Lines Matching full:s
331 ld1 {v0.4s},[x5],#16
334 ld1 {v1.4s,v2.4s},[x3]
336 ld1 {v3.4s},[x4]
338 ld1 {v8.4s,v9.4s},[x5]
340 rev64 v0.4s,v0.4s
350 dup v16.4s,v0.s[0] // unpack key block
352 dup v20.4s,v0.s[1]
354 dup v24.4s,v0.s[2]
356 dup v28.4s,v0.s[3]
358 dup v17.4s,v1.s[0]
360 dup v21.4s,v1.s[1]
362 dup v25.4s,v1.s[2]
364 dup v29.4s,v1.s[3]
366 dup v19.4s,v3.s[0]
368 dup v23.4s,v3.s[1]
370 dup v27.4s,v3.s[2]
372 dup v31.4s,v3.s[3]
374 add v19.4s,v19.4s,v8.4s
376 dup v18.4s,v2.s[0]
378 dup v22.4s,v2.s[1]
380 dup v26.4s,v2.s[2]
382 dup v30.4s,v2.s[3]
388 add v16.4s,v16.4s,v17.4s
390 add v20.4s,v20.4s,v21.4s
392 add v24.4s,v24.4s,v25.4s
394 add v28.4s,v28.4s,v29.4s
412 add v18.4s,v18.4s,v19.4s
414 add v22.4s,v22.4s,v23.4s
416 add v26.4s,v26.4s,v27.4s
418 add v30.4s,v30.4s,v31.4s
428 ushr v17.4s,v4.4s,#20
430 ushr v21.4s,v5.4s,#20
432 ushr v25.4s,v6.4s,#20
434 ushr v29.4s,v7.4s,#20
436 sli v17.4s,v4.4s,#12
438 sli v21.4s,v5.4s,#12
440 sli v25.4s,v6.4s,#12
442 sli v29.4s,v7.4s,#12
444 add v16.4s,v16.4s,v17.4s
446 add v20.4s,v20.4s,v21.4s
448 add v24.4s,v24.4s,v25.4s
450 add v28.4s,v28.4s,v29.4s
468 add v18.4s,v18.4s,v19.4s
470 add v22.4s,v22.4s,v23.4s
472 add v26.4s,v26.4s,v27.4s
474 add v30.4s,v30.4s,v31.4s
484 ushr v17.4s,v4.4s,#25
485 ushr v21.4s,v5.4s,#25
486 ushr v25.4s,v6.4s,#25
487 ushr v29.4s,v7.4s,#25
488 sli v17.4s,v4.4s,#7
489 sli v21.4s,v5.4s,#7
490 sli v25.4s,v6.4s,#7
491 sli v29.4s,v7.4s,#7
492 add v16.4s,v16.4s,v21.4s
494 add v20.4s,v20.4s,v25.4s
496 add v24.4s,v24.4s,v29.4s
498 add v28.4s,v28.4s,v17.4s
516 add v26.4s,v26.4s,v31.4s
518 add v30.4s,v30.4s,v19.4s
520 add v18.4s,v18.4s,v23.4s
522 add v22.4s,v22.4s,v27.4s
532 ushr v21.4s,v4.4s,#20
534 ushr v25.4s,v5.4s,#20
536 ushr v29.4s,v6.4s,#20
538 ushr v17.4s,v7.4s,#20
540 sli v21.4s,v4.4s,#12
542 sli v25.4s,v5.4s,#12
544 sli v29.4s,v6.4s,#12
546 sli v17.4s,v7.4s,#12
548 add v16.4s,v16.4s,v21.4s
550 add v20.4s,v20.4s,v25.4s
552 add v24.4s,v24.4s,v29.4s
554 add v28.4s,v28.4s,v17.4s
572 add v26.4s,v26.4s,v31.4s
574 add v30.4s,v30.4s,v19.4s
576 add v18.4s,v18.4s,v23.4s
578 add v22.4s,v22.4s,v27.4s
588 ushr v21.4s,v4.4s,#25
589 ushr v25.4s,v5.4s,#25
590 ushr v29.4s,v6.4s,#25
591 ushr v17.4s,v7.4s,#25
592 sli v21.4s,v4.4s,#7
593 sli v25.4s,v5.4s,#7
594 sli v29.4s,v6.4s,#7
595 sli v17.4s,v7.4s,#7
598 add v19.4s,v19.4s,v8.4s
600 zip1 v4.4s,v16.4s,v20.4s // transpose data
601 zip1 v5.4s,v24.4s,v28.4s
602 zip2 v6.4s,v16.4s,v20.4s
603 zip2 v7.4s,v24.4s,v28.4s
609 zip1 v4.4s,v17.4s,v21.4s
610 zip1 v5.4s,v25.4s,v29.4s
611 zip2 v6.4s,v17.4s,v21.4s
612 zip2 v7.4s,v25.4s,v29.4s
618 zip1 v4.4s,v18.4s,v22.4s
620 zip1 v5.4s,v26.4s,v30.4s
622 zip2 v6.4s,v18.4s,v22.4s
624 zip2 v7.4s,v26.4s,v30.4s
635 zip1 v4.4s,v19.4s,v23.4s
637 zip1 v5.4s,v27.4s,v31.4s
639 zip2 v6.4s,v19.4s,v23.4s
641 zip2 v7.4s,v27.4s,v31.4s
657 add v16.4s,v16.4s,v0.4s // accumulate key block
661 add v17.4s,v17.4s,v1.4s
665 add v18.4s,v18.4s,v2.4s
669 add v19.4s,v19.4s,v3.4s
683 add v20.4s,v20.4s,v0.4s
685 add v21.4s,v21.4s,v1.4s
687 add v22.4s,v22.4s,v2.4s
689 add v23.4s,v23.4s,v3.4s
692 movi v4.4s,#5
699 add v8.4s,v8.4s,v4.4s // += 5
710 add v24.4s,v24.4s,v0.4s
711 add v25.4s,v25.4s,v1.4s
712 add v26.4s,v26.4s,v2.4s
713 add v27.4s,v27.4s,v3.4s
721 add v28.4s,v28.4s,v0.4s
722 add v29.4s,v29.4s,v1.4s
723 add v30.4s,v30.4s,v2.4s
724 add v31.4s,v31.4s,v3.4s
793 add v16.4s,v16.4s,v0.4s // accumulate key block
795 add v17.4s,v17.4s,v1.4s
797 add v18.4s,v18.4s,v2.4s
799 add v19.4s,v19.4s,v3.4s
814 add v16.4s,v20.4s,v0.4s
815 add v17.4s,v21.4s,v1.4s
817 add v18.4s,v22.4s,v2.4s
819 add v19.4s,v23.4s,v3.4s
830 add v16.4s,v24.4s,v0.4s
831 add v17.4s,v25.4s,v1.4s
833 add v18.4s,v26.4s,v2.4s
835 add v19.4s,v27.4s,v3.4s
846 add v16.4s,v28.4s,v0.4s
847 add v17.4s,v29.4s,v1.4s
848 add v18.4s,v30.4s,v2.4s
849 add v19.4s,v31.4s,v3.4s
904 ld1 {v0.4s},[x5],#16
907 ld1 {v1.4s,v2.4s},[x3]
909 ld1 {v3.4s},[x4]
910 ld1 {v7.s}[0],[x5]
913 rev64 v0.4s,v0.4s
921 add v3.4s,v3.4s,v7.4s // += 1
923 add v3.4s,v3.4s,v7.4s // not typo
925 add v4.4s,v3.4s,v7.4s
926 add v5.4s,v4.4s,v7.4s
927 add v6.4s,v5.4s,v7.4s
928 shl v7.4s,v7.4s,#2 // 1 -> 4
968 add v27.4s,v11.4s,v7.4s // +4
970 add v31.4s,v15.4s,v7.4s // +4
982 ld1 {v6.4s},[x3]
986 add v8.4s,v8.4s,v9.4s
988 add v12.4s,v12.4s,v13.4s
990 add v16.4s,v16.4s,v17.4s
992 add v20.4s,v20.4s,v21.4s
994 add v24.4s,v24.4s,v25.4s
996 add v28.4s,v28.4s,v29.4s
1022 add v10.4s,v10.4s,v11.4s
1024 add v14.4s,v14.4s,v15.4s
1026 add v18.4s,v18.4s,v19.4s
1028 add v22.4s,v22.4s,v23.4s
1030 add v26.4s,v26.4s,v27.4s
1032 add v30.4s,v30.4s,v31.4s
1046 ushr v9.4s,v0.4s,#20
1048 ushr v13.4s,v1.4s,#20
1050 ushr v17.4s,v2.4s,#20
1052 ushr v21.4s,v3.4s,#20
1054 ushr v25.4s,v4.4s,#20
1056 ushr v29.4s,v5.4s,#20
1058 sli v9.4s,v0.4s,#12
1060 sli v13.4s,v1.4s,#12
1062 sli v17.4s,v2.4s,#12
1064 sli v21.4s,v3.4s,#12
1066 sli v25.4s,v4.4s,#12
1068 sli v29.4s,v5.4s,#12
1070 add v8.4s,v8.4s,v9.4s
1072 add v12.4s,v12.4s,v13.4s
1074 add v16.4s,v16.4s,v17.4s
1076 add v20.4s,v20.4s,v21.4s
1078 add v24.4s,v24.4s,v25.4s
1080 add v28.4s,v28.4s,v29.4s
1106 add v10.4s,v10.4s,v11.4s
1108 add v14.4s,v14.4s,v15.4s
1110 add v18.4s,v18.4s,v19.4s
1112 add v22.4s,v22.4s,v23.4s
1114 add v26.4s,v26.4s,v27.4s
1116 add v30.4s,v30.4s,v31.4s
1130 ushr v9.4s,v0.4s,#25
1132 ushr v13.4s,v1.4s,#25
1134 ushr v17.4s,v2.4s,#25
1136 ushr v21.4s,v3.4s,#25
1138 ushr v25.4s,v4.4s,#25
1140 ushr v29.4s,v5.4s,#25
1142 sli v9.4s,v0.4s,#7
1144 sli v13.4s,v1.4s,#7
1146 sli v17.4s,v2.4s,#7
1148 sli v21.4s,v3.4s,#7
1150 sli v25.4s,v4.4s,#7
1152 sli v29.4s,v5.4s,#7
1184 add v8.4s,v8.4s,v9.4s
1186 add v12.4s,v12.4s,v13.4s
1188 add v16.4s,v16.4s,v17.4s
1190 add v20.4s,v20.4s,v21.4s
1192 add v24.4s,v24.4s,v25.4s
1194 add v28.4s,v28.4s,v29.4s
1220 add v10.4s,v10.4s,v11.4s
1222 add v14.4s,v14.4s,v15.4s
1224 add v18.4s,v18.4s,v19.4s
1226 add v22.4s,v22.4s,v23.4s
1228 add v26.4s,v26.4s,v27.4s
1230 add v30.4s,v30.4s,v31.4s
1244 ushr v9.4s,v0.4s,#20
1246 ushr v13.4s,v1.4s,#20
1248 ushr v17.4s,v2.4s,#20
1250 ushr v21.4s,v3.4s,#20
1252 ushr v25.4s,v4.4s,#20
1254 ushr v29.4s,v5.4s,#20
1256 sli v9.4s,v0.4s,#12
1258 sli v13.4s,v1.4s,#12
1260 sli v17.4s,v2.4s,#12
1262 sli v21.4s,v3.4s,#12
1264 sli v25.4s,v4.4s,#12
1266 sli v29.4s,v5.4s,#12
1268 add v8.4s,v8.4s,v9.4s
1270 add v12.4s,v12.4s,v13.4s
1272 add v16.4s,v16.4s,v17.4s
1274 add v20.4s,v20.4s,v21.4s
1276 add v24.4s,v24.4s,v25.4s
1278 add v28.4s,v28.4s,v29.4s
1304 add v10.4s,v10.4s,v11.4s
1306 add v14.4s,v14.4s,v15.4s
1308 add v18.4s,v18.4s,v19.4s
1310 add v22.4s,v22.4s,v23.4s
1312 add v26.4s,v26.4s,v27.4s
1314 add v30.4s,v30.4s,v31.4s
1328 ushr v9.4s,v0.4s,#25
1330 ushr v13.4s,v1.4s,#25
1332 ushr v17.4s,v2.4s,#25
1334 ushr v21.4s,v3.4s,#25
1336 ushr v25.4s,v4.4s,#25
1338 ushr v29.4s,v5.4s,#25
1340 sli v9.4s,v0.4s,#7
1342 sli v13.4s,v1.4s,#7
1344 sli v17.4s,v2.4s,#7
1346 sli v21.4s,v3.4s,#7
1348 sli v25.4s,v4.4s,#7
1350 sli v29.4s,v5.4s,#7
1459 add v8.4s,v8.4s,v9.4s
1461 add v12.4s,v12.4s,v13.4s
1463 add v16.4s,v16.4s,v17.4s
1465 add v20.4s,v20.4s,v21.4s
1467 add v24.4s,v24.4s,v25.4s
1469 add v28.4s,v28.4s,v29.4s
1495 add v10.4s,v10.4s,v11.4s
1497 add v14.4s,v14.4s,v15.4s
1499 add v18.4s,v18.4s,v19.4s
1501 add v22.4s,v22.4s,v23.4s
1503 add v26.4s,v26.4s,v27.4s
1505 add v30.4s,v30.4s,v31.4s
1519 ushr v9.4s,v0.4s,#20
1521 ushr v13.4s,v1.4s,#20
1523 ushr v17.4s,v2.4s,#20
1525 ushr v21.4s,v3.4s,#20
1527 ushr v25.4s,v4.4s,#20
1529 ushr v29.4s,v5.4s,#20
1531 sli v9.4s,v0.4s,#12
1533 sli v13.4s,v1.4s,#12
1535 sli v17.4s,v2.4s,#12
1537 sli v21.4s,v3.4s,#12
1539 sli v25.4s,v4.4s,#12
1541 sli v29.4s,v5.4s,#12
1543 add v8.4s,v8.4s,v9.4s
1545 add v12.4s,v12.4s,v13.4s
1547 add v16.4s,v16.4s,v17.4s
1549 add v20.4s,v20.4s,v21.4s
1551 add v24.4s,v24.4s,v25.4s
1553 add v28.4s,v28.4s,v29.4s
1579 add v10.4s,v10.4s,v11.4s
1581 add v14.4s,v14.4s,v15.4s
1583 add v18.4s,v18.4s,v19.4s
1585 add v22.4s,v22.4s,v23.4s
1587 add v26.4s,v26.4s,v27.4s
1589 add v30.4s,v30.4s,v31.4s
1603 ushr v9.4s,v0.4s,#25
1605 ushr v13.4s,v1.4s,#25
1607 ushr v17.4s,v2.4s,#25
1609 ushr v21.4s,v3.4s,#25
1611 ushr v25.4s,v4.4s,#25
1613 ushr v29.4s,v5.4s,#25
1615 sli v9.4s,v0.4s,#7
1617 sli v13.4s,v1.4s,#7
1619 sli v17.4s,v2.4s,#7
1621 sli v21.4s,v3.4s,#7
1623 sli v25.4s,v4.4s,#7
1625 sli v29.4s,v5.4s,#7
1657 add v8.4s,v8.4s,v9.4s
1659 add v12.4s,v12.4s,v13.4s
1661 add v16.4s,v16.4s,v17.4s
1663 add v20.4s,v20.4s,v21.4s
1665 add v24.4s,v24.4s,v25.4s
1667 add v28.4s,v28.4s,v29.4s
1693 add v10.4s,v10.4s,v11.4s
1695 add v14.4s,v14.4s,v15.4s
1697 add v18.4s,v18.4s,v19.4s
1699 add v22.4s,v22.4s,v23.4s
1701 add v26.4s,v26.4s,v27.4s
1703 add v30.4s,v30.4s,v31.4s
1717 ushr v9.4s,v0.4s,#20
1719 ushr v13.4s,v1.4s,#20
1721 ushr v17.4s,v2.4s,#20
1723 ushr v21.4s,v3.4s,#20
1725 ushr v25.4s,v4.4s,#20
1727 ushr v29.4s,v5.4s,#20
1729 sli v9.4s,v0.4s,#12
1731 sli v13.4s,v1.4s,#12
1733 sli v17.4s,v2.4s,#12
1735 sli v21.4s,v3.4s,#12
1737 sli v25.4s,v4.4s,#12
1739 sli v29.4s,v5.4s,#12
1741 add v8.4s,v8.4s,v9.4s
1743 add v12.4s,v12.4s,v13.4s
1745 add v16.4s,v16.4s,v17.4s
1747 add v20.4s,v20.4s,v21.4s
1749 add v24.4s,v24.4s,v25.4s
1751 add v28.4s,v28.4s,v29.4s
1777 add v10.4s,v10.4s,v11.4s
1779 add v14.4s,v14.4s,v15.4s
1781 add v18.4s,v18.4s,v19.4s
1783 add v22.4s,v22.4s,v23.4s
1785 add v26.4s,v26.4s,v27.4s
1787 add v30.4s,v30.4s,v31.4s
1801 ushr v9.4s,v0.4s,#25
1803 ushr v13.4s,v1.4s,#25
1805 ushr v17.4s,v2.4s,#25
1807 ushr v21.4s,v3.4s,#25
1809 ushr v25.4s,v4.4s,#25
1811 ushr v29.4s,v5.4s,#25
1813 sli v9.4s,v0.4s,#7
1815 sli v13.4s,v1.4s,#7
1817 sli v17.4s,v2.4s,#7
1819 sli v21.4s,v3.4s,#7
1821 sli v25.4s,v4.4s,#7
1823 sli v29.4s,v5.4s,#7
1865 add v8.4s,v8.4s,v0.4s
1867 add v12.4s,v12.4s,v0.4s
1869 add v16.4s,v16.4s,v0.4s
1871 add v20.4s,v20.4s,v0.4s
1873 add v24.4s,v24.4s,v0.4s
1875 add v28.4s,v28.4s,v0.4s
1877 add v10.4s,v10.4s,v2.4s
1879 add v14.4s,v14.4s,v2.4s
1881 add v18.4s,v18.4s,v2.4s
1883 add v22.4s,v22.4s,v2.4s
1885 add v26.4s,v26.4s,v2.4s
1887 add v30.4s,v30.4s,v2.4s
1889 add v27.4s,v27.4s,v7.4s // +4
1891 add v31.4s,v31.4s,v7.4s // +4
1893 add v11.4s,v11.4s,v3.4s
1895 add v15.4s,v15.4s,v4.4s
1897 add v19.4s,v19.4s,v5.4s
1899 add v23.4s,v23.4s,v6.4s
1901 add v27.4s,v27.4s,v3.4s
1903 add v31.4s,v31.4s,v4.4s
1905 add v9.4s,v9.4s,v1.4s
1907 add v13.4s,v13.4s,v1.4s
1909 add v17.4s,v17.4s,v1.4s
1911 add v21.4s,v21.4s,v1.4s
1913 add v25.4s,v25.4s,v1.4s
1915 add v29.4s,v29.4s,v1.4s
1980 shl v8.4s,v7.4s,#1 // 4 -> 8
1987 add v3.4s,v3.4s,v8.4s // += 8
1988 add v4.4s,v4.4s,v8.4s
1989 add v5.4s,v5.4s,v8.4s
1990 add v6.4s,v6.4s,v8.4s
1995 ushr v7.4s,v7.4s,#1 // 4 -> 2
2010 sub v3.4s,v3.4s,v7.4s // -= 2
2011 ld1 {v8.4s,v9.4s},[x3]