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
|
/**
* \file bn_mul.h
*
* \brief Multi-precision integer library
*
* Copyright (C) 2006-2010, Brainspark B.V.
*
* This file is part of PolarSSL (http://www.polarssl.org)
* Lead Maintainer: Paul Bakker <polarssl_maintainer at polarssl.org>
*
* All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License along
* with this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
*/
/*
* Multiply source vector [s] with b, add result
* to destination vector [d] and set carry c.
*
* Currently supports:
*
* . IA-32 (386+) . AMD64 / EM64T
* . IA-32 (SSE2) . Motorola 68000
* . PowerPC, 32-bit . MicroBlaze
* . PowerPC, 64-bit . TriCore
* . SPARC v8 . ARM v3+
* . Alpha . MIPS32
* . C, longlong . C, generic
*/
#ifndef POLARSSL_BN_MUL_H
#define POLARSSL_BN_MUL_H
#include "polarssl/config.h"
#if defined(POLARSSL_HAVE_ASM)
#if defined(__GNUC__)
#if defined(__i386__)
#define MULADDC_INIT \
asm( " \
movl %%ebx, %0; \
movl %5, %%esi; \
movl %6, %%edi; \
movl %7, %%ecx; \
movl %8, %%ebx; \
"
#define MULADDC_CORE \
" \
lodsl; \
mull %%ebx; \
addl %%ecx, %%eax; \
adcl $0, %%edx; \
addl (%%edi), %%eax; \
adcl $0, %%edx; \
movl %%edx, %%ecx; \
stosl; \
"
#if defined(POLARSSL_HAVE_SSE2)
#define MULADDC_HUIT \
" \
movd %%ecx, %%mm1; \
movd %%ebx, %%mm0; \
movd (%%edi), %%mm3; \
paddq %%mm3, %%mm1; \
movd (%%esi), %%mm2; \
pmuludq %%mm0, %%mm2; \
movd 4(%%esi), %%mm4; \
pmuludq %%mm0, %%mm4; \
movd 8(%%esi), %%mm6; \
pmuludq %%mm0, %%mm6; \
movd 12(%%esi), %%mm7; \
pmuludq %%mm0, %%mm7; \
paddq %%mm2, %%mm1; \
movd 4(%%edi), %%mm3; \
paddq %%mm4, %%mm3; \
movd 8(%%edi), %%mm5; \
paddq %%mm6, %%mm5; \
movd 12(%%edi), %%mm4; \
paddq %%mm4, %%mm7; \
movd %%mm1, (%%edi); \
movd 16(%%esi), %%mm2; \
pmuludq %%mm0, %%mm2; \
psrlq $32, %%mm1; \
movd 20(%%esi), %%mm4; \
pmuludq %%mm0, %%mm4; \
paddq %%mm3, %%mm1; \
movd 24(%%esi), %%mm6; \
pmuludq %%mm0, %%mm6; \
movd %%mm1, 4(%%edi); \
psrlq $32, %%mm1; \
movd 28(%%esi), %%mm3; \
pmuludq %%mm0, %%mm3; \
paddq %%mm5, %%mm1; \
movd 16(%%edi), %%mm5; \
paddq %%mm5, %%mm2; \
movd %%mm1, 8(%%edi); \
psrlq $32, %%mm1; \
paddq %%mm7, %%mm1; \
movd 20(%%edi), %%mm5; \
paddq %%mm5, %%mm4; \
movd %%mm1, 12(%%edi); \
psrlq $32, %%mm1; \
paddq %%mm2, %%mm1; \
movd 24(%%edi), %%mm5; \
paddq %%mm5, %%mm6; \
movd %%mm1, 16(%%edi); \
psrlq $32, %%mm1; \
paddq %%mm4, %%mm1; \
movd 28(%%edi), %%mm5; \
paddq %%mm5, %%mm3; \
movd %%mm1, 20(%%edi); \
psrlq $32, %%mm1; \
paddq %%mm6, %%mm1; \
movd %%mm1, 24(%%edi); \
psrlq $32, %%mm1; \
paddq %%mm3, %%mm1; \
movd %%mm1, 28(%%edi); \
addl $32, %%edi; \
addl $32, %%esi; \
psrlq $32, %%mm1; \
movd %%mm1, %%ecx; \
"
#define MULADDC_STOP \
" \
emms; \
movl %4, %%ebx; \
movl %%ecx, %1; \
movl %%edi, %2; \
movl %%esi, %3; \
" \
: "=m" (t), "=m" (c), "=m" (d), "=m" (s) \
: "m" (t), "m" (s), "m" (d), "m" (c), "m" (b) \
: "eax", "ecx", "edx", "esi", "edi" \
);
#else
#define MULADDC_STOP \
" \
movl %4, %%ebx; \
movl %%ecx, %1; \
movl %%edi, %2; \
movl %%esi, %3; \
" \
: "=m" (t), "=m" (c), "=m" (d), "=m" (s) \
: "m" (t), "m" (s), "m" (d), "m" (c), "m" (b) \
: "eax", "ecx", "edx", "esi", "edi" \
);
#endif /* SSE2 */
#endif /* i386 */
#if defined(__amd64__) || defined (__x86_64__)
#define MULADDC_INIT \
asm( "movq %0, %%rsi " :: "m" (s)); \
asm( "movq %0, %%rdi " :: "m" (d)); \
asm( "movq %0, %%rcx " :: "m" (c)); \
asm( "movq %0, %%rbx " :: "m" (b)); \
asm( "xorq %r8, %r8 " );
#define MULADDC_CORE \
asm( "movq (%rsi),%rax " ); \
asm( "mulq %rbx " ); \
asm( "addq $8, %rsi " ); \
asm( "addq %rcx, %rax " ); \
asm( "movq %r8, %rcx " ); \
asm( "adcq $0, %rdx " ); \
asm( "nop " ); \
asm( "addq %rax, (%rdi) " ); \
asm( "adcq %rdx, %rcx " ); \
asm( "addq $8, %rdi " );
#define MULADDC_STOP \
asm( "movq %%rcx, %0 " : "=m" (c)); \
asm( "movq %%rdi, %0 " : "=m" (d)); \
asm( "movq %%rsi, %0 " : "=m" (s) :: \
"rax", "rcx", "rdx", "rbx", "rsi", "rdi", "r8" );
#endif /* AMD64 */
#if defined(__mc68020__) || defined(__mcpu32__)
#define MULADDC_INIT \
asm( "movl %0, %%a2 " :: "m" (s)); \
asm( "movl %0, %%a3 " :: "m" (d)); \
asm( "movl %0, %%d3 " :: "m" (c)); \
asm( "movl %0, %%d2 " :: "m" (b)); \
asm( "moveq #0, %d0 " );
#define MULADDC_CORE \
asm( "movel %a2@+, %d1 " ); \
asm( "mulul %d2, %d4:%d1 " ); \
asm( "addl %d3, %d1 " ); \
asm( "addxl %d0, %d4 " ); \
asm( "moveq #0, %d3 " ); \
asm( "addl %d1, %a3@+ " ); \
asm( "addxl %d4, %d3 " );
#define MULADDC_STOP \
asm( "movl %%d3, %0 " : "=m" (c)); \
asm( "movl %%a3, %0 " : "=m" (d)); \
asm( "movl %%a2, %0 " : "=m" (s) :: \
"d0", "d1", "d2", "d3", "d4", "a2", "a3" );
#define MULADDC_HUIT \
asm( "movel %a2@+, %d1 " ); \
asm( "mulul %d2, %d4:%d1 " ); \
asm( "addxl %d3, %d1 " ); \
asm( "addxl %d0, %d4 " ); \
asm( "addl %d1, %a3@+ " ); \
asm( "movel %a2@+, %d1 " ); \
asm( "mulul %d2, %d3:%d1 " ); \
asm( "addxl %d4, %d1 " ); \
asm( "addxl %d0, %d3 " ); \
asm( "addl %d1, %a3@+ " ); \
asm( "movel %a2@+, %d1 " ); \
asm( "mulul %d2, %d4:%d1 " ); \
asm( "addxl %d3, %d1 " ); \
asm( "addxl %d0, %d4 " ); \
asm( "addl %d1, %a3@+ " ); \
asm( "movel %a2@+, %d1 " ); \
asm( "mulul %d2, %d3:%d1 " ); \
asm( "addxl %d4, %d1 " ); \
asm( "addxl %d0, %d3 " ); \
asm( "addl %d1, %a3@+ " ); \
asm( "movel %a2@+, %d1 " ); \
asm( "mulul %d2, %d4:%d1 " ); \
asm( "addxl %d3, %d1 " ); \
asm( "addxl %d0, %d4 " ); \
asm( "addl %d1, %a3@+ " ); \
asm( "movel %a2@+, %d1 " ); \
asm( "mulul %d2, %d3:%d1 " ); \
asm( "addxl %d4, %d1 " ); \
asm( "addxl %d0, %d3 " ); \
asm( "addl %d1, %a3@+ " ); \
asm( "movel %a2@+, %d1 " ); \
asm( "mulul %d2, %d4:%d1 " ); \
asm( "addxl %d3, %d1 " ); \
asm( "addxl %d0, %d4 " ); \
asm( "addl %d1, %a3@+ " ); \
asm( "movel %a2@+, %d1 " ); \
asm( "mulul %d2, %d3:%d1 " ); \
asm( "addxl %d4, %d1 " ); \
asm( "addxl %d0, %d3 " ); \
asm( "addl %d1, %a3@+ " ); \
asm( "addxl %d0, %d3 " );
#endif /* MC68000 */
#if defined(__powerpc__) || defined(__ppc__)
#if defined(__powerpc64__) || defined(__ppc64__)
#if defined(__MACH__) && defined(__APPLE__)
#define MULADDC_INIT \
asm( "ld r3, %0 " :: "m" (s)); \
asm( "ld r4, %0 " :: "m" (d)); \
asm( "ld r5, %0 " :: "m" (c)); \
asm( "ld r6, %0 " :: "m" (b)); \
asm( "addi r3, r3, -8 " ); \
asm( "addi r4, r4, -8 " ); \
asm( "addic r5, r5, 0 " );
#define MULADDC_CORE \
asm( "ldu r7, 8(r3) " ); \
asm( "mulld r8, r7, r6 " ); \
asm( "mulhdu r9, r7, r6 " ); \
asm( "adde r8, r8, r5 " ); \
asm( "ld r7, 8(r4) " ); \
asm( "addze r5, r9 " ); \
asm( "addc r8, r8, r7 " ); \
asm( "stdu r8, 8(r4) " );
#define MULADDC_STOP \
asm( "addze r5, r5 " ); \
asm( "addi r4, r4, 8 " ); \
asm( "addi r3, r3, 8 " ); \
asm( "std r5, %0 " : "=m" (c)); \
asm( "std r4, %0 " : "=m" (d)); \
asm( "std r3, %0 " : "=m" (s) :: \
"r3", "r4", "r5", "r6", "r7", "r8", "r9" );
#else
#define MULADDC_INIT \
asm( "ld %%r3, %0 " :: "m" (s)); \
asm( "ld %%r4, %0 " :: "m" (d)); \
asm( "ld %%r5, %0 " :: "m" (c)); \
asm( "ld %%r6, %0 " :: "m" (b)); \
asm( "addi %r3, %r3, -8 " ); \
asm( "addi %r4, %r4, -8 " ); \
asm( "addic %r5, %r5, 0 " );
#define MULADDC_CORE \
asm( "ldu %r7, 8(%r3) " ); \
asm( "mulld %r8, %r7, %r6 " ); \
asm( "mulhdu %r9, %r7, %r6 " ); \
asm( "adde %r8, %r8, %r5 " ); \
asm( "ld %r7, 8(%r4) " ); \
asm( "addze %r5, %r9 " ); \
asm( "addc %r8, %r8, %r7 " ); \
asm( "stdu %r8, 8(%r4) " );
#define MULADDC_STOP \
asm( "addze %r5, %r5 " ); \
asm( "addi %r4, %r4, 8 " ); \
asm( "addi %r3, %r3, 8 " ); \
asm( "std %%r5, %0 " : "=m" (c)); \
asm( "std %%r4, %0 " : "=m" (d)); \
asm( "std %%r3, %0 " : "=m" (s) :: \
"r3", "r4", "r5", "r6", "r7", "r8", "r9" );
#endif
#else /* PPC32 */
#if defined(__MACH__) && defined(__APPLE__)
#define MULADDC_INIT \
asm( "lwz r3, %0 " :: "m" (s)); \
asm( "lwz r4, %0 " :: "m" (d)); \
asm( "lwz r5, %0 " :: "m" (c)); \
asm( "lwz r6, %0 " :: "m" (b)); \
asm( "addi r3, r3, -4 " ); \
asm( "addi r4, r4, -4 " ); \
asm( "addic r5, r5, 0 " );
#define MULADDC_CORE \
asm( "lwzu r7, 4(r3) " ); \
asm( "mullw r8, r7, r6 " ); \
asm( "mulhwu r9, r7, r6 " ); \
asm( "adde r8, r8, r5 " ); \
asm( "lwz r7, 4(r4) " ); \
asm( "addze r5, r9 " ); \
asm( "addc r8, r8, r7 " ); \
asm( "stwu r8, 4(r4) " );
#define MULADDC_STOP \
asm( "addze r5, r5 " ); \
asm( "addi r4, r4, 4 " ); \
asm( "addi r3, r3, 4 " ); \
asm( "stw r5, %0 " : "=m" (c)); \
asm( "stw r4, %0 " : "=m" (d)); \
asm( "stw r3, %0 " : "=m" (s) :: \
"r3", "r4", "r5", "r6", "r7", "r8", "r9" );
#else
#define MULADDC_INIT \
asm( "lwz %%r3, %0 " :: "m" (s)); \
asm( "lwz %%r4, %0 " :: "m" (d)); \
asm( "lwz %%r5, %0 " :: "m" (c)); \
asm( "lwz %%r6, %0 " :: "m" (b)); \
asm( "addi %r3, %r3, -4 " ); \
asm( "addi %r4, %r4, -4 " ); \
asm( "addic %r5, %r5, 0 " );
#define MULADDC_CORE \
asm( "lwzu %r7, 4(%r3) " ); \
asm( "mullw %r8, %r7, %r6 " ); \
asm( "mulhwu %r9, %r7, %r6 " ); \
asm( "adde %r8, %r8, %r5 " ); \
asm( "lwz %r7, 4(%r4) " ); \
asm( "addze %r5, %r9 " ); \
asm( "addc %r8, %r8, %r7 " ); \
asm( "stwu %r8, 4(%r4) " );
#define MULADDC_STOP \
asm( "addze %r5, %r5 " ); \
asm( "addi %r4, %r4, 4 " ); \
asm( "addi %r3, %r3, 4 " ); \
asm( "stw %%r5, %0 " : "=m" (c)); \
asm( "stw %%r4, %0 " : "=m" (d)); \
asm( "stw %%r3, %0 " : "=m" (s) :: \
"r3", "r4", "r5", "r6", "r7", "r8", "r9" );
#endif
#endif /* PPC32 */
#endif /* PPC64 */
#if defined(__sparc__)
#define MULADDC_INIT \
asm( "ld %0, %%o0 " :: "m" (s)); \
asm( "ld %0, %%o1 " :: "m" (d)); \
asm( "ld %0, %%o2 " :: "m" (c)); \
asm( "ld %0, %%o3 " :: "m" (b));
#define MULADDC_CORE \
asm( "ld [%o0], %o4 " ); \
asm( "inc 4, %o0 " ); \
asm( "ld [%o1], %o5 " ); \
asm( "umul %o3, %o4, %o4 " ); \
asm( "addcc %o4, %o2, %o4 " ); \
asm( "rd %y, %g1 " ); \
asm( "addx %g1, 0, %g1 " ); \
asm( "addcc %o4, %o5, %o4 " ); \
asm( "st %o4, [%o1] " ); \
asm( "addx %g1, 0, %o2 " ); \
asm( "inc 4, %o1 " );
#define MULADDC_STOP \
asm( "st %%o2, %0 " : "=m" (c)); \
asm( "st %%o1, %0 " : "=m" (d)); \
asm( "st %%o0, %0 " : "=m" (s) :: \
"g1", "o0", "o1", "o2", "o3", "o4", "o5" );
#endif /* SPARCv8 */
#if defined(__microblaze__) || defined(microblaze)
#define MULADDC_INIT \
asm( "lwi r3, %0 " :: "m" (s)); \
asm( "lwi r4, %0 " :: "m" (d)); \
asm( "lwi r5, %0 " :: "m" (c)); \
asm( "lwi r6, %0 " :: "m" (b)); \
asm( "andi r7, r6, 0xffff" ); \
asm( "bsrli r6, r6, 16 " );
#define MULADDC_CORE \
asm( "lhui r8, r3, 0 " ); \
asm( "addi r3, r3, 2 " ); \
asm( "lhui r9, r3, 0 " ); \
asm( "addi r3, r3, 2 " ); \
asm( "mul r10, r9, r6 " ); \
asm( "mul r11, r8, r7 " ); \
asm( "mul r12, r9, r7 " ); \
asm( "mul r13, r8, r6 " ); \
asm( "bsrli r8, r10, 16 " ); \
asm( "bsrli r9, r11, 16 " ); \
asm( "add r13, r13, r8 " ); \
asm( "add r13, r13, r9 " ); \
asm( "bslli r10, r10, 16 " ); \
asm( "bslli r11, r11, 16 " ); \
asm( "add r12, r12, r10 " ); \
asm( "addc r13, r13, r0 " ); \
asm( "add r12, r12, r11 " ); \
asm( "addc r13, r13, r0 " ); \
asm( "lwi r10, r4, 0 " ); \
asm( "add r12, r12, r10 " ); \
asm( "addc r13, r13, r0 " ); \
asm( "add r12, r12, r5 " ); \
asm( "addc r5, r13, r0 " ); \
asm( "swi r12, r4, 0 " ); \
asm( "addi r4, r4, 4 " );
#define MULADDC_STOP \
asm( "swi r5, %0 " : "=m" (c)); \
asm( "swi r4, %0 " : "=m" (d)); \
asm( "swi r3, %0 " : "=m" (s) :: \
"r3", "r4" , "r5" , "r6" , "r7" , "r8" , \
"r9", "r10", "r11", "r12", "r13" );
#endif /* MicroBlaze */
#if defined(__tricore__)
#define MULADDC_INIT \
asm( "ld.a %%a2, %0 " :: "m" (s)); \
asm( "ld.a %%a3, %0 " :: "m" (d)); \
asm( "ld.w %%d4, %0 " :: "m" (c)); \
asm( "ld.w %%d1, %0 " :: "m" (b)); \
asm( "xor %d5, %d5 " );
#define MULADDC_CORE \
asm( "ld.w %d0, [%a2+] " ); \
asm( "madd.u %e2, %e4, %d0, %d1 " ); \
asm( "ld.w %d0, [%a3] " ); \
asm( "addx %d2, %d2, %d0 " ); \
asm( "addc %d3, %d3, 0 " ); \
asm( "mov %d4, %d3 " ); \
asm( "st.w [%a3+], %d2 " );
#define MULADDC_STOP \
asm( "st.w %0, %%d4 " : "=m" (c)); \
asm( "st.a %0, %%a3 " : "=m" (d)); \
asm( "st.a %0, %%a2 " : "=m" (s) :: \
"d0", "d1", "e2", "d4", "a2", "a3" );
#endif /* TriCore */
#if defined(__arm__)
#define MULADDC_INIT \
asm( "ldr r0, %0 " :: "m" (s)); \
asm( "ldr r1, %0 " :: "m" (d)); \
asm( "ldr r2, %0 " :: "m" (c)); \
asm( "ldr r3, %0 " :: "m" (b));
#define MULADDC_CORE \
asm( "ldr r4, [r0], #4 " ); \
asm( "mov r5, #0 " ); \
asm( "ldr r6, [r1] " ); \
asm( "umlal r2, r5, r3, r4 " ); \
asm( "adds r7, r6, r2 " ); \
asm( "adc r2, r5, #0 " ); \
asm( "str r7, [r1], #4 " );
#define MULADDC_STOP \
asm( "str r2, %0 " : "=m" (c)); \
asm( "str r1, %0 " : "=m" (d)); \
asm( "str r0, %0 " : "=m" (s) :: \
"r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7" );
#endif /* ARMv3 */
#if defined(__alpha__)
#define MULADDC_INIT \
asm( "ldq $1, %0 " :: "m" (s)); \
asm( "ldq $2, %0 " :: "m" (d)); \
asm( "ldq $3, %0 " :: "m" (c)); \
asm( "ldq $4, %0 " :: "m" (b));
#define MULADDC_CORE \
asm( "ldq $6, 0($1) " ); \
asm( "addq $1, 8, $1 " ); \
asm( "mulq $6, $4, $7 " ); \
asm( "umulh $6, $4, $6 " ); \
asm( "addq $7, $3, $7 " ); \
asm( "cmpult $7, $3, $3 " ); \
asm( "ldq $5, 0($2) " ); \
asm( "addq $7, $5, $7 " ); \
asm( "cmpult $7, $5, $5 " ); \
asm( "stq $7, 0($2) " ); \
asm( "addq $2, 8, $2 " ); \
asm( "addq $6, $3, $3 " ); \
asm( "addq $5, $3, $3 " );
#define MULADDC_STOP \
asm( "stq $3, %0 " : "=m" (c)); \
asm( "stq $2, %0 " : "=m" (d)); \
asm( "stq $1, %0 " : "=m" (s) :: \
"$1", "$2", "$3", "$4", "$5", "$6", "$7" );
#endif /* Alpha */
#if defined(__mips__)
#define MULADDC_INIT \
asm( "lw $10, %0 " :: "m" (s)); \
asm( "lw $11, %0 " :: "m" (d)); \
asm( "lw $12, %0 " :: "m" (c)); \
asm( "lw $13, %0 " :: "m" (b));
#define MULADDC_CORE \
asm( "lw $14, 0($10) " ); \
asm( "multu $13, $14 " ); \
asm( "addi $10, $10, 4 " ); \
asm( "mflo $14 " ); \
asm( "mfhi $9 " ); \
asm( "addu $14, $12, $14 " ); \
asm( "lw $15, 0($11) " ); \
asm( "sltu $12, $14, $12 " ); \
asm( "addu $15, $14, $15 " ); \
asm( "sltu $14, $15, $14 " ); \
asm( "addu $12, $12, $9 " ); \
asm( "sw $15, 0($11) " ); \
asm( "addu $12, $12, $14 " ); \
asm( "addi $11, $11, 4 " );
#define MULADDC_STOP \
asm( "sw $12, %0 " : "=m" (c)); \
asm( "sw $11, %0 " : "=m" (d)); \
asm( "sw $10, %0 " : "=m" (s) :: \
"$9", "$10", "$11", "$12", "$13", "$14", "$15" );
#endif /* MIPS */
#endif /* GNUC */
#if (defined(_MSC_VER) && defined(_M_IX86)) || defined(__WATCOMC__)
#define MULADDC_INIT \
__asm mov esi, s \
__asm mov edi, d \
__asm mov ecx, c \
__asm mov ebx, b
#define MULADDC_CORE \
__asm lodsd \
__asm mul ebx \
__asm add eax, ecx \
__asm adc edx, 0 \
__asm add eax, [edi] \
__asm adc edx, 0 \
__asm mov ecx, edx \
__asm stosd
#if defined(POLARSSL_HAVE_SSE2)
#define EMIT __asm _emit
#define MULADDC_HUIT \
EMIT 0x0F EMIT 0x6E EMIT 0xC9 \
EMIT 0x0F EMIT 0x6E EMIT 0xC3 \
EMIT 0x0F EMIT 0x6E EMIT 0x1F \
EMIT 0x0F EMIT 0xD4 EMIT 0xCB \
EMIT 0x0F EMIT 0x6E EMIT 0x16 \
EMIT 0x0F EMIT 0xF4 EMIT 0xD0 \
EMIT 0x0F EMIT 0x6E EMIT 0x66 EMIT 0x04 \
EMIT 0x0F EMIT 0xF4 EMIT 0xE0 \
EMIT 0x0F EMIT 0x6E EMIT 0x76 EMIT 0x08 \
EMIT 0x0F EMIT 0xF4 EMIT 0xF0 \
EMIT 0x0F EMIT 0x6E EMIT 0x7E EMIT 0x0C \
EMIT 0x0F EMIT 0xF4 EMIT 0xF8 \
EMIT 0x0F EMIT 0xD4 EMIT 0xCA \
EMIT 0x0F EMIT 0x6E EMIT 0x5F EMIT 0x04 \
EMIT 0x0F EMIT 0xD4 EMIT 0xDC \
EMIT 0x0F EMIT 0x6E EMIT 0x6F EMIT 0x08 \
EMIT 0x0F EMIT 0xD4 EMIT 0xEE \
EMIT 0x0F EMIT 0x6E EMIT 0x67 EMIT 0x0C \
EMIT 0x0F EMIT 0xD4 EMIT 0xFC \
EMIT 0x0F EMIT 0x7E EMIT 0x0F \
EMIT 0x0F EMIT 0x6E EMIT 0x56 EMIT 0x10 \
EMIT 0x0F EMIT 0xF4 EMIT 0xD0 \
EMIT 0x0F EMIT 0x73 EMIT 0xD1 EMIT 0x20 \
EMIT 0x0F EMIT 0x6E EMIT 0x66 EMIT 0x14 \
EMIT 0x0F EMIT 0xF4 EMIT 0xE0 \
EMIT 0x0F EMIT 0xD4 EMIT 0xCB \
EMIT 0x0F EMIT 0x6E EMIT 0x76 EMIT 0x18 \
EMIT 0x0F EMIT 0xF4 EMIT 0xF0 \
EMIT 0x0F EMIT 0x7E EMIT 0x4F EMIT 0x04 \
EMIT 0x0F EMIT 0x73 EMIT 0xD1 EMIT 0x20 \
EMIT 0x0F EMIT 0x6E EMIT 0x5E EMIT 0x1C \
EMIT 0x0F EMIT 0xF4 EMIT 0xD8 \
EMIT 0x0F EMIT 0xD4 EMIT 0xCD \
EMIT 0x0F EMIT 0x6E EMIT 0x6F EMIT 0x10 \
EMIT 0x0F EMIT 0xD4 EMIT 0xD5 \
EMIT 0x0F EMIT 0x7E EMIT 0x4F EMIT 0x08 \
EMIT 0x0F EMIT 0x73 EMIT 0xD1 EMIT 0x20 \
EMIT 0x0F EMIT 0xD4 EMIT 0xCF \
EMIT 0x0F EMIT 0x6E EMIT 0x6F EMIT 0x14 \
EMIT 0x0F EMIT 0xD4 EMIT 0xE5 \
EMIT 0x0F EMIT 0x7E EMIT 0x4F EMIT 0x0C \
EMIT 0x0F EMIT 0x73 EMIT 0xD1 EMIT 0x20 \
EMIT 0x0F EMIT 0xD4 EMIT 0xCA \
EMIT 0x0F EMIT 0x6E EMIT 0x6F EMIT 0x18 \
EMIT 0x0F EMIT 0xD4 EMIT 0xF5 \
EMIT 0x0F EMIT 0x7E EMIT 0x4F EMIT 0x10 \
EMIT 0x0F EMIT 0x73 EMIT 0xD1 EMIT 0x20 \
EMIT 0x0F EMIT 0xD4 EMIT 0xCC \
EMIT 0x0F EMIT 0x6E EMIT 0x6F EMIT 0x1C \
EMIT 0x0F EMIT 0xD4 EMIT 0xDD \
EMIT 0x0F EMIT 0x7E EMIT 0x4F EMIT 0x14 \
EMIT 0x0F EMIT 0x73 EMIT 0xD1 EMIT 0x20 \
EMIT 0x0F EMIT 0xD4 EMIT 0xCE \
EMIT 0x0F EMIT 0x7E EMIT 0x4F EMIT 0x18 \
EMIT 0x0F EMIT 0x73 EMIT 0xD1 EMIT 0x20 \
EMIT 0x0F EMIT 0xD4 EMIT 0xCB \
EMIT 0x0F EMIT 0x7E EMIT 0x4F EMIT 0x1C \
EMIT 0x83 EMIT 0xC7 EMIT 0x20 \
EMIT 0x83 EMIT 0xC6 EMIT 0x20 \
EMIT 0x0F EMIT 0x73 EMIT 0xD1 EMIT 0x20 \
EMIT 0x0F EMIT 0x7E EMIT 0xC9
#define MULADDC_STOP \
EMIT 0x0F EMIT 0x77 \
__asm mov c, ecx \
__asm mov d, edi \
__asm mov s, esi \
#else
#define MULADDC_STOP \
__asm mov c, ecx \
__asm mov d, edi \
__asm mov s, esi \
#endif /* SSE2 */
#endif /* MSVC */
#endif /* POLARSSL_HAVE_ASM */
#if !defined(MULADDC_CORE)
#if defined(POLARSSL_HAVE_LONGLONG)
#define MULADDC_INIT \
{ \
t_udbl r; \
t_uint r0, r1;
#define MULADDC_CORE \
r = *(s++) * (t_udbl) b; \
r0 = r; \
r1 = r >> biL; \
r0 += c; r1 += (r0 < c); \
r0 += *d; r1 += (r0 < *d); \
c = r1; *(d++) = r0;
#define MULADDC_STOP \
}
#else
#define MULADDC_INIT \
{ \
t_uint s0, s1, b0, b1; \
t_uint r0, r1, rx, ry; \
b0 = ( b << biH ) >> biH; \
b1 = ( b >> biH );
#define MULADDC_CORE \
s0 = ( *s << biH ) >> biH; \
s1 = ( *s >> biH ); s++; \
rx = s0 * b1; r0 = s0 * b0; \
ry = s1 * b0; r1 = s1 * b1; \
r1 += ( rx >> biH ); \
r1 += ( ry >> biH ); \
rx <<= biH; ry <<= biH; \
r0 += rx; r1 += (r0 < rx); \
r0 += ry; r1 += (r0 < ry); \
r0 += c; r1 += (r0 < c); \
r0 += *d; r1 += (r0 < *d); \
c = r1; *(d++) = r0;
#define MULADDC_STOP \
}
#endif /* C (generic) */
#endif /* C (longlong) */
#endif /* bn_mul.h */
|
