Repository navigation
Expand file tree
/
Copy pathSDL_audiocvt.c
More file actions
1427 lines (1222 loc) · 50.6 KB
/
Copy pathSDL_audiocvt.c
File metadata and controls
1427 lines (1222 loc) · 50.6 KB
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
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
Simple DirectMedia Layer
Copyright (C) 1997-2023 Sam Lantinga <slouken@libsdl.org>
This software is provided 'as-is', without any
8000
express or implied
warranty. In no event will the authors be held liable for any damages
arising from the use of this software.
Permission is granted to anyone to use this software for any purpose,
including commercial applications, and to alter it and redistribute it
freely, subject to the following restrictions:
1. The origin of this software must not be misrepresented; you must not
claim that you wrote the original software. If you use this software
in a product, an acknowledgment in the product documentation would be
appreciated but is not required.
2. Altered source versions must be plainly marked as such, and must not be
misrepresented as being the original software.
3. This notice may not be removed or altered from any source distribution.
*/
#include "../SDL_internal.h"
/* Functions for audio drivers to perform runtime conversion of audio format */
#include "SDL.h"
#include "SDL_audio.h"
#include "SDL_audio_c.h"
#include "SDL_loadso.h"
#include "../SDL_dataqueue.h"
#include "SDL_cpuinfo.h"
#define DEBUG_AUDIOSTREAM 0
#ifdef __ARM_NEON
#define HAVE_NEON_INTRINSICS 1
#endif
#ifdef __SSE__
#define HAVE_SSE_INTRINSICS 1
#endif
#ifdef __SSE3__
#define HAVE_SSE3_INTRINSICS 1
#endif
#if defined(HAVE_IMMINTRIN_H) && !defined(SDL_DISABLE_IMMINTRIN_H)
#define HAVE_AVX_INTRINSICS 1
#endif
#if defined __clang__
#if (!__has_attribute(target))
#undef HAVE_AVX_INTRINSICS
#endif
#if (defined(_MSC_VER) || defined(__SCE__)) && !defined(__AVX__)
#undef HAVE_AVX_INTRINSICS
#endif
#elif defined __GNUC__
#if (__GNUC__ < 4) || (__GNUC__ == 4 && __GNUC_MINOR__ < 9)
#undef HAVE_AVX_INTRINSICS
#endif
#endif
/*
* CHANNEL LAYOUTS AS SDL EXPECTS THEM:
*
* (Even if the platform expects something else later, that
* SDL will swizzle between the app and the platform).
*
* Abbreviations:
* - FRONT=single mono speaker
* - FL=front left speaker
* - FR=front right speaker
* - FC=front center speaker
* - BL=back left speaker
* - BR=back right speaker
* - SR=surround right speaker
* - SL=surround left speaker
* - BC=back center speaker
* - LFE=low-frequency speaker
*
* These are listed in the order they are laid out in
* memory, so "FL+FR" means "the front left speaker is
* layed out in memory first, then the front right, then
* it repeats for the next audio frame".
*
* 1 channel (mono) layout: FRONT
* 2 channels (stereo) layout: FL+FR
* 3 channels (2.1) layout: FL+FR+LFE
* 4 channels (quad) layout: FL+FR+BL+BR
* 5 channels (4.1) layout: FL+FR+LFE+BL+BR
* 6 channels (5.1) layout: FL+FR+FC+LFE+BL+BR
* 7 channels (6.1) layout: FL+FR+FC+LFE+BC+SL+SR
* 8 channels (7.1) layout: FL+FR+FC+LFE+BL+BR+SL+SR
*/
#if HAVE_SSE3_INTRINSICS
/* Convert from stereo to mono. Average left and right. */
static void SDLCALL SDL_ConvertStereoToMono_SSE3(SDL_AudioCVT *cvt, SDL_AudioFormat format)
{
const __m128 divby2 = _mm_set1_ps(0.5f);
float *dst = (float *)cvt->buf;
const float *src = dst;
int i = cvt->len_cvt / 8;
LOG_DEBUG_CONVERT("stereo", "mono (using SSE3)");
SDL_assert(format == AUDIO_F32SYS);
/* Do SSE blocks as long as we have 16 bytes available.
Just use unaligned load/stores, if the memory at runtime is
aligned it'll be just as fast on modern processors */
while (i >= 4) { /* 4 * float32 */
_mm_storeu_ps(dst, _mm_mul_ps(_mm_hadd_ps(_mm_loadu_ps(src), _mm_loadu_ps(src + 4)), divby2));
i -= 4;
src += 8;
dst += 4;
}
/* Finish off any leftovers with scalar operations. */
while (i) {
*dst = (src[0] + src[1]) * 0.5f;
dst++;
i--;
src += 2;
}
cvt->len_cvt /= 2;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index](cvt, format);
}
}
#endif
#if HAVE_SSE_INTRINSICS
/* Convert from mono to stereo. Duplicate to stereo left and right. */
static void SDLCA
8000
LL SDL_ConvertMonoToStereo_SSE(SDL_AudioCVT *cvt, SDL_AudioFormat format)
{
float *dst = ((float *)(cvt->buf + (cvt->len_cvt * 2))) - 8;
const float *src = ((const float *)(cvt->buf + cvt->len_cvt)) - 4;
int i = cvt->len_cvt / sizeof(float);
LOG_DEBUG_CONVERT("mono", "stereo (using SSE)");
SDL_assert(format == AUDIO_F32SYS);
/* Do SSE blocks as long as we have 16 bytes available.
Just use unaligned load/stores, if the memory at runtime is
aligned it'll be just as fast on modern processors */
/* convert backwards, since output is growing in-place. */
while (i >= 4) { /* 4 * float32 */
const __m128 input = _mm_loadu_ps(src); /* A B C D */
_mm_storeu_ps(dst, _mm_unpacklo_ps(input, input)); /* A A B B */
_mm_storeu_ps(dst + 4, _mm_unpackhi_ps(input, input)); /* C C D D */
i -= 4;
src -= 4;
dst -= 8;
}
/* Finish off any leftovers with scalar operations. */
src += 3;
dst += 6; /* adjust for smaller buffers. */
while (i) { /* convert backwards, since output is growing in-place. */
const float srcFC = src[0];
dst[1] /* FR */ = srcFC;
dst[0] /* FL */ = srcFC;
i--;
src--;
dst -= 2;
}
cvt->len_cvt *= 2;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index](cvt, format);
}
}
#endif
/* Include the autogenerated channel converters... */
#include "SDL_audio_channel_converters.h"
/* SDL's resampler uses a "bandlimited interpolation" algorithm:
https://ccrma.stanford.edu/~jos/resample/ */
#include "SDL_audio_resampler_filter.h"
static Sint32 ResamplerPadding(const Sint32 inrate, const Sint32 outrate)
{
/* This function uses integer arithmetics to avoid precision loss caused
* by large floating point numbers. Sint32 is needed for the large number
* multiplication. The integers are assumed to be non-negative so that
* division rounds by truncation. */
if (inrate == outrate) {
return 0;
}
if (inrate > outrate) {
return (RESAMPLER_SAMPLES_PER_ZERO_CROSSING * inrate + outrate - 1) / outrate;
}
return RESAMPLER_SAMPLES_PER_ZERO_CROSSING;
}
/* lpadding and rpadding are expected to be buffers of (ResamplePadding(inrate, outrate) * chans * sizeof(float)) bytes. */
static int SDL_ResampleAudio(const int chans, const int inrate, const int outrate,
const float *lpadding, const float *rpadding,
const float *inbuf, const int inbuflen,
float *outbuf, const int outbuflen)
{
/* This function uses integer arithmetics to avoid precision loss caused
* by large floating point numbers. For some operations, Sint32 or Sint64
* are needed for the large number multiplications. The input integers are
* assumed to be non-negative so that division rounds by truncation and
* modulo is always non-negative. Note that the operator order is important
* for these integer divisions. */
const int paddinglen = ResamplerPadding(inrate, outrate);
const int framelen = chans * (int)sizeof(float);
const int inframes = inbuflen / framelen;
/* outbuflen isn't total to write, it's total available. */
const int wantedoutframes = (int)((Sint64)inframes * outrate / inrate);
const int maxoutframes = outbuflen / framelen;
const int outframes = SDL_min(wantedoutframes, maxoutframes);
float *dst = outbuf;
int i, j, chan;
for (i = 0; i < outframes; i++) {
const int srcindex = (int)((Sint64)i * inrate / outrate);
/* Calculating the following way avoids subtraction or modulo of large
* floats which have low result precision.
* interpolation1
* = (i / outrate * inrate) - floor(i / outrate * inrate)
* = mod(i / outrate * inrate, 1)
* = mod(i * inrate, outrate) / outrate */
const int srcfraction = ((Sint64)i) * inrate % outrate;
const float interpolation1 = ((float)srcfraction) / ((float)outrate);
const int filterindex1 = ((Sint32)srcfraction) * RESAMPLER_SAMPLES_PER_ZERO_CROSSING / outrate;
const float interpolation2 = 1.0f - interpolation1;
const int filterindex2 = ((Sint32)(outrate - srcfraction)) * RESAMPLER_SAMPLES_PER_ZERO_CROSSING / outrate;
for (chan = 0; chan < chans; chan++) {
float outsample = 0.0f;
/* do this twice to calculate the sample, once for the "left wing" and then same for the right. */
for (j = 0; (filterindex1 + (j * RESAMPLER_SAMPLES_PER_ZERO_CROSSING)) < RESAMPLER_FILTER_SIZE; j++) {
const int filt_ind = filterindex1 + j * RESAMPLER_SAMPLES_PER_ZERO_CROSSING;
const int srcframe = srcindex - j;
/* !!! FIXME: we can bubble this conditional out of here by doing a pre loop. */
const float insample = (srcframe < 0) ? lpadding[((paddinglen + srcframe) * chans) + chan] : inbuf[(srcframe * chans) + chan];
outsample += (float) (insample * (ResamplerFilter[filt_ind] + (interpolation1 * ResamplerFilterDifference[filt_ind])));
}
/* Do the right wing! */
for (j = 0; (filterindex2 + (j * RESAMPLER_SAMPLES_PER_ZERO_CROSSING)) < RESAMPLER_FILTER_SIZE; j++) {
const int filt_ind = filterindex2 + j * RESAMPLER_SAMPLES_PER_ZERO_CROSSING;
const int srcframe = srcindex + 1 + j;
/* !!! FIXME: we can bubble this conditional out of here by doing a post loop. */
const float insample = (srcframe >= inframes) ? rpadding[((srcframe - inframes) * chans) + chan] : inbuf[(srcframe * chans) + chan];
outsample += (float) (insample * (ResamplerFilter[filt_ind] + (interpolation2 * ResamplerFilterDifference[filt_ind])));
}
*(dst++) = outsample;
}
}
return outframes * chans * sizeof(float);
}
int SDL_ConvertAudio(SDL_AudioCVT *cvt)
{
/* !!! FIXME: (cvt) should be const; stack-copy it here. */
/* !!! FIXME: (actually, we can't...len_cvt needs to be updated. Grr.) */
/* Make sure there's data to convert */
if (cvt->buf == NULL) {
return SDL_SetError("No buffer allocated for conversion");
}
/* Return okay if no conversion is necessary */
cvt->len_cvt = cvt->len;
if (cvt->filters[0] == NULL) {
return 0;
}
/* Set up the conversion and go! */
cvt->filter_index = 0;
cvt->filters[0](cvt, cvt->src_format);
return 0;
}
static void SDLCALL SDL_Convert_Byteswap(SDL_AudioCVT *cvt, SDL_AudioFormat format)
{
#if DEBUG_CONVERT
SDL_Log("SDL_AUDIO_CONVERT: Converting byte order\n");
#endif
switch (SDL_AUDIO_BITSIZE(format)) {
#define CASESWAP(b) \
case b: \
{ \
Uint##b *ptr = (Uint##b *)cvt->buf; \
int i; \
for (i = cvt->len_cvt / sizeof(*ptr); i; --i, ++ptr) { \
*ptr = SDL_Swap##b(*ptr); \
} \
break; \
}
CASESWAP(16);
CASESWAP(32);
CASESWAP(64);
#undef CASESWAP
default:
SDL_assert(!"unhandled byteswap datatype!");
break;
}
if (cvt->filters[++cvt->filter_index]) {
/* flip endian flag for data. */
if (format & SDL_AUDIO_MASK_ENDIAN) {
format &= ~SDL_AUDIO_MASK_ENDIAN;
} else {
format |= SDL_AUDIO_MASK_ENDIAN;
}
cvt->filters[cvt->filter_index](cvt, format);
}
}
static int SDL_AddAudioCVTFilter(SDL_AudioCVT *cvt, SDL_AudioFilter filter)
{
if (cvt->filter_index >= SDL_AUDIOCVT_MAX_FILTERS) {
return SDL_SetError("Too many filters needed for conversion, exceeded maximum of %d", SDL_AUDIOCVT_MAX_FILTERS);
}
SDL_assert(filter != NULL);
cvt->filters[cvt->filter_index++] = filter;
cvt->filters[cvt->filter_index] = NULL; /* Moving terminator */
return 0;
}
static int SDL_BuildAudioTypeCVTToFloat(SDL_AudioCVT *cvt, const SDL_AudioFormat src_fmt)
{
int retval = 0; /* 0 == no conversion necessary. */
if ((SDL_AUDIO_ISBIGENDIAN(src_fmt) != 0) == (SDL_BYTEORDER == SDL_LIL_ENDIAN) && SDL_AUDIO_BITSIZE(src_fmt) > 8) {
if (SDL_AddAudioCVTFilter(cvt, SDL_Convert_Byteswap) < 0) {
return -1;
}
retval = 1; /* added a converter. */
}
if (!SDL_AUDIO_ISFLOAT(src_fmt)) {
const Uint16 src_bitsize = SDL_AUDIO_BITSIZE(src_fmt);
const Uint16 dst_bitsize = 32;
SDL_AudioFilter filter = NULL;
switch (src_fmt & ~SDL_AUDIO_MASK_ENDIAN) {
case AUDIO_S8:
filter = SDL_Convert_S8_to_F32;
break;
case AUDIO_U8:
filter = SDL_Convert_U8_to_F32;
break;
case AUDIO_S16:
filter = SDL_Convert_S16_to_F32;
break;
case AUDIO_U16:
filter = SDL_Convert_U16_to_F32;
break;
case AUDIO_S32:
filter = SDL_Convert_S32_to_F32;
break;
default:
SDL_assert(!"Unexpected audio format!");
break;
}
if (!filter) {
return SDL_SetError("No conversion from source format to float available");
}
if (SDL_AddAudioCVTFilter(cvt, filter) < 0) {
return -1;
}
if (src_bitsize < dst_bitsize) {
const int mult = (dst_bitsize / src_bitsize);
cvt->len_mult *= mult;
cvt->len_ratio *= mult;
} else if (src_bitsize > dst_bitsize) {
const int div = (src_bitsize / dst_bitsize);
cvt->len_ratio /= div;
}
retval = 1; /* added a converter. */
}
return retval;
}
static int SDL_BuildAudioTypeCVTFromFloat(SDL_AudioCVT *cvt, const SDL_AudioFormat dst_fmt)
{
int retval = 0; /* 0 == no conversion necessary. */
if (!SDL_AUDIO_ISFLOAT(dst_fmt)) {
const Uint16 dst_bitsize = SDL_AUDIO_BITSIZE(dst_fmt);
const Uint16 src_bitsize = 32;
SDL_AudioFilter filter = NULL;
switch (dst_fmt & ~SDL_AUDIO_MASK_ENDIAN) {
case AUDIO_S8:
filter = SDL_Convert_F32_to_S8;
break;
case AUDIO_U8:
filter = SDL_Convert_F32_to_U8;
break;
case AUDIO_S16:
filter = SDL_Convert_F32_to_S16;
break;
case AUDIO_U16:
filter = SDL_Convert_F32_to_U16;
break;
case AUDIO_S32:
filter = SDL_Convert_F32_to_S32;
break;
default:
SDL_assert(!"Unexpected audio format!");
break;
}
if (!filter) {
return SDL_SetError("No conversion from float to format 0x%.4x available", dst_fmt);
}
if (SDL_AddAudioCVTFilter(cvt, filter) < 0) {
return -1;
}
if (src_bitsize < dst_bitsize) {
const int mult = (dst_bitsize / src_bitsize);
cvt->len_mult *= mult;
cvt->len_ratio *= mult;
} else if (src_bitsize > dst_bitsize) {
const int div = (src_bitsize / dst_bitsize);
cvt->len_ratio /= div;
}
retval = 1; /* added a converter. */
}
if ((SDL_AUDIO_ISBIGENDIAN(dst_fmt) != 0) == (SDL_BYTEORDER == SDL_LIL_ENDIAN) && SDL_AUDIO_BITSIZE(dst_fmt) > 8) {
if (SDL_AddAudioCVTFilter(cvt, SDL_Convert_Byteswap) < 0) {
return -1;
}
retval = 1; /* added a converter. */
}
return retval;
}
#ifdef HAVE_LIBSAMPLERATE_H
static void SDL_ResampleCVT_SRC(SDL_AudioCVT *cvt, const int chans, const SDL_AudioFormat format)
{
const float *src = (const float *)cvt->buf;
const int srclen = cvt->len_cvt;
float *dst = (float *)(cvt->buf + srclen);
const int dstlen = (cvt->len * cvt->len_mult) - srclen;
const int framelen = sizeof(float) * chans;
int result = 0;
SRC_DATA data;
SDL_zero(data);
data.data_in = (float *)src; /* Older versions of libsamplerate had a non-const pointer, but didn't write to it */
data.input_frames = srclen / framelen;
data.data_out = dst;
data.output_frames = dstlen / framelen;
data.src_ratio = cvt->rate_incr;
result = SRC_src_simple(&data, SRC_converter, chans); /* Simple API converts the whole buffer at once. No need for initialization. */
/* !!! FIXME: Handle library failures? */
#ifdef DEBUG_CONVERT
if (result != 0) {
SDL_Log("src_simple() failed: %s", SRC_src_strerror(result));
}
#endif
cvt->len_cvt = data.output_frames_gen * framelen;
SDL_memmove(cvt->buf, dst, cvt->len_cvt);
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index](cvt, format);
}
}
#endif /* HAVE_LIBSAMPLERATE_H */
static void SDL_ResampleCVT(SDL_AudioCVT *cvt, const int chans, const SDL_AudioFormat format)
{
/* !!! FIXME in 2.1: there are ten slots in the filter list, and the theoretical maximum we use is six (seven with NULL terminator).
!!! FIXME in 2.1: We need to store data for this resampler, because the cvt structure doesn't store the original sample rates,
!!! FIXME in 2.1: so we steal the ninth and tenth slot. :( */
const int inrate = (int)(size_t)cvt->filters[SDL_AUDIOCVT_MAX_FILTERS - 1];
const int outrate = (int)(size_t)cvt->filters[SDL_AUDIOCVT_MAX_FILTERS];
const float *src = (const float *)cvt->buf;
const int srclen = cvt->len_cvt;
/*float *dst = (float *) cvt->buf;
const int dstlen = (cvt->len * cvt->len_mult);*/
/* !!! FIXME: remove this if we can get the resampler to work in-place again. */
float *dst = (float *)(cvt->buf + srclen);
const int dstlen = (cvt->len * cvt->len_mult) - srclen;
const int requestedpadding = ResamplerPadding(inrate, outrate);
int paddingsamples;
float *padding;
if (requestedpadding < SDL_MAX_SINT32 / chans) {
paddingsamples = requestedpadding * chans;
} else {
paddingsamples = 0;
}
SDL_assert(format == AUDIO_F32SYS);
/* we keep no streaming state here, so pad with silence on both ends. */
padding = (float *)SDL_calloc(paddingsamples ? paddingsamples : 1, sizeof(float));
if (padding == NULL) {
SDL_OutOfMemory();
return;
}
cvt->len_cvt = SDL_ResampleAudio(chans, inrate, outrate, padding, padding, src, srclen, dst, dstlen);
SDL_free(padding);
SDL_memmove(cvt->buf, dst, cvt->len_cvt); /* !!! FIXME: remove this if we can get the resampler to work in-place again. */
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index](cvt, format);
}
}
/* !!! FIXME: We only have this macro salsa because SDL_AudioCVT doesn't
!!! FIXME: store channel info, so we have to have function entry
!!! FIXME: points for each supported channel count and multiple
!!! FIXME: vs arbitrary. When we rev the ABI, clean this up. */
#define RESAMPLER_FUNCS(chans) \
static void SDLCALL \
SDL_ResampleCVT_c##chans(SDL_AudioCVT *cvt, SDL_AudioFormat format) \
{ \
SDL_ResampleCVT(cvt, chans, format); \
}
RESAMPLER_FUNCS(1)
RESAMPLER_FUNCS(2)
RESAMPLER_FUNCS(4)
RESAMPLER_FUNCS(6)
RESAMPLER_FUNCS(8)
#undef RESAMPLER_FUNCS
#ifdef HAVE_LIBSAMPLERATE_H
#define RESAMPLER_FUNCS(chans) \
static void SDLCALL \
SDL_ResampleCVT_SRC_c##chans(SDL_AudioCVT *cvt, SDL_AudioFormat format) \
{ \
SDL_ResampleCVT_SRC(cvt, chans, format); \
}
RESAMPLER_FUNCS(1)
RESAMPLER_FUNCS(2)
RESAMPLER_FUNCS(4)
RESAMPLER_FUNCS(6)
RESAMPLER_FUNCS(8)
#undef RESAMPLER_FUNCS
#endif /* HAVE_LIBSAMPLERATE_H */
static SDL_AudioFilter ChooseCVTResampler(const int dst_channels)
{
#ifdef HAVE_LIBSAMPLERATE_H
if (SRC_available) {
switch (dst_channels) {
case 1:
return SDL_ResampleCVT_SRC_c1;
case 2:
return SDL_ResampleCVT_SRC_c2;
case 4:
return SDL_ResampleCVT_SRC_c4;
case 6:
return SDL_ResampleCVT_SRC_c6;
case 8:
return SDL_ResampleCVT_SRC_c8;
default:
break;
}
}
#endif /* HAVE_LIBSAMPLERATE_H */
switch (dst_channels) {
case 1:
return SDL_ResampleCVT_c1;
case 2:
return SDL_ResampleCVT_c2;
case 4:
return SDL_ResampleCVT_c4;
case 6:
return SDL_ResampleCVT_c6;
case 8:
return SDL_ResampleCVT_c8;
default:
break;
}
return NULL;
}
static int SDL_BuildAudioResampleCVT(SDL_AudioCVT *cvt, const int dst_channels,
const int src_rate, const int dst_rate)
{
SDL_AudioFilter filter;
if (src_rate == dst_rate) {
return 0; /* no conversion necessary. */
}
filter = ChooseCVTResampler(dst_channels);
if (filter == NULL) {
return SDL_SetError("No conversion available for these rates");
}
/* Update (cvt) with filter details... */
if (SDL_AddAudioCVTFilter(cvt, filter) < 0) {
return -1;
}
/* !!! FIXME in 2.1: there are ten slots in the filter list, and the theoretical maximum we use is six (seven with NULL terminator).
!!! FIXME in 2.1: We need to store data for this resampler, because the cvt structure doesn't store the original sample rates,
!!! FIXME in 2.1: so we steal the ninth and tenth slot. :( */
if (cvt->filter_index >= (SDL_AUDIOCVT_MAX_FILTERS - 2)) {
return SDL_SetError("Too many filters needed for conversion, exceeded maximum of %d", SDL_AUDIOCVT_MAX_FILTERS - 2);
}
cvt->filters[SDL_AUDIOCVT_MAX_FILTERS - 1] = (SDL_AudioFilter)(uintptr_t)src_rate;
cvt->filters[SDL_AUDIOCVT_MAX_FILTERS] = (SDL_AudioFilter)(uintptr_t)dst_rate;
if (src_rate < dst_rate) {
const double mult = ((double)dst_rate) / ((double)src_rate);
cvt->len_mult *= (int)SDL_ceil(mult);
cvt->len_ratio *= mult;
} else {
cvt->len_ratio /= ((double)src_rate) / ((double)dst_rate);
}
/* !!! FIXME: remove this if we can get the resampler to work in-place again. */
/* the buffer is big enough to hold the destination now, but
we need it large enough to hold a separate scratch buffer. */
cvt->len_mult *= 2;
return 1; /* added a converter. */
}
static SDL_bool SDL_SupportedAudioFormat(const SDL_AudioFormat fmt)
{
switch (fmt) {
case AUDIO_U8:
case AUDIO_S8:
case AUDIO_U16LSB:
case AUDIO_S16LSB:
case AUDIO_U16MSB:
case AUDIO_S16MSB:
case AUDIO_S32LSB:
case AUDIO_S32MSB:
case AUDIO_F32LSB:
case AUDIO_F32MSB:
return SDL_TRUE; /* supported. */
default:
break;
}
return SDL_FALSE; /* unsupported. */
}
static SDL_bool SDL_SupportedChannelCount(const int channels)
{
return ((channels >= 1) && (channels <= 8)) ? SDL_TRUE : SDL_FALSE;
}
/* Creates a set of audio filters to convert from one format to another.
Returns 0 if no conversion is needed, 1 if the audio filter is set up,
or -1 if an error like invalid parameter, unsupported format, etc. occurred.
*/
int SDL_BuildAudioCVT(SDL_AudioCVT *cvt,
SDL_AudioFormat src_format, Uint8 src_channels, int src_rate,
SDL_AudioFormat dst_format, Uint8 dst_channels, int dst_rate)
{
SDL_AudioFilter channel_converter = NULL;
/* Sanity check target pointer */
if (cvt == NULL) {
return SDL_InvalidParamError("cvt");
}
/* Make sure we zero out the audio conversion before error checking */
SDL_zerop(cvt);
if (!SDL_SupportedAudioFormat(src_format)) {
return SDL_SetError("Invalid source format");
}
if (!SDL_SupportedAudioFormat(dst_format)) {
return SDL_SetError("Invalid destination format");
}
if (!SDL_SupportedChannelCount(src_channels)) {
return SDL_SetError("Invalid source channels");
}
if (!SDL_SupportedChannelCount(dst_channels)) {
return SDL_SetError("Invalid destination channels");
}
if (src_rate <= 0) {
return SDL_SetError("Source rate is equal to or less than zero");
}
if (dst_rate <= 0) {
return SDL_SetError("Destination rate is equal to or less than zero");
}
if (src_rate >= SDL_MAX_SINT32 / RESAMPLER_SAMPLES_PER_ZERO_CROSSING) {
return SDL_SetError("Source rate is too high");
}
if (dst_rate >= SDL_MAX_SINT32 / RESAMPLER_SAMPLES_PER_ZERO_CROSSING) {
return SDL_SetError("Destination rate is too high");
}
#if DEBUG_CONVERT
SDL_Log("SDL_AUDIO_CONVERT: Build format %04x->%04x, channels %u->%u, rate %d->%d\n",
src_format, dst_format, src_channels, dst_channels, src_rate, dst_rate);
#endif
/* Start off with no conversion necessary */
cvt->src_format = src_format;
cvt->dst_format = dst_format;
cvt->needed = 0;
cvt->filter_index = 0;
SDL_zeroa(cvt->filters);
cvt->len_mult = 1;
cvt->len_ratio = 1.0;
cvt->rate_incr = ((double)dst_rate) / ((double)src_rate);
/* Make sure we've chosen audio conversion functions (SIMD, scalar, etc.) */
SDL_ChooseAudioConverters();
/* Type conversion goes like this now:
- byteswap to CPU native format first if necessary.
- convert to native Float32 if necessary.
- resample and change channel count if necessary.
- convert to final data format.
- byteswap back to foreign format if necessary.
The expectation is we can process data faster in float32
(possibly with SIMD), and making several passes over the same
buffer is likely to be CPU cache-friendly, avoiding the
biggest performance hit in modern times. Previously we had
(script-generated) custom converters for every data type and
it was a bloat on SDL compile times and final library size. */
/* see if we can skip float conversion entirely. */
if (src_rate == dst_rate && src_channels == dst_channels) {
if (src_format == dst_format) {
return 0;
}
/* just a byteswap needed? */
if ((src_format & ~SDL_AUDIO_MASK_ENDIAN) == (dst_format & ~SDL_AUDIO_MASK_ENDIAN)) {
if (SDL_AUDIO_BITSIZE(dst_format) == 8) {
return 0;
}
if (SDL_AddAudioCVTFilter(cvt, SDL_Convert_Byteswap) < 0) {
return -1;
}
cvt->needed = 1;
return 1;
}
}
/* Convert data types, if necessary. Updates (cvt). */
if (SDL_BuildAudioTypeCVTToFloat(cvt, src_format) < 0) {
return -1; /* shouldn't happen, but just in case... */
}
/* Channel conversion */
/* SDL_SupportedChannelCount should have caught these asserts, or we added a new format and forgot to update the table. */
SDL_assert(src_channels <= SDL_arraysize(channel_converters));
SDL_assert(dst_channels <= SDL_arraysize(channel_converters[0]));
channel_converter = channel_converters[src_channels - 1][dst_channels - 1];
if ((channel_converter == NULL) != (src_channels == dst_channels)) {
/* All combinations of supported channel counts should have been handled by now, but let's be defensive */
return SDL_SetError("Invalid channel combination");
} else if (channel_converter != NULL) {
/* swap in some SIMD versions for a few of these. */
if (channel_converter == SDL_ConvertStereoToMono) {
SDL_AudioFilter filter = NULL;
#if HAVE_SSE3_INTRINSICS
if (!filter && SDL_HasSSE3()) {
filter = SDL_ConvertStereoToMono_SSE3;
}
#endif
if (filter) {
channel_converter = filter;
}
} else if (channel_converter == SDL_ConvertMonoToStereo) {
SDL_AudioFilter filter = NULL;
#if HAVE_SSE_INTRINSICS
if (!filter && SDL_HasSSE()) {
filter = SDL_ConvertMonoToStereo_SSE;
}
#endif
if (filter) {
channel_converter = filter;
}
}
if (SDL_AddAudioCVTFilter(cvt, channel_converter) < 0) {
return -1;
}
if (src_channels < dst_channels) {
cvt->len_mult = ((cvt->len_mult * dst_channels) + (src_channels - 1)) / src_channels;
}
cvt->len_ratio = (cvt->len_ratio * dst_channels) / src_channels;
src_channels = dst_channels;
}
/* Do rate conversion, if necessary. Updates (cvt). */
if (SDL_BuildAudioResampleCVT(cvt, dst_channels, src_rate, dst_rate) < 0) {
return -1; /* shouldn't happen, but just in case... */
}
/* Move to final data type. */
if (SDL_BuildAudioTypeCVTFromFloat(cvt, dst_format) < 0) {
return -1; /* shouldn't happen, but just in case... */
}
cvt->needed = (cvt->filter_index != 0);
return cvt->needed;
}
typedef int (*SDL_ResampleAudioStreamFunc)(SDL_AudioStream *stream, const void *inbuf, const int inbuflen, void *outbuf, const int outbuflen);
typedef void (*SDL_ResetAudioStreamResamplerFunc)(SDL_AudioStream *stream);
typedef void (*SDL_CleanupAudioStreamResamplerFunc)(SDL_AudioStream *stream);
struct _SDL_AudioStream
{
SDL_AudioCVT cvt_before_resampling;
SDL_AudioCVT cvt_after_resampling;
SDL_DataQueue *queue;
SDL_bool first_run;
Uint8 *staging_buffer;
int staging_buffer_size;
int staging_buffer_filled;
Uint8 *work_buffer_base; /* maybe unaligned pointer from SDL_realloc(). */
int work_buffer_len;
int src_sample_frame_size;
SDL_AudioFormat src_format;
Uint8 src_channels;
int src_rate;
int dst_sample_frame_size;
SDL_AudioFormat dst_format;
Uint8 dst_channels;
int dst_rate;
double rate_incr;
Uint8 pre_resample_channels;
int packetlen;
int resampler_padding_samples;
float *resampler_padding;
void *resampler_state;
SDL_ResampleAudioStreamFunc resampler_func;
SDL_ResetAudioStreamResamplerFunc reset_resampler_func;
SDL_CleanupAudioStreamResamplerFunc cleanup_resampler_func;
};
static Uint8 *EnsureStreamBufferSize(SDL_AudioStream *stream, int newlen)
{
Uint8 *ptr;
size_t offset;
if (stream->work_buffer_len >= newlen) {
ptr = stream->work_buffer_base;
} else {
ptr = (Uint8 *)SDL_realloc(stream->work_buffer_base, (size_t)newlen + 32);
if (ptr == NULL) {
SDL_OutOfMemory();
return NULL;
}
/* Make sure we're aligned to 16 bytes for SIMD code. */
stream->work_buffer_base = ptr;
stream->work_buffer_len = newlen;
}
offset = ((size_t)ptr) & 15;
return offset ? ptr + (16 - offset) : ptr;
}
#ifdef HAVE_LIBSAMPLERATE_H
static int SDL_ResampleAudioStream_SRC(SDL_AudioStream *stream, const void *_inbuf, const int inbuflen, void *_outbuf, const int outbuflen)
{
const float *inbuf = (const float *)_inbuf;
float *outbuf = (float *)_outbuf;
const int framelen = sizeof(float) * stream->pre_resample_channels;
SRC_STATE *state = (SRC_STATE *)stream->resampler_state;
SRC_DATA data;
int result;
SDL_assert(inbuf != ((const float *)outbuf)); /* SDL_AudioStreamPut() shouldn't allow in-place resamples. */
data.data_in = (float *)inbuf; /* Older versions of libsamplerate had a non-const pointer, but didn't write to it */
data.input_frames = inbuflen / framelen;
data.input_frames_used = 0;
data.data_out = outbuf;
data.output_frames = outbuflen / framelen;
data.end_of_input = 0;
data.src_ratio = stream->rate_incr;
result = SRC_src_process(state, &data);
if (result != 0) {
SDL_SetError("src_process() failed: %s", SRC_src_strerror(result));
return 0;
}
/* If this fails, we need to store them off somewhere */
SDL_assert(data.input_frames_used == data.input_frames);
return data.output_frames_gen * (sizeof(float) * stream->pre_resample_channels);
}
static void SDL_ResetAudioStreamResampler_SRC(SDL_AudioStream *stream)
{
SRC_src_reset((SRC_STATE *)stream->resampler_state);
}
static void SDL_CleanupAudioStreamResampler_SRC(SDL_AudioStream *stream)
{
SRC_STATE *state = (SRC_STATE *)stream->resampler_state;
if (state) {
SRC_src_delete(state);
}
stream->resampler_state = NULL;
stream->resampler_func = NULL;
stream->reset_resampler_func = NULL;
stream->cleanup_resampler_func = NULL;
}
static SDL_bool SetupLibSampleRateResampling(SDL_AudioStream *stream)
{
int result = 0;
SRC_STATE *state = NULL;
if (SRC_available) {
state = SRC_src_new(SRC_converter, stream->pre_resample_channels, &result);
if (state == NULL) {
SDL_SetError("src_new() failed: %s", SRC_src_strerror(result));
}
}
if (state == NULL) {
SDL_CleanupAudioStreamResampler_SRC(stream);
return SDL_FALSE;
}
stream->resampler_state = state;
stream->resampler_func = SDL_ResampleAudioStream_SRC;
stream->reset_resampler_func = SDL_ResetAudioStreamResampler_SRC;
stream->cleanup_resampler_func = SDL_CleanupAudioStreamResampler_SRC;
return SDL_TRUE;
}
#endif /* HAVE_LIBSAMPLERATE_H */
static int SDL_ResampleAudioStream(SDL_AudioStream *stream, const void *_inbuf, const int inbuflen, void *_outbuf, const int outbuflen)
{
const Uint8 *inbufend = ((const Uint8 *)_inbuf) + inbuflen;
const float *inbuf = (const float *)_inbuf;
float *outbuf = (float *)_outbuf;
const int chans = (int)stream->pre_resample_channels;
const int inrate = stream->src_rate;
const int outrate = stream->dst_rate;
const int paddingsamples = stream->resampler_padding_samples;
const int paddingbytes = paddingsamples * sizeof(float);
float *lpadding = (float *)stream->resampler_state;
const float *rpadding = (const float *)inbufend; /* we set this up so there are valid padding samples at the end of the input buffer. */
const int cpy = SDL_min(inbuflen, paddingbytes);
int retval;
SDL_assert(inbuf != ((const float *)outbuf)); /* SDL_AudioStreamPut() shouldn't allow in-place resamples. */
retval = SDL_ResampleAudio(chans, inrate, outrate, lpadding, rpadding, inbuf, inbuflen, outbuf, outbuflen);
/* update our left padding with end of current input, for next run. */
SDL_memcpy((lpadding + paddingsamples) - (cpy / sizeof(float)), inbufend - cpy, cpy);
return retval;
}
static void SDL_ResetAudioStreamResampler(SDL_AudioStream *stream)
{
/* set all the padding to silence. */
const int len = stream->resampler_padding_samples;
SDL_memset(stream->resampler_state, '\0', len * sizeof(float));