aboutsummaryrefslogtreecommitdiff
path: root/vendor/gmp-6.3.0/mpn/ia64/mul_1.asm
blob: 21bf6d0e14f3e99a413ead7ba40c80278f28da13 (plain) (blame)
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
dnl  IA-64 mpn_mul_1, mpn_mul_1c -- Multiply a limb vector with a limb and
dnl  store the result in a second limb vector.

dnl  Contributed to the GNU project by Torbjorn Granlund.

dnl  Copyright 2000-2004, 2006, 2007 Free Software Foundation, Inc.

dnl  This file is part of the GNU MP Library.
dnl
dnl  The GNU MP Library is free software; you can redistribute it and/or modify
dnl  it under the terms of either:
dnl
dnl    * the GNU Lesser General Public License as published by the Free
dnl      Software Foundation; either version 3 of the License, or (at your
dnl      option) any later version.
dnl
dnl  or
dnl
dnl    * the GNU General Public License as published by the Free Software
dnl      Foundation; either version 2 of the License, or (at your option) any
dnl      later version.
dnl
dnl  or both in parallel, as here.
dnl
dnl  The GNU MP Library is distributed in the hope that it will be useful, but
dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
dnl  for more details.
dnl
dnl  You should have received copies of the GNU General Public License and the
dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
dnl  see https://www.gnu.org/licenses/.

include(`../config.m4')

C         cycles/limb
C Itanium:    4.0
C Itanium 2:  2.0

C TODO
C  * Further optimize feed-in and wind-down code, both for speed and code size.
C  * Handle low limb input and results specially, using a common stf8 in the
C    epilogue.
C  * Use 1 c/l carry propagation scheme in wind-down code.
C  * Use extra pointer register for `up' to speed up feed-in loads.
C  * Work out final differences with addmul_1.asm.

C INPUT PARAMETERS
define(`rp', `r32')
define(`up', `r33')
define(`n', `r34')
define(`vl', `r35')
define(`cy', `r36')	C for mpn_mul_1c

ASM_START()
PROLOGUE(mpn_mul_1)
	.prologue
	.save	ar.lc, r2
	.body

ifdef(`HAVE_ABI_32',
`	addp4		rp = 0, rp		C M I
	addp4		up = 0, up		C M I
	zxt4		n = n			C I
	;;
')
{.mfi
	adds		r15 = -1, n		C M I
	mov		f9 = f0			C F
	mov.i		r2 = ar.lc		C I0
}
{.mmi
	ldf8		f7 = [up], 8		C M
	nop.m		0			C M
	and		r14 = 3, n		C M I
	;;
}
.Lcommon:
{.mii
	setf.sig	f6 = vl			C M2 M3
	shr.u		r31 = r15, 2		C I0
	cmp.eq		p10, p0 = 0, r14	C M I
}
{.mii
	cmp.eq		p11, p0 = 2, r14	C M I
	cmp.eq		p12, p0 = 3, r14	C M I
	nop.i		0			C I
	;;
}
{.mii
	cmp.ne		p6, p7 = r0, r0		C M I
	mov.i		ar.lc = r31		C I0
	cmp.ne		p8, p9 = r0, r0		C M I
}
{.bbb
  (p10)	br.dptk		.Lb00			C B
  (p11)	br.dptk		.Lb10			C B
  (p12)	br.dptk		.Lb11			C B
	;;
}

.Lb01:	mov		r20 = 0
	br.cloop.dptk	.grt1			C B

	xma.l		f39 = f7, f6, f9	C F
	xma.hu		f43 = f7, f6, f9	C F
	;;
	getf.sig	r8 = f43		C M2
	stf8		[rp] = f39		C M2 M3
	mov.i		ar.lc = r2		C I0
	br.ret.sptk.many b0			C B

.grt1:
	ldf8		f32 = [up], 8
	;;
	ldf8		f33 = [up], 8
	;;
	ldf8		f34 = [up], 8
	xma.l		f39 = f7, f6, f9
	xma.hu		f43 = f7, f6, f9
	;;
	ldf8		f35 = [up], 8
	br.cloop.dptk	.grt5

	xma.l		f36 = f32, f6, f0
	xma.hu		f40 = f32, f6, f0
	;;
	stf8		[rp] = f39, 8
	xma.l		f37 = f33, f6, f0
	xma.hu		f41 = f33, f6, f0
	;;
	getf.sig	r21 = f43
	getf.sig	r18 = f36
	xma.l		f38 = f34, f6, f0
	xma.hu		f42 = f34, f6, f0
	;;
	getf.sig	r22 = f40
	getf.sig	r19 = f37
	xma.l		f39 = f35, f6, f0
	xma.hu		f43 = f35, f6, f0
	;;
	getf.sig	r23 = f41
	getf.sig	r16 = f38
	br		.Lcj5

.grt5:
	xma.l		f36 = f32, f6, f0
	xma.hu		f40 = f32, f6, f0
	;;
	getf.sig	r17 = f39
	ldf8		f32 = [up], 8
	xma.l		f37 = f33, f6, f0
	xma.hu		f41 = f33, f6, f0
	;;
	getf.sig	r21 = f43
	ldf8		f33 = [up], 8
	xma.l		f38 = f34, f6, f0
	;;
	getf.sig	r18 = f36
	xma.hu		f42 = f34, f6, f0
	;;
	getf.sig	r22 = f40
	ldf8		f34 = [up], 8
	xma.l		f39 = f35, f6, f0
	;;
	getf.sig	r19 = f37
	xma.hu		f43 = f35, f6, f0
	br		.LL01


.Lb10:	ldf8		f35 = [up], 8
	mov		r23 = 0
	br.cloop.dptk	.grt2

	xma.l		f38 = f7, f6, f9
	xma.hu		f42 = f7, f6, f9
	;;
	stf8		[rp] = f38, 8
	xma.l		f39 = f35, f6, f42
	xma.hu		f43 = f35, f6, f42
	;;
	getf.sig	r8 = f43
	stf8		[rp] = f39
	mov.i		ar.lc = r2
	br.ret.sptk.many b0


.grt2:
	ldf8		f32 = [up], 8
	;;
	ldf8		f33 = [up], 8
	xma.l		f38 = f7, f6, f9
	xma.hu		f42 = f7, f6, f9
	;;
	ldf8		f34 = [up], 8
	xma.l		f39 = f35, f6, f0
	xma.hu		f43 = f35, f6, f0
	;;
	ldf8		f35 = [up], 8
	br.cloop.dptk	.grt6

	stf8		[rp] = f38, 8
	xma.l		f36 = f32, f6, f0
	xma.hu		f40 = f32, f6, f0
	;;
	getf.sig	r20 = f42
	getf.sig	r17 = f39
	xma.l		f37 = f33, f6, f0
	xma.hu		f41 = f33, f6, f0
	;;
	getf.sig	r21 = f43
	getf.sig	r18 = f36
	xma.l		f38 = f34, f6, f0
	xma.hu		f42 = f34, f6, f0
	;;
	getf.sig	r22 = f40
	getf.sig	r19 = f37
	xma.l		f39 = f35, f6, f0
	xma.hu		f43 = f35, f6, f0
	br		.Lcj6

.grt6:
	getf.sig	r16 = f38
	xma.l		f36 = f32, f6, f0
	xma.hu		f40 = f32, f6, f0
	;;
	getf.sig	r20 = f42
	ldf8		f32 = [up], 8
	xma.l		f37 = f33, f6, f0
	;;
	getf.sig	r17 = f39
	xma.hu		f41 = f33, f6, f0
	;;
	getf.sig	r21 = f43
	ldf8		f33 = [up], 8
	xma.l		f38 = f34, f6, f0
	;;
	getf.sig	r18 = f36
	xma.hu		f42 = f34, f6, f0
	br		.LL10


.Lb11:	ldf8		f34 = [up], 8
	mov		r22 = 0
	;;
	ldf8		f35 = [up], 8
	br.cloop.dptk	.grt3
	;;

	xma.l		f37 = f7, f6, f9
	xma.hu		f41 = f7, f6, f9
	xma.l		f38 = f34, f6, f0
	xma.hu		f42 = f34, f6, f0
	xma.l		f39 = f35, f6, f0
	xma.hu		f43 = f35, f6, f0
	;;
	getf.sig	r23 = f41
	stf8		[rp] = f37, 8
	getf.sig	r16 = f38
	getf.sig	r20 = f42
	getf.sig	r17 = f39
	getf.sig	r8 = f43
	br		.Lcj3

.grt3:
	ldf8		f32 = [up], 8
	xma.l		f37 = f7, f6, f9
	xma.hu		f41 = f7, f6, f9
	;;
	ldf8		f33 = [up], 8
	xma.l		f38 = f34, f6, f0
	xma.hu		f42 = f34, f6, f0
	;;
	getf.sig	r19 = f37
	ldf8		f34 = [up], 8
	xma.l		f39 = f35, f6, f0
	xma.hu		f43 = f35, f6, f0
	;;
	getf.sig	r23 = f41
	ldf8		f35 = [up], 8
	br.cloop.dptk	.grt7

	getf.sig	r16 = f38
	xma.l		f36 = f32, f6, f0
	getf.sig	r20 = f42
	xma.hu		f40 = f32, f6, f0
	;;
	getf.sig	r17 = f39
	xma.l		f37 = f33, f6, f0
	getf.sig	r21 = f43
	xma.hu		f41 = f33, f6, f0
	;;
	getf.sig	r18 = f36
	st8		[rp] = r19, 8
	xma.l		f38 = f34, f6, f0
	xma.hu		f42 = f34, f6, f0
	br		.Lcj7

.grt7:
	getf.sig	r16 = f38
	xma.l		f36 = f32, f6, f0
	xma.hu		f40 = f32, f6, f0
	;;
	getf.sig	r20 = f42
	ldf8		f32 = [up], 8
	xma.l		f37 = f33, f6, f0
	;;
	getf.sig	r17 = f39
	xma.hu		f41 = f33, f6, f0
	br		.LL11


.Lb00:	ldf8		f33 = [up], 8
	mov		r21 = 0
	;;
	ldf8		f34 = [up], 8
	;;
	ldf8		f35 = [up], 8
	xma.l		f36 = f7, f6, f9
	xma.hu		f40 = f7, f6, f9
	br.cloop.dptk	.grt4

	xma.l		f37 = f33, f6, f0
	xma.hu		f41 = f33, f6, f0
	xma.l		f38 = f34, f6, f0
	xma.hu		f42 = f34, f6, f0
	;;
	getf.sig	r22 = f40
	stf8		[rp] = f36, 8
	xma.l		f39 = f35, f6, f0
	getf.sig	r19 = f37
	xma.hu		f43 = f35, f6, f0
	;;
	getf.sig	r23 = f41
	getf.sig	r16 = f38
	getf.sig	r20 = f42
	getf.sig	r17 = f39
	br		.Lcj4

.grt4:
	ldf8		f32 = [up], 8
	xma.l		f37 = f33, f6, f0
	xma.hu		f41 = f33, f6, f0
	;;
	getf.sig	r18 = f36
	ldf8		f33 = [up], 8
	xma.l		f38 = f34, f6, f0
	xma.hu		f42 = f34, f6, f0
	;;
	getf.sig	r22 = f40
	ldf8		f34 = [up], 8
	xma.l		f39 = f35, f6, f0
	;;
	getf.sig	r19 = f37
	getf.sig	r23 = f41
	xma.hu		f43 = f35, f6, f0
	ldf8		f35 = [up], 8
	br.cloop.dptk	.grt8

	getf.sig	r16 = f38
	xma.l		f36 = f32, f6, f0
	getf.sig	r20 = f42
	xma.hu		f40 = f32, f6, f0
	;;
	getf.sig	r17 = f39
	st8		[rp] = r18, 8
	xma.l		f37 = f33, f6, f0
	xma.hu		f41 = f33, f6, f0
	br		.Lcj8

.grt8:
	getf.sig	r16 = f38
	xma.l		f36 = f32, f6, f0
	xma.hu		f40 = f32, f6, f0
	br		.LL00


C *** MAIN LOOP START ***
	ALIGN(32)
.Loop:
	.pred.rel "mutex",p6,p7
	getf.sig	r16 = f38
	xma.l		f36 = f32, f6, f0
   (p6)	cmp.leu		p8, p9 = r24, r17
	st8		[rp] = r24, 8
	xma.hu		f40 = f32, f6, f0
   (p7)	cmp.ltu		p8, p9 = r24, r17
	;;
.LL00:
	.pred.rel "mutex",p8,p9
	getf.sig	r20 = f42
   (p8)	add		r24 = r18, r21, 1
	nop.b		0
	ldf8		f32 = [up], 8
   (p9)	add		r24 = r18, r21
	nop.b		0
	;;
	.pred.rel "mutex",p8,p9
	getf.sig	r17 = f39
	xma.l		f37 = f33, f6, f0
   (p8)	cmp.leu		p6, p7 = r24, r18
	st8		[rp] = r24, 8
	xma.hu		f41 = f33, f6, f0
   (p9)	cmp.ltu		p6, p7 = r24, r18
	;;
.LL11:
	.pred.rel "mutex",p6,p7
	getf.sig	r21 = f43
   (p6)	add		r24 = r19, r22, 1
	nop.b		0
	ldf8		f33 = [up], 8
   (p7)	add		r24 = r19, r22
	nop.b		0
	;;
	.pred.rel "mutex",p6,p7
	getf.sig	r18 = f36
	xma.l		f38 = f34, f6, f0
   (p6)	cmp.leu		p8, p9 = r24, r19
	st8		[rp] = r24, 8
	xma.hu		f42 = f34, f6, f0
   (p7)	cmp.ltu		p8, p9 = r24, r19
	;;
.LL10:
	.pred.rel "mutex",p8,p9
	getf.sig	r22 = f40
   (p8)	add		r24 = r16, r23, 1
	nop.b		0
	ldf8		f34 = [up], 8
   (p9)	add		r24 = r16, r23
	nop.b		0
	;;
	.pred.rel "mutex",p8,p9
	getf.sig	r19 = f37
	xma.l		f39 = f35, f6, f0
   (p8)	cmp.leu		p6, p7 = r24, r16
	st8		[rp] = r24, 8
	xma.hu		f43 = f35, f6, f0
   (p9)	cmp.ltu		p6, p7 = r24, r16
	;;
.LL01:
	.pred.rel "mutex",p6,p7
	getf.sig	r23 = f41
   (p6)	add		r24 = r17, r20, 1
	nop.b		0
	ldf8		f35 = [up], 8
   (p7)	add		r24 = r17, r20
	br.cloop.dptk	.Loop
C *** MAIN LOOP END ***
	;;

.Lcj9:
	.pred.rel "mutex",p6,p7
	getf.sig	r16 = f38
	xma.l		f36 = f32, f6, f0
   (p6)	cmp.leu		p8, p9 = r24, r17
	st8		[rp] = r24, 8
	xma.hu		f40 = f32, f6, f0
   (p7)	cmp.ltu		p8, p9 = r24, r17
	;;
	.pred.rel "mutex",p8,p9
	getf.sig	r20 = f42
   (p8)	add		r24 = r18, r21, 1
   (p9)	add		r24 = r18, r21
	;;
	.pred.rel "mutex",p8,p9
	getf.sig	r17 = f39
	xma.l		f37 = f33, f6, f0
   (p8)	cmp.leu		p6, p7 = r24, r18
	st8		[rp] = r24, 8
	xma.hu		f41 = f33, f6, f0
   (p9)	cmp.ltu		p6, p7 = r24, r18
	;;
.Lcj8:
	.pred.rel "mutex",p6,p7
	getf.sig	r21 = f43
   (p6)	add		r24 = r19, r22, 1
   (p7)	add		r24 = r19, r22
	;;
	.pred.rel "mutex",p6,p7
	getf.sig	r18 = f36
	xma.l		f38 = f34, f6, f0
   (p6)	cmp.leu		p8, p9 = r24, r19
	st8		[rp] = r24, 8
	xma.hu		f42 = f34, f6, f0
   (p7)	cmp.ltu		p8, p9 = r24, r19
	;;
.Lcj7:
	.pred.rel "mutex",p8,p9
	getf.sig	r22 = f40
   (p8)	add		r24 = r16, r23, 1
   (p9)	add		r24 = r16, r23
	;;
	.pred.rel "mutex",p8,p9
	getf.sig	r19 = f37
	xma.l		f39 = f35, f6, f0
   (p8)	cmp.leu		p6, p7 = r24, r16
	st8		[rp] = r24, 8
	xma.hu		f43 = f35, f6, f0
   (p9)	cmp.ltu		p6, p7 = r24, r16
	;;
.Lcj6:
	.pred.rel "mutex",p6,p7
	getf.sig	r23 = f41
   (p6)	add		r24 = r17, r20, 1
   (p7)	add		r24 = r17, r20
	;;
	.pred.rel "mutex",p6,p7
   (p6)	cmp.leu		p8, p9 = r24, r17
   (p7)	cmp.ltu		p8, p9 = r24, r17
	getf.sig	r16 = f38
	st8		[rp] = r24, 8
	;;
.Lcj5:
	.pred.rel "mutex",p8,p9
	getf.sig	r20 = f42
   (p8)	add		r24 = r18, r21, 1
   (p9)	add		r24 = r18, r21
	;;
	.pred.rel "mutex",p8,p9
   (p8)	cmp.leu		p6, p7 = r24, r18
   (p9)	cmp.ltu		p6, p7 = r24, r18
	getf.sig	r17 = f39
	st8		[rp] = r24, 8
	;;
.Lcj4:
	.pred.rel "mutex",p6,p7
	getf.sig	r8 = f43
   (p6)	add		r24 = r19, r22, 1
   (p7)	add		r24 = r19, r22
	;;
	.pred.rel "mutex",p6,p7
	st8		[rp] = r24, 8
   (p6)	cmp.leu		p8, p9 = r24, r19
   (p7)	cmp.ltu		p8, p9 = r24, r19
	;;
.Lcj3:
	.pred.rel "mutex",p8,p9
   (p8)	add		r24 = r16, r23, 1
   (p9)	add		r24 = r16, r23
	;;
	.pred.rel "mutex",p8,p9
	st8		[rp] = r24, 8
   (p8)	cmp.leu		p6, p7 = r24, r16
   (p9)	cmp.ltu		p6, p7 = r24, r16
	;;
.Lcj2:
	.pred.rel "mutex",p6,p7
   (p6)	add		r24 = r17, r20, 1
   (p7)	add		r24 = r17, r20
	;;
	.pred.rel "mutex",p6,p7
	st8		[rp] = r24, 8
   (p6)	cmp.leu		p8, p9 = r24, r17
   (p7)	cmp.ltu		p8, p9 = r24, r17
	;;
   (p8)	add		r8 = 1, r8
	mov.i		ar.lc = r2
	br.ret.sptk.many b0
EPILOGUE()

PROLOGUE(mpn_mul_1c)
	.prologue
	.save	ar.lc, r2
	.body

ifdef(`HAVE_ABI_32',
`	addp4		rp = 0, rp		C M I
	addp4		up = 0, up		C M I
	zxt4		n = n			C I
	;;
')
{.mmi
	adds		r15 = -1, n		C M I
	setf.sig	f9 = cy			C M2 M3
	mov.i		r2 = ar.lc		C I0
}
{.mmb
	ldf8		f7 = [up], 8		C M
	and		r14 = 3, n		C M I
	br.sptk		.Lcommon
	;;
}
EPILOGUE()
ASM_END()