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
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
|
// Copyright 2018 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// This file contains constant-time, 64-bit assembly implementation of
// P256. The optimizations performed here are described in detail in:
// S.Gueron and V.Krasnov, "Fast prime field elliptic-curve cryptography with
// 256-bit primes"
// http://link.springer.com/article/10.1007%2Fs13389-014-0090-x
// https://eprint.iacr.org/2013/816.pdf
#include "textflag.h"
#define res_ptr R0
#define a_ptr R1
#define b_ptr R2
#define acc0 R3
#define acc1 R4
#define acc2 R5
#define acc3 R6
#define acc4 R7
#define acc5 R8
#define acc6 R9
#define acc7 R10
#define t0 R11
#define t1 R12
#define t2 R13
#define t3 R14
#define const0 R15
#define const1 R16
#define hlp0 R17
#define hlp1 res_ptr
#define x0 R19
#define x1 R20
#define x2 R21
#define x3 R22
#define y0 R23
#define y1 R24
#define y2 R25
#define y3 R26
#define const2 t2
#define const3 t3
DATA p256const0<>+0x00(SB)/8, $0x00000000ffffffff
DATA p256const1<>+0x00(SB)/8, $0xffffffff00000001
DATA p256ordK0<>+0x00(SB)/8, $0xccd1c8aaee00bc4f
DATA p256ord<>+0x00(SB)/8, $0xf3b9cac2fc632551
DATA p256ord<>+0x08(SB)/8, $0xbce6faada7179e84
DATA p256ord<>+0x10(SB)/8, $0xffffffffffffffff
DATA p256ord<>+0x18(SB)/8, $0xffffffff00000000
DATA p256one<>+0x00(SB)/8, $0x0000000000000001
DATA p256one<>+0x08(SB)/8, $0xffffffff00000000
DATA p256one<>+0x10(SB)/8, $0xffffffffffffffff
DATA p256one<>+0x18(SB)/8, $0x00000000fffffffe
GLOBL p256const0<>(SB), 8, $8
GLOBL p256const1<>(SB), 8, $8
GLOBL p256ordK0<>(SB), 8, $8
GLOBL p256ord<>(SB), 8, $32
GLOBL p256one<>(SB), 8, $32
/* ---------------------------------------*/
// func p256LittleToBig(res []byte, in []uint64)
TEXT ·p256LittleToBig(SB),NOSPLIT,$0
JMP ·p256BigToLittle(SB)
/* ---------------------------------------*/
// func p256BigToLittle(res []uint64, in []byte)
TEXT ·p256BigToLittle(SB),NOSPLIT,$0
MOVD res+0(FP), res_ptr
MOVD in+24(FP), a_ptr
LDP 0*16(a_ptr), (acc0, acc1)
LDP 1*16(a_ptr), (acc2, acc3)
REV acc0, acc0
REV acc1, acc1
REV acc2, acc2
REV acc3, acc3
STP (acc3, acc2), 0*16(res_ptr)
STP (acc1, acc0), 1*16(res_ptr)
RET
/* ---------------------------------------*/
// func p256MovCond(res, a, b []uint64, cond int)
// If cond == 0 res=b, else res=a
TEXT ·p256MovCond(SB),NOSPLIT,$0
MOVD res+0(FP), res_ptr
MOVD a+24(FP), a_ptr
MOVD b+48(FP), b_ptr
MOVD cond+72(FP), R3
CMP $0, R3
// Two remarks:
// 1) Will want to revisit NEON, when support is better
// 2) CSEL might not be constant time on all ARM processors
LDP 0*16(a_ptr), (R4, R5)
LDP 1*16(a_ptr), (R6, R7)
LDP 2*16(a_ptr), (R8, R9)
LDP 0*16(b_ptr), (R16, R17)
LDP 1*16(b_ptr), (R19, R20)
LDP 2*16(b_ptr), (R21, R22)
CSEL EQ, R16, R4, R4
CSEL EQ, R17, R5, R5
CSEL EQ, R19, R6, R6
CSEL EQ, R20, R7, R7
CSEL EQ, R21, R8, R8
CSEL EQ, R22, R9, R9
STP (R4, R5), 0*16(res_ptr)
STP (R6, R7), 1*16(res_ptr)
STP (R8, R9), 2*16(res_ptr)
LDP 3*16(a_ptr), (R4, R5)
LDP 4*16(a_ptr), (R6, R7)
LDP 5*16(a_ptr), (R8, R9)
LDP 3*16(b_ptr), (R16, R17)
LDP 4*16(b_ptr), (R19, R20)
LDP 5*16(b_ptr), (R21, R22)
CSEL EQ, R16, R4, R4
CSEL EQ, R17, R5, R5
CSEL EQ, R19, R6, R6
CSEL EQ, R20, R7, R7
CSEL EQ, R21, R8, R8
CSEL EQ, R22, R9, R9
STP (R4, R5), 3*16(res_ptr)
STP (R6, R7), 4*16(res_ptr)
STP (R8, R9), 5*16(res_ptr)
RET
/* ---------------------------------------*/
// func p256NegCond(val []uint64, cond int)
TEXT ·p256NegCond(SB),NOSPLIT,$0
MOVD val+0(FP), a_ptr
MOVD cond+24(FP), hlp0
MOVD a_ptr, res_ptr
// acc = poly
MOVD $-1, acc0
MOVD p256const0<>(SB), acc1
MOVD $0, acc2
MOVD p256const1<>(SB), acc3
// Load the original value
LDP 0*16(a_ptr), (t0, t1)
LDP 1*16(a_ptr), (t2, t3)
// Speculatively subtract
SUBS t0, acc0
SBCS t1, acc1
SBCS t2, acc2
SBC t3, acc3
// If condition is 0, keep original value
CMP $0, hlp0
CSEL EQ, t0, acc0, acc0
CSEL EQ, t1, acc1, acc1
CSEL EQ, t2, acc2, acc2
CSEL EQ, t3, acc3, acc3
// Store result
STP (acc0, acc1), 0*16(res_ptr)
STP (acc2, acc3), 1*16(res_ptr)
RET
/* ---------------------------------------*/
// func p256Sqr(res, in []uint64, n int)
TEXT ·p256Sqr(SB),NOSPLIT,$0
MOVD res+0(FP), res_ptr
MOVD in+24(FP), a_ptr
MOVD n+48(FP), b_ptr
MOVD p256const0<>(SB), const0
MOVD p256const1<>(SB), const1
LDP 0*16(a_ptr), (x0, x1)
LDP 1*16(a_ptr), (x2, x3)
sqrLoop:
SUB $1, b_ptr
CALL p256SqrInternal<>(SB)
MOVD y0, x0
MOVD y1, x1
MOVD y2, x2
MOVD y3, x3
CBNZ b_ptr, sqrLoop
STP (y0, y1), 0*16(res_ptr)
STP (y2, y3), 1*16(res_ptr)
RET
/* ---------------------------------------*/
// func p256Mul(res, in1, in2 []uint64)
TEXT ·p256Mul(SB),NOSPLIT,$0
MOVD res+0(FP), res_ptr
MOVD in1+24(FP), a_ptr
MOVD in2+48(FP), b_ptr
MOVD p256const0<>(SB), const0
MOVD p256const1<>(SB), const1
LDP 0*16(a_ptr), (x0, x1)
LDP 1*16(a_ptr), (x2, x3)
LDP 0*16(b_ptr), (y0, y1)
LDP 1*16(b_ptr), (y2, y3)
CALL p256MulInternal<>(SB)
STP (y0, y1), 0*16(res_ptr)
STP (y2, y3), 1*16(res_ptr)
RET
/* ---------------------------------------*/
// func p256FromMont(res, in []uint64)
TEXT ·p256FromMont(SB),NOSPLIT,$0
MOVD res+0(FP), res_ptr
MOVD in+24(FP), a_ptr
MOVD p256const0<>(SB), const0
MOVD p256const1<>(SB), const1
LDP 0*16(a_ptr), (acc0, acc1)
LDP 1*16(a_ptr), (acc2, acc3)
// Only reduce, no multiplications are needed
// First reduction step
ADDS acc0<<32, acc1, acc1
LSR $32, acc0, t0
MUL acc0, const1, t1
UMULH acc0, const1, acc0
ADCS t0, acc2
ADCS t1, acc3
ADC $0, acc0
// Second reduction step
ADDS acc1<<32, acc2, acc2
LSR $32, acc1, t0
MUL acc1, const1, t1
UMULH acc1, const1, acc1
ADCS t0, acc3
ADCS t1, acc0
ADC $0, acc1
// Third reduction step
ADDS acc2<<32, acc3, acc3
LSR $32, acc2, t0
MUL acc2, const1, t1
UMULH acc2, const1, acc2
ADCS t0, acc0
ADCS t1, acc1
ADC $0, acc2
// Last reduction step
ADDS acc3<<32, acc0, acc0
LSR $32, acc3, t0
MUL acc3, const1, t1
UMULH acc3, const1, acc3
ADCS t0, acc1
ADCS t1, acc2
ADC $0, acc3
SUBS $-1, acc0, t0
SBCS const0, acc1, t1
SBCS $0, acc2, t2
SBCS const1, acc3, t3
CSEL CS, t0, acc0, acc0
CSEL CS, t1, acc1, acc1
CSEL CS, t2, acc2, acc2
CSEL CS, t3, acc3, acc3
STP (acc0, acc1), 0*16(res_ptr)
STP (acc2, acc3), 1*16(res_ptr)
RET
/* ---------------------------------------*/
// Constant time point access to arbitrary point table.
// Indexed from 1 to 15, with -1 offset
// (index 0 is implicitly point at infinity)
// func p256Select(point, table []uint64, idx int)
TEXT ·p256Select(SB),NOSPLIT,$0
MOVD idx+48(FP), const0
MOVD table+24(FP), b_ptr
MOVD point+0(FP), res_ptr
EOR x0, x0, x0
EOR x1, x1, x1
EOR x2, x2, x2
EOR x3, x3, x3
EOR y0, y0, y0
EOR y1, y1, y1
EOR y2, y2, y2
EOR y3, y3, y3
EOR t0, t0, t0
EOR t1, t1, t1
EOR t2, t2, t2
EOR t3, t3, t3
MOVD $0, const1
loop_select:
ADD $1, const1
CMP const0, const1
LDP.P 16(b_ptr), (acc0, acc1)
CSEL EQ, acc0, x0, x0
CSEL EQ, acc1, x1, x1
LDP.P 16(b_ptr), (acc2, acc3)
CSEL EQ, acc2, x2, x2
CSEL EQ, acc3, x3, x3
LDP.P 16(b_ptr), (acc4, acc5)
CSEL EQ, acc4, y0, y0
CSEL EQ, acc5, y1, y1
LDP.P 16(b_ptr), (acc6, acc7)
CSEL EQ, acc6, y2, y2
CSEL EQ, acc7, y3, y3
LDP.P 16(b_ptr), (acc0, acc1)
CSEL EQ, acc0, t0, t0
CSEL EQ, acc1, t1, t1
LDP.P 16(b_ptr), (acc2, acc3)
CSEL EQ, acc2, t2, t2
CSEL EQ, acc3, t3, t3
CMP $16, const1
BNE loop_select
STP (x0, x1), 0*16(res_ptr)
STP (x2, x3), 1*16(res_ptr)
STP (y0, y1), 2*16(res_ptr)
STP (y2, y3), 3*16(res_ptr)
STP (t0, t1), 4*16(res_ptr)
STP (t2, t3), 5*16(res_ptr)
RET
/* ---------------------------------------*/
// Constant time point access to base point table.
// func p256SelectBase(point *[12]uint64, table string, idx int)
TEXT ·p256SelectBase(SB),NOSPLIT,$0
MOVD idx+24(FP), t0
MOVD table_base+8(FP), t1
MOVD point+0(FP), res_ptr
EOR x0, x0, x0
EOR x1, x1, x1
EOR x2, x2, x2
EOR x3, x3, x3
EOR y0, y0, y0
EOR y1, y1, y1
EOR y2, y2, y2
EOR y3, y3, y3
MOVD $0, t2
loop_select:
ADD $1, t2
CMP t0, t2
LDP.P 16(t1), (acc0, acc1)
CSEL EQ, acc0, x0, x0
CSEL EQ, acc1, x1, x1
LDP.P 16(t1), (acc2, acc3)
CSEL EQ, acc2, x2, x2
CSEL EQ, acc3, x3, x3
LDP.P 16(t1), (acc4, acc5)
CSEL EQ, acc4, y0, y0
CSEL EQ, acc5, y1, y1
LDP.P 16(t1), (acc6, acc7)
CSEL EQ, acc6, y2, y2
CSEL EQ, acc7, y3, y3
CMP $32, t2
BNE loop_select
STP (x0, x1), 0*16(res_ptr)
STP (x2, x3), 1*16(res_ptr)
STP (y0, y1), 2*16(res_ptr)
STP (y2, y3), 3*16(res_ptr)
RET
/* ---------------------------------------*/
// func p256OrdSqr(res, in []uint64, n int)
TEXT ·p256OrdSqr(SB),NOSPLIT,$0
MOVD in+24(FP), a_ptr
MOVD n+48(FP), b_ptr
MOVD p256ordK0<>(SB), hlp1
LDP p256ord<>+0x00(SB), (const0, const1)
LDP p256ord<>+0x10(SB), (const2, const3)
LDP 0*16(a_ptr), (x0, x1)
LDP 1*16(a_ptr), (x2, x3)
ordSqrLoop:
SUB $1, b_ptr
// x[1:] * x[0]
MUL x0, x1, acc1
UMULH x0, x1, acc2
MUL x0, x2, t0
ADDS t0, acc2, acc2
UMULH x0, x2, acc3
MUL x0, x3, t0
ADCS t0, acc3, acc3
UMULH x0, x3, acc4
ADC $0, acc4, acc4
// x[2:] * x[1]
MUL x1, x2, t0
ADDS t0, acc3
UMULH x1, x2, t1
ADCS t1, acc4
ADC $0, ZR, acc5
MUL x1, x3, t0
ADDS t0, acc4
UMULH x1, x3, t1
ADC t1, acc5
// x[3] * x[2]
MUL x2, x3, t0
ADDS t0, acc5
UMULH x2, x3, acc6
ADC $0, acc6
MOVD $0, acc7
// *2
ADDS acc1, acc1
ADCS acc2, acc2
ADCS acc3, acc3
ADCS acc4, acc4
ADCS acc5, acc5
ADCS acc6, acc6
ADC $0, acc7
// Missing products
MUL x0, x0, acc0
UMULH x0, x0, t0
ADDS t0, acc1, acc1
MUL x1, x1, t0
ADCS t0, acc2, acc2
UMULH x1, x1, t1
ADCS t1, acc3, acc3
MUL x2, x2, t0
ADCS t0, acc4, acc4
UMULH x2, x2, t1
ADCS t1, acc5, acc5
MUL x3, x3, t0
ADCS t0, acc6, acc6
UMULH x3, x3, t1
ADC t1, acc7, acc7
// First reduction step
MUL acc0, hlp1, hlp0
MUL const0, hlp1, t0
ADDS t0, acc0, acc0
UMULH const0, hlp0, t1
MUL const1, hlp0, t0
ADCS t0, acc1, acc1
UMULH const1, hlp0, y0
MUL const2, hlp0, t0
ADCS t0, acc2, acc2
UMULH const2, hlp0, acc0
MUL const3, hlp0, t0
ADCS t0, acc3, acc3
UMULH const3, hlp0, hlp0
ADC $0, hlp0
ADDS t1, acc1, acc1
ADCS y0, acc2, acc2
ADCS acc0, acc3, acc3
ADC $0, hlp0, acc0
// Second reduction step
MUL acc1, hlp1, hlp0
MUL const0, hlp1, t0
ADDS t0, acc1, acc1
UMULH const0, hlp0, t1
MUL const1, hlp0, t0
ADCS t0, acc2, acc2
UMULH const1, hlp0, y0
MUL const2, hlp0, t0
ADCS t0, acc3, acc3
UMULH const2, hlp0, acc1
MUL const3, hlp0, t0
ADCS t0, acc0, acc0
UMULH const3, hlp0, hlp0
ADC $0, hlp0
ADDS t1, acc2, acc2
ADCS y0, acc3, acc3
ADCS acc1, acc0, acc0
ADC $0, hlp0, acc1
// Third reduction step
MUL acc2, hlp1, hlp0
MUL const0, hlp1, t0
ADDS t0, acc2, acc2
UMULH const0, hlp0, t1
MUL const1, hlp0, t0
ADCS t0, acc3, acc3
UMULH const1, hlp0, y0
MUL const2, hlp0, t0
ADCS t0, acc0, acc0
UMULH const2, hlp0, acc2
MUL const3, hlp0, t0
ADCS t0, acc1, acc1
UMULH const3, hlp0, hlp0
ADC $0, hlp0
ADDS t1, acc3, acc3
ADCS y0, acc0, acc0
ADCS acc2, acc1, acc1
ADC $0, hlp0, acc2
// Last reduction step
MUL acc3, hlp1, hlp0
MUL const0, hlp1, t0
ADDS t0, acc3, acc3
UMULH const0, hlp0, t1
MUL const1, hlp0, t0
ADCS t0, acc0, acc0
UMULH const1, hlp0, y0
MUL const2, hlp0, t0
ADCS t0, acc1, acc1
UMULH const2, hlp0, acc3
MUL const3, hlp0, t0
ADCS t0, acc2, acc2
UMULH const3, hlp0, hlp0
ADC $0, acc7
ADDS t1, acc0, acc0
ADCS y0, acc1, acc1
ADCS acc3, acc2, acc2
ADC $0, hlp0, acc3
ADDS acc4, acc0, acc0
ADCS acc5, acc1, acc1
ADCS acc6, acc2, acc2
ADCS acc7, acc3, acc3
ADC $0, ZR, acc4
SUBS const0, acc0, y0
SBCS const1, acc1, y1
SBCS const2, acc2, y2
SBCS const3, acc3, y3
SBCS $0, acc4, acc4
CSEL CS, y0, acc0, x0
CSEL CS, y1, acc1, x1
CSEL CS, y2, acc2, x2
CSEL CS, y3, acc3, x3
CBNZ b_ptr, ordSqrLoop
MOVD res+0(FP), res_ptr
STP (x0, x1), 0*16(res_ptr)
STP (x2, x3), 1*16(res_ptr)
RET
/* ---------------------------------------*/
// func p256OrdMul(res, in1, in2 []uint64)
TEXT ·p256OrdMul(SB),NOSPLIT,$0
MOVD in1+24(FP), a_ptr
MOVD in2+48(FP), b_ptr
MOVD p256ordK0<>(SB), hlp1
LDP p256ord<>+0x00(SB), (const0, const1)
LDP p256ord<>+0x10(SB), (const2, const3)
LDP 0*16(a_ptr), (x0, x1)
LDP 1*16(a_ptr), (x2, x3)
LDP 0*16(b_ptr), (y0, y1)
LDP 1*16(b_ptr), (y2, y3)
// y[0] * x
MUL y0, x0, acc0
UMULH y0, x0, acc1
MUL y0, x1, t0
ADDS t0, acc1
UMULH y0, x1, acc2
MUL y0, x2, t0
ADCS t0, acc2
UMULH y0, x2, acc3
MUL y0, x3, t0
ADCS t0, acc3
UMULH y0, x3, acc4
ADC $0, acc4
// First reduction step
MUL acc0, hlp1, hlp0
MUL const0, hlp1, t0
ADDS t0, acc0, acc0
UMULH const0, hlp0, t1
MUL const1, hlp0, t0
ADCS t0, acc1, acc1
UMULH const1, hlp0, y0
MUL const2, hlp0, t0
ADCS t0, acc2, acc2
UMULH const2, hlp0, acc0
MUL const3, hlp0, t0
ADCS t0, acc3, acc3
UMULH const3, hlp0, hlp0
ADC $0, acc4
ADDS t1, acc1, acc1
ADCS y0, acc2, acc2
ADCS acc0, acc3, acc3
ADC $0, hlp0, acc0
// y[1] * x
MUL y1, x0, t0
ADDS t0, acc1
UMULH y1, x0, t1
MUL y1, x1, t0
ADCS t0, acc2
UMULH y1, x1, hlp0
MUL y1, x2, t0
ADCS t0, acc3
UMULH y1, x2, y0
MUL y1, x3, t0
ADCS t0, acc4
UMULH y1, x3, y1
ADC $0, ZR, acc5
ADDS t1, acc2
ADCS hlp0, acc3
ADCS y0, acc4
ADC y1, acc5
// Second reduction step
MUL acc1, hlp1, hlp0
MUL const0, hlp1, t0
ADDS t0, acc1, acc1
UMULH const0, hlp0, t1
MUL const1, hlp0, t0
ADCS t0, acc2, acc2
UMULH const1, hlp0, y0
MUL const2, hlp0, t0
ADCS t0, acc3, acc3
UMULH const2, hlp0, acc1
MUL const3, hlp0, t0
ADCS t0, acc0, acc0
UMULH const3, hlp0, hlp0
ADC $0, acc5
ADDS t1, acc2, acc2
ADCS y0, acc3, acc3
ADCS acc1, acc0, acc0
ADC $0, hlp0, acc1
// y[2] * x
MUL y2, x0, t0
ADDS t0, acc2
UMULH y2, x0, t1
MUL y2, x1, t0
ADCS t0, acc3
UMULH y2, x1, hlp0
MUL y2, x2, t0
ADCS t0, acc4
UMULH y2, x2, y0
MUL y2, x3, t0
ADCS t0, acc5
UMULH y2, x3, y1
ADC $0, ZR, acc6
ADDS t1, acc3
ADCS hlp0, acc4
ADCS y0, acc5
ADC y1, acc6
// Third reduction step
MUL acc2, hlp1, hlp0
MUL const0, hlp1, t0
ADDS t0, acc2, acc2
UMULH const0, hlp0, t1
MUL const1, hlp0, t0
ADCS t0, acc3, acc3
UMULH const1, hlp0, y0
MUL const2, hlp0, t0
ADCS t0, acc0, acc0
UMULH const2, hlp0, acc2
MUL const3, hlp0, t0
ADCS t0, acc1, acc1
UMULH const3, hlp0, hlp0
ADC $0, acc6
ADDS t1, acc3, acc3
ADCS y0, acc0, acc0
ADCS acc2, acc1, acc1
ADC $0, hlp0, acc2
// y[3] * x
MUL y3, x0, t0
ADDS t0, acc3
UMULH y3, x0, t1
MUL y3, x1, t0
ADCS t0, acc4
UMULH y3, x1, hlp0
MUL y3, x2, t0
ADCS t0, acc5
UMULH y3, x2, y0
MUL y3, x3, t0
ADCS t0, acc6
UMULH y3, x3, y1
ADC $0, ZR, acc7
ADDS t1, acc4
ADCS hlp0, acc5
ADCS y0, acc6
ADC y1, acc7
// Last reduction step
MUL acc3, hlp1, hlp0
MUL const0, hlp1, t0
ADDS t0, acc3, acc3
UMULH const0, hlp0, t1
MUL const1, hlp0, t0
ADCS t0, acc0, acc0
UMULH const1, hlp0, y0
MUL const2, hlp0, t0
ADCS t0, acc1, acc1
UMULH const2, hlp0, acc3
MUL const3, hlp0, t0
ADCS t0, acc2, acc2
UMULH const3, hlp0, hlp0
ADC $0, acc7
ADDS t1, acc0, acc0
ADCS y0, acc1, acc1
ADCS acc3, acc2, acc2
ADC $0, hlp0, acc3
ADDS acc4, acc0, acc0
ADCS acc5, acc1, acc1
ADCS acc6, acc2, acc2
ADCS acc7, acc3, acc3
ADC $0, ZR, acc4
SUBS const0, acc0, t0
SBCS const1, acc1, t1
SBCS const2, acc2, t2
SBCS const3, acc3, t3
SBCS $0, acc4, acc4
CSEL CS, t0, acc0, acc0
CSEL CS, t1, acc1, acc1
CSEL CS, t2, acc2, acc2
CSEL CS, t3, acc3, acc3
MOVD res+0(FP), res_ptr
STP (acc0, acc1), 0*16(res_ptr)
STP (acc2, acc3), 1*16(res_ptr)
RET
/* ---------------------------------------*/
TEXT p256SubInternal<>(SB),NOSPLIT,$0
SUBS x0, y0, acc0
SBCS x1, y1, acc1
SBCS x2, y2, acc2
SBCS x3, y3, acc3
SBC $0, ZR, t0
ADDS $-1, acc0, acc4
ADCS const0, acc1, acc5
ADCS $0, acc2, acc6
ADC const1, acc3, acc7
ANDS $1, t0
CSEL EQ, acc0, acc4, x0
CSEL EQ, acc1, acc5, x1
CSEL EQ, acc2, acc6, x2
CSEL EQ, acc3, acc7, x3
RET
/* ---------------------------------------*/
TEXT p256SqrInternal<>(SB),NOSPLIT,$0
// x[1:] * x[0]
MUL x0, x1, acc1
UMULH x0, x1, acc2
MUL x0, x2, t0
ADDS t0, acc2, acc2
UMULH x0, x2, acc3
MUL x0, x3, t0
ADCS t0, acc3, acc3
UMULH x0, x3, acc4
ADC $0, acc4, acc4
// x[2:] * x[1]
MUL x1, x2, t0
ADDS t0, acc3
UMULH x1, x2, t1
ADCS t1, acc4
ADC $0, ZR, acc5
MUL x1, x3, t0
ADDS t0, acc4
UMULH x1, x3, t1
ADC t1, acc5
// x[3] * x[2]
MUL x2, x3, t0
ADDS t0, acc5
UMULH x2, x3, acc6
ADC $0, acc6
MOVD $0, acc7
// *2
ADDS acc1, acc1
ADCS acc2, acc2
ADCS acc3, acc3
ADCS acc4, acc4
ADCS acc5, acc5
ADCS acc6, acc6
ADC $0, acc7
// Missing products
MUL x0, x0, acc0
UMULH x0, x0, t0
ADDS t0, acc1, acc1
MUL x1, x1, t0
ADCS t0, acc2, acc2
UMULH x1, x1, t1
ADCS t1, acc3, acc3
MUL x2, x2, t0
ADCS t0, acc4, acc4
UMULH x2, x2, t1
ADCS t1, acc5, acc5
MUL x3, x3, t0
ADCS t0, acc6, acc6
UMULH x3, x3, t1
ADCS t1, acc7, acc7
// First reduction step
ADDS acc0<<32, acc1, acc1
LSR $32, acc0, t0
MUL acc0, const1, t1
UMULH acc0, const1, acc0
ADCS t0, acc2, acc2
ADCS t1, acc3, acc3
ADC $0, acc0, acc0
// Second reduction step
ADDS acc1<<32, acc2, acc2
LSR $32, acc1, t0
MUL acc1, const1, t1
UMULH acc1, const1, acc1
ADCS t0, acc3, acc3
ADCS t1, acc0, acc0
ADC $0, acc1, acc1
// Third reduction step
ADDS acc2<<32, acc3, acc3
LSR $32, acc2, t0
MUL acc2, const1, t1
UMULH acc2, const1, acc2
ADCS t0, acc0, acc0
ADCS t1, acc1, acc1
ADC $0, acc2, acc2
// Last reduction step
ADDS acc3<<32, acc0, acc0
LSR $32, acc3, t0
MUL acc3, const1, t1
UMULH acc3, const1, acc3
ADCS t0, acc1, acc1
ADCS t1, acc2, acc2
ADC $0, acc3, acc3
// Add bits [511:256] of the sqr result
ADDS acc4, acc0, acc0
ADCS acc5, acc1, acc1
ADCS acc6, acc2, acc2
ADCS acc7, acc3, acc3
ADC $0, ZR, acc4
SUBS $-1, acc0, t0
SBCS const0, acc1, t1
SBCS $0, acc2, t2
SBCS const1, acc3, t3
SBCS $0, acc4, acc4
CSEL CS, t0, acc0, y0
CSEL CS, t1, acc1, y1
CSEL CS, t2, acc2, y2
CSEL CS, t3, acc3, y3
RET
/* ---------------------------------------*/
TEXT p256MulInternal<>(SB),NOSPLIT,$0
// y[0] * x
MUL y0, x0, acc0
UMULH y0, x0, acc1
MUL y0, x1, t0
ADDS t0, acc1
UMULH y0, x1, acc2
MUL y0, x2, t0
ADCS t0, acc2
UMULH y0, x2, acc3
MUL y0, x3, t0
ADCS t0, acc3
UMULH y0, x3, acc4
ADC $0, acc4
// First reduction step
ADDS acc0<<32, acc1, acc1
LSR $32, acc0, t0
MUL acc0, const1, t1
UMULH acc0, const1, acc0
ADCS t0, acc2
ADCS t1, acc3
ADC $0, acc0
// y[1] * x
MUL y1, x0, t0
ADDS t0, acc1
UMULH y1, x0, t1
MUL y1, x1, t0
ADCS t0, acc2
UMULH y1, x1, t2
MUL y1, x2, t0
ADCS t0, acc3
UMULH y1, x2, t3
MUL y1, x3, t0
ADCS t0, acc4
UMULH y1, x3, hlp0
ADC $0, ZR, acc5
ADDS t1, acc2
ADCS t2, acc3
ADCS t3, acc4
ADC hlp0, acc5
// Second reduction step
ADDS acc1<<32, acc2, acc2
LSR $32, acc1, t0
MUL acc1, const1, t1
UMULH acc1, const1, acc1
ADCS t0, acc3
ADCS t1, acc0
ADC $0, acc1
// y[2] * x
MUL y2, x0, t0
ADDS t0, acc2
UMULH y2, x0, t1
MUL y2, x1, t0
ADCS t0, acc3
UMULH y2, x1, t2
MUL y2, x2, t0
ADCS t0, acc4
UMULH y2, x2, t3
MUL y2, x3, t0
ADCS t0, acc5
UMULH y2, x3, hlp0
ADC $0, ZR, acc6
ADDS t1, acc3
ADCS t2, acc4
ADCS t3, acc5
ADC hlp0, acc6
// Third reduction step
ADDS acc2<<32, acc3, acc3
LSR $32, acc2, t0
MUL acc2, const1, t1
UMULH acc2, const1, acc2
ADCS t0, acc0
ADCS t1, acc1
ADC $0, acc2
// y[3] * x
MUL y3, x0, t0
ADDS t0, acc3
UMULH y3, x0, t1
MUL y3, x1, t0
ADCS t0, acc4
UMULH y3, x1, t2
MUL y3, x2, t0
ADCS t0, acc5
UMULH y3, x2, t3
MUL y3, x3, t0
ADCS t0, acc6
UMULH y3, x3, hlp0
ADC $0, ZR, acc7
ADDS t1, acc4
ADCS t2, acc5
ADCS t3, acc6
ADC hlp0, acc7
// Last reduction step
ADDS acc3<<32, acc0, acc0
LSR $32, acc3, t0
MUL acc3, const1, t1
UMULH acc3, const1, acc3
ADCS t0, acc1
ADCS t1, acc2
ADC $0, acc3
// Add bits [511:256] of the mul result
ADDS acc4, acc0, acc0
ADCS acc5, acc1, acc1
ADCS acc6, acc2, acc2
ADCS acc7, acc3, acc3
ADC $0, ZR, acc4
SUBS $-1, acc0, t0
SBCS const0, acc1, t1
SBCS $0, acc2, t2
SBCS const1, acc3, t3
SBCS $0, acc4, acc4
CSEL CS, t0, acc0, y0
CSEL CS, t1, acc1, y1
CSEL CS, t2, acc2, y2
CSEL CS, t3, acc3, y3
RET
/* ---------------------------------------*/
#define p256MulBy2Inline \
ADDS y0, y0, x0; \
ADCS y1, y1, x1; \
ADCS y2, y2, x2; \
ADCS y3, y3, x3; \
ADC $0, ZR, hlp0; \
SUBS $-1, x0, t0; \
SBCS const0, x1, t1;\
SBCS $0, x2, t2; \
SBCS const1, x3, t3;\
SBCS $0, hlp0, hlp0;\
CSEL CC, x0, t0, x0;\
CSEL CC, x1, t1, x1;\
CSEL CC, x2, t2, x2;\
CSEL CC, x3, t3, x3;
/* ---------------------------------------*/
#define x1in(off) (off)(a_ptr)
#define y1in(off) (off + 32)(a_ptr)
#define z1in(off) (off + 64)(a_ptr)
#define x2in(off) (off)(b_ptr)
#define z2in(off) (off + 64)(b_ptr)
#define x3out(off) (off)(res_ptr)
#define y3out(off) (off + 32)(res_ptr)
#define z3out(off) (off + 64)(res_ptr)
#define LDx(src) LDP src(0), (x0, x1); LDP src(16), (x2, x3)
#define LDy(src) LDP src(0), (y0, y1); LDP src(16), (y2, y3)
#define STx(src) STP (x0, x1), src(0); STP (x2, x3), src(16)
#define STy(src) STP (y0, y1), src(0); STP (y2, y3), src(16)
/* ---------------------------------------*/
#define y2in(off) (32*0 + 8 + off)(RSP)
#define s2(off) (32*1 + 8 + off)(RSP)
#define z1sqr(off) (32*2 + 8 + off)(RSP)
#define h(off) (32*3 + 8 + off)(RSP)
#define r(off) (32*4 + 8 + off)(RSP)
#define hsqr(off) (32*5 + 8 + off)(RSP)
#define rsqr(off) (32*6 + 8 + off)(RSP)
#define hcub(off) (32*7 + 8 + off)(RSP)
#define z2sqr(off) (32*8 + 8 + off)(RSP)
#define s1(off) (32*9 + 8 + off)(RSP)
#define u1(off) (32*10 + 8 + off)(RSP)
#define u2(off) (32*11 + 8 + off)(RSP)
// func p256PointAddAffineAsm(res, in1, in2 []uint64, sign, sel, zero int)
TEXT ·p256PointAddAffineAsm(SB),0,$264-96
MOVD in1+24(FP), a_ptr
MOVD in2+48(FP), b_ptr
MOVD sign+72(FP), hlp0
MOVD sel+80(FP), hlp1
MOVD zero+88(FP), t2
MOVD $1, t0
CMP $0, t2
CSEL EQ, ZR, t0, t2
CMP $0, hlp1
CSEL EQ, ZR, t0, hlp1
MOVD p256const0<>(SB), const0
MOVD p256const1<>(SB), const1
EOR t2<<1, hlp1
// Negate y2in based on sign
LDP 2*16(b_ptr), (y0, y1)
LDP 3*16(b_ptr), (y2, y3)
MOVD $-1, acc0
SUBS y0, acc0, acc0
SBCS y1, const0, acc1
SBCS y2, ZR, acc2
SBCS y3, const1, acc3
SBC $0, ZR, t0
ADDS $-1, acc0, acc4
ADCS const0, acc1, acc5
ADCS $0, acc2, acc6
ADCS const1, acc3, acc7
ADC $0, t0, t0
CMP $0, t0
CSEL EQ, acc4, acc0, acc0
CSEL EQ, acc5, acc1, acc1
CSEL EQ, acc6, acc2, acc2
CSEL EQ, acc7, acc3, acc3
// If condition is 0, keep original value
CMP $0, hlp0
CSEL EQ, y0, acc0, y0
CSEL EQ, y1, acc1, y1
CSEL EQ, y2, acc2, y2
CSEL EQ, y3, acc3, y3
// Store result
STy(y2in)
// Begin point add
LDx(z1in)
CALL p256SqrInternal<>(SB) // z1ˆ2
STy(z1sqr)
LDx(x2in)
CALL p256MulInternal<>(SB) // x2 * z1ˆ2
LDx(x1in)
CALL p256SubInternal<>(SB) // h = u2 - u1
STx(h)
LDy(z1in)
CALL p256MulInternal<>(SB) // z3 = h * z1
LDP 4*16(a_ptr), (acc0, acc1)// iff select[0] == 0, z3 = z1
LDP 5*16(a_ptr), (acc2, acc3)
ANDS $1, hlp1, ZR
CSEL EQ, acc0, y0, y0
CSEL EQ, acc1, y1, y1
CSEL EQ, acc2, y2, y2
CSEL EQ, acc3, y3, y3
LDP p256one<>+0x00(SB), (acc0, acc1)
LDP p256one<>+0x10(SB), (acc2, acc3)
ANDS $2, hlp1, ZR // iff select[1] == 0, z3 = 1
CSEL EQ, acc0, y0, y0
CSEL EQ, acc1, y1, y1
CSEL EQ, acc2, y2, y2
CSEL EQ, acc3, y3, y3
LDx(z1in)
MOVD res+0(FP), t0
STP (y0, y1), 4*16(t0)
STP (y2, y3), 5*16(t0)
LDy(z1sqr)
CALL p256MulInternal<>(SB) // z1 ^ 3
LDx(y2in)
CALL p256MulInternal<>(SB) // s2 = y2 * z1ˆ3
STy(s2)
LDx(y1in)
CALL p256SubInternal<>(SB) // r = s2 - s1
STx(r)
CALL p256SqrInternal<>(SB) // rsqr = rˆ2
STy (rsqr)
LDx(h)
CALL p256SqrInternal<>(SB) // hsqr = hˆ2
STy(hsqr)
CALL p256MulInternal<>(SB) // hcub = hˆ3
STy(hcub)
LDx(y1in)
CALL p256MulInternal<>(SB) // y1 * hˆ3
STy(s2)
LDP hsqr(0*8), (x0, x1)
LDP hsqr(2*8), (x2, x3)
LDP 0*16(a_ptr), (y0, y1)
LDP 1*16(a_ptr), (y2, y3)
CALL p256MulInternal<>(SB) // u1 * hˆ2
STP (y0, y1), h(0*8)
STP (y2, y3), h(2*8)
p256MulBy2Inline // u1 * hˆ2 * 2, inline
LDy(rsqr)
CALL p256SubInternal<>(SB) // rˆ2 - u1 * hˆ2 * 2
MOVD x0, y0
MOVD x1, y1
MOVD x2, y2
MOVD x3, y3
LDx(hcub)
CALL p256SubInternal<>(SB)
LDP 0*16(a_ptr), (acc0, acc1)
LDP 1*16(a_ptr), (acc2, acc3)
ANDS $1, hlp1, ZR // iff select[0] == 0, x3 = x1
CSEL EQ, acc0, x0, x0
CSEL EQ, acc1, x1, x1
CSEL EQ, acc2, x2, x2
CSEL EQ, acc3, x3, x3
LDP 0*16(b_ptr), (acc0, acc1)
LDP 1*16(b_ptr), (acc2, acc3)
ANDS $2, hlp1, ZR // iff select[1] == 0, x3 = x2
CSEL EQ, acc0, x0, x0
CSEL EQ, acc1, x1, x1
CSEL EQ, acc2, x2, x2
CSEL EQ, acc3, x3, x3
MOVD res+0(FP), t0
STP (x0, x1), 0*16(t0)
STP (x2, x3), 1*16(t0)
LDP h(0*8), (y0, y1)
LDP h(2*8), (y2, y3)
CALL p256SubInternal<>(SB)
LDP r(0*8), (y0, y1)
LDP r(2*8), (y2, y3)
CALL p256MulInternal<>(SB)
LDP s2(0*8), (x0, x1)
LDP s2(2*8), (x2, x3)
CALL p256SubInternal<>(SB)
LDP 2*16(a_ptr), (acc0, acc1)
LDP 3*16(a_ptr), (acc2, acc3)
ANDS $1, hlp1, ZR // iff select[0] == 0, y3 = y1
CSEL EQ, acc0, x0, x0
CSEL EQ, acc1, x1, x1
CSEL EQ, acc2, x2, x2
CSEL EQ, acc3, x3, x3
LDP y2in(0*8), (acc0, acc1)
LDP y2in(2*8), (acc2, acc3)
ANDS $2, hlp1, ZR // iff select[1] == 0, y3 = y2
CSEL EQ, acc0, x0, x0
CSEL EQ, acc1, x1, x1
CSEL EQ, acc2, x2, x2
CSEL EQ, acc3, x3, x3
MOVD res+0(FP), t0
STP (x0, x1), 2*16(t0)
STP (x2, x3), 3*16(t0)
RET
#define p256AddInline \
ADDS y0, x0, x0; \
ADCS y1, x1, x1; \
ADCS y2, x2, x2; \
ADCS y3, x3, x3; \
ADC $0, ZR, hlp0; \
SUBS $-1, x0, t0; \
SBCS const0, x1, t1;\
SBCS $0, x2, t2; \
SBCS const1, x3, t3;\
SBCS $0, hlp0, hlp0;\
CSEL CC, x0, t0, x0;\
CSEL CC, x1, t1, x1;\
CSEL CC, x2, t2, x2;\
CSEL CC, x3, t3, x3;
#define s(off) (32*0 + 8 + off)(RSP)
#define m(off) (32*1 + 8 + off)(RSP)
#define zsqr(off) (32*2 + 8 + off)(RSP)
#define tmp(off) (32*3 + 8 + off)(RSP)
//func p256PointDoubleAsm(res, in []uint64)
TEXT ·p256PointDoubleAsm(SB),NOSPLIT,$136-48
MOVD res+0(FP), res_ptr
MOVD in+24(FP), a_ptr
MOVD p256const0<>(SB), const0
MOVD p256const1<>(SB), const1
// Begin point double
LDP 4*16(a_ptr), (x0, x1)
LDP 5*16(a_ptr), (x2, x3)
CALL p256SqrInternal<>(SB)
STP (y0, y1), zsqr(0*8)
STP (y2, y3), zsqr(2*8)
LDP 0*16(a_ptr), (x0, x1)
LDP 1*16(a_ptr), (x2, x3)
p256AddInline
STx(m)
LDx(z1in)
LDy(y1in)
CALL p256MulInternal<>(SB)
p256MulBy2Inline
STx(z3out)
LDy(x1in)
LDx(zsqr)
CALL p256SubInternal<>(SB)
LDy(m)
CALL p256MulInternal<>(SB)
// Multiply by 3
p256MulBy2Inline
p256AddInline
STx(m)
LDy(y1in)
p256MulBy2Inline
CALL p256SqrInternal<>(SB)
STy(s)
MOVD y0, x0
MOVD y1, x1
MOVD y2, x2
MOVD y3, x3
CALL p256SqrInternal<>(SB)
// Divide by 2
ADDS $-1, y0, t0
ADCS const0, y1, t1
ADCS $0, y2, t2
ADCS const1, y3, t3
ADC $0, ZR, hlp0
ANDS $1, y0, ZR
CSEL EQ, y0, t0, t0
CSEL EQ, y1, t1, t1
CSEL EQ, y2, t2, t2
CSEL EQ, y3, t3, t3
AND y0, hlp0, hlp0
EXTR $1, t0, t1, y0
EXTR $1, t1, t2, y1
EXTR $1, t2, t3, y2
EXTR $1, t3, hlp0, y3
STy(y3out)
LDx(x1in)
LDy(s)
CALL p256MulInternal<>(SB)
STy(s)
p256MulBy2Inline
STx(tmp)
LDx(m)
CALL p256SqrInternal<>(SB)
LDx(tmp)
CALL p256SubInternal<>(SB)
STx(x3out)
LDy(s)
CALL p256SubInternal<>(SB)
LDy(m)
CALL p256MulInternal<>(SB)
LDx(y3out)
CALL p256SubInternal<>(SB)
STx(y3out)
RET
/* ---------------------------------------*/
#undef y2in
#undef x3out
#undef y3out
#undef z3out
#define y2in(off) (off + 32)(b_ptr)
#define x3out(off) (off)(b_ptr)
#define y3out(off) (off + 32)(b_ptr)
#define z3out(off) (off + 64)(b_ptr)
//func p256PointAddAsm(res, in1, in2 []uint64) int
TEXT ·p256PointAddAsm(SB),0,$392-80
// See https://hyperelliptic.org/EFD/g1p/auto-shortw-jacobian-3.html#addition-add-2007-bl
// Move input to stack in order to free registers
MOVD in1+24(FP), a_ptr
MOVD in2+48(FP), b_ptr
MOVD p256const0<>(SB), const0
MOVD p256const1<>(SB), const1
// Begin point add
LDx(z2in)
CALL p256SqrInternal<>(SB) // z2^2
STy(z2sqr)
CALL p256MulInternal<>(SB) // z2^3
LDx(y1in)
CALL p256MulInternal<>(SB) // s1 = z2ˆ3*y1
STy(s1)
LDx(z1in)
CALL p256SqrInternal<>(SB) // z1^2
STy(z1sqr)
CALL p256MulInternal<>(SB) // z1^3
LDx(y2in)
CALL p256MulInternal<>(SB) // s2 = z1ˆ3*y2
LDx(s1)
CALL p256SubInternal<>(SB) // r = s2 - s1
STx(r)
MOVD $1, t2
ORR x0, x1, t0 // Check if zero mod p256
ORR x2, x3, t1
ORR t1, t0, t0
CMP $0, t0
CSEL EQ, t2, ZR, hlp1
EOR $-1, x0, t0
EOR const0, x1, t1
EOR const1, x3, t3
ORR t0, t1, t0
ORR x2, t3, t1
ORR t1, t0, t0
CMP $0, t0
CSEL EQ, t2, hlp1, hlp1
LDx(z2sqr)
LDy(x1in)
CALL p256MulInternal<>(SB) // u1 = x1 * z2ˆ2
STy(u1)
LDx(z1sqr)
LDy(x2in)
CALL p256MulInternal<>(SB) // u2 = x2 * z1ˆ2
STy(u2)
LDx(u1)
CALL p256SubInternal<>(SB) // h = u2 - u1
STx(h)
MOVD $1, t2
ORR x0, x1, t0 // Check if zero mod p256
ORR x2, x3, t1
ORR t1, t0, t0
CMP $0, t0
CSEL EQ, t2, ZR, hlp0
EOR $-1, x0, t0
EOR const0, x1, t1
EOR const1, x3, t3
ORR t0, t1, t0
ORR x2, t3, t1
ORR t1, t0, t0
CMP $0, t0
CSEL EQ, t2, hlp0, hlp0
AND hlp0, hlp1, hlp1
LDx(r)
CALL p256SqrInternal<>(SB) // rsqr = rˆ2
STy(rsqr)
LDx(h)
CALL p256SqrInternal<>(SB) // hsqr = hˆ2
STy(hsqr)
LDx(h)
CALL p256MulInternal<>(SB) // hcub = hˆ3
STy(hcub)
LDx(s1)
CALL p256MulInternal<>(SB)
STy(s2)
LDx(z1in)
LDy(z2in)
CALL p256MulInternal<>(SB) // z1 * z2
LDx(h)
CALL p256MulInternal<>(SB) // z1 * z2 * h
MOVD res+0(FP), b_ptr
STy(z3out)
LDx(hsqr)
LDy(u1)
CALL p256MulInternal<>(SB) // hˆ2 * u1
STy(u2)
p256MulBy2Inline // u1 * hˆ2 * 2, inline
LDy(rsqr)
CALL p256SubInternal<>(SB) // rˆ2 - u1 * hˆ2 * 2
MOVD x0, y0
MOVD x1, y1
MOVD x2, y2
MOVD x3, y3
LDx(hcub)
CALL p256SubInternal<>(SB)
STx(x3out)
LDy(u2)
CALL p256SubInternal<>(SB)
LDy(r)
CALL p256MulInternal<>(SB)
LDx(s2)
CALL p256SubInternal<>(SB)
STx(y3out)
MOVD hlp1, R0
MOVD R0, ret+72(FP)
RET
|