forked from weidai11/cryptopp
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathsha512_armv4.S
1861 lines (1820 loc) · 41.4 KB
/
sha512_armv4.S
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
@ Copyright 2007-2019 The OpenSSL Project Authors. All Rights Reserved.
@
@ ====================================================================
@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
@ project. The module is, however, dual licensed under OpenSSL and
@ CRYPTOGAMS licenses depending on where you obtain it. For further
@ details see http://www.openssl.org/~appro/cryptogams/.
@ ====================================================================
@ JW, MAY 2019: Begin defines from taken from arm_arch.h
@ The defines were included through the header.
# if !defined(__ARM_ARCH__)
# if defined(__CC_ARM)
# define __ARM_ARCH__ __TARGET_ARCH_ARM
# if defined(__BIG_ENDIAN)
# define __ARMEB__
# else
# define __ARMEL__
# endif
# elif defined(__GNUC__)
# if defined(__aarch64__)
# define __ARM_ARCH__ 8
# if __BYTE_ORDER__==__ORDER_BIG_ENDIAN__
# define __ARMEB__
# else
# define __ARMEL__
# endif
# elif defined(__ARM_ARCH)
# define __ARM_ARCH__ __ARM_ARCH
# elif defined(__ARM_ARCH_8A__)
# define __ARM_ARCH__ 8
# elif defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) || \
defined(__ARM_ARCH_7R__)|| defined(__ARM_ARCH_7M__) || \
defined(__ARM_ARCH_7EM__)
# define __ARM_ARCH__ 7
# elif defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || \
defined(__ARM_ARCH_6K__)|| defined(__ARM_ARCH_6M__) || \
defined(__ARM_ARCH_6Z__)|| defined(__ARM_ARCH_6ZK__) || \
defined(__ARM_ARCH_6T2__)
# define __ARM_ARCH__ 6
# elif defined(__ARM_ARCH_5__) || defined(__ARM_ARCH_5T__) || \
defined(__ARM_ARCH_5E__)|| defined(__ARM_ARCH_5TE__) || \
defined(__ARM_ARCH_5TEJ__)
# define __ARM_ARCH__ 5
# elif defined(__ARM_ARCH_4__) || defined(__ARM_ARCH_4T__)
# define __ARM_ARCH__ 4
# else
# error "unsupported ARM architecture"
# endif
# endif
# endif
# if !defined(__ARM_MAX_ARCH__)
# define __ARM_MAX_ARCH__ __ARM_ARCH__
# endif
# if __ARM_MAX_ARCH__<__ARM_ARCH__
# error "__ARM_MAX_ARCH__ can't be less than __ARM_ARCH__"
# elif __ARM_MAX_ARCH__!=__ARM_ARCH__
# if __ARM_ARCH__<7 && __ARM_MAX_ARCH__>=7 && defined(__ARMEB__)
# error "can't build universal big-endian binary"
# endif
# endif
# define CRYPTOGAMS_ARMV7_NEON (1<<0)
@ JW, MAY 2019: End defines from taken from arm_arch.h
@ Back to original Cryptogams code
#ifdef __ARMEL__
# define LO 0
# define HI 4
# define WORD64(hi0,lo0,hi1,lo1) .word lo0,hi0, lo1,hi1
#else
# define HI 0
# define LO 4
# define WORD64(hi0,lo0,hi1,lo1) .word hi0,lo0, hi1,lo1
#endif
#if defined(__thumb2__)
.syntax unified
.thumb
# define adrl adr
#else
.code 32
#endif
.text
.type K512,%object
.align 5
K512:
WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd)
WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc)
WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019)
WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118)
WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe)
WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2)
WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1)
WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694)
WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3)
WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65)
WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483)
WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5)
WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210)
WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4)
WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725)
WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70)
WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926)
WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df)
WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8)
WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b)
WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001)
WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30)
WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910)
WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8)
WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53)
WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8)
WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb)
WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3)
WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60)
WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec)
WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9)
WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b)
WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207)
WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178)
WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6)
WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b)
WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493)
WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c)
WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a)
WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
.size K512,.-K512
.skip 32
.align 5
.globl cryptogams_sha512_block_data_order
.type cryptogams_sha512_block_data_order,%function
cryptogams_sha512_block_data_order:
.Lcryptogams_sha512_block_data_order:
#if __ARM_ARCH__<7 && !defined(__thumb2__)
sub r3,pc,#8 @ cryptogams_sha512_block_data_order
#else
adr r3,.Lcryptogams_sha512_block_data_order
#endif
add r2,r1,r2,lsl#7 @ len to point at the end of inp
stmdb sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,lr}
sub r14,r3,#672 @ K512
sub sp,sp,#9*8
ldr r7,[r0,#32+LO]
ldr r8,[r0,#32+HI]
ldr r9, [r0,#48+LO]
ldr r10, [r0,#48+HI]
ldr r11, [r0,#56+LO]
ldr r12, [r0,#56+HI]
.Loop:
str r9, [sp,#48+0]
str r10, [sp,#48+4]
str r11, [sp,#56+0]
str r12, [sp,#56+4]
ldr r5,[r0,#0+LO]
ldr r6,[r0,#0+HI]
ldr r3,[r0,#8+LO]
ldr r4,[r0,#8+HI]
ldr r9, [r0,#16+LO]
ldr r10, [r0,#16+HI]
ldr r11, [r0,#24+LO]
ldr r12, [r0,#24+HI]
str r3,[sp,#8+0]
str r4,[sp,#8+4]
str r9, [sp,#16+0]
str r10, [sp,#16+4]
str r11, [sp,#24+0]
str r12, [sp,#24+4]
ldr r3,[r0,#40+LO]
ldr r4,[r0,#40+HI]
str r3,[sp,#40+0]
str r4,[sp,#40+4]
.L00_15:
#if __ARM_ARCH__<7
ldrb r3,[r1,#7]
ldrb r9, [r1,#6]
ldrb r10, [r1,#5]
ldrb r11, [r1,#4]
ldrb r4,[r1,#3]
ldrb r12, [r1,#2]
orr r3,r3,r9,lsl#8
ldrb r9, [r1,#1]
orr r3,r3,r10,lsl#16
ldrb r10, [r1],#8
orr r3,r3,r11,lsl#24
orr r4,r4,r12,lsl#8
orr r4,r4,r9,lsl#16
orr r4,r4,r10,lsl#24
#else
ldr r3,[r1,#4]
ldr r4,[r1],#8
#ifdef __ARMEL__
rev r3,r3
rev r4,r4
#endif
#endif
@ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41))
@ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
@ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
mov r9,r7,lsr#14
str r3,[sp,#64+0]
mov r10,r8,lsr#14
str r4,[sp,#64+4]
eor r9,r9,r8,lsl#18
ldr r11,[sp,#56+0] @ h.lo
eor r10,r10,r7,lsl#18
ldr r12,[sp,#56+4] @ h.hi
eor r9,r9,r7,lsr#18
eor r10,r10,r8,lsr#18
eor r9,r9,r8,lsl#14
eor r10,r10,r7,lsl#14
eor r9,r9,r8,lsr#9
eor r10,r10,r7,lsr#9
eor r9,r9,r7,lsl#23
eor r10,r10,r8,lsl#23 @ Sigma1(e)
adds r3,r3,r9
ldr r9,[sp,#40+0] @ f.lo
adc r4,r4,r10 @ T += Sigma1(e)
ldr r10,[sp,#40+4] @ f.hi
adds r3,r3,r11
ldr r11,[sp,#48+0] @ g.lo
adc r4,r4,r12 @ T += h
ldr r12,[sp,#48+4] @ g.hi
eor r9,r9,r11
str r7,[sp,#32+0]
eor r10,r10,r12
str r8,[sp,#32+4]
and r9,r9,r7
str r5,[sp,#0+0]
and r10,r10,r8
str r6,[sp,#0+4]
eor r9,r9,r11
ldr r11,[r14,#LO] @ K[i].lo
eor r10,r10,r12 @ Ch(e,f,g)
ldr r12,[r14,#HI] @ K[i].hi
adds r3,r3,r9
ldr r7,[sp,#24+0] @ d.lo
adc r4,r4,r10 @ T += Ch(e,f,g)
ldr r8,[sp,#24+4] @ d.hi
adds r3,r3,r11
and r9,r11,#0xff
adc r4,r4,r12 @ T += K[i]
adds r7,r7,r3
ldr r11,[sp,#8+0] @ b.lo
adc r8,r8,r4 @ d += T
teq r9,#148
ldr r12,[sp,#16+0] @ c.lo
#ifdef __thumb2__
it eq @ Thumb2 thing, sanity check in ARM
#endif
orreq r14,r14,#1
@ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
@ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
@ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
mov r9,r5,lsr#28
mov r10,r6,lsr#28
eor r9,r9,r6,lsl#4
eor r10,r10,r5,lsl#4
eor r9,r9,r6,lsr#2
eor r10,r10,r5,lsr#2
eor r9,r9,r5,lsl#30
eor r10,r10,r6,lsl#30
eor r9,r9,r6,lsr#7
eor r10,r10,r5,lsr#7
eor r9,r9,r5,lsl#25
eor r10,r10,r6,lsl#25 @ Sigma0(a)
adds r3,r3,r9
and r9,r5,r11
adc r4,r4,r10 @ T += Sigma0(a)
ldr r10,[sp,#8+4] @ b.hi
orr r5,r5,r11
ldr r11,[sp,#16+4] @ c.hi
and r5,r5,r12
and r12,r6,r10
orr r6,r6,r10
orr r5,r5,r9 @ Maj(a,b,c).lo
and r6,r6,r11
adds r5,r5,r3
orr r6,r6,r12 @ Maj(a,b,c).hi
sub sp,sp,#8
adc r6,r6,r4 @ h += T
tst r14,#1
add r14,r14,#8
tst r14,#1
beq .L00_15
ldr r9,[sp,#184+0]
ldr r10,[sp,#184+4]
bic r14,r14,#1
.L16_79:
@ sigma0(x) (ROTR((x),1) ^ ROTR((x),8) ^ ((x)>>7))
@ LO lo>>1^hi<<31 ^ lo>>8^hi<<24 ^ lo>>7^hi<<25
@ HI hi>>1^lo<<31 ^ hi>>8^lo<<24 ^ hi>>7
mov r3,r9,lsr#1
ldr r11,[sp,#80+0]
mov r4,r10,lsr#1
ldr r12,[sp,#80+4]
eor r3,r3,r10,lsl#31
eor r4,r4,r9,lsl#31
eor r3,r3,r9,lsr#8
eor r4,r4,r10,lsr#8
eor r3,r3,r10,lsl#24
eor r4,r4,r9,lsl#24
eor r3,r3,r9,lsr#7
eor r4,r4,r10,lsr#7
eor r3,r3,r10,lsl#25
@ sigma1(x) (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
@ LO lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26
@ HI hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6
mov r9,r11,lsr#19
mov r10,r12,lsr#19
eor r9,r9,r12,lsl#13
eor r10,r10,r11,lsl#13
eor r9,r9,r12,lsr#29
eor r10,r10,r11,lsr#29
eor r9,r9,r11,lsl#3
eor r10,r10,r12,lsl#3
eor r9,r9,r11,lsr#6
eor r10,r10,r12,lsr#6
ldr r11,[sp,#120+0]
eor r9,r9,r12,lsl#26
ldr r12,[sp,#120+4]
adds r3,r3,r9
ldr r9,[sp,#192+0]
adc r4,r4,r10
ldr r10,[sp,#192+4]
adds r3,r3,r11
adc r4,r4,r12
adds r3,r3,r9
adc r4,r4,r10
@ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41))
@ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
@ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
mov r9,r7,lsr#14
str r3,[sp,#64+0]
mov r10,r8,lsr#14
str r4,[sp,#64+4]
eor r9,r9,r8,lsl#18
ldr r11,[sp,#56+0] @ h.lo
eor r10,r10,r7,lsl#18
ldr r12,[sp,#56+4] @ h.hi
eor r9,r9,r7,lsr#18
eor r10,r10,r8,lsr#18
eor r9,r9,r8,lsl#14
eor r10,r10,r7,lsl#14
eor r9,r9,r8,lsr#9
eor r10,r10,r7,lsr#9
eor r9,r9,r7,lsl#23
eor r10,r10,r8,lsl#23 @ Sigma1(e)
adds r3,r3,r9
ldr r9,[sp,#40+0] @ f.lo
adc r4,r4,r10 @ T += Sigma1(e)
ldr r10,[sp,#40+4] @ f.hi
adds r3,r3,r11
ldr r11,[sp,#48+0] @ g.lo
adc r4,r4,r12 @ T += h
ldr r12,[sp,#48+4] @ g.hi
eor r9,r9,r11
str r7,[sp,#32+0]
eor r10,r10,r12
str r8,[sp,#32+4]
and r9,r9,r7
str r5,[sp,#0+0]
and r10,r10,r8
str r6,[sp,#0+4]
eor r9,r9,r11
ldr r11,[r14,#LO] @ K[i].lo
eor r10,r10,r12 @ Ch(e,f,g)
ldr r12,[r14,#HI] @ K[i].hi
adds r3,r3,r9
ldr r7,[sp,#24+0] @ d.lo
adc r4,r4,r10 @ T += Ch(e,f,g)
ldr r8,[sp,#24+4] @ d.hi
adds r3,r3,r11
and r9,r11,#0xff
adc r4,r4,r12 @ T += K[i]
adds r7,r7,r3
ldr r11,[sp,#8+0] @ b.lo
adc r8,r8,r4 @ d += T
teq r9,#23
ldr r12,[sp,#16+0] @ c.lo
#ifdef __thumb2__
it eq @ Thumb2 thing, sanity check in ARM
#endif
orreq r14,r14,#1
@ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
@ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
@ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
mov r9,r5,lsr#28
mov r10,r6,lsr#28
eor r9,r9,r6,lsl#4
eor r10,r10,r5,lsl#4
eor r9,r9,r6,lsr#2
eor r10,r10,r5,lsr#2
eor r9,r9,r5,lsl#30
eor r10,r10,r6,lsl#30
eor r9,r9,r6,lsr#7
eor r10,r10,r5,lsr#7
eor r9,r9,r5,lsl#25
eor r10,r10,r6,lsl#25 @ Sigma0(a)
adds r3,r3,r9
and r9,r5,r11
adc r4,r4,r10 @ T += Sigma0(a)
ldr r10,[sp,#8+4] @ b.hi
orr r5,r5,r11
ldr r11,[sp,#16+4] @ c.hi
and r5,r5,r12
and r12,r6,r10
orr r6,r6,r10
orr r5,r5,r9 @ Maj(a,b,c).lo
and r6,r6,r11
adds r5,r5,r3
orr r6,r6,r12 @ Maj(a,b,c).hi
sub sp,sp,#8
adc r6,r6,r4 @ h += T
tst r14,#1
add r14,r14,#8
#ifdef __thumb2__
ittt eq @ Thumb2 thing, sanity check in ARM
#endif
ldreq r9,[sp,#184+0]
ldreq r10,[sp,#184+4]
beq .L16_79
bic r14,r14,#1
ldr r3,[sp,#8+0]
ldr r4,[sp,#8+4]
ldr r9, [r0,#0+LO]
ldr r10, [r0,#0+HI]
ldr r11, [r0,#8+LO]
ldr r12, [r0,#8+HI]
adds r9,r5,r9
str r9, [r0,#0+LO]
adc r10,r6,r10
str r10, [r0,#0+HI]
adds r11,r3,r11
str r11, [r0,#8+LO]
adc r12,r4,r12
str r12, [r0,#8+HI]
ldr r5,[sp,#16+0]
ldr r6,[sp,#16+4]
ldr r3,[sp,#24+0]
ldr r4,[sp,#24+4]
ldr r9, [r0,#16+LO]
ldr r10, [r0,#16+HI]
ldr r11, [r0,#24+LO]
ldr r12, [r0,#24+HI]
adds r9,r5,r9
str r9, [r0,#16+LO]
adc r10,r6,r10
str r10, [r0,#16+HI]
adds r11,r3,r11
str r11, [r0,#24+LO]
adc r12,r4,r12
str r12, [r0,#24+HI]
ldr r3,[sp,#40+0]
ldr r4,[sp,#40+4]
ldr r9, [r0,#32+LO]
ldr r10, [r0,#32+HI]
ldr r11, [r0,#40+LO]
ldr r12, [r0,#40+HI]
adds r7,r7,r9
str r7,[r0,#32+LO]
adc r8,r8,r10
str r8,[r0,#32+HI]
adds r11,r3,r11
str r11, [r0,#40+LO]
adc r12,r4,r12
str r12, [r0,#40+HI]
ldr r5,[sp,#48+0]
ldr r6,[sp,#48+4]
ldr r3,[sp,#56+0]
ldr r4,[sp,#56+4]
ldr r9, [r0,#48+LO]
ldr r10, [r0,#48+HI]
ldr r11, [r0,#56+LO]
ldr r12, [r0,#56+HI]
adds r9,r5,r9
str r9, [r0,#48+LO]
adc r10,r6,r10
str r10, [r0,#48+HI]
adds r11,r3,r11
str r11, [r0,#56+LO]
adc r12,r4,r12
str r12, [r0,#56+HI]
add sp,sp,#640
sub r14,r14,#640
teq r1,r2
bne .Loop
add sp,sp,#8*9 @ destroy frame
#if __ARM_ARCH__>=5
ldmia sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,pc}
#else
ldmia sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,lr}
tst lr,#1
moveq pc,lr @ be binary compatible with V4, yet
.word 0xe12fff1e @ interoperable with Thumb ISA:-)
#endif
.size cryptogams_sha512_block_data_order,.-cryptogams_sha512_block_data_order
#if __ARM_MAX_ARCH__>=7
.arch armv7-a
.fpu neon
.align 4
.globl cryptogams_sha512_block_data_order_neon
.type cryptogams_sha512_block_data_order_neon,%function
cryptogams_sha512_block_data_order_neon:
dmb @ errata #451034 on early Cortex A8
add r2,r1,r2,lsl#7 @ len to point at the end of inp
adr r3,K512
vstmdb sp!,{d8-d15}
vldmia r0,{d16,d17,d18,d19,d20,d21,d22,d23} @ load context
.Loop_neon:
vshr.u64 d24,d20,#14 @ 0
#if 0<16
vld1.64 {d0},[r1]! @ handles unaligned
#endif
vshr.u64 d25,d20,#18
#if 0>0
vadd.i64 d16,d30 @ h+=Maj from the past
#endif
vshr.u64 d26,d20,#41
vld1.64 {d28},[r3,:64]! @ K[i++]
vsli.64 d24,d20,#50
vsli.64 d25,d20,#46
vmov d29,d20
vsli.64 d26,d20,#23
#if 0<16 && defined(__ARMEL__)
vrev64.8 d0,d0
#endif
veor d25,d24
vbsl d29,d21,d22 @ Ch(e,f,g)
vshr.u64 d24,d16,#28
veor d26,d25 @ Sigma1(e)
vadd.i64 d27,d29,d23
vshr.u64 d25,d16,#34
vsli.64 d24,d16,#36
vadd.i64 d27,d26
vshr.u64 d26,d16,#39
vadd.i64 d28,d0
vsli.64 d25,d16,#30
veor d30,d16,d17
vsli.64 d26,d16,#25
veor d23,d24,d25
vadd.i64 d27,d28
vbsl d30,d18,d17 @ Maj(a,b,c)
veor d23,d26 @ Sigma0(a)
vadd.i64 d19,d27
vadd.i64 d30,d27
@ vadd.i64 d23,d30
vshr.u64 d24,d19,#14 @ 1
#if 1<16
vld1.64 {d1},[r1]! @ handles unaligned
#endif
vshr.u64 d25,d19,#18
#if 1>0
vadd.i64 d23,d30 @ h+=Maj from the past
#endif
vshr.u64 d26,d19,#41
vld1.64 {d28},[r3,:64]! @ K[i++]
vsli.64 d24,d19,#50
vsli.64 d25,d19,#46
vmov d29,d19
vsli.64 d26,d19,#23
#if 1<16 && defined(__ARMEL__)
vrev64.8 d1,d1
#endif
veor d25,d24
vbsl d29,d20,d21 @ Ch(e,f,g)
vshr.u64 d24,d23,#28
veor d26,d25 @ Sigma1(e)
vadd.i64 d27,d29,d22
vshr.u64 d25,d23,#34
vsli.64 d24,d23,#36
vadd.i64 d27,d26
vshr.u64 d26,d23,#39
vadd.i64 d28,d1
vsli.64 d25,d23,#30
veor d30,d23,d16
vsli.64 d26,d23,#25
veor d22,d24,d25
vadd.i64 d27,d28
vbsl d30,d17,d16 @ Maj(a,b,c)
veor d22,d26 @ Sigma0(a)
vadd.i64 d18,d27
vadd.i64 d30,d27
@ vadd.i64 d22,d30
vshr.u64 d24,d18,#14 @ 2
#if 2<16
vld1.64 {d2},[r1]! @ handles unaligned
#endif
vshr.u64 d25,d18,#18
#if 2>0
vadd.i64 d22,d30 @ h+=Maj from the past
#endif
vshr.u64 d26,d18,#41
vld1.64 {d28},[r3,:64]! @ K[i++]
vsli.64 d24,d18,#50
vsli.64 d25,d18,#46
vmov d29,d18
vsli.64 d26,d18,#23
#if 2<16 && defined(__ARMEL__)
vrev64.8 d2,d2
#endif
veor d25,d24
vbsl d29,d19,d20 @ Ch(e,f,g)
vshr.u64 d24,d22,#28
veor d26,d25 @ Sigma1(e)
vadd.i64 d27,d29,d21
vshr.u64 d25,d22,#34
vsli.64 d24,d22,#36
vadd.i64 d27,d26
vshr.u64 d26,d22,#39
vadd.i64 d28,d2
vsli.64 d25,d22,#30
veor d30,d22,d23
vsli.64 d26,d22,#25
veor d21,d24,d25
vadd.i64 d27,d28
vbsl d30,d16,d23 @ Maj(a,b,c)
veor d21,d26 @ Sigma0(a)
vadd.i64 d17,d27
vadd.i64 d30,d27
@ vadd.i64 d21,d30
vshr.u64 d24,d17,#14 @ 3
#if 3<16
vld1.64 {d3},[r1]! @ handles unaligned
#endif
vshr.u64 d25,d17,#18
#if 3>0
vadd.i64 d21,d30 @ h+=Maj from the past
#endif
vshr.u64 d26,d17,#41
vld1.64 {d28},[r3,:64]! @ K[i++]
vsli.64 d24,d17,#50
vsli.64 d25,d17,#46
vmov d29,d17
vsli.64 d26,d17,#23
#if 3<16 && defined(__ARMEL__)
vrev64.8 d3,d3
#endif
veor d25,d24
vbsl d29,d18,d19 @ Ch(e,f,g)
vshr.u64 d24,d21,#28
veor d26,d25 @ Sigma1(e)
vadd.i64 d27,d29,d20
vshr.u64 d25,d21,#34
vsli.64 d24,d21,#36
vadd.i64 d27,d26
vshr.u64 d26,d21,#39
vadd.i64 d28,d3
vsli.64 d25,d21,#30
veor d30,d21,d22
vsli.64 d26,d21,#25
veor d20,d24,d25
vadd.i64 d27,d28
vbsl d30,d23,d22 @ Maj(a,b,c)
veor d20,d26 @ Sigma0(a)
vadd.i64 d16,d27
vadd.i64 d30,d27
@ vadd.i64 d20,d30
vshr.u64 d24,d16,#14 @ 4
#if 4<16
vld1.64 {d4},[r1]! @ handles unaligned
#endif
vshr.u64 d25,d16,#18
#if 4>0
vadd.i64 d20,d30 @ h+=Maj from the past
#endif
vshr.u64 d26,d16,#41
vld1.64 {d28},[r3,:64]! @ K[i++]
vsli.64 d24,d16,#50
vsli.64 d25,d16,#46
vmov d29,d16
vsli.64 d26,d16,#23
#if 4<16 && defined(__ARMEL__)
vrev64.8 d4,d4
#endif
veor d25,d24
vbsl d29,d17,d18 @ Ch(e,f,g)
vshr.u64 d24,d20,#28
veor d26,d25 @ Sigma1(e)
vadd.i64 d27,d29,d19
vshr.u64 d25,d20,#34
vsli.64 d24,d20,#36
vadd.i64 d27,d26
vshr.u64 d26,d20,#39
vadd.i64 d28,d4
vsli.64 d25,d20,#30
veor d30,d20,d21
vsli.64 d26,d20,#25
veor d19,d24,d25
vadd.i64 d27,d28
vbsl d30,d22,d21 @ Maj(a,b,c)
veor d19,d26 @ Sigma0(a)
vadd.i64 d23,d27
vadd.i64 d30,d27
@ vadd.i64 d19,d30
vshr.u64 d24,d23,#14 @ 5
#if 5<16
vld1.64 {d5},[r1]! @ handles unaligned
#endif
vshr.u64 d25,d23,#18
#if 5>0
vadd.i64 d19,d30 @ h+=Maj from the past
#endif
vshr.u64 d26,d23,#41
vld1.64 {d28},[r3,:64]! @ K[i++]
vsli.64 d24,d23,#50
vsli.64 d25,d23,#46
vmov d29,d23
vsli.64 d26,d23,#23
#if 5<16 && defined(__ARMEL__)
vrev64.8 d5,d5
#endif
veor d25,d24
vbsl d29,d16,d17 @ Ch(e,f,g)
vshr.u64 d24,d19,#28
veor d26,d25 @ Sigma1(e)
vadd.i64 d27,d29,d18
vshr.u64 d25,d19,#34
vsli.64 d24,d19,#36
vadd.i64 d27,d26
vshr.u64 d26,d19,#39
vadd.i64 d28,d5
vsli.64 d25,d19,#30
veor d30,d19,d20
vsli.64 d26,d19,#25
veor d18,d24,d25
vadd.i64 d27,d28
vbsl d30,d21,d20 @ Maj(a,b,c)
veor d18,d26 @ Sigma0(a)
vadd.i64 d22,d27
vadd.i64 d30,d27
@ vadd.i64 d18,d30
vshr.u64 d24,d22,#14 @ 6
#if 6<16
vld1.64 {d6},[r1]! @ handles unaligned
#endif
vshr.u64 d25,d22,#18
#if 6>0
vadd.i64 d18,d30 @ h+=Maj from the past
#endif
vshr.u64 d26,d22,#41
vld1.64 {d28},[r3,:64]! @ K[i++]
vsli.64 d24,d22,#50
vsli.64 d25,d22,#46
vmov d29,d22
vsli.64 d26,d22,#23
#if 6<16 && defined(__ARMEL__)
vrev64.8 d6,d6
#endif
veor d25,d24
vbsl d29,d23,d16 @ Ch(e,f,g)
vshr.u64 d24,d18,#28
veor d26,d25 @ Sigma1(e)
vadd.i64 d27,d29,d17
vshr.u64 d25,d18,#34
vsli.64 d24,d18,#36
vadd.i64 d27,d26
vshr.u64 d26,d18,#39
vadd.i64 d28,d6
vsli.64 d25,d18,#30
veor d30,d18,d19
vsli.64 d26,d18,#25
veor d17,d24,d25
vadd.i64 d27,d28
vbsl d30,d20,d19 @ Maj(a,b,c)
veor d17,d26 @ Sigma0(a)
vadd.i64 d21,d27
vadd.i64 d30,d27
@ vadd.i64 d17,d30
vshr.u64 d24,d21,#14 @ 7
#if 7<16
vld1.64 {d7},[r1]! @ handles unaligned
#endif
vshr.u64 d25,d21,#18
#if 7>0
vadd.i64 d17,d30 @ h+=Maj from the past
#endif
vshr.u64 d26,d21,#41
vld1.64 {d28},[r3,:64]! @ K[i++]
vsli.64 d24,d21,#50
vsli.64 d25,d21,#46
vmov d29,d21
vsli.64 d26,d21,#23
#if 7<16 && defined(__ARMEL__)
vrev64.8 d7,d7
#endif
veor d25,d24
vbsl d29,d22,d23 @ Ch(e,f,g)
vshr.u64 d24,d17,#28
veor d26,d25 @ Sigma1(e)
vadd.i64 d27,d29,d16
vshr.u64 d25,d17,#34
vsli.64 d24,d17,#36
vadd.i64 d27,d26
vshr.u64 d26,d17,#39
vadd.i64 d28,d7
vsli.64 d25,d17,#30
veor d30,d17,d18
vsli.64 d26,d17,#25
veor d16,d24,d25
vadd.i64 d27,d28
vbsl d30,d19,d18 @ Maj(a,b,c)
veor d16,d26 @ Sigma0(a)
vadd.i64 d20,d27
vadd.i64 d30,d27
@ vadd.i64 d16,d30
vshr.u64 d24,d20,#14 @ 8
#if 8<16
vld1.64 {d8},[r1]! @ handles unaligned
#endif
vshr.u64 d25,d20,#18
#if 8>0
vadd.i64 d16,d30 @ h+=Maj from the past
#endif
vshr.u64 d26,d20,#41
vld1.64 {d28},[r3,:64]! @ K[i++]
vsli.64 d24,d20,#50
vsli.64 d25,d20,#46
vmov d29,d20
vsli.64 d26,d20,#23
#if 8<16 && defined(__ARMEL__)
vrev64.8 d8,d8
#endif
veor d25,d24
vbsl d29,d21,d22 @ Ch(e,f,g)
vshr.u64 d24,d16,#28
veor d26,d25 @ Sigma1(e)
vadd.i64 d27,d29,d23
vshr.u64 d25,d16,#34
vsli.64 d24,d16,#36
vadd.i64 d27,d26
vshr.u64 d26,d16,#39
vadd.i64 d28,d8
vsli.64 d25,d16,#30
veor d30,d16,d17
vsli.64 d26,d16,#25
veor d23,d24,d25
vadd.i64 d27,d28
vbsl d30,d18,d17 @ Maj(a,b,c)
veor d23,d26 @ Sigma0(a)
vadd.i64 d19,d27
vadd.i64 d30,d27
@ vadd.i64 d23,d30
vshr.u64 d24,d19,#14 @ 9
#if 9<16
vld1.64 {d9},[r1]! @ handles unaligned
#endif
vshr.u64 d25,d19,#18
#if 9>0
vadd.i64 d23,d30 @ h+=Maj from the past
#endif
vshr.u64 d26,d19,#41
vld1.64 {d28},[r3,:64]! @ K[i++]
vsli.64 d24,d19,#50
vsli.64 d25,d19,#46
vmov d29,d19
vsli.64 d26,d19,#23
#if 9<16 && defined(__ARMEL__)
vrev64.8 d9,d9
#endif
veor d25,d24
vbsl d29,d20,d21 @ Ch(e,f,g)
vshr.u64 d24,d23,#28
veor d26,d25 @ Sigma1(e)
vadd.i64 d27,d29,d22
vshr.u64 d25,d23,#34
vsli.64 d24,d23,#36
vadd.i64 d27,d26
vshr.u64 d26,d23,#39
vadd.i64 d28,d9
vsli.64 d25,d23,#30
veor d30,d23,d16
vsli.64 d26,d23,#25
veor d22,d24,d25
vadd.i64 d27,d28
vbsl d30,d17,d16 @ Maj(a,b,c)
veor d22,d26 @ Sigma0(a)
vadd.i64 d18,d27
vadd.i64 d30,d27
@ vadd.i64 d22,d30
vshr.u64 d24,d18,#14 @ 10
#if 10<16
vld1.64 {d10},[r1]! @ handles unaligned
#endif
vshr.u64 d25,d18,#18
#if 10>0
vadd.i64 d22,d30 @ h+=Maj from the past
#endif
vshr.u64 d26,d18,#41
vld1.64 {d28},[r3,:64]! @ K[i++]
vsli.64 d24,d18,#50
vsli.64 d25,d18,#46
vmov d29,d18
vsli.64 d26,d18,#23
#if 10<16 && defined(__ARMEL__)
vrev64.8 d10,d10
#endif
veor d25,d24
vbsl d29,d19,d20 @ Ch(e,f,g)
vshr.u64 d24,d22,#28
veor d26,d25 @ Sigma1(e)
vadd.i64 d27,d29,d21
vshr.u64 d25,d22,#34
vsli.64 d24,d22,#36
vadd.i64 d27,d26
vshr.u64 d26,d22,#39
vadd.i64 d28,d10
vsli.64 d25,d22,#30
veor d30,d22,d23
vsli.64 d26,d22,#25
veor d21,d24,d25
vadd.i64 d27,d28
vbsl d30,d16,d23 @ Maj(a,b,c)
veor d21,d26 @ Sigma0(a)
vadd.i64 d17,d27
vadd.i64 d30,d27
@ vadd.i64 d21,d30
vshr.u64 d24,d17,#14 @ 11
#if 11<16
vld1.64 {d11},[r1]! @ handles unaligned
#endif
vshr.u64 d25,d17,#18
#if 11>0
vadd.i64 d21,d30 @ h+=Maj from the past
#endif
vshr.u64 d26,d17,#41
vld1.64 {d28},[r3,:64]! @ K[i++]
vsli.64 d24,d17,#50
vsli.64 d25,d17,#46
vmov d29,d17
vsli.64 d26,d17,#23
#if 11<16 && defined(__ARMEL__)
vrev64.8 d11,d11
#endif
veor d25,d24
vbsl d29,d18,d19 @ Ch(e,f,g)
vshr.u64 d24,d21,#28
veor d26,d25 @ Sigma1(e)
vadd.i64 d27,d29,d20
vshr.u64 d25,d21,#34
vsli.64 d24,d21,#36
vadd.i64 d27,d26
vshr.u64 d26,d21,#39
vadd.i64 d28,d11
vsli.64 d25,d21,#30
veor d30,d21,d22
vsli.64 d26,d21,#25
veor d20,d24,d25
vadd.i64 d27,d28
vbsl d30,d23,d22 @ Maj(a,b,c)
veor d20,d26 @ Sigma0(a)
vadd.i64 d16,d27
vadd.i64 d30,d27
@ vadd.i64 d20,d30
vshr.u64 d24,d16,#14 @ 12
#if 12<16
vld1.64 {d12},[r1]! @ handles unaligned
#endif
vshr.u64 d25,d16,#18
#if 12>0
vadd.i64 d20,d30 @ h+=Maj from the past
#endif
vshr.u64 d26,d16,#41
vld1.64 {d28},[r3,:64]! @ K[i++]