summaryrefslogtreecommitdiffstats
path: root/comm/third_party/libgcrypt/mpi/pentium4/mmx/mpih-rshift.S
blob: e3374e3ba3c273a49d4c4d01946c4900505c864a (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
/* Intel Pentium-4 mpn_rshift -- right shift.
 *
 * Copyright 2001, 2002 Free Software Foundation, Inc.
 *
 * This file is part of Libgcrypt.
 *
 * Libgcrypt is free software; you can redistribute it and/or modify
 * it under the terms of the GNU Lesser General Public License as
 * published by the Free Software Foundation; either version 2.1 of
 * the License, or (at your option) any later version.
 *
 * Libgcrypt 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 Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
 *
 * Note: This code is heavily based on the GNU MP Library.
 *	 Actually it's the same code with only minor changes in the
 *	 way the data is stored; this is to support the abstraction
 *	 of an optional secure memory allocation which may be used
 *	 to avoid revealing of sensitive data due to paging etc.
 */


#include "sysdep.h"
#include "asm-syntax.h"


/*******************
 * mpi_limb_t
 * _gcry_mpih_rshift( mpi_ptr_t wp,	(sp + 4)
 *		   mpi_ptr_t up,	(sp + 8)
 *		   mpi_size_t usize,	(sp + 12)
 *		   unsigned cnt)	(sp + 16)
 *
 * P4 Willamette, Northwood: 1.75 cycles/limb
 * P4 Prescott:		     2.0 cycles/limb
 */

.text
	ALIGN (3)
	.globl C_SYMBOL_NAME(_gcry_mpih_rshift)
C_SYMBOL_NAME(_gcry_mpih_rshift:)
	pushl	%ebx
	pushl	%edi


	movl	20(%esp), %eax
	movl	12(%esp), %edx

	movl	16(%esp), %ebx
	movl	24(%esp), %ecx

	cmp	$5, %eax
	jae	.Lunroll

	decl	%eax
	movl	(%ebx), %edi		

	jnz	.Lsimple

	shrdl	%cl, %edi, %eax	

	shrl	%cl, %edi

	movl	%edi, (%edx)		
	popl	%edi			

	popl	%ebx

	ret





	.align	8, 0x90
.Lsimple:
	
	
	
	
	
	
	


	movd	(%ebx), %mm5		
	leal	(%ebx,%eax,4), %ebx	

	movd	%ecx, %mm6		
	leal	-4(%edx,%eax,4), %edx	

	psllq	$32, %mm5
	negl	%eax







.Lsimple_top:
	
	
	
	
	
	
	
	

	movq	(%ebx,%eax,4), %mm0
	incl	%eax

	psrlq	%mm6, %mm0

	movd	%mm0, (%edx,%eax,4)
	jnz	.Lsimple_top


	movd	(%ebx), %mm0
	psrlq	%mm6, %mm5		

	psrlq	%mm6, %mm0
	popl	%edi

	movd	%mm5, %eax
	popl	%ebx

	movd	%mm0, 4(%edx)

	emms

	ret





	.align	8, 0x90
.Lunroll:
	
	
	
	
	
	
	


	movd	(%ebx), %mm5		
	movl	$4, %edi

	movd	%ecx, %mm6		
	testl	%edi, %ebx

	psllq	$32, %mm5
	jz	.Lstart_src_aligned


	
	
	
	
	
	
	
	
	
	
	
	
	

	movq	(%ebx), %mm0		

	psrlq	%mm6, %mm0
	addl	$4, %ebx

	decl	%eax

	movd	%mm0, (%edx)
	addl	$4, %edx
.Lstart_src_aligned:


	movq	(%ebx), %mm1
	testl	%edi, %edx

	psrlq	%mm6, %mm5		
	jz	.Lstart_dst_aligned

	
	
	
	
	
	
	
	
	
	
	
	
	
	
	

	movq	%mm1, %mm0
	addl	$32, %ecx		

	psrlq	%mm6, %mm0

	movd	%ecx, %mm6

	movd	%mm0, (%edx)
	addl	$4, %edx
.Lstart_dst_aligned:


	movq	8(%ebx), %mm3
	negl	%ecx

	movq	%mm3, %mm2		
	addl	$64, %ecx

	movd	%ecx, %mm7
	psrlq	%mm6, %mm1

	leal	-12(%ebx,%eax,4), %ebx
	leal	-20(%edx,%eax,4), %edx

	psllq	%mm7, %mm3
	subl	$7, %eax		

	por	%mm1, %mm3		
	negl	%eax			

	jns	.Lfinish


	
	
	
	
	
	
	
	
	
	
	
	

	.align	8, 0x90
.Lunroll_loop:
	
	
	
	
	
	
	
	
	
	
	
	
	
	
	

	movq	(%ebx,%eax,4), %mm0
	psrlq	%mm6, %mm2

	movq	%mm0, %mm1
	psllq	%mm7, %mm0

	movq	%mm3, -8(%edx,%eax,4)	
	por	%mm2, %mm0

	movq	8(%ebx,%eax,4), %mm3	
	psrlq	%mm6, %mm1		

	movq	%mm0, (%edx,%eax,4)
	movq	%mm3, %mm2		

	psllq	%mm7, %mm3		
	addl	$4, %eax

	por	%mm1, %mm3		
	js	.Lunroll_loop


.Lfinish:
	

	testb	$2, %al

	jnz	.Lfinish_no_two

	movq	(%ebx,%eax,4), %mm0
	psrlq	%mm6, %mm2

	movq	%mm0, %mm1
	psllq	%mm7, %mm0

	movq	%mm3, -8(%edx,%eax,4)	
	por	%mm2, %mm0

	movq	%mm1, %mm2
	movq	%mm0, %mm3

	addl	$2, %eax
.Lfinish_no_two:


	
	
	
	

	testb	$1, %al
	popl	%edi

	movd	%mm5, %eax	
	jnz	.Lfinish_zero


	
	
	
	
	
	
	
	
	
	
	
	
	
	


	
	
	
	
	
	
	
	
	
	
	
	
	
	


	
	
	


	movd	8(%ebx), %mm0
	psrlq	%mm6, %mm2

	movq	%mm0, %mm1
	psllq	%mm7, %mm0

	movq	%mm3, (%edx)
	por	%mm2, %mm0

	psrlq	%mm6, %mm1
	andl	$32, %ecx

	popl	%ebx
	jz	.Lfinish_one_unaligned

	
	movd	%mm1, 16(%edx)
.Lfinish_one_unaligned:

	movq	%mm0, 8(%edx)

	emms

	ret




.Lfinish_zero:

	
	
	
	
	
	
	
	
	
	
	
	
	
	


	
	
	
	
	
	
	
	
	
	
	
	
	
	


	
	
	


	movq	%mm3, 4(%edx)
	psrlq	%mm6, %mm2

	movd	%mm2, 12(%edx)
	andl	$32, %ecx

	popl	%ebx
	jz	.Lfinish_zero_unaligned

	movq	%mm2, 12(%edx)
.Lfinish_zero_unaligned:

	emms

	ret