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
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
|
/***************************************************************************
* __________ __ ___.
* Open \______ \ ____ ____ | | _\_ |__ _______ ___
* Source | _// _ \_/ ___\| |/ /| __ \ / _ \ \/ /
* Jukebox | | ( <_> ) \___| < | \_\ ( <_> > < <
* Firmware |____|_ /\____/ \___ >__|_ \|___ /\____/__/\_ \
* \/ \/ \/ \/ \/
* $Id$
*
* Copyright (C) 2006 Thom Johansen
* Copyright (C) 2007, 2012 Michael Sevakis
* Copyright (C) 2010 Bertrik Sikken
*
* 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 software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
* KIND, either express or implied.
*
****************************************************************************/
#include "rbcodecconfig.h"
/****************************************************************************
* void pga_process(struct dsp_proc_entry *this, struct dsp_buffer **buf_p)
*/
.section .text
.align 2
.global pga_process
pga_process:
| input: 4(sp) = this, 8(sp) = buf_p
movem.l 4(%sp), %a0-%a1 | %a0 = this, %a1 = buf_p
move.l (%a0), %a0 | %a0 = this->data = &pga_data
move.l (%a0), %a0 | %a0 = data->gain
move.l (%a1), %a1 | %a1 = buf = *buf_p
lea.l -20(%sp), %sp | save registers
movem.l %d2-%d4/%a2-%a3, (%sp) |
clr.l %d1 | %d1 = buf->format.num_channels
move.b 17(%a1), %d1 |
10: | channel loop |
move.l (%a1), %d0 | %d0 = buf->remcount
move.l (%a1, %d1.l*4), %a2 | %a2 = s = buf->p32[ch-1]
move.l %a2, %a3 | %a3 = d = s
move.l (%a2)+, %d2 | %d2 = *s++,
mac.l %a0, %d2, (%a2)+, %d2, %acc0 | %acc0 = S(n)*gain, load S(n+1)
subq.l #1, %d0 | --count > 0 ? : effectively n++
ble.b 30f | loop done | no? finish up
20: | loop |
move.l %accext01, %d4 | fetch S(n-1)[7:0]
movclr.l %acc0, %d3 | fetch S(n-1)[40:8] in %d5[31:0]
asl.l #8, %d3 | *s++ = (S(n-1)[40:8] << 8) | S(n-1)[7:0]
mac.l %a0, %d2, (%a2)+, %d2, %acc0 | %acc0 = S(n)*gain, load S(n+1)
move.b %d4, %d3 |
move.l %d3, (%a3)+ |
subq.l #1, %d0 | --count > 0 ? : effectively n++
bgt.b 20b | loop | yes? do more samples
30: | loop done |
move.l %accext01, %d4 | fetch S(n-1)[7:0]
movclr.l %acc0, %d3 | fetch S(n-1)[40:8] in %d5[31:0]
asl.l #8, %d3 | *s = (S(n-1)[40:8] << 8) | S(n-1)[7:0]
move.b %d4, %d3 |
move.l %d3, (%a3) |
subq.l #1, %d1 | next channel
bgt.b 10b | channel loop |
movem.l (%sp), %d2-%d4/%a2-%a3 | restore registers
lea.l 20(%sp), %sp | cleanup stack
rts |
.size pga_process, .-pga_process
/****************************************************************************
* void crossfeed_process(struct dsp_proc_entry *this,
* struct dsp_buffer **buf_p)
*/
.section .text
.align 2
.global crossfeed_process
crossfeed_process:
| input: 4(sp) = this, 8(sp) = buf_p
lea.l -44(%sp), %sp |
movem.l %d2-%d7/%a2-%a6, (%sp) | save all regs
movem.l 48(%sp), %a1/%a4 | %a1 = this, %a4 = buf_p
move.l (%a4), %a4 | %a4 = buf = *buf_p
movem.l (%a4), %d0/%a4-%a5 | %d0 = buf->remcount, %a4 = buf->p32[0],
| %a5 = buf->p32[1]
move.l (%a1), %a6 | %d7 = state = &crossfeed_state
movem.l (%a6), %d1-%d6/%a0-%a3 | %d1 = gain, %d2-%d4 = coefs,
| %d5..%d6 = history[0..1],
| %a0..%a1 = history[2..3],
| %a2 = index, %a3 = index_max
lea.l 0x28(%a6), %a6 | %a6 = state->delay
move.l %a6, -(%sp) | push state->delay
bra.b .cfp_loop_start
/* Register usage in loop:
* %d0 = count, %d1 = direct gain, %d2..%d4 = b0, b1, a1 (filter coefs),
* %d5..%d6 = history[0..1], %d7 = scratch
* %a0..%a1 = history[2..3], %a2 = index, %a3 = index_max,
* %a4 = buf[0], %a5 = buf[1], %a6 = scratch
*/
.cfp_loop:
movclr.l %acc0, %d7 | write outputs
move.l %d7, (%a4)+ | .
movclr.l %acc1, %a6 | .
move.l %a6, (%a5)+ | .
.cfp_loop_start:
mac.l %d3, %d5, (%a2)+, %d5, %acc1 | %acc1 = b1*dl[n - 1], %d5 = dl[n]
mac.l %d2, %d5 , %acc1 | %acc1 += b0*dl[n]
mac.l %d4, %d6, (%a4), %d7, %acc1 | %acc1 += a1*y_l[n - 1], %d7 = x_l[n]
mac.l %d3, %a0, (%a2)+, %a0, %acc0 | %acc0 = b1*dr[n - 1], %a0 = dr[n]
mac.l %a2, %a0 , %acc0 | %acc0 += b0*dr[n]
mac.l %d4, %a1, (%a5), %a6, %acc0 | %acc0 += a1*y_r[n - 1], %a6 = x_r[n]
movem.l %d7/%a6, -8(%a2) | save x_l[n] and x_r[n] to delay line
move.l %acc1, %d6 | get filtered delayed left sample (y_l[n])
move.l %acc0, %a1 | get filtered delayed right sample (y_r[n])
mac.l %d1, %d7, %acc0 | %acc0 = gain*x_l[n] + y_r[n]
mac.l %d1, %a6, %acc1 | %acc1 = gain*x_r[n] + y_l[n]
cmp.l %a3, %a2 | wrap index if past end
bhs.b 1f |
tpf.w | trap the buffer wrap
1: | ...fwd taken branches more costly
move.l (%sp), %a2 | 2b | wrap it up
subq.l #1, %d0 | --count > 0 ?
bgt.b .cfp_loop | yes? do more
movclr.l %acc0, %d7 | write last outputs
move.l %d7, (%a4) | .
movclr.l %acc1, %a6 | .
move.l %a6, (%a5) | .
move.l (%sp)+, %a6 | pop state->delay
movem.l %d5-%d6/%a0-%a2, -0x18(%a6) | save history, index
movem.l (%sp), %d2-%d7/%a2-%a6 | restore all regs
lea.l 44(%sp), %sp |
rts |
.size crossfeed_process, .-crossfeed_process
/****************************************************************************
* void crossfeed_meier_process(struct dsp_proc_entry *this,
* struct dsp_buffer **buf_p)
*/
.section .text
.global crossfeed_meier_process
crossfeed_meier_process:
| input: 4(sp) = this, 8(sp) = buf_p
movem.l 4(%sp), %a0-%a1 | %a0 = this, %a1 = buf_p
lea.l -24(%sp), %sp | save non-volatiles
movem.l %d2-%d6/%a2, (%sp) | .
move.l (%a0), %a0 | %a0 = &this->data = &crossfeed_state
move.l (%a1), %a1 | %a1 = buf = *buf_p
movem.l 4(%a0), %d1-%d5 | %d1 = vcl, %d2 = vcr, %d3 = vdiff,
| %d4 = coef1, %d5 = coef2
movem.l (%a1), %d0/%a1-%a2 | %d0 = count = buf->remcount
| %a1 = p32[0], %a2 = p32[1]
| Register usage in loop:
| %d0 = count, %d1 = vcl, %d2 = vcr, %d3 = vdiff/lout,
| %d4 = coef1, %d5 = coef2, %d6 = rout/scratch
| %a1 = p32[0], %a2 = p32[1]
.cfmp_loop:
mac.l %d5, %d3, %acc0 | %acc0 = common = coef2*vdiff
move.l %acc0, %acc1 | copy common
mac.l %d4, %d1, (%a1), %d3, %acc0 | %acc0 += coef1*vcl, %d3 = lout
msac.l %d4, %d2, (%a2), %d6, %acc1 | %acc1 -= coef1*vcr, %d6 = rout
add.l %d1, %d3 | lout += vcl
add.l %d2, %d6 | rout += vcr
move.l %d3, (%a1)+ | store left channel, pos inc
move.l %d6, (%a2)+ | store right channel, pos inc
sub.l %d6, %d3 | vdiff = lout - rout
movclr.l %acc0, %d6 | %d4 = fetch res1 in s0.31
sub.l %d6, %d1 | vcl -= res1
movclr.l %acc1, %d6 | %d5 = fetch -res2 in s0.31
add.l %d6, %d2 | vcr += -res2
subq.l #1, %d0 | count--
bgt .cfmp_loop | more samples?
|
movem.l %d1-%d3, 4(%a0) | save vcl, vcr, vdiff
movem.l (%sp), %d2-%d6/%a2 | restore non-volatiles
lea.l 24(%sp), %sp | .
rts |
.size crossfeed_meier_process, .-crossfeed_meier_process
/****************************************************************************
* int resample_hermite(struct resample_data *data, struct dsp_buffer *src,
* struct dsp_buffer *dst)
*/
.section .text
.align 2
.global resample_hermite
resample_hermite:
| input: 4(sp) = data, 8(sp) = src, 12(sp) = dst
lea.l -52(%sp), %sp | save non-volatiles, allocate temps
movem.l %d2-%d7/%a2-%a6, 8(%sp) |
movem.l 56(%sp), %a0-%a2 | %a0 = data
| %a1 = src
| %a2 = dst
clr.l %d5 | %d5 = ch = src->format.num_channels
move.b 17(%a1), %d5 |
lea.l 8(%a0), %a5 | %a5 = h = history[ch]
moveq.l #16, %d7 | %d7 = shift val
.hrs_channel_loop: |
movem.l %d5/%a5, (%sp) | store ch, h
movem.l (%a0), %d1-%d2 | %d1 = delta = data->delta,
| %d2 = phase = data->phase
move.l (%a1), %d3 | %d3 = srcrem = src->remcount
move.l 12(%a2), %d4 | %d4 = dstrem = dst->bufcount
cmp.l #0x8000, %d3 | %d4 = MIN(srcrem, 0x8000)
ble.b 1f |
move.l #0x8000, %d3 |
1: |
move.l (%a1, %d5.l*4), %a1 | %a1 = s = src->p32[ch]
move.l (%a2, %d5.l*4), %a2 | %a2 = d = dst->p32[ch]
move.l %d2, %d0 | %d0 = pos = phase >> 16
lsr.l %d7, %d0 |
cmp.l %d3, %d0 | pos = MIN(pos, srcrem)
ble.b 1f |
move.l %d3, %d0 |
1:
lea.l (%a1, %d0.l*4), %a1 | %a1 = &s[pos]
cmp.l #3, %d0 |
bge.b 1f |
move.l %d0, %a0 |
lea.l (%a0, %a0.l*2), %a0 |
jmp 2(%pc, %a0.l*4) | 4b |
| 0
movem.l (%a5), %a3-%a5 | 4b | x3..x1 = h[0]..h[2]
bra.b 2f | 2b |
.dcb.w 3,0 | 6b | filler
| 1
movem.l 4(%a5), %a3-%a4 | 6b | x3..x2 = h[1]..h[2]
move.l -4(%a1), %a5 | 4b | x1 = s[0]
bra.b 2f | 2b |
| 2
move.l 8(%a5), %a3 | 4b | x3 = h[2]
movem.l -8(%a1), %a4-%a5 | 6b | x2..x1 = s[0]..s[1]
bra.b 2f | 2b |
1: | 3 +
movem.l -12(%a1), %a3-%a5 | x3...x1 = s[pos-3]..s[pos-1]
2:
cmp.l %d3, %d0 | pos past end?
bge.w .hrs_channel_done |
cmp.l #0x10000, %d1 | delta >= 1.0?
bhs.w .hrs_dsstart | yes? downsampling
|
/** Upsampling **/ |
sub.l %d3, %d0 | %d0 = pos - srcrem = -dte
lsl.l %d7, %d1 | move delta to bits 30..15
lsr.l #1, %d1 |
lsl.l %d7, %d2 | move phase to bits 30..15
lsr.l #1, %d2 |
|
| Register usage in loop:
| r0 = dte, d1 = delta, d2 = phase, d3 = srcrem, d4 = dstrem
| d5 = scratch, d6 = c3, d7 = scratch
| a0 = c2, a1 = &s[pos], a2 = d,
| a3 = x3, a4 = x2, a5 = x1, a6 = x0
|
| Try to avoid overflow as much as possible and at the same time preserve
| accuracy. Same formulas apply to downsampling but registers and
| instruction order differ due to specific constraints.
| c1 = -0.5*x3 + 0.5*x1
| = 0.5*(x1 - x3) <--
|
| v = x1 - x2, -v = x2 - x1
| c2 = x3 - 2.5*x2 + 2*x1 - 0.5*x0
| = x3 + 2*(x1 - x2) - 0.5*(x0 + x2)
| = x3 + 2*v - 0.5*(x0 + x2) <--
|
| c3 = -0.5*x3 + 1.5*x2 - 1.5*x1 + 0.5*x0
| = 0.5*x0 - 0.5*x3 + 0.5*(x2 - x1) + (x2 - x1)
| = 0.5*(x0 - x3 - v) - v <--
|
.hrs_usloop_carry:
move.l (%a1)+, %a6 | %a6 = s[pos]
move.l %a5, %d5 | v
sub.l %a4, %d5 |
move.l %a6, %d6 | c3
sub.l %a3, %d6 |
sub.l %d5, %d6 |
asr.l #1, %d6 |
sub.l %d5, %d6 |
lea.l (%a3, %d5.l*2), %a0 | c2
move.l %a6, %d5 |
add.l %a4, %d5 |
asr.l #1, %d5 |
sub.l %d5, %a0 |
.hrs_usloop_frac:
move.l %a0, %acc0 | %acc0 = frac * c3 + c2
mac.l %d2, %d6, %acc0 |
move.l %a5, %d5 | c1
sub.l %a3, %d5 |
asr.l #1, %d5 |
movclr.l %acc0, %d7 | %acc1 = frac * acc + c1
move.l %d5, %acc1 |
mac.l %d2, %d7, %acc1 |
move.l %a4, %acc0 | %acc0 = frac * acc + x2
movclr.l %acc1, %d5 |
mac.l %d2, %d5, %acc0 |
subq.l #1, %d4 | dstrem <= 0?
ble.b .hrs_usfull | yes? stop
movclr.l %acc0, %d5 | *d++ = d5 = result
move.l %d5, (%a2)+ |
add.l %d1, %d2 | phase += delta
bpl.b .hrs_usloop_frac | load next values?
move.l %a4, %a3 | x3 = x2
move.l %a5, %a4 | x2 = x1
move.l %a6, %a5 | x1 = x0
bclr.l #31, %d2 | clear sign bit
addq.l #1, %d0 | dte > 0?
bmi.b .hrs_usloop_carry | yes? continue resampling
bra.b .hrs_usdone
.hrs_usfull:
movclr.l %acc0, %d5 | *d++ = d5 = result
move.l %d5, (%a2) |
add.l %d1, %d2 | do missed phase increment
bpl.b .hrs_usdone | was sign bit set?
move.l %a4, %a3 | do missed history update
move.l %a5, %a4 |
move.l %a6, %a5 |
addq.l #1, %d0 | do missed dte decrement
.hrs_usdone:
moveq.l #16, %d7 | restore shift
lsl.l #1, %d2 | frac -> phase
add.l %d3, %d0 | %d0 = -dte + srcrem = pos
or.l %d0, %d2 | restore phase
swap.w %d2 |
bra.w .hrs_channel_done |
/** Downsampling **/
|
| Register usage in loop:
| r0 = pos, d1 = delta, d2 = phase, d3 = srcrem, d4 = dstrem
| d5 = scratch, d6 = scratch, d7 = 16 (shift value)
| a0 = scratch, a1 = &s[pos], a2 = d,
| a3 = x3, a4 = x2, a5 = x1, a6 = x0
|
.hrs_dsloop:
movclr.l %acc0, %d5 | *d++ = acc
move.l %d5, (%a2)+ |
sub.l %d0, %a0 | %a0 = -shift = last_pos - pos
move.l %a0, %d5 |
asl.l #2, %d5 | -shift -> -bytes
sub.l %d5, %a1 | %a1 = s = s - -bytes
cmp.l #-4, %a0 | >= 4?
ble.b 1f |
add.l %d5, %a0 | %a0 = 5 * -shift
jmp 40(%pc, %a0.l*2) | 4b |
1: | +4 +
movem.l -12(%a1), %a3-%a5 | 6b | x3..x0 = s[pos-3]..s[pos-1]
bra.b 1f | 2b |
| +3
move.l %a6, %a3 | 2b | x3 = x0
movem.l -8(%a1), %a4-%a5 | 6b | x2..x0 = s[pos-2]..s[pos-1]
bra.b 1f | 2b | 10
| +2
move.l %a5, %a3 | 2b | x3 = x1
move.l %a6, %a4 | 2b | x2 = x0
move.l -4(%a1), %a5 | 4b | x1 = s[pos-1]
bra.b 1f | 2b | 10
| +1
move.l %a4, %a3 | 2b | x3 = x2 | expected loop destination
move.l %a5, %a4 | 2b | x2 = x1
move.l %a6, %a5 | 2b | x1 = x0
1:
subq.l #1, %d4 | 2b | dstrem <= 0?
ble.b .hrs_channel_done | 2b | yes? stop
cmp.l %d3, %d0 |
bge.b .hrs_channel_done |
.hrs_dsstart:
move.l (%a1), %a6 | %a6 = s[pos]
move.l %a5, %d5 | v
sub.l %a4, %d5 |
move.l %a6, %d6 | c3
sub.l %a3, %d6 |
sub.l %d5, %d6 |
asr.l #1, %d6 |
sub.l %d5, %d6 |
lea.l (%a3, %d5.l*2), %a0 | c2
move.l %a6, %d5 |
add.l %a4, %d5 |
asr.l #1, %d5 |
sub.l %d5, %a0 |
move.l %d2, %d5 | phase -> frac
lsl.l %d7, %d5 |
lsr.l #1, %d5 |
move.l %a0, %acc0 | %acc0 = frac * c3 + c2
mac.l %d5, %d6, %acc0 |
move.l %a5, %d6 | c1
sub.l %a3, %d6 |
asr.l #1, %d6 |
movclr.l %acc0, %a0 | %acc1 = frac * acc + c1
move.l %d6, %acc1 |
mac.l %d5, %a0, %acc1 |
move.l %d0, %a0 | %a0 = last_pos
add.l %d1, %d2 | phase += delta
move.l %d2, %d0 | pos = phase >> 16
lsr.l %d7, %d0 |
movclr.l %acc1, %d6 | %acc0 = frac * acc + x2
move.l %a4, %acc0 |
mac.l %d5, %d6, %acc0 |
cmp.l %d3, %d0 | %d0 = MIN(pos, srcrem)
ble.w .hrs_dsloop |
move.l %d3, %d0 |
bra.w .hrs_dsloop |
.hrs_channel_done: |
movem.l (%sp), %d5/%a0 | restore ch, h
movem.l %a3-%a5, (%a0) | h[0..2] = x3..x1
lea.l 12(%a0), %a5 | h++
movem.l 56(%sp), %a0-%a2 | load data, src, dst
subq.l #1, %d5 | ch > 0?
bgt.w .hrs_channel_loop | yes? process next channel
move.l 12(%a2), %d1 | %d1 = dst->bufcount
sub.l %d4, %d1 | written = dst->bufcount - dstrem
move.l %d1, (%a2) | dst->remcount = written
move.l %d0, %d1 | wrap phase to position in next frame
lsl.l %d7, %d1 | data->phase = phase - (pos << 16)
sub.l %d1, %d2 |
move.l %d2, 4(%a0) |
movem.l 8(%sp), %d2-%d7/%a2-%a6 | restore non-volatiles
lea.l 52(%sp), %sp | cleanup stack
rts | buh-bye
.size resample_hermite, .-resample_hermite
/****************************************************************************
* void channel_mode_proc_mono(struct dsp_proc_entry *this,
* struct dsp_buffer **buf_p)
*
* Mix left and right channels 50/50 into a center channel.
*/
.section .text
.align 2
.global channel_mode_proc_mono
channel_mode_proc_mono:
| input: 4(sp) = this, 8(sp) = buf_p
move.l 8(%sp), %a0 | %a0 = buf_p
move.l (%a0), %a0 | %a0 = buf = *buf_p
lea.l -20(%sp), %sp | save registers
movem.l %d2-%d4/%a2-%a3, (%sp) |
movem.l (%a0), %d0/%a0-%a1 | %d0 = buf->remcount, %a0 = buf->p32[0],
| %a1 = buf->p32[1]
move.l %a0, %a2 | use separate dst pointers since read
move.l %a1, %a3 | pointers run one ahead of write
move.l #0x40000000, %d3 | %d3 = 0.5
move.l (%a0)+, %d1 | prime the input registers
move.l (%a1)+, %d2 |
mac.l %d1, %d3, (%a0)+, %d1, %acc0 |
mac.l %d2, %d3, (%a1)+, %d2, %acc0 |
subq.l #1, %d0 |
ble.s 20f | loop done |
10: | loop |
movclr.l %acc0, %d4 | L = R = l/2 + r/2
mac.l %d1, %d3, (%a0)+, %d1, %acc0 |
mac.l %d2, %d3, (%a1)+, %d2, %acc0 |
move.l %d4, (%a2)+ | output to original buffer
move.l %d4, (%a3)+ |
subq.l #1, %d0 |
bgt.s 10b | loop |
20: | loop done |
movclr.l %acc0, %d4 | output last sample
move.l %d4, (%a2) |
move.l %d4, (%a3) |
movem.l (%sp), %d2-%d4/%a2-%a3 | restore registers
lea.l 20(%sp), %sp | cleanup
rts |
.size channel_mode_proc_mono, .-channel_mode_proc_mono
/****************************************************************************
* void channel_mode_proc_custom(struct dsp_proc_entry *this,
* struct dsp_buffer **buf_p)
*
* Apply stereo width (narrowing/expanding) effect.
*/
.section .text
.align 2
.global channel_mode_proc_custom
channel_mode_proc_custom:
| input: 4(sp) = this, 8(sp) = buf_p
lea.l -28(%sp), %sp | save registers
movem.l %d2-%d6/%a2-%a3, (%sp) |
movem.l 32(%sp), %a0-%a1 | %a0 = this, %a1 = buf_p
move.l (%a1), %a1 | %a1 = buf = *buf_p
move.l (%a0), %a2 | %a2 = this->data = &channel_mode_data
movem.l (%a1), %d0/%a0-%a1 | %d0 = buf->remcount, %a0 = buf->p32[0],
| %a1 = buf->p32[1]
movem.l (%a2), %d3-%d4 | %d3 = sw_gain, %d4 = sw_cross
move.l %a0, %a2 | use separate dst pointers since read
move.l %a1, %a3 | pointers run one ahead of write
move.l (%a0)+, %d1 | prime the input registers
move.l (%a1)+, %d2 |
mac.l %d1, %d3 , %acc0 | L = l*gain + r*cross
mac.l %d1, %d4, (%a0)+, %d1, %acc1 | R = r*gain + l*cross
mac.l %d2, %d4 , %acc0 |
mac.l %d2, %d3, (%a1)+, %d2, %acc1 |
subq.l #1, %d0 |
ble.b 20f | loop done |
10: | loop |
movclr.l %acc0, %d5 |
movclr.l %acc1, %d6 |
mac.l %d1, %d3 , %acc0 | L = l*gain + r*cross
mac.l %d1, %d4, (%a0)+, %d1, %acc1 | R = r*gain + l*cross
mac.l %d2, %d4 , %acc0 |
mac.l %d2, %d3, (%a1)+, %d2, %acc1 |
move.l %d5, (%a2)+ |
move.l %d6, (%a3)+ |
subq.l #1, %d0 |
bgt.s 10b | loop |
20: | loop done |
movclr.l %acc0, %d5 | output last sample
movclr.l %acc1, %d6 |
move.l %d5, (%a2) |
move.l %d6, (%a3) |
movem.l (%sp), %d2-%d6/%a2-%a3 | restore registers
lea.l 28(%sp), %sp | cleanup
rts |
.size channel_mode_proc_custom, .-channel_mode_proc_custom
/****************************************************************************
* void channel_mode_proc_karaoke(struct dsp_proc_entry *this,
* struct dsp_buffer **buf_p)
*
* Separate channels into side channels.
*/
.section .text
.align 2
.global channel_mode_proc_karaoke
channel_mode_proc_karaoke:
| input: 4(sp) = this, 8(sp) = buf_p
move.l 8(%sp), %a0 | %a0 = buf_p
move.l (%a0), %a0 | %a0 = buf = *buf_p
lea.l -20(%sp), %sp | save registers
movem.l %d2-%d4/%a2-%a3, (%sp) |
movem.l (%a0), %d0/%a0-%a1 | %d0 = buf->remcount, %a0 = buf->p32[0],
| %a1 = buf->p32[1]
move.l %a0, %a2 | use separate dst pointers since read
move.l %a1, %a3 | pointers run one ahead of write
move.l #0x40000000, %d3 | %d3 = 0.5
move.l (%a0)+, %d1 | prime the input registers
move.l (%a1)+, %d2 |
mac.l %d1, %d3, (%a0)+, %d1, %acc0 | L = l/2 - r/2
msac.l %d2, %d3, (%a1)+, %d2, %acc0 |
subq.l #1, %d0 |
ble.b 20f | loop done |
10: | loop |
movclr.l %acc0, %d4 |
mac.l %d1, %d3, (%a0)+, %d1, %acc0 | L = l/2 - r/2
msac.l %d2, %d3, (%a1)+, %d2, %acc0 |
move.l %d4, (%a2)+ |
neg.l %d4 | R = -L = -(l/2 - r/2) = r/2 - l/2
move.l %d4, (%a3)+ |
subq.l #1, %d0 |
bgt.s 10b | loop |
20: | loop done |
movclr.l %acc0, %d4 | output last sample
move.l %d4, (%a2) |
neg.l %d4 | R = -L = -(l/2 - r/2) = r/2 - l/2
move.l %d4, (%a3) |
movem.l (%sp), %d2-%d4/%a2-%a3 | restore registers
lea.l 20(%sp), %sp | cleanup
rts |
.size channel_mode_proc_karaoke, .-channel_mode_proc_karaoke
/****************************************************************************
* void filter_process(struct dsp_filter *f, int32_t *buf[], int count,
* unsigned int channels)
*
* define HIGH_PRECISION as '1' to make filtering calculate lower bits after
* shifting. without this, "shift" - 1 of the lower bits will be lost here.
*/
#define HIGH_PRECISION 0
.text
.global filter_process
filter_process:
| input: 4(sp) = f, 8(sp) = buf, 12(sp) = count, 16(sp) = channels
lea.l -44(%sp), %sp | save clobbered regs
#if HIGH_PRECISION
movem.l %d2-%d7/%a2-%a6, (%sp) | .
#else
movem.l %d2-%d6/%a2-%a6, (%sp) |
#endif
move.l 48(%sp), %a5 | fetch filter structure address
clr.l %d6 | load shift count
move.b 52(%a5), %d6 | .
subq.l #1, %d6 | EMAC gives us one free shift
#if HIGH_PRECISION
moveq.l #8, %d7
sub.l %d6, %d7 | shift for lower part of accumulator
#endif
movem.l (%a5), %a0-%a4 | load coefs
lea.l 20(%a5), %a5 | point to filter history
10: | channel loop
move.l 52(%sp), %a6 | load input channel pointer
addq.l #4, 52(%sp) | point x to next channel
move.l (%a6), %a6 |
move.l 56(%sp), %d5 | number of samples
movem.l (%a5), %d0-%d3 | load filter history
| d0-d3 = history, d4 = temp, d5 = sample count, d6 = upper shift amount,
| d7 = lower shift amount,a0-a4 = coefs, a5 = history pointer, a6 = buf[ch]
20: | loop
| Direct form 1 filtering code. We assume DSP has put EMAC in frac mode.
| y[n] = b0*x[i] + b1*x[i - 1] + b2*x[i - 2] + a1*y[i - 1] + a2*y[i - 2],
| where y[] is output and x[] is input. This is performed out of order
| to do parallel load of input value.
mac.l %a2, %d1, %acc0 | acc = b2*x[i - 2]
move.l %d0, %d1 | fix input history
mac.l %a1, %d0, (%a6), %d0, %acc0 | acc += b1*x[i - 1], x[i] -> d0
mac.l %a0, %d0, %acc0 | acc += b0*x[i]
mac.l %a3, %d2, %acc0 | acc += a1*y[i - 1]
mac.l %a4, %d3, %acc0 | acc += a2*y[i - 2]
move.l %d2, %d3 | fix output history
#if HIGH_PRECISION
move.l %accext01, %d2 | fetch lower part of accumulator
move.b %d2, %d4 | clear upper three bytes
lsr.l %d7, %d4 | shift lower bits
#endif
movclr.l %acc0, %d2 | fetch upper part of result
asl.l %d6, %d2 | restore fixed point format
#if HIGH_PRECISION
or.l %d2, %d4 | combine lower and upper parts
#endif
move.l %d2, (%a6)+ | save result
subq.l #1, %d5 | are we done with this channel?
bgt 20b | loop
movem.l %d0-%d3, (%a5) | save history back to struct
lea.l 16(%a5), %a5 | point to next channel's history
subq.l #1, 60(%sp) | have we processed both channels?
bhi 10b | channel loop
#if HIGH_PRECISION
movem.l (%sp), %d2-%d7/%a2-%a6
#else
movem.l (%sp), %d2-%d6/%a2-%a6
#endif
lea.l 44(%sp), %sp
rts
.size filter_process, .-filter_process
/****************************************************************************
* void sample_output_stereo(struct sample_io_data *this,
* struct dsp_buffer *src,
* struct dsp_buffer *dst)
*
* Framework based on the ubiquitous Rockbox line transfer logic for
* Coldfire CPUs.
*
* Does emac clamping and scaling (which proved faster than the usual
* checks and branches - even single test clamping) and writes using
* line burst transfers. Also better than writing a single L-R pair per
* loop but a good deal more code.
*
* Attemping bursting during reads is rather futile since the source and
* destination alignments rarely agree and too much complication will
* slow us up. The parallel loads seem to do a bit better at least until
* a pcm buffer can always give line aligned chunk and then aligning the
* dest can then imply the source is aligned if the source buffers are.
* For now longword alignment is assumed of both the source and dest.
*
*/
.section .text
.align 2
.global sample_output_stereo
sample_output_stereo:
| input: 4(sp) = count, 8(sp) = src, 12(sp) = dst
lea.l -48(%sp), %sp | save registers
move.l %macsr, %d1 | do it now as at many lines will
movem.l %d1-%d7/%a2-%a6, (%sp) | be the far more common condition
move.l #0x80, %macsr | put emac unit in signed int mode
movem.l 52(%sp), %a0-%a2 | %a0 = this, %a1 = src, %a2 = dst
move.l (%a0), %a0 | %a0 = this->outcount
move.l 4(%a2), %a4 | %a4 = dst->p16out
lea.l (%a4, %a0.l*4), %a0 | %a0 = count -> end address
movem.l 4(%a1), %a2-%a3 | %a2 = src->p32[0], %a3 = src->p32[1]
clr.l %d1 | %a1 = multiplier: (1 << (16 - scale))
move.b 19(%a1), %d1 | %d1 = src->format.output_scale
sub.l #16, %d1 |
neg.l %d1 |
moveq.l #1, %d0 |
asl.l %d1, %d0 |
move.l %d0, %a1 |
move.l #0x8000, %a6 | %a6 = rounding term
moveq.l #28, %d0 | %d0 = second line bound
add.l %a4, %d0 |
and.l #0xfffffff0, %d0 |
cmp.l %a0, %d0 | at least a full line?
bhi.w 40f | long loop 1 start | no? do as trailing longwords
sub.l #16, %d0 | %d1 = first line bound
cmp.l %a4, %d0 | any leading longwords?
bls.b 20f | line loop start | no? start line loop
10: | long loop 0 |
move.l (%a2)+, %d1 | read longword from L and R
move.l %a6, %acc0 |
move.l %acc0, %acc1 |
mac.l %d1, %a1, (%a3)+, %d2, %acc0 | shift L to high word
mac.l %d2, %a1, %acc1 | shift R to high word
movclr.l %acc0, %d1 | get possibly saturated results
movclr.l %acc1, %d2 |
swap.w %d2 | move R to low word
move.w %d2, %d1 | interleave MS 16 bits of each
move.l %d1, (%a4)+ | ...and write both
cmp.l %a4, %d0 |
bhi.b 10b | long loop 0 |
20: | line loop start |
lea.l -12(%a0), %a5 | %a5 = at or just before last line bound
30: | line loop |
move.l (%a3)+, %d4 | get next 4 R samples and scale
move.l %a6, %acc0 |
move.l %acc0, %acc1 |
move.l %acc1, %acc2 |
move.l %acc2, %acc3 |
mac.l %d4, %a1, (%a3)+, %d5, %acc0 | with saturation
mac.l %d5, %a1, (%a3)+, %d6, %acc1 |
mac.l %d6, %a1, (%a3)+, %d7, %acc2 |
mac.l %d7, %a1, (%a2)+, %d0, %acc3 |
lea.l 16(%a4), %a4 | increment dest here, mitigate stalls
movclr.l %acc0, %d4 | obtain R results
movclr.l %acc1, %d5 |
movclr.l %acc2, %d6 |
movclr.l %acc3, %d7 |
move.l %a6, %acc0 |
move.l %acc0, %acc1 |
move.l %acc1, %acc2 |
move.l %acc2, %acc3 |
mac.l %d0, %a1, (%a2)+, %d1, %acc0 | get next 4 L samples and scale
mac.l %d1, %a1, (%a2)+, %d2, %acc1 | with saturation
mac.l %d2, %a1, (%a2)+, %d3, %acc2 |
mac.l %d3, %a1 , %acc3 |
swap.w %d4 | a) interleave most significant...
swap.w %d5 |
swap.w %d6 |
swap.w %d7 |
movclr.l %acc0, %d0 | obtain L results
movclr.l %acc1, %d1 |
movclr.l %acc2, %d2 |
movclr.l %acc3, %d3 |
move.w %d4, %d0 | a) ... 16 bits of L and R
move.w %d5, %d1 |
move.w %d6, %d2 |
move.w %d7, %d3 |
movem.l %d0-%d3, -16(%a4) | write four stereo samples
cmp.l %a4, %a5 |
bhi.b 30b | line loop |
40: | long loop 1 start |
cmp.l %a4, %a0 | any longwords left?
bls.b 60f | output end | no? stop
50: | long loop 1 |
move.l (%a2)+, %d1 | handle trailing longwords
move.l %a6, %acc0 |
move.l %acc0, %acc1 |
mac.l %d1, %a1, (%a3)+, %d2, %acc0 | the same way as leading ones
mac.l %d2, %a1, %acc1 |
movclr.l %acc0, %d1 |
movclr.l %acc1, %d2 |
swap.w %d2 |
move.w %d2, %d1 |
move.l %d1, (%a4)+ |
cmp.l %a4, %a0 |
bhi.b 50b | long loop 1
60: | output end |
movem.l (%sp), %d1-%d7/%a2-%a6 | restore registers
move.l %d1, %macsr |
lea.l 48(%sp), %sp | cleanup
rts |
.size sample_output_stereo, .-sample_output_stereo
/****************************************************************************
* void sample_output_mono(struct sample_io_data *this,
* struct dsp_buffer *src,
* struct dsp_buffer *dst)
*
* Same treatment as sample_output_stereo but for one channel.
*/
.section .text
.align 2
.global sample_output_mono
sample_output_mono:
| input: 4(sp) = count, 8(sp) = src, 12(sp) = dst
lea.l -32(%sp), %sp | save registers
move.l %macsr, %d1 | do it now as at many lines will
movem.l %d1-%d5/%a2-%a4, (%sp) | be the far more common condition
move.l #0x80, %macsr | put emac unit in signed int mode
movem.l 36(%sp), %a0-%a2 | %a0 = this, %a1 = src, %a2 = dst
move.l (%a0), %a0 | %a0 = this->outcount
move.l 4(%a2), %a3 | %a3 = dst->p16out
movem.l 4(%a1), %a2 | %a2 = src->p32[0]
lea.l (%a3, %a0.l*4), %a0 | %a0 = count -> end address
clr.l %d1 | %d5 = multiplier: (1 << (16 - scale))
move.b 19(%a1), %d1 | %d1 = src->format.output_scale
sub.l #16, %d1 |
neg.l %d1 |
moveq.l #1, %d5 |
asl.l %d1, %d5 |
move.l #0x8000, %a4 | %a4 = rounding term
moveq.l #28, %d0 | %d0 = second line bound
add.l %a3, %d0 |
and.l #0xfffffff0, %d0 |
cmp.l %a0, %d0 | at least a full line?
bhi.w 40f | long loop 1 start | no? do as trailing longwords
sub.l #16, %d0 | %d1 = first line bound
cmp.l %a3, %d0 | any leading longwords?
bls.b 20f | line loop start | no? start line loop
10: | long loop 0 |
move.l (%a2)+, %d1 | read longword from L and R
move.l %a4, %acc0 |
mac.l %d1, %d5, %acc0 | shift L to high word
movclr.l %acc0, %d1 | get possibly saturated results
move.l %d1, %d2 |
swap.w %d2 | move R to low word
move.w %d2, %d1 | duplicate single channel into
move.l %d1, (%a3)+ | L and R
cmp.l %a3, %d0 |
bhi.b 10b | long loop 0 |
20: | line loop start |
lea.l -12(%a0), %a1 | %a1 = at or just before last line bound
30: | line loop |
move.l (%a2)+, %d0 | get next 4 L samples and scale
move.l %a4, %acc0 |
move.l %acc0, %acc1 |
move.l %acc1, %acc2 |
move.l %acc2, %acc3 |
mac.l %d0, %d5, (%a2)+, %d1, %acc0 | with saturation
mac.l %d1, %d5, (%a2)+, %d2, %acc1 |
mac.l %d2, %d5, (%a2)+, %d3, %acc2 |
mac.l %d3, %d5 , %acc3 |
lea.l 16(%a3), %a3 | increment dest here, mitigate stalls
movclr.l %acc0, %d0 | obtain results
movclr.l %acc1, %d1 |
movclr.l %acc2, %d2 |
movclr.l %acc3, %d3 |
move.l %d0, %d4 | duplicate single channel
swap.w %d4 | into L and R
move.w %d4, %d0 |
move.l %d1, %d4 |
swap.w %d4 |
move.w %d4, %d1 |
move.l %d2, %d4 |
swap.w %d4 |
move.w %d4, %d2 |
move.l %d3, %d4 |
swap.w %d4 |
move.w %d4, %d3 |
movem.l %d0-%d3, -16(%a3) | write four stereo samples
cmp.l %a3, %a1 |
bhi.b 30b | line loop |
40: | long loop 1 start |
cmp.l %a3, %a0 | any longwords left?
bls.b 60f | output end | no? stop
50: | loop loop 1 |
move.l (%a2)+, %d1 | handle trailing longwords
move.l %a4, %acc0 |
mac.l %d1, %d5, %acc0 | the same way as leading ones
movclr.l %acc0, %d1 |
move.l %d1, %d2 |
swap.w %d2 |
move.w %d2, %d1 |
move.l %d1, (%a3)+ |
cmp.l %a3, %a0 |
bhi.b 50b | long loop 1 |
60: | output end |
movem.l (%sp), %d1-%d5/%a2-%a4 | restore registers
move.l %d1, %macsr |
lea.l 32(%sp), %sp | cleanup
rts |
.size sample_output_mono, .-sample_output_mono
|
