Xoodoo-avr8-u1.s 28.5 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341
;
; The eXtended Keccak Code Package (XKCP)
; https://github.com/XKCP/XKCP
;
; The Xoodoo permutation, designed by Joan Daemen, Seth Hoffert, Gilles Van Assche and Ronny Van Keer.
;
; Implementation by Ronny Van Keer, hereby denoted as "the implementer".
;
; For more information, feedback or questions, please refer to the Keccak Team website:
; https://keccak.team/
;
; To the extent possible under law, the implementer has waived all copyright
; and related or neighboring rights to the source code in this file.
; http://creativecommons.org/publicdomain/zero/1.0/
;
; ---
;
; This file implements Xoodoo in a SnP-compatible way.
; Please refer to SnP-documentation.h for more details.
;
; This implementation comes with Xoodoo-SnP.h in the same folder.
; Please refer to LowLevel.build for the exact list of other files it must be combined with.
;

; INFO: Tested on ATmega1280 simulator

; Registers used in all routines
#define zero    1
#define rpState 24
#define rX      26
#define rY      28
#define rZ      30
#define sp      0x3D

;----------------------------------------------------------------------------
;
; void Xoodoo_StaticInitialize( void )
;
.global Xoodoo_StaticInitialize

;----------------------------------------------------------------------------
;
; void Xoodoo_Initialize(void *state)
;
; argument state   is passed in r24:r25
;
.global Xoodoo_Initialize
Xoodoo_Initialize:
    movw    rZ, r24
    ldi     r23, 3*4/2        ; clear state (8 bytes / 2 lanes) per iteration
Xoodoo_Initialize_Loop:
    st      z+, zero
    st      z+, zero
    st      z+, zero
    st      z+, zero
    st      z+, zero
    st      z+, zero
    st      z+, zero
    st      z+, zero
    dec     r23
    brne    Xoodoo_Initialize_Loop
Xoodoo_StaticInitialize:
    ret

;----------------------------------------------------------------------------
;
; void Xoodoo_AddByte(void *state, unsigned char data, unsigned int offset)
;
; argument state     is passed in r24:r25
; argument data      is passed in r22:r23, only LSB (r22) is used
; argument offset    is passed in r20:r21, only LSB (r20) is used
;
.global Xoodoo_AddByte
Xoodoo_AddByte:
    movw    rZ, r24
    add     rZ, r20
    adc     rZ+1, zero
    ld      r0, Z
    eor     r0, r22
    st      Z, r0
    ret

;----------------------------------------------------------------------------
;
; void Xoodoo_AddBytes(void *state, const unsigned char *data, unsigned int offset, unsigned int length)
;
; argument state     is passed in r24:r25
; argument data      is passed in r22:r23
; argument offset    is passed in r20:r21, only LSB (r20) is used
; argument length    is passed in r18:r19, only LSB (r18) is used
;
.global Xoodoo_AddBytes
Xoodoo_AddBytes:
    movw    rZ, r24
    add     rZ, r20
    adc     rZ+1, zero
    movw    rX, r22
    subi    r18, 8
    brcs    Xoodoo_AddBytes_Byte
    ;do 8 bytes per iteration
Xoodoo_AddBytes_Loop8:
    ld      r21, X+
    ld      r0, Z
    eor     r0, r21
    st      Z+, r0
    ld      r21, X+
    ld      r0, Z
    eor     r0, r21
    st      Z+, r0
    ld      r21, X+
    ld      r0, Z
    eor     r0, r21
    st      Z+, r0
    ld      r21, X+
    ld      r0, Z
    eor     r0, r21
    st      Z+, r0
    ld      r21, X+
    ld      r0, Z
    eor     r0, r21
    st      Z+, r0
    ld      r21, X+
    ld      r0, Z
    eor     r0, r21
    st      Z+, r0
    ld      r21, X+
    ld      r0, Z
    eor     r0, r21
    st      Z+, r0
    ld      r21, X+
    ld      r0, Z
    eor     r0, r21
    st      Z+, r0
    subi    r18, 8
    brcc    Xoodoo_AddBytes_Loop8
Xoodoo_AddBytes_Byte:
    ldi     r19, 8
    add     r18, r19
    breq    Xoodoo_AddBytes_End
Xoodoo_AddBytes_Loop1:
    ld      r21, X+
    ld      r0, Z
    eor     r0, r21
    st      Z+, r0
    dec     r18
    brne    Xoodoo_AddBytes_Loop1
Xoodoo_AddBytes_End:
    ret


;----------------------------------------------------------------------------
;
; void Xoodoo_OverwriteBytes(void *state, const unsigned char *data, unsigned int offset, unsigned int length)
;
; argument state     is passed in r24:r25
; argument data      is passed in r22:r23
; argument offset    is passed in r20:r21, only LSB (r20) is used
; argument length    is passed in r18:r19, only LSB (r18) is used
;
.global Xoodoo_OverwriteBytes
Xoodoo_OverwriteBytes:
    movw    rZ, r24
    add     rZ, r20
    adc     rZ+1, zero
    movw    rX, r22
    subi    r18, 8
    brcs    Xoodoo_OverwriteBytes_Byte
    ;do 8 bytes per iteration
Xoodoo_OverwriteBytes_Loop8:
    ld      r0, X+
    st      Z+, r0
    ld      r0, X+
    st      Z+, r0
    ld      r0, X+
    st      Z+, r0
    ld      r0, X+
    st      Z+, r0
    ld      r0, X+
    st      Z+, r0
    ld      r0, X+
    st      Z+, r0
    ld      r0, X+
    st      Z+, r0
    ld      r0, X+
    st      Z+, r0
    subi    r18, 8
    brcc    Xoodoo_OverwriteBytes_Loop8
Xoodoo_OverwriteBytes_Byte:
    ldi     r19, 8
    add     r18, r19
    breq    Xoodoo_OverwriteBytes_End
Xoodoo_OverwriteBytes_Loop1:
    ld      r0, X+
    st      Z+, r0
    dec     r18
    brne    Xoodoo_OverwriteBytes_Loop1
Xoodoo_OverwriteBytes_End:
    ret

;----------------------------------------------------------------------------
;
; void Xoodoo_OverwriteWithZeroes(void *state, unsigned int byteCount)
;
; argument state        is passed in r24:r25
; argument byteCount    is passed in r22:r23, only LSB (r22) is used
;
.global Xoodoo_OverwriteWithZeroes
Xoodoo_OverwriteWithZeroes:
    movw    rZ, r24         ; rZ = state
    mov     r23, r22
    lsr     r23
    lsr     r23
    lsr     r23
    breq    Xoodoo_OverwriteWithZeroes_Bytes
Xoodoo_OverwriteWithZeroes_LoopLanes:
    st      Z+, r1
    st      Z+, r1
    st      Z+, r1
    st      Z+, r1
    st      Z+, r1
    st      Z+, r1
    st      Z+, r1
    st      Z+, r1
    dec     r23
    brne    Xoodoo_OverwriteWithZeroes_LoopLanes
Xoodoo_OverwriteWithZeroes_Bytes:
    andi    r22, 7
    breq    Xoodoo_OverwriteWithZeroes_End
Xoodoo_OverwriteWithZeroes_LoopBytes:
    st      Z+, r1
    dec     r22
    brne    Xoodoo_OverwriteWithZeroes_LoopBytes
Xoodoo_OverwriteWithZeroes_End:
    ret

;----------------------------------------------------------------------------
;
; void Xoodoo_ExtractBytes(void *state, const unsigned char *data, unsigned int offset, unsigned int length)
;
; argument state     is passed in r24:r25
; argument data      is passed in r22:r23
; argument offset    is passed in r20:r21, only LSB (r20) is used
; argument length    is passed in r18:r19, only LSB (r18) is used
;
.global Xoodoo_ExtractBytes
Xoodoo_ExtractBytes:
    movw    rZ, r24
    add     rZ, r20
    adc     rZ+1, zero
    movw    rX, r22
    subi    r18, 8
    brcs    Xoodoo_ExtractBytes_Byte
    ;do 8 bytes per iteration
Xoodoo_ExtractBytes_Loop8:
    ld      r0, Z+
    st      X+, r0
    ld      r0, Z+
    st      X+, r0
    ld      r0, Z+
    st      X+, r0
    ld      r0, Z+
    st      X+, r0
    ld      r0, Z+
    st      X+, r0
    ld      r0, Z+
    st      X+, r0
    ld      r0, Z+
    st      X+, r0
    ld      r0, Z+
    st      X+, r0
    subi    r18, 8
    brcc    Xoodoo_ExtractBytes_Loop8
Xoodoo_ExtractBytes_Byte:
    ldi     r19, 8
    add     r18, r19
    breq    Xoodoo_ExtractBytes_End
Xoodoo_ExtractBytes_Loop1:
    ld      r0, Z+
    st      X+, r0
    dec     r18
    brne    Xoodoo_ExtractBytes_Loop1
Xoodoo_ExtractBytes_End:
    ret

;----------------------------------------------------------------------------
;
; void Xoodoo_ExtractAndAddBytes(void *state, const unsigned char *input, unsigned char *output, unsigned int offset, unsigned int length)
;
; argument state     is passed in r24:r25
; argument input     is passed in r22:r23
; argument output    is passed in r20:r21
; argument offset    is passed in r18:r19, only LSB (r18) is used
; argument length    is passed in r16:r17, only LSB (r16) is used
;
.global Xoodoo_ExtractAndAddBytes
Xoodoo_ExtractAndAddBytes:
    tst     r16
    breq    Xoodoo_ExtractAndAddBytes_End
    push    r16
    push    r28
    push    r29
    movw    rZ, r24
    add     rZ, r18
    adc     rZ+1, zero
    movw    rX, r22
    movw    rY, r20
    subi    r16, 8
    brcs    Xoodoo_ExtractAndAddBytes_Byte
Xoodoo_ExtractAndAddBytes_LoopLane:
    ld      r21, Z+
    ld      r0, X+
    eor     r0, r21
    st      Y+, r0
    ld      r21, Z+
    ld      r0, X+
    eor     r0, r21
    st      Y+, r0
    ld      r21, Z+
    ld      r0, X+
    eor     r0, r21
    st      Y+, r0
    ld      r21, Z+
    ld      r0, X+
    eor     r0, r21
    st      Y+, r0
    ld      r21, Z+
    ld      r0, X+
    eor     r0, r21
    st      Y+, r0
    ld      r21, Z+
    ld      r0, X+
    eor     r0, r21
    st      Y+, r0
    ld      r21, Z+
    ld      r0, X+
    eor     r0, r21
    st      Y+, r0
    ld      r21, Z+
    ld      r0, X+
    eor     r0, r21
    st      Y+, r0
    subi    r16, 8
    brcc    Xoodoo_ExtractAndAddBytes_LoopLane
Xoodoo_ExtractAndAddBytes_Byte:
    ldi     r19, 8
    add     r16, r19
    breq    Xoodoo_ExtractAndAddBytes_Done
Xoodoo_ExtractAndAddBytes_Loop1:
    ld      r21, Z+
    ld      r0, X+
    eor     r0, r21
    st      Y+, r0
    dec     r16
    brne    Xoodoo_ExtractAndAddBytes_Loop1
Xoodoo_ExtractAndAddBytes_Done:
    pop     r29
    pop     r28
    pop     r16
Xoodoo_ExtractAndAddBytes_End:
    ret

Xoodoo_RoundConstants_12:
    .BYTE   0x58, 0x00
    .BYTE   0x38, 0x00
    .BYTE   0xC0, 0x03
    .BYTE   0xD0, 0x00
    .BYTE   0x20, 0x01
    .BYTE   0x14, 0x00
Xoodoo_RoundConstants_6:
    .BYTE   0x60, 0x00
    .BYTE   0x2C, 0x00
    .BYTE   0x80, 0x03
    .BYTE   0xF0, 0x00
    .BYTE   0xA0, 0x01
    .BYTE   0x12, 0x00
Xoodoo_RoundConstants_0:
    .BYTE   0xFF, 0        ; terminator

    .text

; Register variables used in permutation
#define rC0          2      // 4 regs (2-5)
#define rC1          6      // 4 regs (6-9)
#define rC2         10      // 4 regs (10-13)
#define rC3         14      // 4 regs (14-17)
#define rVv         18      // 4 regs (18-21)
#define rTt         22      // 4 regs (22-25)
// r26-27 free
#define a00          0
#define a01          4
#define a02          8
#define a03         12
#define a10         16
#define a11         20
#define a12         24
#define a13         28
#define a20         32
#define a21         36
#define a22         40
#define a23         44

;----------------------------------------------------------------------------
;
; void Xoodoo_Permute_Nrounds( void *state, unsigned int nrounds )
;
; argument state     is passed in r24:r25
; argument nrounds   is passed in r22:r23 (only LSB (r22) is used)
;
.global Xoodoo_Permute_Nrounds
Xoodoo_Permute_Nrounds:
	mov		r26, r22
    ldi     rZ+0, lo8(Xoodoo_RoundConstants_0)
    ldi     rZ+1, hi8(Xoodoo_RoundConstants_0)
	lsl		r26
    sub     rZ, r26
    sbc     rZ+1, zero
    rjmp    Xoodoo_Permute

;----------------------------------------------------------------------------
;
; void Xoodoo_Permute_6rounds( void *state )
;
; argument state     is passed in r24:r25
;
.global Xoodoo_Permute_6rounds
Xoodoo_Permute_6rounds:
    ldi     rZ+0, lo8(Xoodoo_RoundConstants_6)
    ldi     rZ+1, hi8(Xoodoo_RoundConstants_6)
    rjmp    Xoodoo_Permute

;----------------------------------------------------------------------------
;
; void Xoodoo_Permute_12rounds( void *state )
;
; argument state     is passed in r24:r25
;
.global Xoodoo_Permute_12rounds
Xoodoo_Permute_12rounds:
    ldi     rZ+0, lo8(Xoodoo_RoundConstants_12)
    ldi     rZ+1, hi8(Xoodoo_RoundConstants_12)
Xoodoo_Permute:
    push    r2
    push    r3
    push    r4
    push    r5
    push    r6
    push    r7
    push    r8
    push    r9
    push    r10
    push    r11
    push    r12
    push    r13
    push    r14
    push    r15
    push    r16
    push    r17
    push    r28
    push    r29

    ; Initial Prepare Theta
    movw    rY, rpState
    ld      rC0+0, Y+          ; a00
    ld      rC0+1, Y+
    ld      rC0+2, Y+
    ld      rC0+3, Y+
    ld      rC1+0, Y+          ; a01
    ld      rC1+1, Y+
    ld      rC1+2, Y+
    ld      rC1+3, Y+
    ld      rC2+0, Y+          ; a02
    ld      rC2+1, Y+
    ld      rC2+2, Y+
    ld      rC2+3, Y+
    ld      rC3+0, Y+          ; a03
    ld      rC3+1, Y+
    ld      rC3+2, Y+
    ld      rC3+3, Y+

    ld      r0, Y+             ; a10
    eor     rC0+0, r0
    ld      r0, Y+
    eor     rC0+1, r0
    ld      r0, Y+
    eor     rC0+2, r0
    ld      r0, Y+
    eor     rC0+3, r0
    ld      r0, Y+             ; a11
    eor     rC1+0, r0
    ld      r0, Y+
    eor     rC1+1, r0
    ld      r0, Y+
    eor     rC1+2, r0
    ld      r0, Y+
    eor     rC1+3, r0
    ld      r0, Y+             ; a12
    eor     rC2+0, r0
    ld      r0, Y+
    eor     rC2+1, r0
    ld      r0, Y+
    eor     rC2+2, r0
    ld      r0, Y+
    eor     rC2+3, r0
    ld      r0, Y+             ; a13
    eor     rC3+0, r0
    ld      r0, Y+
    eor     rC3+1, r0
    ld      r0, Y+
    eor     rC3+2, r0
    ld      r0, Y+
    eor     rC3+3, r0

    ld      r0, Y+             ; a20
    eor     rC0+0, r0
    ld      r0, Y+
    eor     rC0+1, r0
    ld      r0, Y+
    eor     rC0+2, r0
    ld      r0, Y+
    eor     rC0+3, r0
    ld      r0, Y+             ; a21
    eor     rC1+0, r0
    ld      r0, Y+
    eor     rC1+1, r0
    ld      r0, Y+
    eor     rC1+2, r0
    ld      r0, Y+
    eor     rC1+3, r0
    ld      r0, Y+             ; a22
    eor     rC2+0, r0
    ld      r0, Y+
    eor     rC2+1, r0
    ld      r0, Y+
    eor     rC2+2, r0
    ld      r0, Y+
    eor     rC2+3, r0
    ld      r0, Y+             ; a23
    eor     rC3+0, r0
    ld      r0, Y+
    eor     rC3+1, r0
    ld      r0, Y+
    eor     rC3+2, r0
    ld      r0, Y+
    eor     rC3+3, r0
	sbiw    rY, 48

Xoodoo_RoundLoop:
    ; Theta + Rho west
    ; c0 = ROTL32(c0 ^ ROTL32(c0, 9), 5);
    mov     rVv+1, rC0+0     ; rol 9
    mov     rVv+2, rC0+1
    mov     rVv+3, rC0+2
    mov     rVv+0, rC0+3
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
    eor     rVv+0, rC0+0
    eor     rVv+1, rC0+1
    eor     rVv+2, rC0+2
    eor     rVv+3, rC0+3
    bst     rVv, 0           ; rol 5 (= ror 3 + rol 8)
    ror     rVv+3
    ror     rVv+2
    ror     rVv+1
    ror     rVv
    bld     rVv+3, 7
    bst     rVv, 0
    ror     rVv+3
    ror     rVv+2
    ror     rVv+1
    ror     rVv
    bld     rVv+3, 7
    bst     rVv, 0
    ror     rVv+3
    ror     rVv+2
    ror     rVv+1
    ror     rVv
    bld     rVv+3, 7
    mov     rC0+0, rVv+3
    mov     rC0+1, rVv+0
    mov     rC0+2, rVv+1
    mov     rC0+3, rVv+2

    ; c1 = ROTL32(c1 ^ ROTL32(c1, 9), 5);
    mov     rVv+1, rC1+0     ; rol 9
    mov     rVv+2, rC1+1
    mov     rVv+3, rC1+2
    mov     rVv+0, rC1+3
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
    eor     rVv+0, rC1+0
    eor     rVv+1, rC1+1
    eor     rVv+2, rC1+2
    eor     rVv+3, rC1+3
    bst     rVv, 0           ; rol 5 (= ror 3 + rol 8)
    ror     rVv+3
    ror     rVv+2
    ror     rVv+1
    ror     rVv
    bld     rVv+3, 7
    bst     rVv, 0
    ror     rVv+3
    ror     rVv+2
    ror     rVv+1
    ror     rVv
    bld     rVv+3, 7
    bst     rVv, 0
    ror     rVv+3
    ror     rVv+2
    ror     rVv+1
    ror     rVv
    bld     rVv+3, 7
    mov     rC1+0, rVv+3
    mov     rC1+1, rVv+0
    mov     rC1+2, rVv+1
    mov     rC1+3, rVv+2

    ; c2 = ROTL32(c2 ^ ROTL32(c2, 9), 5);
    mov     rVv+1, rC2+0     ; rol 9
    mov     rVv+2, rC2+1
    mov     rVv+3, rC2+2
    mov     rVv+0, rC2+3
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
    eor     rVv+0, rC2+0
    eor     rVv+1, rC2+1
    eor     rVv+2, rC2+2
    eor     rVv+3, rC2+3
    bst     rVv, 0           ; rol 5 (= ror 3 + rol 8)
    ror     rVv+3
    ror     rVv+2
    ror     rVv+1
    ror     rVv
    bld     rVv+3, 7
    bst     rVv, 0
    ror     rVv+3
    ror     rVv+2
    ror     rVv+1
    ror     rVv
    bld     rVv+3, 7
    bst     rVv, 0
    ror     rVv+3
    ror     rVv+2
    ror     rVv+1
    ror     rVv
    bld     rVv+3, 7
    mov     rC2+0, rVv+3
    mov     rC2+1, rVv+0
    mov     rC2+2, rVv+1
    mov     rC2+3, rVv+2

    ; c3 = ROTL32(c3 ^ ROTL32(c3, 9), 5);
    mov     rVv+1, rC3+0     ; rol 9
    mov     rVv+2, rC3+1
    mov     rVv+3, rC3+2
    mov     rVv+0, rC3+3
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
    eor     rVv+0, rC3+0
    eor     rVv+1, rC3+1
    eor     rVv+2, rC3+2
    eor     rVv+3, rC3+3
    bst     rVv, 0           ; rol 5 (= ror 3 + rol 8)
    ror     rVv+3
    ror     rVv+2
    ror     rVv+1
    ror     rVv
    bld     rVv+3, 7
    bst     rVv, 0
    ror     rVv+3
    ror     rVv+2
    ror     rVv+1
    ror     rVv
    bld     rVv+3, 7
    bst     rVv, 0
    ror     rVv+3
    ror     rVv+2
    ror     rVv+1
    ror     rVv
    bld     rVv+3, 7
    mov     rC3+0, rVv+3
    mov     rC3+1, rVv+0
    mov     rC3+2, rVv+1
    mov     rC3+3, rVv+2
	
    ; v1 = a13;
	ldd		rVv+0, Y+a13+0
	ldd		rVv+1, Y+a13+1
	ldd		rVv+2, Y+a13+2
	ldd		rVv+3, Y+a13+3

    ; a13 = a12 ^ c1;
	ldd		r0, Y+a12+0
	eor		r0, rC1+0
	std		Y+a13+0, r0
	ldd		r0, Y+a12+1
	eor		r0, rC1+1
	std		Y+a13+1, r0
	ldd		r0, Y+a12+2
	eor		r0, rC1+2
	std		Y+a13+2, r0
	ldd		r0, Y+a12+3
	eor		r0, rC1+3
	std		Y+a13+3, r0

    ; a12 = a11 ^ c0;
	ldd		r0, Y+a11+0
	eor		r0, rC0+0
	std		Y+a12+0, r0
	ldd		r0, Y+a11+1
	eor		r0, rC0+1
	std		Y+a12+1, r0
	ldd		r0, Y+a11+2
	eor		r0, rC0+2
	std		Y+a12+2, r0
	ldd		r0, Y+a11+3
	eor		r0, rC0+3
	std		Y+a12+3, r0

    ; a11 = a10 ^ c3;
	ldd		r0, Y+a10+0
	eor		r0, rC3+0
	std		Y+a11+0, r0
	ldd		r0, Y+a10+1
	eor		r0, rC3+1
	std		Y+a11+1, r0
	ldd		r0, Y+a10+2
	eor		r0, rC3+2
	std		Y+a11+2, r0
	ldd		r0, Y+a10+3
	eor		r0, rC3+3
	std		Y+a11+3, r0

    ; a10 = v1  ^ c2;
	eor		rVv+0, rC2+0
	std		Y+a10+0, rVv+0
	eor		rVv+1, rC2+1
	std		Y+a10+1, rVv+1
	eor		rVv+2, rC2+2
	std		Y+a10+2, rVv+2
	eor		rVv+3, rC2+3
	std		Y+a10+3, rVv+3

    ; a20 = ROTL32(a20 ^ c3, 11);
	ldd		rVv+0, Y+a20+3
	eor		rVv+0, rC3+3
	ldd		rVv+1, Y+a20+0
	eor		rVv+1, rC3+0
	ldd		rVv+2, Y+a20+1
	eor		rVv+2, rC3+1
	ldd		rVv+3, Y+a20+2
	eor		rVv+3, rC3+2
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
	std		Y+a20+0, rVv+0
	std		Y+a20+1, rVv+1
	std		Y+a20+2, rVv+2
	std		Y+a20+3, rVv+3

    ; a21 = ROTL32(a21 ^ c0, 11);
	ldd		rVv+0, Y+a21+3
	eor		rVv+0, rC0+3
	ldd		rVv+1, Y+a21+0
	eor		rVv+1, rC0+0
	ldd		rVv+2, Y+a21+1
	eor		rVv+2, rC0+1
	ldd		rVv+3, Y+a21+2
	eor		rVv+3, rC0+2
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
	std		Y+a21+0, rVv+0
	std		Y+a21+1, rVv+1
	std		Y+a21+2, rVv+2
	std		Y+a21+3, rVv+3

    ; a22 = ROTL32(a22 ^ c1, 11);
	ldd		rVv+0, Y+a22+3
	eor		rVv+0, rC1+3
	ldd		rVv+1, Y+a22+0
	eor		rVv+1, rC1+0
	ldd		rVv+2, Y+a22+1
	eor		rVv+2, rC1+1
	ldd		rVv+3, Y+a22+2
	eor		rVv+3, rC1+2
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
	std		Y+a22+0, rVv+0
	std		Y+a22+1, rVv+1
	std		Y+a22+2, rVv+2
	std		Y+a22+3, rVv+3

    ; a23 = ROTL32(a23 ^ c2, 11);
	ldd		rVv+0, Y+a23+3
	eor		rVv+0, rC2+3
	ldd		rVv+1, Y+a23+0
	eor		rVv+1, rC2+0
	ldd		rVv+2, Y+a23+1
	eor		rVv+2, rC2+1
	ldd		rVv+3, Y+a23+2
	eor		rVv+3, rC2+2
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
    lsl     rVv+0
    rol     rVv+1
    rol     rVv+2
    rol     rVv+3
    adc     rVv+0, zero
	std		Y+a23+0, rVv+0
	std		Y+a23+1, rVv+1
	std		Y+a23+2, rVv+2
	std		Y+a23+3, rVv+3

	; v1 = c3;
	movw    rVv+0, rC3+0
	movw    rVv+2, rC3+2

    ; c3 = a03 ^ c2; /* a03 resides in c3 */
	ldd		rC3+0, Y+a03+0
	eor     rC3+0, rC2+0
	ldd		rC3+1, Y+a03+1
	eor     rC3+1, rC2+1
	ldd		rC3+2, Y+a03+2
	eor     rC3+2, rC2+2
	ldd		rC3+3, Y+a03+3
	eor     rC3+3, rC2+3

    ; c2 = a02 ^ c1; /* a02 resides in c2 */
	ldd		rC2+0, Y+a02+0
	eor     rC2+0, rC1+0
	ldd		rC2+1, Y+a02+1
	eor     rC2+1, rC1+1
	ldd		rC2+2, Y+a02+2
	eor     rC2+2, rC1+2
	ldd		rC2+3, Y+a02+3
	eor     rC2+3, rC1+3

    ; c1 = a01 ^ c0; /* a01 resides in c1 */
	ldd		rC1+0, Y+a01+0
	eor     rC1+0, rC0+0
	ldd		rC1+1, Y+a01+1
	eor     rC1+1, rC0+1
	ldd		rC1+2, Y+a01+2
	eor     rC1+2, rC0+2
	ldd		rC1+3, Y+a01+3
	eor     rC1+3, rC0+3

    ; c0 = a00 ^ v1; /* a00 resides in c0 */
	ldd		rC0+0, Y+a00+0
	eor     rC0+0, rVv+0
	ldd		rC0+1, Y+a00+1
	eor     rC0+1, rVv+1
	ldd		rC0+2, Y+a00+2
	eor     rC0+2, rVv+2
	ldd		rC0+3, Y+a00+3
	eor     rC0+3, rVv+3

    ; c0 ^= __rc;    /* +Iota */
    lpm     rVv+0, Z+
    lpm     rVv+1, Z+
	eor     rC0+0, rVv+0
	eor     rC0+1, rVv+1

    ; Chi + Rho east + Early Theta
    ; a00 = c0 ^= ~a10 & a20;
	ldd		r0, Y+a10+0
    com     r0
	ldd		rTt+0, Y+a20+0		; a20 in rTt
    and     r0, rTt+0
    eor     rC0+0, r0
	std		Y+a00+0, rC0+0
	ldd		r0, Y+a10+1
    com     r0
	ldd		rTt+1, Y+a20+1
    and     r0, rTt+1
    eor     rC0+1, r0
	std		Y+a00+1, rC0+1
	ldd		r0, Y+a10+2
    com     r0
	ldd		rTt+2, Y+a20+2
    and     r0, rTt+2
    eor     rC0+2, r0
	std		Y+a00+2, rC0+2
	ldd		r0, Y+a10+3
    com     r0
	ldd		rTt+3, Y+a20+3
    and     r0, rTt+3
    eor     rC0+3, r0
	std		Y+a00+3, rC0+3

    ; a10 ^= ~a20 & c0;
    com     rTt+0
	and		rTt+0, rC0+0
	ldd     r0, Y+a10+0
    eor     rTt+0, r0			; new a10 in rTt
	std     Y+a10+0, rTt+0
    com     rTt+1
	and		rTt+1, rC0+1
	ldd     r0, Y+a10+1
    eor     rTt+1, r0
	std     Y+a10+1, rTt+1
    com     rTt+2
	and		rTt+2, rC0+2
	ldd     r0, Y+a10+2
    eor     rTt+2, r0
	std     Y+a10+2, rTt+2
    com     rTt+3
	and		rTt+3, rC0+3
	ldd     r0, Y+a10+3
    eor     rTt+3, r0
	std     Y+a10+3, rTt+3

    ; v1(a20) = ROTL32(a20 ^ ~c0 & a10, 8);
	movw	rVv+0, rTt+0	; a10 in rVv
	movw	rVv+2, rTt+2
    mov     r0, rC0+0
    com     r0
	and		rTt+0, r0
	ldd     r0, Y+a20+0
	eor     rTt+0, r0	

    mov     r0, rC0+1
    com     r0
	and		rTt+1, r0
	ldd     r0, Y+a20+1
	eor     rTt+1, r0

    mov     r0, rC0+2
    com     r0
	and		rTt+2, r0
	ldd     r0, Y+a20+2
	eor     rTt+2, r0

    mov     r0, rC0+3
    com     r0
	and		rTt+3, r0
	ldd     r0, Y+a20+3
	eor     rTt+3, r0
	std     Y+a20+0, rTt+3
	std     Y+a20+1, rTt+0
	std     Y+a20+2, rTt+1
	std     Y+a20+3, rTt+2

    ; c0 ^= a10 = ROTL32(a10, 1);
    lsl     rVv+0
    rol     rVv+1
	std     Y+a10+1, rVv+1
	eor		rC0+1, rVv+1
    rol     rVv+2
	std     Y+a10+2, rVv+2
	eor		rC0+2, rVv+2
    rol     rVv+3
	std     Y+a10+3, rVv+3
	eor		rC0+3, rVv+3
    adc     rVv+0, zero
	std     Y+a10+0, rVv+0
	eor		rC0+0, rVv+0

    ; a02 = c2 ^= ~a12 & a22;
	ldd     r0, Y+a12+0
    com     r0
	ldd     rVv+0, Y+a22+0	; a22 in rVv
	and		r0, rVv+0
	eor		rC2+0, r0
	std		Y+a02+0, rC2+0
	ldd     r0, Y+a12+1
    com     r0
	ldd     rVv+1, Y+a22+1
	and		r0, rVv+1
	eor		rC2+1, r0
	std		Y+a02+1, rC2+1
	ldd     r0, Y+a12+2
    com     r0
	ldd     rVv+2, Y+a22+2
	and		r0, rVv+2
	eor		rC2+2, r0
	std		Y+a02+2, rC2+2
	ldd     r0, Y+a12+3
    com     r0
	ldd     rVv+3, Y+a22+3
	and		r0, rVv+3
	eor		rC2+3, r0
	std		Y+a02+3, rC2+3

    ; a12 ^= ~a22 & c2;
	mov     r0, rVv+0		; a12 in rTt
	com		r0
	and		r0, rC2+0
	ldd		rTt+0, Y+a12+0
	eor		rTt+0, r0
	std		Y+a12+0, rTt+0
	mov     r0, rVv+1
	com		r0
	and		r0, rC2+1
	ldd		rTt+1, Y+a12+1
	eor		rTt+1, r0
	std		Y+a12+1, rTt+1
	mov     r0, rVv+2
	com		r0
	and		r0, rC2+2
	ldd		rTt+2, Y+a12+2
	eor		rTt+2, r0
	std		Y+a12+2, rTt+2
	mov     r0, rVv+3
	com		r0
	and		r0, rC2+3
	ldd		rTt+3, Y+a12+3
	eor		rTt+3, r0
	std		Y+a12+3, rTt+3

    ; c0 ^= a20 = ROTL32(a22 ^ ~c2 & a12, 8);
	mov     r0, rC2+0
	com		r0
	and		r0, rTt+0
	eor		r0, rVv+0
	ldd		rVv+0, Y+a20+1		; rVv = a22
	std		Y+a20+1, r0
	eor		rC0+1, r0
	mov     r0, rC2+1
	com		r0
	and		r0, rTt+1
	eor		r0, rVv+1
	ldd		rVv+1, Y+a20+2
	std		Y+a20+2, r0
	eor		rC0+2, r0
	mov     r0, rC2+2
	com		r0
	and		r0, rTt+2
	eor		r0, rVv+2
	ldd		rVv+2, Y+a20+3
	std		Y+a20+3, r0
	eor		rC0+3, r0
	mov     r0, rC2+3
	com		r0
	and		r0, rTt+3
	eor		r0, rVv+3
	ldd		rVv+3, Y+a20+0
	std		Y+a20+0, r0
	eor		rC0+0, r0

    ; c2 ^= a12 = ROTL32(a12, 1);
    lsl     rTt+0
    rol     rTt+1
	eor		rC2+1, rTt+1
	std     Y+a12+1, rTt+1
    rol     rTt+2
	eor		rC2+2, rTt+2
	std     Y+a12+2, rTt+2
    rol     rTt+3
	eor		rC2+3, rTt+3
	std     Y+a12+3, rTt+3
    adc     rTt+0, zero
	eor		rC2+0, rTt+0
	std     Y+a12+0, rTt+0

    ; a22 = v1;
	std     Y+a22+0, rVv+3
	std     Y+a22+1, rVv+0
	std     Y+a22+2, rVv+1
	std     Y+a22+3, rVv+2

	; c2 ^= v1;
	eor		rC2+0, rVv+3
	eor		rC2+1, rVv+0
	eor		rC2+2, rVv+1
	eor		rC2+3, rVv+2

    ; a01 = c1 ^= ~a11 & a21;
	ldd		rTt+0, Y+a11+0  ;rTt holds a11
	mov		r0, rTt+0
	com		r0
	ldd		rVv+0, Y+a21+0  ;rVv holds a21
	and		r0, rVv+0
	eor		rC1+0, r0
	std		Y+a01+0, rC1+0
	ldd		rTt+1, Y+a11+1
	mov		r0, rTt+1
	com		r0
	ldd		rVv+1, Y+a21+1
	and		r0, rVv+1
	eor		rC1+1, r0
	std		Y+a01+1, rC1+1
	ldd		rTt+2, Y+a11+2
	mov		r0, rTt+2
	com		r0
	ldd		rVv+2, Y+a21+2
	and		r0, rVv+2
	eor		rC1+2, r0
	std		Y+a01+2, rC1+2
	ldd		rTt+3, Y+a11+3
	mov		r0, rTt+3
	com		r0
	ldd		rVv+3, Y+a21+3
	and		r0, rVv+3
	eor		rC1+3, r0
	std		Y+a01+3, rC1+3

    ; a11 ^= ~a21 & c1;
	mov		r0, rVv+0
	com		r0
	and		r0, rC1+0
	eor		rTt+0, r0
	std		Y+a11+0, rTt+0
	mov		r0, rVv+1
	com		r0
	and		r0, rC1+1
	eor		rTt+1, r0
	std		Y+a11+1, rTt+1
	mov		r0, rVv+2
	com		r0
	and		r0, rC1+2
	eor		rTt+2, r0
	std		Y+a11+2, rTt+2
	mov		r0, rVv+3
	com		r0
	and		r0, rC1+3
	eor		rTt+3, r0
	std		Y+a11+3, rTt+3

    ; v1 = ROTL32(a21 ^ ~c1 & a11, 8);
	mov     r0, rC1+0
	com		r0
	and		r0, rTt+0
	eor		rVv+0, r0           ; v1 not yet ROTL32'ed(8)
	mov     r0, rC1+1
	com		r0
	and		r0, rTt+1
	eor		rVv+1, r0
	mov     r0, rC1+2
	com		r0
	and		r0, rTt+2
	eor		rVv+2, r0
	mov     r0, rC1+3
	com		r0
	and		r0, rTt+3
	eor		rVv+3, r0

    ; c1 ^= a11 = ROTL32(a11, 1);
    lsl     rTt+0
    rol     rTt+1
	eor		rC1+1, rTt+1
	std     Y+a11+1, rTt+1
    rol     rTt+2
	eor		rC1+2, rTt+2
	std     Y+a11+2, rTt+2
    rol     rTt+3
	eor		rC1+3, rTt+3
	std     Y+a11+3, rTt+3
    adc     rTt+0, zero
	eor		rC1+0, rTt+0
	std     Y+a11+0, rTt+0

    ; a03 = c3 ^= ~a13 & a23;
	ldd     r0, Y+a13+0
    com     r0
	ldd     rTt+0, Y+a23+0	; a23 in rTt
	and		r0, rTt+0
	eor		rC3+0, r0
	std		Y+a03+0, rC3+0
	ldd     r0, Y+a13+1
    com     r0
	ldd     rTt+1, Y+a23+1
	and		r0, rTt+1
	eor		rC3+1, r0
	std		Y+a03+1, rC3+1
	ldd     r0, Y+a13+2
    com     r0
	ldd     rTt+2, Y+a23+2
	and		r0, rTt+2
	eor		rC3+2, r0
	std		Y+a03+2, rC3+2
	ldd     r0, Y+a13+3
    com     r0
	ldd     rTt+3, Y+a23+3
	and		r0, rTt+3
	eor		rC3+3, r0
	std		Y+a03+3, rC3+3

    ; a13 ^= ~a23 & c3;
	mov     r0, rTt+0
    com     r0
	and     r0, rC3+0
	ldd		rTt+0, Y+a13+0		; a13 in rTt
	eor		rTt+0, r0
	mov     r0, rTt+1
    com     r0
	and     r0, rC3+1
	ldd		rTt+1, Y+a13+1
	eor		rTt+1, r0
	mov     r0, rTt+2
    com     r0
	and     r0, rC3+2
	ldd		rTt+2, Y+a13+2
	eor		rTt+2, r0
	mov     r0, rTt+3
    com     r0
	and     r0, rC3+3
	ldd		rTt+3, Y+a13+3
	eor		rTt+3, r0

    ; c1 ^= a21 = ROTL32(a23 ^ ~c3 & a13, 8);
	push	rVv
	mov     r0, rC3+0
    com     r0
	and     r0, rTt+0
	ldd		rVv, Y+a23+0
	eor     r0, rVv
	eor     rC1+1, r0
	std		Y+a21+1, r0
	mov     r0, rC3+1
    com     r0
	and     r0, rTt+1
	ldd		rVv, Y+a23+1
	eor     r0, rVv
	eor     rC1+2, r0
	std		Y+a21+2, r0
	mov     r0, rC3+2
    com     r0
	and     r0, rTt+2
	ldd		rVv, Y+a23+2
	eor     r0, rVv
	eor     rC1+3, r0
	std		Y+a21+3, r0
	mov     r0, rC3+3
    com     r0
	and     r0, rTt+3
	ldd		rVv, Y+a23+3
	eor     r0, rVv
	eor     rC1+0, r0
	std		Y+a21+0, r0
	pop     rVv

    ; a23 = v1;
	std		Y+a23+0, rVv+3 ; rol8(rVv)
	std		Y+a23+1, rVv+0
	std		Y+a23+2, rVv+1
	std		Y+a23+3, rVv+2

	; c3 ^= v1;
	eor     rC3+0, rVv+3
	eor     rC3+1, rVv+0
	eor     rC3+2, rVv+1
	eor     rC3+3, rVv+2

    ; c3 ^= a13 = ROTL32(a13, 1);
    lsl     rTt+0
    rol     rTt+1
	std     Y+a13+1, rTt+1
	eor		rC3+1, rTt+1
    rol     rTt+2
	std     Y+a13+2, rTt+2
	eor		rC3+2, rTt+2
    rol     rTt+3
	std     Y+a13+3, rTt+3
	eor		rC3+3, rTt+3
    adc     rTt+0, zero
	std     Y+a13+0, rTt+0
	eor		rC3+0, rTt+0

    ; Check for terminator
    lpm     r0, Z
    inc     r0
    breq    Xoodoo_Done
    rjmp    Xoodoo_RoundLoop
Xoodoo_Done:
    pop     r29
    pop     r28
    pop     r17
    pop     r16
    pop     r15
    pop     r14
    pop     r13
    pop     r12
    pop     r11
    pop     r10
    pop     r9
    pop     r8
    pop     r7
    pop     r6
    pop     r5
    pop     r4
    pop     r3
    pop     r2
    ret