aboutsummaryrefslogtreecommitdiff
path: root/arch/arm/crypto/sha1-armv4-large.S
blob: 99207c45ec10f56891cd40d53b8a5fe524337f0f (plain)
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
#define __ARM_ARCH__ __LINUX_ARM_ARCH__
@ ====================================================================
@ Written by Andy Polyakov <appro@fy.chalmers.se> 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/.
@ ====================================================================

@ sha1_block procedure for ARMv4.
@
@ January 2007.

@ Size/performance trade-off
@ ====================================================================
@ impl		size in bytes	comp cycles[*]	measured performance
@ ====================================================================
@ thumb		304		3212		4420
@ armv4-small	392/+29%	1958/+64%	2250/+96%
@ armv4-compact	740/+89%	1552/+26%	1840/+22%
@ armv4-large	1420/+92%	1307/+19%	1370/+34%[***]
@ full unroll	~5100/+260%	~1260/+4%	~1300/+5%
@ ====================================================================
@ thumb		= same as 'small' but in Thumb instructions[**] and
@		  with recurring code in two private functions;
@ small		= detached Xload/update, loops are folded;
@ compact	= detached Xload/update, 5x unroll;
@ large		= interleaved Xload/update, 5x unroll;
@ full unroll	= interleaved Xload/update, full unroll, estimated[!];
@
@ [*]	Manually counted instructions in "grand" loop body. Measured
@	performance is affected by prologue and epilogue overhead,
@	i-cache availability, branch penalties, etc.
@ [**]	While each Thumb instruction is twice smaller, they are not as
@	diverse as ARM ones: e.g., there are only two arithmetic
@	instructions with 3 arguments, no [fixed] rotate, addressing
@	modes are limited. As result it takes more instructions to do
@	the same job in Thumb, therefore the code is never twice as
@	small and always slower.
@ [***]	which is also ~35% better than compiler generated code. Dual-
@	issue Cortex A8 core was measured to process input block in
@	~990 cycles.

@ August 2010.
@
@ Rescheduling for dual-issue pipeline resulted in 13% improvement on
@ Cortex A8 core and in absolute terms ~870 cycles per input block
@ [or 13.6 cycles per byte].

@ February 2011.
@
@ Profiler-assisted and platform-specific optimization resulted in 10%
@ improvement on Cortex A8 core and 12.2 cycles per byte.

#include <linux/linkage.h>

.text

.align	2
ENTRY(sha1_block_data_order)
	stmdb	sp!,{r4-r12,lr}
	add	r2,r1,r2,lsl#6	@ r2 to point at the end of r1
	ldmia	r0,{r3,r4,r5,r6,r7}
.Lloop:
	ldr	r8,.LK_00_19
	mov	r14,sp
	sub	sp,sp,#15*4
	mov	r5,r5,ror#30
	mov	r6,r6,ror#30
	mov	r7,r7,ror#30		@ [6]
.L_00_15:
#if __ARM_ARCH__<7
	ldrb	r10,[r1,#2]
	ldrb	r9,[r1,#3]
	ldrb	r11,[r1,#1]
	add	r7,r8,r7,ror#2			@ E+=K_00_19
	ldrb	r12,[r1],#4
	orr	r9,r9,r10,lsl#8
	eor	r10,r5,r6			@ F_xx_xx
	orr	r9,r9,r11,lsl#16
	add	r7,r7,r3,ror#27			@ E+=ROR(A,27)
	orr	r9,r9,r12,lsl#24
#else
	ldr	r9,[r1],#4			@ handles unaligned
	add	r7,r8,r7,ror#2			@ E+=K_00_19
	eor	r10,r5,r6			@ F_xx_xx
	add	r7,r7,r3,ror#27			@ E+=ROR(A,27)
#ifdef __ARMEL__
	rev	r9,r9				@ byte swap
#endif
#endif
	and	r10,r4,r10,ror#2
	add	r7,r7,r9			@ E+=X[i]
	eor	r10,r10,r6,ror#2		@ F_00_19(B,C,D)
	str	r9,[r14,#-4]!
	add	r7,r7,r10			@ E+=F_00_19(B,C,D)
#if __ARM_ARCH__<7
	ldrb	r10,[r1,#2]
	ldrb	r9,[r1,#3]
	ldrb	r11,[r1,#1]
	add	r6,r8,r6,ror#2			@ E+=K_00_19
	ldrb	r12,[r1],#4
	orr	r9,r9,r10,lsl#8
	eor	r10,r4,r5			@ F_xx_xx
	orr	r9,r9,r11,lsl#16
	add	r6,r6,r7,ror#27			@ E+=ROR(A,27)
	orr	r9,r9,r12,lsl#24
#else
	ldr	r9,[r1],#4			@ handles unaligned
	add	r6,r8,r6,ror#2			@ E+=K_00_19
	eor	r10,r4,r5			@ F_xx_xx
	add	r6,r6,r7,ror#27			@ E+=ROR(A,27)
#ifdef __ARMEL__
	rev	r9,r9				@ byte swap
#endif
#endif
	and	r10,r3,r10,ror#2
	add	r6,r6,r9			@ E+=X[i]
	eor	r10,r10,r5,ror#2		@ F_00_19(B,C,D)
	str	r9,[r14,#-4]!
	add	r6,r6,r10			@ E+=F_00_19(B,C,D)
#if __ARM_ARCH__<7
	ldrb	r10,[r1,#2]
	ldrb	r9,[r1,#3]
	ldrb	r11,[r1,#1]
	add	r5,r8,r5,ror#2			@ E+=K_00_19
	ldrb	r12,[r1],#4
	orr	r9,r9,r10,lsl#8
	eor	r10,r3,r4			@ F_xx_xx
	orr	r9,r9,r11,lsl#16
	add	r5,r5,r6,ror#27			@ E+=ROR(A,27)
	orr	r9,r9,r12,lsl#24
#else
	ldr	r9,[r1],#4			@ handles unaligned
	add	r5,r8,r5,ror#2			@ E+=K_00_19
	eor	r10,r3,r4			@ F_xx_xx
	add	r5,r5,r6,ror#27			@ E+=ROR(A,27)
#ifdef __ARMEL__
	rev	r9,r9				@ byte swap
#endif
#endif
	and	r10,r7,r10,ror#2
	add	r5,r5,r9			@ E+=X[i]
	eor	r10,r10,r4,ror#2		@ F_00_19(B,C,D)
	str	r9,[r14,#-4]!
	add	r5,r5,r10			@ E+=F_00_19(B,C,D)
#if __ARM_ARCH__<7
	ldrb	r10,[r1,#2]
	ldrb	r9,[r1,#3]
	ldrb	r11,[r1,#1]
	add	r4,r8,r4,ror#2			@ E+=K_00_19
	ldrb	r12,[r1],#4
	orr	r9,r9,r10,lsl#8
	eor	r10,r7,r3			@ F_xx_xx
	orr	r9,r9,r11,lsl#16
	add	r4,r4,r5,ror#27			@ E+=ROR(A,27)
	orr	r9,r9,r12,lsl#24
#else
	ldr	r9,[r1],#4			@ handles unaligned
	add	r4,r8,r4,ror#2			@ E+=K_00_19
	eor	r10,r7,r3			@ F_xx_xx
	add	r4,r4,r5,ror#27			@ E+=ROR(A,27)
#ifdef __ARMEL__
	rev	r9,r9				@ byte swap
#endif
#endif
	and	r10,r6,r10,ror#2
	add	r4,r4,r9			@ E+=X[i]
	eor	r10,r10,r3,ror#2		@ F_00_19(B,C,D)
	str	r9,[r14,#-4]!
	add	r4,r4,r10			@ E+=F_00_19(B,C,D)
#if __ARM_ARCH__<7
	ldrb	r10,[r1,#2]
	ldrb	r9,[r1,#3]
	ldrb	r11,[r1,#1]
	add	r3,r8,r3,ror#2			@ E+=K_00_19
	ldrb	r12,[r1],#4
	orr	r9,r9,r10,lsl#8
	eor	r10,r6,r7			@ F_xx_xx
	orr	r9,r9,r11,lsl#16
	add	r3,r3,r4,ror#27			@ E+=ROR(A,27)
	orr	r9,r9,r12,lsl#24
#else
	ldr	r9,[r1],#4			@ handles unaligned
	add	r3,r8,r3,ror#2			@ E+=K_00_19
	eor	r10,r6,r7			@ F_xx_xx
	add	r3,r3,r4,ror#27			@ E+=ROR(A,27)
#ifdef __ARMEL__
	rev	r9,r9				@ byte swap
#endif
#endif
	and	r10,r5,r10,ror#2
	add	r3,r3,r9			@ E+=X[i]
	eor	r10,r10,r7,ror#2		@ F_00_19(B,C,D)
	str	r9,[r14,#-4]!
	add	r3,r3,r10			@ E+=F_00_19(B,C,D)
	cmp	r14,sp
	bne	.L_00_15		@ [((11+4)*5+2)*3]
	sub	sp,sp,#25*4
#if __ARM_ARCH__<7
	ldrb	r10,[r1,#2]
	ldrb	r9,[r1,#3]
	ldrb	r11,[r1,#1]
	add	r7,r8,r7,ror#2			@ E+=K_00_19
	ldrb	r12,[r1],#4
	orr	r9,r9,r10,lsl#8
	eor	r10,r5,r6			@ F_xx_xx
	orr	r9,r9,r11,lsl#16
	add	r7,r7,r3,ror#27			@ E+=ROR(A,27)
	orr	r9,r9,r12,lsl#24
#else
	ldr	r9,[r1],#4			@ handles unaligned
	add	r7,r8,r7,ror#2			@ E+=K_00_19
	eor	r10,r5,r6			@ F_xx_xx
	add	r7,r7,r3,ror#27			@ E+=ROR(A,27)
#ifdef __ARMEL__
	rev	r9,r9				@ byte swap
#endif
#endif
	and	r10,r4,r10,ror#2
	add	r7,r7,r9			@ E+=X[i]
	eor	r10,r10,r6,ror#2		@ F_00_19(B,C,D)
	str	r9,[r14,#-4]!
	add	r7,r7,r10			@ E+=F_00_19(B,C,D)
	ldr	r9,[r14,#15*4]
	ldr	r10,[r14,#13*4]
	ldr	r11,[r14,#7*4]
	add	r6,r8,r6,ror#2			@ E+=K_xx_xx
	ldr	r12,[r14,#2*4]
	eor	r9,r9,r10
	eor	r11,r11,r12			@ 1 cycle stall
	eor	r10,r4,r5			@ F_xx_xx
	mov	r9,r9,ror#31
	add	r6,r6,r7,ror#27			@ E+=ROR(A,27)
	eor	r9,r9,r11,ror#31
	str	r9,[r14,#-4]!
	and r10,r3,r10,ror#2					@ F_xx_xx
						@ F_xx_xx
	add	r6,r6,r9			@ E+=X[i]
	eor	r10,r10,r5,ror#2		@ F_00_19(B,C,D)
	add	r6,r6,r10			@ E+=F_00_19(B,C,D)
	ldr	r9,[r14,#15*4]
	ldr	r10,[r14,#13*4]
	ldr	r11,[r14,#7*4]
	add	r5,r8,r5,ror#2			@ E+=K_xx_xx
	ldr	r12,[r14,#2*4]
	eor	r9,r9,r10
	eor	r11,r11,r12			@ 1 cycle stall
	eor	r10,r3,r4			@ F_xx_xx
	mov	r9,r9,ror#31
	add	r5,r5,r6,ror#27			@ E+=ROR(A,27)
	eor	r9,r9,r11,ror#31
	str	r9,[r14,#-4]!
	and r10,r7,r10,ror#2					@ F_xx_xx
						@ F_xx_xx
	add	r5,r5,r9			@ E+=X[i]
	eor	r10,r10,r4,ror#2		@ F_00_19(B,C,D)
	add	r5,r5,r10			@ E+=F_00_19(B,C,D)
	ldr	r9,[r14,#15*4]
	ldr	r10,[r14,#13*4]
	ldr	r11,[r14,#7*4]
	add	r4,r8,r4,ror#2			@ E+=K_xx_xx
	ldr	r12,[r14,#2*4]
	eor	r9,r9,r10
	eor	r11,r11,r12			@ 1 cycle stall
	eor	r10,r7,r3			@ F_xx_xx
	mov	r9,r9,ror#31
	add	r4,r4,r5,ror#27			@ E+=ROR(A,27)
	eor	r9,r9,r11,ror#31
	str	r9,[r14,#-4]!
	and r10,r6,r10,ror#2					@ F_xx_xx
						@ F_xx_xx
	add	r4,r4,r9			@ E+=X[i]
	eor	r10,r10,r3,ror#2		@ F_00_19(B,C,D)
	add	r4,r4,r10			@ E+=F_00_19(B,C,D)
	ldr	r9,[r14,#15*4]
	ldr	r10,[r14,#13*4]
	ldr	r11,[r14,#7*4]
	add	r3,r8,r3,ror#2			@ E+=K_xx_xx
	ldr	r12,[r14,#2*4]
	eor	r9,r9,r10
	eor	r11,r11,r12			@ 1 cycle stall
	eor	r10,r6,r7			@ F_xx_xx
	mov	r9,r9,ror#31
	add	r3,r3,r4,ror#27			@ E+=ROR(A,27)
	eor	r9,r9,r11,ror#31
	str	r9,[r14,#-4]!
	and r10,r5,r10,ror#2					@ F_xx_xx
						@ F_xx_xx
	add	r3,r3,r9			@ E+=X[i]
	eor	r10,r10,r7,ror#2		@ F_00_19(B,C,D)
	add	r3,r3,r10			@ E+=F_00_19(B,C,D)

	ldr	r8,.LK_20_39		@ [+15+16*4]
	cmn	sp,#0			@ [+3], clear carry to denote 20_39
.L_20_39_or_60_79:
	ldr	r9,[r14,#15*4]
	ldr	r10,[r14,#13*4]
	ldr	r11,[r14,#7*4]
	add	r7,r8,r7,ror#2			@ E+=K_xx_xx
	ldr	r12,[r14,#2*4]
	eor	r9,r9,r10
	eor	r11,r11,r12			@ 1 cycle stall
	eor	r10,r5,r6			@ F_xx_xx
	mov	r9,r9,ror#31
	add	r7,r7,r3,ror#27			@ E+=ROR(A,27)
	eor	r9,r9,r11,ror#31
	str	r9,[r14,#-4]!
	eor r10,r4,r10,ror#2					@ F_xx_xx
						@ F_xx_xx
	add	r7,r7,r9			@ E+=X[i]
	add	r7,r7,r10			@ E+=F_20_39(B,C,D)
	ldr	r9,[r14,#15*4]
	ldr	r10,[r14,#13*4]
	ldr	r11,[r14,#7*4]
	add	r6,r8,r6,ror#2			@ E+=K_xx_xx
	ldr	r12,[r14,#2*4]
	eor	r9,r9,r10
	eor	r11,r11,r12			@ 1 cycle stall
	eor	r10,r4,r5			@ F_xx_xx
	mov	r9,r9,ror#31
	add	r6,r6,r7,ror#27			@ E+=ROR(A,27)
	eor	r9,r9,r11,ror#31
	str	r9,[r14,#-4]!
	eor r10,r3,r10,ror#2					@ F_xx_xx
						@ F_xx_xx
	add	r6,r6,r9			@ E+=X[i]
	add	r6,r6,r10			@ E+=F_20_39(B,C,D)
	ldr	r9,[r14,#15*4]
	ldr	r10,[r14,#13*4]
	ldr	r11,[r14,#7*4]
	add	r5,r8,r5,ror#2			@ E+=K_xx_xx
	ldr	r12,[r14,#2*4]
	eor	r9,r9,r10
	eor	r11,r11,r12			@ 1 cycle stall
	eor	r10,r3,r4			@ F_xx_xx
	mov	r9,r9,ror#31
	add	r5,r5,r6,ror#27			@ E+=ROR(A,27)
	eor	r9,r9,r11,ror#31
	str	r9,[r14,#-4]!
	eor r10,r7,r10,ror#2					@ F_xx_xx
						@ F_xx_xx
	add	r5,r5,r9			@ E+=X[i]
	add	r5,r5,r10			@ E+=F_20_39(B,C,D)
	ldr	r9,[r14,#15*4]
	ldr	r10,[r14,#13*4]
	ldr	r11,[r14,#7*4]
	add	r4,r8,r4,ror#2			@ E+=K_xx_xx
	ldr	r12,[r14,#2*4]
	eor	r9,r9,r10
	eor	r11,r11,r12			@ 1 cycle stall
	eor	r10,r7,r3			@ F_xx_xx
	mov	r9,r9,ror#31
	add	r4,r4,r5,ror#27			@ E+=ROR(A,27)
	eor	r9,r9,r11,ror#31
	str	r9,[r14,#-4]!
	eor r10,r6,r10,ror#2					@ F_xx_xx
						@ F_xx_xx
	add	r4,r4,r9			@ E+=X[i]
	add	r4,r4,r10			@ E+=F_20_39(B,C,D)
	ldr	r9,[r14,#15*4]
	ldr	r10,[r14,#13*4]
	ldr	r11,[r14,#7*4]
	add	r3,r8,r3,ror#2			@ E+=K_xx_xx
	ldr	r12,[r14,#2*4]
	eor	r9,r9,r10
	eor	r11,r11,r12			@ 1 cycle stall
	eor	r10,r6,r7			@ F_xx_xx
	mov	r9,r9,ror#31
	add	r3,r3,r4,ror#27			@ E+=ROR(A,27)
	eor	r9,r9,r11,ror#31
	str	r9,[r14,#-4]!
	eor r10,r5,r10,ror#2					@ F_xx_xx
						@ F_xx_xx
	add	r3,r3,r9			@ E+=X[i]
	add	r3,r3,r10			@ E+=F_20_39(B,C,D)
 ARM(	teq	r14,sp		)	@ preserve carry
 THUMB(	mov	r11,sp		)
 THUMB(	teq	r14,r11		)	@ preserve carry
	bne	.L_20_39_or_60_79	@ [+((12+3)*5+2)*4]
	bcs	.L_done			@ [+((12+3)*5+2)*4], spare 300 bytes

	ldr	r8,.LK_40_59
	sub	sp,sp,#20*4		@ [+2]
.L_40_59:
	ldr	r9,[r14,#15*4]
	ldr	r10,[r14,#13*4]
	ldr	r11,[r14,#7*4]
	add	r7,r8,r7,ror#2			@ E+=K_xx_xx
	ldr	r12,[r14,#2*4]
	eor	r9,r9,r10
	eor	r11,r11,r12			@ 1 cycle stall
	eor	r10,r5,r6			@ F_xx_xx
	mov	r9,r9,ror#31
	add	r7,r7,r3,ror#27			@ E+=ROR(A,27)
	eor	r9,r9,r11,ror#31
	str	r9,[r14,#-4]!
	and r10,r4,r10,ror#2					@ F_xx_xx
	and r11,r5,r6					@ F_xx_xx
	add	r7,r7,r9			@ E+=X[i]
	add	r7,r7,r10			@ E+=F_40_59(B,C,D)
	add	r7,r7,r11,ror#2
	ldr	r9,[r14,#15*4]
	ldr	r10,[r14,#13*4]
	ldr	r11,[r14,#7*4]
	add	r6,r8,r6,ror#2			@ E+=K_xx_xx
	ldr	r12,[r14,#2*4]
	eor	r9,r9,r10
	eor	r11,r11,r12			@ 1 cycle stall
	eor	r10,r4,r5			@ F_xx_xx
	mov	r9,r9,ror#31
	add	r6,r6,r7,ror#27			@ E+=ROR(A,27)
	eor	r9,r9,r11,ror#31
	str	r9,[r14,#-4]!
	and r10,r3,r10,ror#2					@ F_xx_xx
	and r11,r4,r5					@ F_xx_xx
	add	r6,r6,r9			@ E+=X[i]
	add	r6,r6,r10			@ E+=F_40_59(B,C,D)
	add	r6,r6,r11,ror#2
	ldr	r9,[r14,#15*4]
	ldr	r10,[r14,#13*4]
	ldr	r11,[r14,#7*4]
	add	r5,r8,r5,ror#2			@ E+=K_xx_xx
	ldr	r12,[r14,#2*4]
	eor	r9,r9,r10
	eor	r11,r11,r12			@ 1 cycle stall
	eor	r10,r3,r4			@ F_xx_xx
	mov	r9,r9,ror#31
	add	r5,r5,r6,ror#27			@ E+=ROR(A,27)
	eor	r9,r9,r11,ror#31
	str	r9,[r14,#-4]!
	and r10,r7,r10,ror#2					@ F_xx_xx
	and r11,r3,r4					@ F_xx_xx
	add	r5,r5,r9			@ E+=X[i]
	add	r5,r5,r10			@ E+=F_40_59(B,C,D)
	add	r5,r5,r11,ror#2
	ldr	r9,[r14,#15*4]
	ldr	r10,[r14,#13*4]
	ldr	r11,[r14,#7*4]
	add	r4,r8,r4,ror#2			@ E+=K_xx_xx
	ldr	r12,[r14,#2*4]
	eor	r9,r9,r10
	eor	r11,r11,r12			@ 1 cycle stall
	eor	r10,r7,r3			@ F_xx_xx
	mov	r9,r9,ror#31
	add	r4,r4,r5,ror#27			@ E+=ROR(A,27)
	eor	r9,r9,r11,ror#31
	str	r9,[r14,#-4]!
	and r10,r6,r10,ror#2					@ F_xx_xx
	and r11,r7,r3					@ F_xx_xx
	add	r4,r4,r9			@ E+=X[i]
	add	r4,r4,r10			@ E+=F_40_59(B,C,D)
	add	r4,r4,r11,ror#2
	ldr	r9,[r14,#15*4]
	ldr	r10,[r14,#13*4]
	ldr	r11,[r14,#7*4]
	add	r3,r8,r3,ror#2			@ E+=K_xx_xx
	ldr	r12,[r14,#2*4]
	eor	r9,r9,r10
	eor	r11,r11,r12			@ 1 cycle stall
	eor	r10,r6,r7			@ F_xx_xx
	mov	r9,r9,ror#31
	add	r3,r3,r4,ror#27			@ E+=ROR(A,27)
	eor	r9,r9,r11,ror#31
	str	r9,[r14,#-4]!
	and r10,r5,r10,ror#2					@ F_xx_xx
	and r11,r6,r7					@ F_xx_xx
	add	r3,r3,r9			@ E+=X[i]
	add	r3,r3,r10			@ E+=F_40_59(B,C,D)
	add	r3,r3,r11,ror#2
	cmp	r14,sp
	bne	.L_40_59		@ [+((12+5)*5+2)*4]

	ldr	r8,.LK_60_79
	sub	sp,sp,#20*4
	cmp	sp,#0			@ set carry to denote 60_79
	b	.L_20_39_or_60_79	@ [+4], spare 300 bytes
.L_done:
	add	sp,sp,#80*4		@ "deallocate" stack frame
	ldmia	r0,{r8,r9,r10,r11,r12}
	add	r3,r8,r3
	add	r4,r9,r4
	add	r5,r10,r5,ror#2
	add	r6,r11,r6,ror#2
	add	r7,r12,r7,ror#2
	stmia	r0,{r3,r4,r5,r6,r7}
	teq	r1,r2
	bne	.Lloop			@ [+18], total 1307

	ldmia	sp!,{r4-r12,pc}
.align	2
.LK_00_19:	.word	0x5a827999
.LK_20_39:	.word	0x6ed9eba1
.LK_40_59:	.word	0x8f1bbcdc
.LK_60_79:	.word	0xca62c1d6
ENDPROC(sha1_block_data_order)
.asciz	"SHA1 block transform for ARMv4, CRYPTOGAMS by <appro@openssl.org>"
.align	2