpent-sse2-x86_64-asm_64.S by
8 * Copyright (C) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
10 * This program is free software; you can redistribute it and/or modify
11 * it under the terms of the GNU General Public License as published by
12 * the Free Software Foundation; either version 2 of the License, or
13 * (at your option) any later version.
15 * This program is distributed in the hope that it will be useful,
16 * but WITHOUT ANY WARRANTY; without even the implied warranty of
17 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18 * GNU General Public License for more details.
20 * You should have received a copy of the GNU General Public License
21 * along with this program; if not, write to the Free Software
22 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
27 #include <linux/linkage.h>
28 #include "glue_helper-asm-avx.S"
30 .file "serpent-avx-x86_64-asm_64.S"
36 .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
42 /**********************************************************************
44 **********************************************************************/
67 #define S0_1(x0, x1, x2, x3, x4) \
76 #define S0_2(x0, x1, x2, x3, x4) \
86 #define S1_1(x0, x1, x2, x3, x4) \
95 #define S1_2(x0, x1, x2, x3, x4) \
102 vpxor RNOT, x0, x0; \
106 #define S2_1(x0, x1, x2, x3, x4) \
107 vpxor RNOT, x3, x3; \
115 #define S2_2(x0, x1, x2, x3, x4) \
119 vpxor RNOT, tp, tp; \
125 #define S3_1(x0, x1, x2, x3, x4) \
135 #define S3_2(x0, x1, x2, x3, x4) \
146 #define S4_1(x0, x1, x2, x3, x4) \
155 #define S4_2(x0, x1, x2, x3, x4) \
162 vpxor RNOT, x1, x1; \
165 #define S5_1(x0, x1, x2, x3, x4) \
168 vpxor RNOT, x3, x3; \
174 #define S5_2(x0, x1, x2, x3, x4) \
184 #define S6_1(x0, x1, x2, x3, x4) \
190 vpxor RNOT, x1, x4; \
193 #define S6_2(x0, x1, x2, x3, x4) \
203 #define S7_1(x0, x1, x2, x3, x4) \
204 vpxor RNOT, x1, tp; \
205 vpxor RNOT, x0, x0; \
213 #define S7_2(x0, x1, x2, x3, x4) \
224 #define SI0_1(x0, x1, x2, x3, x4) \
228 vpxor RNOT, x0, x0; \
233 #define SI0_2(x0, x1, x2, x3, x4) \
243 #define SI1_1(x0, x1, x2, x3, x4) \
246 vpxor RNOT, x2, x2; \
252 #define SI1_2(x0, x1, x2, x3, x4) \
262 #define SI2_1(x0, x1, x2, x3, x4) \
264 vpxor RNOT, x3, tp; \
271 #define SI2_2(x0, x1, x2, x3, x4) \
281 #define SI3_1(x0, x1, x2, x3, x4) \
290 #define SI3_2(x0, x1, x2, x3, x4) \
301 #define SI4_1(x0, x1, x2, x3, x4) \
306 vpxor RNOT, x0, x4; \
310 #define SI4_2(x0, x1, x2, x3, x4) \
321 #define SI5_1(x0, x1, x2, x3, x4) \
328 vpxor RNOT, x0, x0; \
331 #define SI5_2(x0, x1, x2, x3, x4) \
343 #define SI6_1(x0, x1, x2, x3, x4) \
352 #define SI6_2(x0, x1, x2, x3, x4) \
353 vpxor RNOT, tp, tp; \
362 #define SI7_1(x0, x1, x2, x3, x4) \
367 vpxor RNOT, x0, x0; \
372 #define SI7_2(x0, x1, x2, x3, x4) \
383 #define get_key(i, j, t) \
384 vbroadcastss (4*(i)+(j))*4(CTX), t;
386 #define K2(x0, x1, x2, x3, x4, i) \
387 get_key(i, 0, RK0); \
388 get_key(i, 1, RK1); \
389 get_key(i, 2, RK2); \
390 get_key(i, 3, RK3); \
391 vpxor RK0, x0 ## 1, x0 ## 1; \
392 vpxor RK1, x1 ## 1, x1 ## 1; \
393 vpxor RK2, x2 ## 1, x2 ## 1; \
394 vpxor RK3, x3 ## 1, x3 ## 1; \
395 vpxor RK0, x0 ## 2, x0 ## 2; \
396 vpxor RK1, x1 ## 2, x1 ## 2; \
397 vpxor RK2, x2 ## 2, x2 ## 2; \
398 vpxor RK3, x3 ## 2, x3 ## 2;
400 #define LK2(x0, x1, x2, x3, x4, i) \
401 vpslld $13, x0 ## 1, x4 ## 1; \
402 vpsrld $(32 - 13), x0 ## 1, x0 ## 1; \
403 vpor x4 ## 1, x0 ## 1, x0 ## 1; \
404 vpxor x0 ## 1, x1 ## 1, x1 ## 1; \
405 vpslld $3, x2 ## 1, x4 ## 1; \
406 vpsrld $(32 - 3), x2 ## 1, x2 ## 1; \
407 vpor x4 ## 1, x2 ## 1, x2 ## 1; \
408 vpxor x2 ## 1, x1 ## 1, x1 ## 1; \
409 vpslld $13, x0 ## 2, x4 ## 2; \
410 vpsrld $(32 - 13), x0 ## 2, x0 ## 2; \
411 vpor x4 ## 2, x0 ## 2, x0 ## 2; \
412 vpxor x0 ## 2, x1 ## 2, x1 ## 2; \
413 vpslld $3, x2 ## 2, x4 ## 2; \
414 vpsrld $(32 - 3), x2 ## 2, x2 ## 2; \
415 vpor x4 ## 2, x2 ## 2, x2 ## 2; \
416 vpxor x2 ## 2, x1 ## 2, x1 ## 2; \
417 vpslld $1, x1 ## 1, x4 ## 1; \
418 vpsrld $(32 - 1), x1 ## 1, x1 ## 1; \
419 vpor x4 ## 1, x1 ## 1, x1 ## 1; \
420 vpslld $3, x0 ## 1, x4 ## 1; \
421 vpxor x2 ## 1, x3 ## 1, x3 ## 1; \
422 vpxor x4 ## 1, x3 ## 1, x3 ## 1; \
423 get_key(i, 1, RK1); \
424 vpslld $1, x1 ## 2, x4 ## 2; \
425 vpsrld $(32 - 1), x1 ## 2, x1 ## 2; \
426 vpor x4 ## 2, x1 ## 2, x1 ## 2; \
427 vpslld $3, x0 ## 2, x4 ## 2; \
428 vpxor x2 ## 2, x3 ## 2, x3 ## 2; \
429 vpxor x4 ## 2, x3 ## 2, x3 ## 2; \
430 get_key(i, 3, RK3); \
431 vpslld $7, x3 ## 1, x4 ## 1; \
432 vpsrld $(32 - 7), x3 ## 1, x3 ## 1; \
433 vpor x4 ## 1, x3 ## 1, x3 ## 1; \
434 vpslld $7, x1 ## 1, x4 ## 1; \
435 vpxor x1 ## 1, x0 ## 1, x0 ## 1; \
436 vpxor x3 ## 1, x0 ## 1, x0 ## 1; \
437 vpxor x3 ## 1, x2 ## 1, x2 ## 1; \
438 vpxor x4 ## 1, x2 ## 1, x2 ## 1; \
439 get_key(i, 0, RK0); \
440 vpslld $7, x3 ## 2, x4 ## 2; \
441 vpsrld $(32 - 7), x3 ## 2, x3 ## 2; \
442 vpor x4 ## 2, x3 ## 2, x3 ## 2; \
443 vpslld $7, x1 ## 2, x4 ## 2; \
444 vpxor x1 ## 2, x0 ## 2, x0 ## 2; \
445 vpxor x3 ## 2, x0 ## 2, x0 ## 2; \
446 vpxor x3 ## 2, x2 ## 2, x2 ## 2; \
447 vpxor x4 ## 2, x2 ## 2, x2 ## 2; \
448 get_key(i, 2, RK2); \
449 vpxor RK1, x1 ## 1, x1 ## 1; \
450 vpxor RK3, x3 ## 1, x3 ## 1; \
451 vpslld $5, x0 ## 1, x4 ## 1; \
452 vpsrld $(32 - 5), x0 ## 1, x0 ## 1; \
453 vpor x4 ## 1, x0 ## 1, x0 ## 1; \
454 vpslld $22, x2 ## 1, x4 ## 1; \
455 vpsrld $(32 - 22), x2 ## 1, x2 ## 1; \
456 vpor x4 ## 1, x2 ## 1, x2 ## 1; \
457 vpxor RK0, x0 ## 1, x0 ## 1; \
458 vpxor RK2, x2 ## 1, x2 ## 1; \
459 vpxor RK1, x1 ## 2, x1 ## 2; \
460 vpxor RK3, x3 ## 2, x3 ## 2; \
461 vpslld $5, x0 ## 2, x4 ## 2; \
462 vpsrld $(32 - 5), x0 ## 2, x0 ## 2; \
463 vpor x4 ## 2, x0 ## 2, x0 ## 2; \
464 vpslld $22, x2 ## 2, x4 ## 2; \
465 vpsrld $(32 - 22), x2 ## 2, x2 ## 2; \
466 vpor x4 ## 2, x2 ## 2, x2 ## 2; \
467 vpxor RK0, x0 ## 2, x0 ## 2; \
468 vpxor RK2, x2 ## 2, x2 ## 2;
470 #define KL2(x0, x1, x2, x3, x4, i) \
471 vpxor RK0, x0 ## 1, x0 ## 1; \
472 vpxor RK2, x2 ## 1, x2 ## 1; \
473 vpsrld $5, x0 ## 1, x4 ## 1; \
474 vpslld $(32 - 5), x0 ## 1, x0 ## 1; \
475 vpor x4 ## 1, x0 ## 1, x0 ## 1; \
476 vpxor RK3, x3 ## 1, x3 ## 1; \
477 vpxor RK1, x1 ## 1, x1 ## 1; \
478 vpsrld $22, x2 ## 1, x4 ## 1; \
479 vpslld $(32 - 22), x2 ## 1, x2 ## 1; \
480 vpor x4 ## 1, x2 ## 1, x2 ## 1; \
481 vpxor x3 ## 1, x2 ## 1, x2 ## 1; \
482 vpxor RK0, x0 ## 2, x0 ## 2; \
483 vpxor RK2, x2 ## 2, x2 ## 2; \
484 vpsrld $5, x0 ## 2, x4 ## 2; \
485 vpslld $(32 - 5), x0 ## 2, x0 ## 2; \
486 vpor x4 ## 2, x0 ## 2, x0 ## 2; \
487 vpxor RK3, x3 ## 2, x3 ## 2; \
488 vpxor RK1, x1 ## 2, x1 ## 2; \
489 vpsrld $22, x2 ## 2, x4 ## 2; \
490 vpslld $(32 - 22), x2 ## 2, x2 ## 2; \
491 vpor x4 ## 2, x2 ## 2, x2 ## 2; \
492 vpxor x3 ## 2, x2 ## 2, x2 ## 2; \
493 vpxor x3 ## 1, x0 ## 1, x0 ## 1; \
494 vpslld $7, x1 ## 1, x4 ## 1; \
495 vpxor x1 ## 1, x0 ## 1, x0 ## 1; \
496 vpxor x4 ## 1, x2 ## 1, x2 ## 1; \
497 vpsrld $1, x1 ## 1, x4 ## 1; \
498 vpslld $(32 - 1), x1 ## 1, x1 ## 1; \
499 vpor x4 ## 1, x1 ## 1, x1 ## 1; \
500 vpxor x3 ## 2, x0 ## 2, x0 ## 2; \
501 vpslld $7, x1 ## 2, x4 ## 2; \
502 vpxor x1 ## 2, x0 ## 2, x0 ## 2; \
503 vpxor x4 ## 2, x2 ## 2, x2 ## 2; \
504 vpsrld $1, x1 ## 2, x4 ## 2; \
505 vpslld $(32 - 1), x1 ## 2, x1 ## 2; \
506 vpor x4 ## 2, x1 ## 2, x1 ## 2; \
507 vpsrld $7, x3 ## 1, x4 ## 1; \
508 vpslld $(32 - 7), x3 ## 1, x3 ## 1; \
509 vpor x4 ## 1, x3 ## 1, x3 ## 1; \
510 vpxor x0 ## 1, x1 ## 1, x1 ## 1; \
511 vpslld $3, x0 ## 1, x4 ## 1; \
512 vpxor x4 ## 1, x3 ## 1, x3 ## 1; \
513 vpsrld $7, x3 ## 2, x4 ## 2; \
514 vpslld $(32 - 7), x3 ## 2, x3 ## 2; \
515 vpor x4 ## 2, x3 ## 2, x3 ## 2; \
516 vpxor x0 ## 2, x1 ## 2, x1 ## 2; \
517 vpslld $3, x0 ## 2, x4 ## 2; \
518 vpxor x4 ## 2, x3 ## 2, x3 ## 2; \
519 vpsrld $13, x0 ## 1, x4 ## 1; \
520 vpslld $(32 - 13), x0 ## 1, x0 ## 1; \
521 vpor x4 ## 1, x0 ## 1, x0 ## 1; \
522 vpxor x2 ## 1, x1 ## 1, x1 ## 1; \
523 vpxor x2 ## 1, x3 ## 1, x3 ## 1; \
524 vpsrld $3, x2 ## 1, x4 ## 1; \
525 vpslld $(32 - 3), x2 ## 1, x2 ## 1; \
526 vpor x4 ## 1, x2 ## 1, x2 ## 1; \
527 vpsrld $13, x0 ## 2, x4 ## 2; \
528 vpslld $(32 - 13), x0 ## 2, x0 ## 2; \
529 vpor x4 ## 2, x0 ## 2, x0 ## 2; \
530 vpxor x2 ## 2, x1 ## 2, x1 ## 2; \
531 vpxor x2 ## 2, x3 ## 2, x3 ## 2; \
532 vpsrld $3, x2 ## 2, x4 ## 2; \
533 vpslld $(32 - 3), x2 ## 2, x2 ## 2; \
534 vpor x4 ## 2, x2 ## 2, x2 ## 2;
536 #define S(SBOX, x0, x1, x2, x3, x4) \
537 SBOX ## _1(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
538 SBOX ## _2(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
539 SBOX ## _1(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2); \
540 SBOX ## _2(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2);
542 #define SP(SBOX, x0, x1, x2, x3, x4, i) \
543 get_key(i, 0, RK0); \
544 SBOX ## _1(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
545 get_key(i, 2, RK2); \
546 SBOX ## _2(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
547 get_key(i, 3, RK3); \
548 SBOX ## _1(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2); \
549 get_key(i, 1, RK1); \
550 SBOX ## _2(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2); \
552 #define transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
553 vpunpckldq x1, x0, t0; \
554 vpunpckhdq x1, x0, t2; \
555 vpunpckldq x3, x2, t1; \
556 vpunpckhdq x3, x2, x3; \
558 vpunpcklqdq t1, t0, x0; \
559 vpunpckhqdq t1, t0, x1; \
560 vpunpcklqdq x3, t2, x2; \
561 vpunpckhqdq x3, t2, x3;
563 #define read_blocks(x0, x1, x2, x3, t0, t1, t2) \
564 transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
566 #define write_blocks(x0, x1, x2, x3, t0, t1, t2) \
567 transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
570 __serpent_enc_blk8_avx:
573 * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
575 * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
578 vpcmpeqd RNOT, RNOT, RNOT;
580 read_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
581 read_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
583 K2(RA, RB, RC, RD, RE, 0);
584 S(S0, RA, RB, RC, RD, RE); LK2(RC, RB, RD, RA, RE, 1);
585 S(S1, RC, RB, RD, RA, RE); LK2(RE, RD, RA, RC, RB, 2);
586 S(S2, RE, RD, RA, RC, RB); LK2(RB, RD, RE, RC, RA, 3);
587 S(S3, RB, RD, RE, RC, RA); LK2(RC, RA, RD, RB, RE, 4);
588 S(S4, RC, RA, RD, RB, RE); LK2(RA, RD, RB, RE, RC, 5);
589 S(S5, RA, RD, RB, RE, RC); LK2(RC, RA, RD, RE, RB, 6);
590 S(S6, RC, RA, RD, RE, RB); LK2(RD, RB, RA, RE, RC, 7);
591 S(S7, RD, RB, RA, RE, RC); LK2(RC, RA, RE, RD, RB, 8);
592 S(S0, RC, RA, RE, RD, RB); LK2(RE, RA, RD, RC, RB, 9);
593 S(S1, RE, RA, RD, RC, RB); LK2(RB, RD, RC, RE, RA, 10);
594 S(S2, RB, RD, RC, RE, RA); LK2(RA, RD, RB, RE, RC, 11);
595 S(S3, RA, RD, RB, RE, RC); LK2(RE, RC, RD, RA, RB, 12);
596 S(S4, RE, RC, RD, RA, RB); LK2(RC, RD, RA, RB, RE, 13);
597 S(S5, RC, RD, RA, RB, RE); LK2(RE, RC, RD, RB, RA, 14);
598 S(S6, RE, RC, RD, RB, RA); LK2(RD, RA, RC, RB, RE, 15);
599 S(S7, RD, RA, RC, RB, RE); LK2(RE, RC, RB, RD, RA, 16);
600 S(S0, RE, RC, RB, RD, RA); LK2(RB, RC, RD, RE, RA, 17);
601 S(S1, RB, RC, RD, RE, RA); LK2(RA, RD, RE, RB, RC, 18);
602 S(S2, RA, RD, RE, RB, RC); LK2(RC, RD, RA, RB, RE, 19);
603 S(S3, RC, RD, RA, RB, RE); LK2(RB, RE, RD, RC, RA, 20);
604 S(S4, RB, RE, RD, RC, RA); LK2(RE, RD, RC, RA, RB, 21);
605 S(S5, RE, RD, RC, RA, RB); LK2(RB, RE, RD, RA, RC, 22);
606 S(S6, RB, RE, RD, RA, RC); LK2(RD, RC, RE, RA, RB, 23);
607 S(S7, RD, RC, RE, RA, RB); LK2(RB, RE, RA, RD, RC, 24);
608 S(S0, RB, RE, RA, RD, RC); LK2(RA, RE, RD, RB, RC, 25);
609 S(S1, RA, RE, RD, RB, RC); LK2(RC, RD, RB, RA, RE, 26);
610 S(S2, RC, RD, RB, RA, RE); LK2(RE, RD, RC, RA, RB, 27);
611 S(S3, RE, RD, RC, RA, RB); LK2(RA, RB, RD, RE, RC, 28);
612 S(S4, RA, RB, RD, RE, RC); LK2(RB, RD, RE, RC, RA, 29);
613 S(S5, RB, RD, RE, RC, RA); LK2(RA, RB, RD, RC, RE, 30);
614 S(S6, RA, RB, RD, RC, RE); LK2(RD, RE, RB, RC, RA, 31);
615 S(S7, RD, RE, RB, RC, RA); K2(RA, RB, RC, RD, RE, 32);
617 write_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
618 write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
621 ENDPROC(__serpent_enc_blk8_avx)
624 __serpent_dec_blk8_avx:
627 * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
629 * RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2: decrypted blocks
632 vpcmpeqd RNOT, RNOT, RNOT;
634 read_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
635 read_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
637 K2(RA, RB, RC, RD, RE, 32);
638 SP(SI7, RA, RB, RC, RD, RE, 31); KL2(RB, RD, RA, RE, RC, 31);
639 SP(SI6, RB, RD, RA, RE, RC, 30); KL2(RA, RC, RE, RB, RD, 30);
640 SP(SI5, RA, RC, RE, RB, RD, 29); KL2(RC, RD, RA, RE, RB, 29);
641 SP(SI4, RC, RD, RA, RE, RB, 28); KL2(RC, RA, RB, RE, RD, 28);
642 SP(SI3, RC, RA, RB, RE, RD, 27); KL2(RB, RC, RD, RE, RA, 27);
643 SP(SI2, RB, RC, RD, RE, RA, 26); KL2(RC, RA, RE, RD, RB, 26);
644 SP(SI1, RC, RA, RE, RD, RB, 25); KL2(RB, RA, RE, RD, RC, 25);
645 SP(SI0, RB, RA, RE, RD, RC, 24); KL2(RE, RC, RA, RB, RD, 24);
646 SP(SI7, RE, RC, RA, RB, RD, 23); KL2(RC, RB, RE, RD, RA, 23);
647 SP(SI6, RC, RB, RE, RD, RA, 22); KL2(RE, RA, RD, RC, RB, 22);
648 SP(SI5, RE, RA, RD, RC, RB, 21); KL2(RA, RB, RE, RD, RC, 21);
649 SP(SI4, RA, RB, RE, RD, RC, 20); KL2(RA, RE, RC, RD, RB, 20);
650 SP(SI3, RA, RE, RC, RD, RB, 19); KL2(RC, RA, RB, RD, RE, 19);
651 SP(SI2, RC, RA, RB, RD, RE, 18); KL2(RA, RE, RD, RB, RC, 18);
652 SP(SI1, RA, RE, RD, RB, RC, 17); KL2(RC, RE, RD, RB, RA, 17);
653 SP(SI0, RC, RE, RD, RB, RA, 16); KL2(RD, RA, RE, RC, RB, 16);
654 SP(SI7, RD, RA, RE, RC, RB, 15); KL2(RA, RC, RD, RB, RE, 15);
655 SP(SI6, RA, RC, RD, RB, RE, 14); KL2(RD, RE, RB, RA, RC, 14);
656 SP(SI5, RD, RE, RB, RA, RC, 13); KL2(RE, RC, RD, RB, RA, 13);
657 SP(SI4, RE, RC, RD, RB, RA, 12); KL2(RE, RD, RA, RB, RC, 12);
658 SP(SI3, RE, RD, RA, RB, RC, 11); KL2(RA, RE, RC, RB, RD, 11);
659 SP(SI2, RA, RE, RC, RB, RD, 10); KL2(RE, RD, RB, RC, RA, 10);
660 SP(SI1, RE, RD, RB, RC, RA, 9); KL2(RA, RD, RB, RC, RE, 9);
661 SP(SI0, RA, RD, RB, RC, RE, 8); KL2(RB, RE, RD, RA, RC, 8);
662 SP(SI7, RB, RE, RD, RA, RC, 7); KL2(RE, RA, RB, RC, RD, 7);
663 SP(SI6, RE, RA, RB, RC, RD, 6); KL2(RB, RD, RC, RE, RA, 6);
664 SP(SI5, RB, RD, RC, RE, RA, 5); KL2(RD, RA, RB, RC, RE, 5);
665 SP(SI4, RD, RA, RB, RC, RE, 4); KL2(RD, RB, RE, RC, RA, 4);
666 SP(SI3, RD, RB, RE, RC, RA, 3); KL2(RE, RD, RA, RC, RB, 3);
667 SP(SI2, RE, RD, RA, RC, RB, 2); KL2(RD, RB, RC, RA, RE, 2);
668 SP(SI1, RD, RB, RC, RA, RE, 1); KL2(RE, RB, RC, RA, RD, 1);
669 S(SI0, RE, RB, RC, RA, RD); K2(RC, RD, RB, RE, RA, 0);
671 write_blocks(RC1, RD1, RB1, RE1, RK0, RK1, RK2);
672 write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);
675 ENDPROC(__serpent_dec_blk8_avx)
677 ENTRY(serpent_ecb_enc_8way_avx)
684 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
686 call __serpent_enc_blk8_avx;
688 store_8way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
691 ENDPROC(serpent_ecb_enc_8way_avx)
693 ENTRY(serpent_ecb_dec_8way_avx)
700 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
702 call __serpent_dec_blk8_avx;
704 store_8way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
707 ENDPROC(serpent_ecb_dec_8way_avx)
709 ENTRY(serpent_cbc_dec_8way_avx)
716 load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
718 call __serpent_dec_blk8_avx;
720 store_cbc_8way(%rdx, %rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
723 ENDPROC(serpent_cbc_dec_8way_avx)
725 ENTRY(serpent_ctr_8way_avx)
730 * %rcx: iv (little endian, 128bit)
733 load_ctr_8way(%rcx, .Lbswap128_mask, RA1, RB1, RC1, RD1, RA2, RB2, RC2,
736 call __serpent_enc_blk8_avx;
738 store_ctr_8way(%rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
741 ENDPROC(serpent_ctr_8way_avx)