Lines Matching defs:x0
45 * x0..x7: byte-sliced AB state
49 * x0..x7: new byte-sliced CD state
51 #define roundsm16(x0, x1, x2, x3, x4, x5, x6, x7, t0, t1, t2, t3, t4, t5, t6, \
62 vpshufb t4, x0, x0; \
74 filter_8bit(x0, t0, t1, t7, t6); \
89 vaesenclast t4, x0, x0; \
101 filter_8bit(x0, t0, t1, t7, t6); \
135 vpxor x5, x0, x0; \
142 vpxor x0, x6, x6; \
145 vpxor x7, x0, x0; \
151 vpxor x0, x5, x5; \
175 vpxor t7, x0, x0; \
176 vpxor 4 * 16(mem_cd), x0, x0; \
209 * x0..x7: byte-sliced AB state preloaded
213 #define two_roundsm16(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
222 vmovdqu x0, 4 * 16(mem_cd); \
230 store_ab(x0, x1, x2, x3, x4, x5, x6, x7, mem_ab);
232 #define dummy_store(x0, x1, x2, x3, x4, x5, x6, x7, mem_ab) /* do nothing */
234 #define store_ab_state(x0, x1, x2, x3, x4, x5, x6, x7, mem_ab) \
236 vmovdqu x0, 0 * 16(mem_ab); \
245 #define enc_rounds16(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
247 two_roundsm16(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
249 two_roundsm16(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
251 two_roundsm16(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
254 #define dec_rounds16(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
256 two_roundsm16(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
258 two_roundsm16(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
260 two_roundsm16(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
297 * x0..x7: new byte-sliced CD state
420 #define transpose_4x4(x0, x1, x2, x3, t1, t2) \
421 vpunpckhdq x1, x0, t2; \
422 vpunpckldq x1, x0, x0; \
427 vpunpckhqdq t1, x0, x1; \
428 vpunpcklqdq t1, x0, x0; \
483 #define inpack16_pre(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
485 vmovq key, x0; \
486 vpshufb .Lpack_bswap(%rip), x0, x0; \
488 vpxor 0 * 16(rio), x0, y7; \
489 vpxor 1 * 16(rio), x0, y6; \
490 vpxor 2 * 16(rio), x0, y5; \
491 vpxor 3 * 16(rio), x0, y4; \
492 vpxor 4 * 16(rio), x0, y3; \
493 vpxor 5 * 16(rio), x0, y2; \
494 vpxor 6 * 16(rio), x0, y1; \
495 vpxor 7 * 16(rio), x0, y0; \
496 vpxor 8 * 16(rio), x0, x7; \
497 vpxor 9 * 16(rio), x0, x6; \
498 vpxor 10 * 16(rio), x0, x5; \
499 vpxor 11 * 16(rio), x0, x4; \
500 vpxor 12 * 16(rio), x0, x3; \
501 vpxor 13 * 16(rio), x0, x2; \
502 vpxor 14 * 16(rio), x0, x1; \
503 vpxor 15 * 16(rio), x0, x0;
506 #define inpack16_post(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
508 byteslice_16x16b(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, \
511 vmovdqu x0, 0 * 16(mem_ab); \
529 #define outunpack16(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, \
531 byteslice_16x16b(y0, y4, x0, x4, y1, y5, x1, x5, y2, y6, x2, x6, y3, \
534 vmovdqu x0, stack_tmp0; \
536 vmovq key, x0; \
537 vpshufb .Lpack_bswap(%rip), x0, x0; \
539 vpxor x0, y7, y7; \
540 vpxor x0, y6, y6; \
541 vpxor x0, y5, y5; \
542 vpxor x0, y4, y4; \
543 vpxor x0, y3, y3; \
544 vpxor x0, y2, y2; \
545 vpxor x0, y1, y1; \
546 vpxor x0, y0, y0; \
547 vpxor x0, x7, x7; \
548 vpxor x0, x6, x6; \
549 vpxor x0, x5, x5; \
550 vpxor x0, x4, x4; \
551 vpxor x0, x3, x3; \
552 vpxor x0, x2, x2; \
553 vpxor x0, x1, x1; \
554 vpxor stack_tmp0, x0, x0;
556 #define write_output(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
558 vmovdqu x0, 0 * 16(rio); \