Lines Matching +full:0 +full:x7
35 ( (((a0) & 1) << 0) | \
45 ( ((l7) << (0 * 8)) | \
188 x4, x5, x6, x7, \ argument
192 vmovdqu (0 * 32)(rio), x0; \
199 vmovdqu (7 * 32)(rio), x7; \
211 x4, x5, x6, x7, \ argument
216 x4, x5, x6, x7, \
221 vmovdqu x0, 0 * 32(mem_ab); \
228 vmovdqu x7, 7 * 32(mem_ab); \
229 vmovdqu y0, 0 * 32(mem_cd); \
239 x4, x5, x6, x7, \ argument
243 vmovdqu x0, 0 * 32(mem); \
250 vmovdqu x7, 7 * 32(mem); \
261 x4, x5, x6, x7, \ argument
263 vmovdqu x0, ((idx + 0) * 32)(mem_tmp); \
270 vmovdqu x7, ((idx + 7) * 32)(mem_tmp);
273 x4, x5, x6, x7, \ argument
275 vmovdqu ((idx + 0) * 32)(mem_tmp), x0; \
282 vmovdqu ((idx + 7) * 32)(mem_tmp), x7;
285 x4, x5, x6, x7, \ argument
294 vpbroadcastb ((round * 16) + idx + 0)(rk), t0; \
303 vpxor t0, x7, x7;
307 x4, x5, x6, x7, \ argument
319 vgf2p8affineinvqb $0, t2, x2, x2; \
320 vgf2p8affineinvqb $0, t2, x6, x6; \
324 vgf2p8affineqb $(tf_x2_const), t4, x7, x7; \
325 vgf2p8affineinvqb $0, t2, x3, x3; \
326 vgf2p8affineinvqb $0, t2, x7, x7
330 x4, x5, x6, x7, \ argument
380 vpshufb t1, x7, x7; \
392 filter_8bit(x7, t4, t5, t6, t0); \
400 vextracti128 $1, x7, t6##_x; \
401 vaesdeclast t7##_x, x7##_x, x7##_x; \
403 vinserti128 $1, t6##_x, x7, x7; \
421 x4, x5, x6, x7, \ argument
428 vpxor y3, x7, x7; \
440 vpxor x7, x3, x3; \
446 vpxor x7, y7, y7; \
458 vpxor y3, x7, x7;
461 x4, x5, x6, x7, \ argument
465 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
468 aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \
472 aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \
474 x4, x5, x6, x7, \
478 x4, x5, x6, x7, \
479 mem_tmp, 0); \
480 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
481 y0, rk, 0, round); \
483 aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \
487 aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \
489 x4, x5, x6, x7, \
490 mem_tmp, 0); \
495 x4, x5, x6, x7, \
504 * T1 = x4, x5, x6, x7 -> x7, x6, x5, x4 \
507 x7, x6, x5, x4, \
511 x6, x7, x4, x5, \
512 mem_tmp, 0);
515 x4, x5, x6, x7, \ argument
519 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
522 aria_sbox_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
526 aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \
528 x4, x5, x6, x7, \
532 x4, x5, x6, x7, \
533 mem_tmp, 0); \
534 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
535 y0, rk, 0, round); \
537 aria_sbox_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
541 aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \
543 x4, x5, x6, x7, \
544 mem_tmp, 0); \
549 x4, x5, x6, x7, \
554 * T1 = x4, x5, x6, x7 -> x5, x4, x7, x6 \
561 x5, x4, x7, x6, \
565 x6, x7, x4, x5, \
566 mem_tmp, 0);
569 x4, x5, x6, x7, \ argument
573 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
576 aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \
579 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
583 x4, x5, x6, x7, \
587 x4, x5, x6, x7, \
588 mem_tmp, 0); \
589 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
590 y0, rk, 0, round); \
592 aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \
595 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
596 y0, rk, 0, last_round); \
603 x4, x5, x6, x7, \ argument
607 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
611 x6, x7, x4, x5, \
616 aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \
618 x4, x5, x6, x7, \
622 x4, x5, x6, x7, \
623 mem_tmp, 0); \
624 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
625 y0, rk, 0, round); \
628 x6, x7, x4, x5, \
633 aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \
635 x4, x5, x6, x7, \
636 mem_tmp, 0); \
641 x4, x5, x6, x7, \
650 * T1 = x4, x5, x6, x7 -> x7, x6, x5, x4 \
653 x7, x6, x5, x4, \
657 x6, x7, x4, x5, \
658 mem_tmp, 0);
661 x4, x5, x6, x7, \ argument
665 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
669 x4, x5, x6, x7, \
674 aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \
676 x4, x5, x6, x7, \
680 x4, x5, x6, x7, \
681 mem_tmp, 0); \
682 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
683 y0, rk, 0, round); \
686 x4, x5, x6, x7, \
691 aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \
693 x4, x5, x6, x7, \
694 mem_tmp, 0); \
699 x4, x5, x6, x7, \
704 * T1 = x4, x5, x6, x7 -> x5, x4, x7, x6 \
711 x5, x4, x7, x6, \
715 x6, x7, x4, x5, \
716 mem_tmp, 0);
719 x4, x5, x6, x7, \ argument
723 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
727 x6, x7, x4, x5, \
731 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
735 x4, x5, x6, x7, \
739 x4, x5, x6, x7, \
740 mem_tmp, 0); \
741 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
742 y0, rk, 0, round); \
745 x6, x7, x4, x5, \
749 aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \
750 y0, rk, 0, last_round); \
760 0 + (idx), 4 + (idx), 8 + (idx), 12 + (idx)
762 .byte SHUFB_BYTES(0), SHUFB_BYTES(1), SHUFB_BYTES(2), SHUFB_BYTES(3)
763 .byte SHUFB_BYTES(0), SHUFB_BYTES(1), SHUFB_BYTES(2), SHUFB_BYTES(3)
769 .byte 0x00, 0x0d, 0x0a, 0x07, 0x04, 0x01, 0x0e, 0x0b
770 .byte 0x08, 0x05, 0x02, 0x0f, 0x0c, 0x09, 0x06, 0x03
772 .byte 0x00, 0x05, 0x0a, 0x0f, 0x04, 0x09, 0x0e, 0x03
773 .byte 0x08, 0x0d, 0x02, 0x07, 0x0c, 0x01, 0x06, 0x0b
776 .byte 0x0f, 0x0e, 0x0d, 0x0c, 0x0b, 0x0a, 0x09, 0x08
777 .byte 0x07, 0x06, 0x05, 0x04, 0x03, 0x02, 0x01, 0x00
780 * 1 1 0 0 0 0 0 1 x0 0
781 * 0 1 0 0 1 0 0 0 x1 0
782 * 1 1 0 0 1 1 1 1 x2 0
783 * 0 1 1 0 1 0 0 1 x3 1
784 * 0 1 0 0 1 1 0 0 * x4 + 0
785 * 0 1 0 1 1 0 0 0 x5 0
786 * 0 0 0 0 0 1 0 1 x6 0
787 * 1 1 1 0 0 1 1 1 x7 1
790 .octa 0x92172DA81A9FA520B2370D883ABF8500
792 .octa 0x2B15FFC1AF917B45E6D8320C625CB688
795 * 1 0 1 1 0 0 0 1 x0 0
796 * 0 1 1 1 1 0 1 1 x1 0
797 * 0 0 0 1 1 0 1 0 x2 1
798 * 0 1 0 0 0 1 0 0 x3 0
799 * 0 0 1 1 1 0 1 1 * x4 + 0
800 * 0 1 0 0 1 0 0 0 x5 0
801 * 1 1 0 1 0 0 1 1 x6 0
802 * 0 1 0 0 1 0 1 0 x7 0
805 .octa 0xEFAE0544FCBD1657B8F95213ABEA4100
807 .octa 0x3F893781E95FE1576CDA64D2BA0CB204
813 #define tf_aff_const BV8(1, 1, 0, 0, 0, 1, 1, 0)
815 .quad BM8X8(BV8(1, 0, 0, 0, 1, 1, 1, 1),
816 BV8(1, 1, 0, 0, 0, 1, 1, 1),
817 BV8(1, 1, 1, 0, 0, 0, 1, 1),
818 BV8(1, 1, 1, 1, 0, 0, 0, 1),
819 BV8(1, 1, 1, 1, 1, 0, 0, 0),
820 BV8(0, 1, 1, 1, 1, 1, 0, 0),
821 BV8(0, 0, 1, 1, 1, 1, 1, 0),
822 BV8(0, 0, 0, 1, 1, 1, 1, 1))
825 #define tf_inv_const BV8(1, 0, 1, 0, 0, 0, 0, 0)
827 .quad BM8X8(BV8(0, 0, 1, 0, 0, 1, 0, 1),
828 BV8(1, 0, 0, 1, 0, 0, 1, 0),
829 BV8(0, 1, 0, 0, 1, 0, 0, 1),
830 BV8(1, 0, 1, 0, 0, 1, 0, 0),
831 BV8(0, 1, 0, 1, 0, 0, 1, 0),
832 BV8(0, 0, 1, 0, 1, 0, 0, 1),
833 BV8(1, 0, 0, 1, 0, 1, 0, 0),
834 BV8(0, 1, 0, 0, 1, 0, 1, 0))
837 #define tf_s2_const BV8(0, 1, 0, 0, 0, 1, 1, 1)
839 .quad BM8X8(BV8(0, 1, 0, 1, 0, 1, 1, 1),
840 BV8(0, 0, 1, 1, 1, 1, 1, 1),
841 BV8(1, 1, 1, 0, 1, 1, 0, 1),
842 BV8(1, 1, 0, 0, 0, 0, 1, 1),
843 BV8(0, 1, 0, 0, 0, 0, 1, 1),
844 BV8(1, 1, 0, 0, 1, 1, 1, 0),
845 BV8(0, 1, 1, 0, 0, 0, 1, 1),
846 BV8(1, 1, 1, 1, 0, 1, 1, 0))
849 #define tf_x2_const BV8(0, 0, 1, 1, 0, 1, 0, 0)
851 .quad BM8X8(BV8(0, 0, 0, 1, 1, 0, 0, 0),
852 BV8(0, 0, 1, 0, 0, 1, 1, 0),
853 BV8(0, 0, 0, 0, 1, 0, 1, 0),
854 BV8(1, 1, 1, 0, 0, 0, 1, 1),
855 BV8(1, 1, 1, 0, 1, 1, 0, 0),
856 BV8(0, 1, 1, 0, 1, 0, 1, 1),
857 BV8(1, 0, 1, 1, 1, 1, 0, 1),
858 BV8(1, 0, 0, 1, 0, 0, 1, 1))
862 .quad BM8X8(BV8(1, 0, 0, 0, 0, 0, 0, 0),
863 BV8(0, 1, 0, 0, 0, 0, 0, 0),
864 BV8(0, 0, 1, 0, 0, 0, 0, 0),
865 BV8(0, 0, 0, 1, 0, 0, 0, 0),
866 BV8(0, 0, 0, 0, 1, 0, 0, 0),
867 BV8(0, 0, 0, 0, 0, 1, 0, 0),
868 BV8(0, 0, 0, 0, 0, 0, 1, 0),
869 BV8(0, 0, 0, 0, 0, 0, 0, 1))
877 .long 0x0f0f0f0f
899 %rax, %r9, 0);
1035 vpsrldq $8, %ymm0, %ymm0; /* ab: -1:0 ; cd: -1:0 */
1036 vpaddq %ymm0, %ymm0, %ymm5; /* ab: -2:0 ; cd: -2:0 */
1044 vpshufb %ymm6, %ymm3, %ymm8; /* +1 ; +0 */
1047 cmpq $(0xffffffffffffffff - 32), %r11;
1065 vmovdqu %ymm8, (0 * 32)(%rcx);
1093 vmovdqu (0 * 32)(%rcx), %ymm0;
1126 vmovdqu %ymm8, (0 * 32)(%rcx);
1163 vmovdqu (0 * 32)(%rcx), %ymm0;
1198 vpxor (0 * 32)(%r11), %ymm1, %ymm1;
1245 %rax, %r9, 0);
1418 vpxor (0 * 32)(%r11), %ymm1, %ymm1;