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
|
;********************************************************************
;* *
;* THIS FILE IS PART OF THE OggTheora SOFTWARE CODEC SOURCE CODE. *
;* USE, DISTRIBUTION AND REPRODUCTION OF THIS LIBRARY SOURCE IS *
;* GOVERNED BY A BSD-STYLE SOURCE LICENSE INCLUDED WITH THIS SOURCE *
;* IN 'COPYING'. PLEASE READ THESE TERMS BEFORE DISTRIBUTING. *
;* *
;* THE Theora SOURCE CODE IS COPYRIGHT (C) 2002-2010 *
;* by the Xiph.Org Foundation and contributors http://www.xiph.org/ *
;* *
;********************************************************************
; Original implementation:
; Copyright (C) 2009 Robin Watts for Pinknoise Productions Ltd
; last mod: $Id$
;********************************************************************
AREA |.text|, CODE, READONLY
GET armopts.s
; Vanilla ARM v4 versions
EXPORT oc_frag_copy_list_arm
EXPORT oc_frag_recon_intra_arm
EXPORT oc_frag_recon_inter_arm
EXPORT oc_frag_recon_inter2_arm
oc_frag_copy_list_arm PROC
; r0 = _dst_frame
; r1 = _src_frame
; r2 = _ystride
; r3 = _fragis
; <> = _nfragis
; <> = _frag_buf_offs
LDR r12,[r13] ; r12 = _nfragis
STMFD r13!,{r4-r6,r11,r14}
SUBS r12, r12, #1
LDR r4,[r3],#4 ; r4 = _fragis[fragii]
LDRGE r14,[r13,#4*6] ; r14 = _frag_buf_offs
BLT ofcl_arm_end
SUB r2, r2, #4
ofcl_arm_lp
LDR r11,[r14,r4,LSL #2] ; r11 = _frag_buf_offs[_fragis[fragii]]
SUBS r12, r12, #1
; Stall (on XScale)
ADD r4, r1, r11 ; r4 = _src_frame+frag_buf_off
LDR r6, [r4], #4
ADD r11,r0, r11 ; r11 = _dst_frame+frag_buf_off
LDR r5, [r4], r2
STR r6, [r11],#4
LDR r6, [r4], #4
STR r5, [r11],r2
LDR r5, [r4], r2
STR r6, [r11],#4
LDR r6, [r4], #4
STR r5, [r11],r2
LDR r5, [r4], r2
STR r6, [r11],#4
LDR r6, [r4], #4
STR r5, [r11],r2
LDR r5, [r4], r2
STR r6, [r11],#4
LDR r6, [r4], #4
STR r5, [r11],r2
LDR r5, [r4], r2
STR r6, [r11],#4
LDR r6, [r4], #4
STR r5, [r11],r2
LDR r5, [r4], r2
STR r6, [r11],#4
LDR r6, [r4], #4
STR r5, [r11],r2
LDR r5, [r4], r2
STR r6, [r11],#4
LDR r6, [r4], #4
STR r5, [r11],r2
LDR r5, [r4]
LDRGE r4,[r3],#4 ; r4 = _fragis[fragii]
STR r6, [r11],#4
STR r5, [r11]
BGE ofcl_arm_lp
ofcl_arm_end
LDMFD r13!,{r4-r6,r11,PC}
oc_frag_recon_intra_arm
; r0 = unsigned char *_dst
; r1 = int _ystride
; r2 = const ogg_int16_t _residue[64]
STMFD r13!,{r4,r5,r14}
MOV r14,#8
MOV r5, #255
SUB r1, r1, #7
ofrintra_lp_arm
LDRSH r3, [r2], #2
LDRSH r4, [r2], #2
LDRSH r12,[r2], #2
ADDS r3, r3, #128
CMPGT r5, r3
EORLT r3, r5, r3, ASR #32
STRB r3, [r0], #1
ADDS r4, r4, #128
CMPGT r5, r4
EORLT r4, r5, r4, ASR #32
LDRSH r3, [r2], #2
STRB r4, [r0], #1
ADDS r12,r12,#128
CMPGT r5, r12
EORLT r12,r5, r12,ASR #32
LDRSH r4, [r2], #2
STRB r12,[r0], #1
ADDS r3, r3, #128
CMPGT r5, r3
EORLT r3, r5, r3, ASR #32
LDRSH r12,[r2], #2
STRB r3, [r0], #1
ADDS r4, r4, #128
CMPGT r5, r4
EORLT r4, r5, r4, ASR #32
LDRSH r3, [r2], #2
STRB r4, [r0], #1
ADDS r12,r12,#128
CMPGT r5, r12
EORLT r12,r5, r12,ASR #32
LDRSH r4, [r2], #2
STRB r12,[r0], #1
ADDS r3, r3, #128
CMPGT r5, r3
EORLT r3, r5, r3, ASR #32
STRB r3, [r0], #1
ADDS r4, r4, #128
CMPGT r5, r4
EORLT r4, r5, r4, ASR #32
STRB r4, [r0], r1
SUBS r14,r14,#1
BGT ofrintra_lp_arm
LDMFD r13!,{r4,r5,PC}
ENDP
oc_frag_recon_inter_arm PROC
; r0 = unsigned char *dst
; r1 = const unsigned char *src
; r2 = int ystride
; r3 = const ogg_int16_t residue[64]
STMFD r13!,{r5,r9-r11,r14}
MOV r9, #8
MOV r5, #255
SUB r2, r2, #7
ofrinter_lp_arm
LDRSH r12,[r3], #2
LDRB r14,[r1], #1
LDRSH r11,[r3], #2
LDRB r10,[r1], #1
ADDS r12,r12,r14
CMPGT r5, r12
EORLT r12,r5, r12,ASR #32
STRB r12,[r0], #1
ADDS r11,r11,r10
CMPGT r5, r11
LDRSH r12,[r3], #2
LDRB r14,[r1], #1
EORLT r11,r5, r11,ASR #32
STRB r11,[r0], #1
ADDS r12,r12,r14
CMPGT r5, r12
LDRSH r11,[r3], #2
LDRB r10,[r1], #1
EORLT r12,r5, r12,ASR #32
STRB r12,[r0], #1
ADDS r11,r11,r10
CMPGT r5, r11
LDRSH r12,[r3], #2
LDRB r14,[r1], #1
EORLT r11,r5, r11,ASR #32
STRB r11,[r0], #1
ADDS r12,r12,r14
CMPGT r5, r12
LDRSH r11,[r3], #2
LDRB r10,[r1], #1
EORLT r12,r5, r12,ASR #32
STRB r12,[r0], #1
ADDS r11,r11,r10
CMPGT r5, r11
LDRSH r12,[r3], #2
LDRB r14,[r1], #1
EORLT r11,r5, r11,ASR #32
STRB r11,[r0], #1
ADDS r12,r12,r14
CMPGT r5, r12
LDRSH r11,[r3], #2
LDRB r10,[r1], r2
EORLT r12,r5, r12,ASR #32
STRB r12,[r0], #1
ADDS r11,r11,r10
CMPGT r5, r11
EORLT r11,r5, r11,ASR #32
STRB r11,[r0], r2
SUBS r9, r9, #1
BGT ofrinter_lp_arm
LDMFD r13!,{r5,r9-r11,PC}
ENDP
oc_frag_recon_inter2_arm PROC
; r0 = unsigned char *dst
; r1 = const unsigned char *src1
; r2 = const unsigned char *src2
; r3 = int ystride
LDR r12,[r13]
; r12= const ogg_int16_t residue[64]
STMFD r13!,{r4-r8,r14}
MOV r14,#8
MOV r8, #255
SUB r3, r3, #7
ofrinter2_lp_arm
LDRB r5, [r1], #1
LDRB r6, [r2], #1
LDRSH r4, [r12],#2
LDRB r7, [r1], #1
ADD r5, r5, r6
ADDS r5, r4, r5, LSR #1
CMPGT r8, r5
LDRB r6, [r2], #1
LDRSH r4, [r12],#2
EORLT r5, r8, r5, ASR #32
STRB r5, [r0], #1
ADD r7, r7, r6
ADDS r7, r4, r7, LSR #1
CMPGT r8, r7
LDRB r5, [r1], #1
LDRB r6, [r2], #1
LDRSH r4, [r12],#2
EORLT r7, r8, r7, ASR #32
STRB r7, [r0], #1
ADD r5, r5, r6
ADDS r5, r4, r5, LSR #1
CMPGT r8, r5
LDRB r7, [r1], #1
LDRB r6, [r2], #1
LDRSH r4, [r12],#2
EORLT r5, r8, r5, ASR #32
STRB r5, [r0], #1
ADD r7, r7, r6
ADDS r7, r4, r7, LSR #1
CMPGT r8, r7
LDRB r5, [r1], #1
LDRB r6, [r2], #1
LDRSH r4, [r12],#2
EORLT r7, r8, r7, ASR #32
STRB r7, [r0], #1
ADD r5, r5, r6
ADDS r5, r4, r5, LSR #1
CMPGT r8, r5
LDRB r7, [r1], #1
LDRB r6, [r2], #1
LDRSH r4, [r12],#2
EORLT r5, r8, r5, ASR #32
STRB r5, [r0], #1
ADD r7, r7, r6
ADDS r7, r4, r7, LSR #1
CMPGT r8, r7
LDRB r5, [r1], #1
LDRB r6, [r2], #1
LDRSH r4, [r12],#2
EORLT r7, r8, r7, ASR #32
STRB r7, [r0], #1
ADD r5, r5, r6
ADDS r5, r4, r5, LSR #1
CMPGT r8, r5
LDRB r7, [r1], r3
LDRB r6, [r2], r3
LDRSH r4, [r12],#2
EORLT r5, r8, r5, ASR #32
STRB r5, [r0], #1
ADD r7, r7, r6
ADDS r7, r4, r7, LSR #1
CMPGT r8, r7
EORLT r7, r8, r7, ASR #32
STRB r7, [r0], r3
SUBS r14,r14,#1
BGT ofrinter2_lp_arm
LDMFD r13!,{r4-r8,PC}
ENDP
[ OC_ARM_ASM_EDSP
EXPORT oc_frag_copy_list_edsp
oc_frag_copy_list_edsp PROC
; r0 = _dst_frame
; r1 = _src_frame
; r2 = _ystride
; r3 = _fragis
; <> = _nfragis
; <> = _frag_buf_offs
LDR r12,[r13] ; r12 = _nfragis
STMFD r13!,{r4-r11,r14}
SUBS r12, r12, #1
LDRGE r5, [r3],#4 ; r5 = _fragis[fragii]
LDRGE r14,[r13,#4*10] ; r14 = _frag_buf_offs
BLT ofcl_edsp_end
ofcl_edsp_lp
MOV r4, r1
LDR r5, [r14,r5, LSL #2] ; r5 = _frag_buf_offs[_fragis[fragii]]
SUBS r12, r12, #1
; Stall (on XScale)
LDRD r6, [r4, r5]! ; r4 = _src_frame+frag_buf_off
LDRD r8, [r4, r2]!
; Stall
STRD r6, [r5, r0]! ; r5 = _dst_frame+frag_buf_off
STRD r8, [r5, r2]!
; Stall
LDRD r6, [r4, r2]! ; On Xscale at least, doing 3 consecutive
LDRD r8, [r4, r2]! ; loads causes a stall, but that's no worse
LDRD r10,[r4, r2]! ; than us only doing 2, and having to do
; another pair of LDRD/STRD later on.
; Stall
STRD r6, [r5, r2]!
STRD r8, [r5, r2]!
STRD r10,[r5, r2]!
LDRD r6, [r4, r2]!
LDRD r8, [r4, r2]!
LDRD r10,[r4, r2]!
STRD r6, [r5, r2]!
STRD r8, [r5, r2]!
STRD r10,[r5, r2]!
LDRGE r5, [r3],#4 ; r5 = _fragis[fragii]
BGE ofcl_edsp_lp
ofcl_edsp_end
LDMFD r13!,{r4-r11,PC}
ENDP
]
[ OC_ARM_ASM_MEDIA
EXPORT oc_frag_recon_intra_v6
EXPORT oc_frag_recon_inter_v6
EXPORT oc_frag_recon_inter2_v6
oc_frag_recon_intra_v6 PROC
; r0 = unsigned char *_dst
; r1 = int _ystride
; r2 = const ogg_int16_t _residue[64]
STMFD r13!,{r4-r6,r14}
MOV r14,#8
MOV r12,r2
LDR r6, =0x00800080
ofrintra_v6_lp
LDRD r2, [r12],#8 ; r2 = 11110000 r3 = 33332222
LDRD r4, [r12],#8 ; r4 = 55554444 r5 = 77776666
SUBS r14,r14,#1
QADD16 r2, r2, r6
QADD16 r3, r3, r6
QADD16 r4, r4, r6
QADD16 r5, r5, r6
USAT16 r2, #8, r2 ; r2 = __11__00
USAT16 r3, #8, r3 ; r3 = __33__22
USAT16 r4, #8, r4 ; r4 = __55__44
USAT16 r5, #8, r5 ; r5 = __77__66
ORR r2, r2, r2, LSR #8 ; r2 = __111100
ORR r3, r3, r3, LSR #8 ; r3 = __333322
ORR r4, r4, r4, LSR #8 ; r4 = __555544
ORR r5, r5, r5, LSR #8 ; r5 = __777766
PKHBT r2, r2, r3, LSL #16 ; r2 = 33221100
PKHBT r3, r4, r5, LSL #16 ; r3 = 77665544
STRD r2, [r0], r1
BGT ofrintra_v6_lp
LDMFD r13!,{r4-r6,PC}
ENDP
oc_frag_recon_inter_v6 PROC
; r0 = unsigned char *_dst
; r1 = const unsigned char *_src
; r2 = int _ystride
; r3 = const ogg_int16_t _residue[64]
STMFD r13!,{r4-r7,r14}
MOV r14,#8
ofrinter_v6_lp
LDRD r6, [r3], #8 ; r6 = 11110000 r7 = 33332222
SUBS r14,r14,#1
[ OC_ARM_CAN_UNALIGN_LDRD
LDRD r4, [r1], r2 ; Unaligned ; r4 = 33221100 r5 = 77665544
|
LDR r5, [r1, #4]
LDR r4, [r1], r2
]
PKHBT r12,r6, r7, LSL #16 ; r12= 22220000
PKHTB r7, r7, r6, ASR #16 ; r7 = 33331111
UXTB16 r6,r4 ; r6 = __22__00
UXTB16 r4,r4, ROR #8 ; r4 = __33__11
QADD16 r12,r12,r6 ; r12= xx22xx00
QADD16 r4, r7, r4 ; r4 = xx33xx11
LDRD r6, [r3], #8 ; r6 = 55554444 r7 = 77776666
USAT16 r4, #8, r4 ; r4 = __33__11
USAT16 r12,#8,r12 ; r12= __22__00
ORR r4, r12,r4, LSL #8 ; r4 = 33221100
PKHBT r12,r6, r7, LSL #16 ; r12= 66664444
PKHTB r7, r7, r6, ASR #16 ; r7 = 77775555
UXTB16 r6,r5 ; r6 = __66__44
UXTB16 r5,r5, ROR #8 ; r5 = __77__55
QADD16 r12,r12,r6 ; r12= xx66xx44
QADD16 r5, r7, r5 ; r5 = xx77xx55
USAT16 r12,#8, r12 ; r12= __66__44
USAT16 r5, #8, r5 ; r4 = __77__55
ORR r5, r12,r5, LSL #8 ; r5 = 33221100
STRD r4, [r0], r2
BGT ofrinter_v6_lp
LDMFD r13!,{r4-r7,PC}
ENDP
oc_frag_recon_inter2_v6 PROC
; r0 = unsigned char *_dst
; r1 = const unsigned char *_src1
; r2 = const unsigned char *_src2
; r3 = int _ystride
LDR r12,[r13]
; r12= const ogg_int16_t _residue[64]
STMFD r13!,{r4-r9,r14}
MOV r14,#8
ofrinter2_v6_lp
LDRD r6, [r12,#8] ; r6 = 55554444 r7 = 77776666
SUBS r14,r14,#1
LDR r4, [r1, #4] ; Unaligned ; r4 = src1[1] = 77665544
LDR r5, [r2, #4] ; Unaligned ; r5 = src2[1] = 77665544
PKHBT r8, r6, r7, LSL #16 ; r8 = 66664444
PKHTB r9, r7, r6, ASR #16 ; r9 = 77775555
UHADD8 r4, r4, r5 ; r4 = (src1[7,6,5,4] + src2[7,6,5,4])>>1
UXTB16 r5, r4 ; r5 = __66__44
UXTB16 r4, r4, ROR #8 ; r4 = __77__55
QADD16 r8, r8, r5 ; r8 = xx66xx44
QADD16 r9, r9, r4 ; r9 = xx77xx55
LDRD r6,[r12],#16 ; r6 = 33332222 r7 = 11110000
USAT16 r8, #8, r8 ; r8 = __66__44
LDR r4, [r1], r3 ; Unaligned ; r4 = src1[0] = 33221100
USAT16 r9, #8, r9 ; r9 = __77__55
LDR r5, [r2], r3 ; Unaligned ; r5 = src2[0] = 33221100
ORR r9, r8, r9, LSL #8 ; r9 = 77665544
PKHBT r8, r6, r7, LSL #16 ; r8 = 22220000
UHADD8 r4, r4, r5 ; r4 = (src1[3,2,1,0] + src2[3,2,1,0])>>1
PKHTB r7, r7, r6, ASR #16 ; r7 = 33331111
UXTB16 r5, r4 ; r5 = __22__00
UXTB16 r4, r4, ROR #8 ; r4 = __33__11
QADD16 r8, r8, r5 ; r8 = xx22xx00
QADD16 r7, r7, r4 ; r7 = xx33xx11
USAT16 r8, #8, r8 ; r8 = __22__00
USAT16 r7, #8, r7 ; r7 = __33__11
ORR r8, r8, r7, LSL #8 ; r8 = 33221100
STRD r8, [r0], r3
BGT ofrinter2_v6_lp
LDMFD r13!,{r4-r9,PC}
ENDP
]
[ OC_ARM_ASM_NEON
EXPORT oc_frag_copy_list_neon
EXPORT oc_frag_recon_intra_neon
EXPORT oc_frag_recon_inter_neon
EXPORT oc_frag_recon_inter2_neon
oc_frag_copy_list_neon PROC
; r0 = _dst_frame
; r1 = _src_frame
; r2 = _ystride
; r3 = _fragis
; <> = _nfragis
; <> = _frag_buf_offs
LDR r12,[r13] ; r12 = _nfragis
STMFD r13!,{r4-r7,r14}
CMP r12, #1
LDRGE r6, [r3] ; r6 = _fragis[fragii]
LDRGE r14,[r13,#4*6] ; r14 = _frag_buf_offs
BLT ofcl_neon_end
; Stall (2 on Xscale)
LDR r6, [r14,r6, LSL #2] ; r6 = _frag_buf_offs[_fragis[fragii]]
; Stall (on XScale)
MOV r7, r6 ; Guarantee PLD points somewhere valid.
ofcl_neon_lp
ADD r4, r1, r6
VLD1.64 {D0}, [r4@64], r2
ADD r5, r0, r6
VLD1.64 {D1}, [r4@64], r2
SUBS r12, r12, #1
VLD1.64 {D2}, [r4@64], r2
LDRGT r6, [r3,#4]! ; r6 = _fragis[fragii]
VLD1.64 {D3}, [r4@64], r2
LDRGT r6, [r14,r6, LSL #2] ; r6 = _frag_buf_offs[_fragis[fragii]]
VLD1.64 {D4}, [r4@64], r2
ADDGT r7, r1, r6
VLD1.64 {D5}, [r4@64], r2
PLD [r7]
VLD1.64 {D6}, [r4@64], r2
PLD [r7, r2]
VLD1.64 {D7}, [r4@64]
PLD [r7, r2, LSL #1]
VST1.64 {D0}, [r5@64], r2
ADDGT r7, r7, r2, LSL #2
VST1.64 {D1}, [r5@64], r2
PLD [r7, -r2]
VST1.64 {D2}, [r5@64], r2
PLD [r7]
VST1.64 {D3}, [r5@64], r2
PLD [r7, r2]
VST1.64 {D4}, [r5@64], r2
PLD [r7, r2, LSL #1]
VST1.64 {D5}, [r5@64], r2
ADDGT r7, r7, r2, LSL #2
VST1.64 {D6}, [r5@64], r2
PLD [r7, -r2]
VST1.64 {D7}, [r5@64]
BGT ofcl_neon_lp
ofcl_neon_end
LDMFD r13!,{r4-r7,PC}
ENDP
oc_frag_recon_intra_neon PROC
; r0 = unsigned char *_dst
; r1 = int _ystride
; r2 = const ogg_int16_t _residue[64]
VMOV.I16 Q0, #128
VLDMIA r2, {D16-D31} ; D16= 3333222211110000 etc ; 9(8) cycles
VQADD.S16 Q8, Q8, Q0
VQADD.S16 Q9, Q9, Q0
VQADD.S16 Q10,Q10,Q0
VQADD.S16 Q11,Q11,Q0
VQADD.S16 Q12,Q12,Q0
VQADD.S16 Q13,Q13,Q0
VQADD.S16 Q14,Q14,Q0
VQADD.S16 Q15,Q15,Q0
VQMOVUN.S16 D16,Q8 ; D16= 7766554433221100 ; 1 cycle
VQMOVUN.S16 D17,Q9 ; D17= FFEEDDCCBBAA9988 ; 1 cycle
VQMOVUN.S16 D18,Q10 ; D18= NNMMLLKKJJIIHHGG ; 1 cycle
VST1.64 {D16},[r0@64], r1
VQMOVUN.S16 D19,Q11 ; D19= VVUUTTSSRRQQPPOO ; 1 cycle
VST1.64 {D17},[r0@64], r1
VQMOVUN.S16 D20,Q12 ; D20= ddccbbaaZZYYXXWW ; 1 cycle
VST1.64 {D18},[r0@64], r1
VQMOVUN.S16 D21,Q13 ; D21= llkkjjiihhggffee ; 1 cycle
VST1.64 {D19},[r0@64], r1
VQMOVUN.S16 D22,Q14 ; D22= ttssrrqqppoonnmm ; 1 cycle
VST1.64 {D20},[r0@64], r1
VQMOVUN.S16 D23,Q15 ; D23= !!@@zzyyxxwwvvuu ; 1 cycle
VST1.64 {D21},[r0@64], r1
VST1.64 {D22},[r0@64], r1
VST1.64 {D23},[r0@64], r1
MOV PC,R14
ENDP
oc_frag_recon_inter_neon PROC
; r0 = unsigned char *_dst
; r1 = const unsigned char *_src
; r2 = int _ystride
; r3 = const ogg_int16_t _residue[64]
VLDMIA r3, {D16-D31} ; D16= 3333222211110000 etc ; 9(8) cycles
VLD1.64 {D0}, [r1], r2
VLD1.64 {D2}, [r1], r2
VMOVL.U8 Q0, D0 ; Q0 = __77__66__55__44__33__22__11__00
VLD1.64 {D4}, [r1], r2
VMOVL.U8 Q1, D2 ; etc
VLD1.64 {D6}, [r1], r2
VMOVL.U8 Q2, D4
VMOVL.U8 Q3, D6
VQADD.S16 Q8, Q8, Q0
VLD1.64 {D0}, [r1], r2
VQADD.S16 Q9, Q9, Q1
VLD1.64 {D2}, [r1], r2
VQADD.S16 Q10,Q10,Q2
VLD1.64 {D4}, [r1], r2
VQADD.S16 Q11,Q11,Q3
VLD1.64 {D6}, [r1], r2
VMOVL.U8 Q0, D0
VMOVL.U8 Q1, D2
VMOVL.U8 Q2, D4
VMOVL.U8 Q3, D6
VQADD.S16 Q12,Q12,Q0
VQADD.S16 Q13,Q13,Q1
VQADD.S16 Q14,Q14,Q2
VQADD.S16 Q15,Q15,Q3
VQMOVUN.S16 D16,Q8
VQMOVUN.S16 D17,Q9
VQMOVUN.S16 D18,Q10
VST1.64 {D16},[r0@64], r2
VQMOVUN.S16 D19,Q11
VST1.64 {D17},[r0@64], r2
VQMOVUN.S16 D20,Q12
VST1.64 {D18},[r0@64], r2
VQMOVUN.S16 D21,Q13
VST1.64 {D19},[r0@64], r2
VQMOVUN.S16 D22,Q14
VST1.64 {D20},[r0@64], r2
VQMOVUN.S16 D23,Q15
VST1.64 {D21},[r0@64], r2
VST1.64 {D22},[r0@64], r2
VST1.64 {D23},[r0@64], r2
MOV PC,R14
ENDP
oc_frag_recon_inter2_neon PROC
; r0 = unsigned char *_dst
; r1 = const unsigned char *_src1
; r2 = const unsigned char *_src2
; r3 = int _ystride
LDR r12,[r13]
; r12= const ogg_int16_t _residue[64]
VLDMIA r12,{D16-D31}
VLD1.64 {D0}, [r1], r3
VLD1.64 {D4}, [r2], r3
VLD1.64 {D1}, [r1], r3
VLD1.64 {D5}, [r2], r3
VHADD.U8 Q2, Q0, Q2 ; Q2 = FFEEDDCCBBAA99887766554433221100
VLD1.64 {D2}, [r1], r3
VLD1.64 {D6}, [r2], r3
VMOVL.U8 Q0, D4 ; Q0 = __77__66__55__44__33__22__11__00
VLD1.64 {D3}, [r1], r3
VMOVL.U8 Q2, D5 ; etc
VLD1.64 {D7}, [r2], r3
VHADD.U8 Q3, Q1, Q3
VQADD.S16 Q8, Q8, Q0
VQADD.S16 Q9, Q9, Q2
VLD1.64 {D0}, [r1], r3
VMOVL.U8 Q1, D6
VLD1.64 {D4}, [r2], r3
VMOVL.U8 Q3, D7
VLD1.64 {D1}, [r1], r3
VQADD.S16 Q10,Q10,Q1
VLD1.64 {D5}, [r2], r3
VQADD.S16 Q11,Q11,Q3
VLD1.64 {D2}, [r1], r3
VHADD.U8 Q2, Q0, Q2
VLD1.64 {D6}, [r2], r3
VLD1.64 {D3}, [r1], r3
VMOVL.U8 Q0, D4
VLD1.64 {D7}, [r2], r3
VMOVL.U8 Q2, D5
VHADD.U8 Q3, Q1, Q3
VQADD.S16 Q12,Q12,Q0
VQADD.S16 Q13,Q13,Q2
VMOVL.U8 Q1, D6
VMOVL.U8 Q3, D7
VQADD.S16 Q14,Q14,Q1
VQADD.S16 Q15,Q15,Q3
VQMOVUN.S16 D16,Q8
VQMOVUN.S16 D17,Q9
VQMOVUN.S16 D18,Q10
VST1.64 {D16},[r0@64], r3
VQMOVUN.S16 D19,Q11
VST1.64 {D17},[r0@64], r3
VQMOVUN.S16 D20,Q12
VST1.64 {D18},[r0@64], r3
VQMOVUN.S16 D21,Q13
VST1.64 {D19},[r0@64], r3
VQMOVUN.S16 D22,Q14
VST1.64 {D20},[r0@64], r3
VQMOVUN.S16 D23,Q15
VST1.64 {D21},[r0@64], r3
VST1.64 {D22},[r0@64], r3
VST1.64 {D23},[r0@64], r3
MOV PC,R14
ENDP
]
END
|