/
SDL_audiocvt.c
1481 lines (1269 loc) · 49.8 KB
1
2
/*
Simple DirectMedia Layer
3
Copyright (C) 1997-2017 Sam Lantinga <slouken@libsdl.org>
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
This software is provided 'as-is', without any 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 */
25
#include "SDL.h"
26
27
28
#include "SDL_audio.h"
#include "SDL_audio_c.h"
29
#include "SDL_loadso.h"
30
#include "SDL_assert.h"
31
#include "../SDL_dataqueue.h"
32
33
#include "SDL_cpuinfo.h"
34
35
#ifdef __SSE3__
#define HAVE_SSE3_INTRINSICS 1
36
37
38
#endif
#if HAVE_SSE3_INTRINSICS
39
/* Convert from stereo to mono. Average left and right. */
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
static void SDLCALL
SDL_ConvertStereoToMono_SSE3(SDL_AudioCVT * cvt, SDL_AudioFormat format)
{
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);
/* We can only do this if dst is aligned to 16 bytes; since src is the
same pointer and it moves by 2, it can't be forcibly aligned. */
if ((((size_t) dst) & 15) == 0) {
/* Aligned! Do SSE blocks as long as we have 16 bytes available. */
const __m128 divby2 = _mm_set1_ps(0.5f);
while (i >= 4) { /* 4 * float32 */
_mm_store_ps(dst, _mm_mul_ps(_mm_hadd_ps(_mm_load_ps(src), _mm_load_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
74
/* Convert from stereo to mono. Average left and right. */
75
static void SDLCALL
76
SDL_ConvertStereoToMono(SDL_AudioCVT * cvt, SDL_AudioFormat format)
77
{
78
79
float *dst = (float *) cvt->buf;
const float *src = dst;
80
81
int i;
82
83
84
85
LOG_DEBUG_CONVERT("stereo", "mono");
SDL_assert(format == AUDIO_F32SYS);
for (i = cvt->len_cvt / 8; i; --i, src += 2) {
86
*(dst++) = (src[0] + src[1]) * 0.5f;
87
88
89
90
91
92
93
94
95
}
cvt->len_cvt /= 2;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
96
/* Convert from 5.1 to stereo. Average left and right, distribute center, discard LFE. */
97
static void SDLCALL
98
SDL_Convert51ToStereo(SDL_AudioCVT * cvt, SDL_AudioFormat format)
99
{
100
101
float *dst = (float *) cvt->buf;
const float *src = dst;
102
103
int i;
104
LOG_DEBUG_CONVERT("5.1", "stereo");
105
SDL_assert(format == AUDIO_F32SYS);
106
107
/* SDL's 5.1 layout: FL+FR+FC+LFE+BL+BR */
108
for (i = cvt->len_cvt / (sizeof (float) * 6); i; --i, src += 6, dst += 2) {
109
110
111
const float front_center_distributed = src[2] * 0.5f;
dst[0] = (src[0] + front_center_distributed + src[4]) / 2.5f; /* left */
dst[1] = (src[1] + front_center_distributed + src[5]) / 2.5f; /* right */
112
113
114
115
116
117
118
119
120
}
cvt->len_cvt /= 3;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
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
/* Convert from quad to stereo. Average left and right. */
static void SDLCALL
SDL_ConvertQuadToStereo(SDL_AudioCVT * cvt, SDL_AudioFormat format)
{
float *dst = (float *) cvt->buf;
const float *src = dst;
int i;
LOG_DEBUG_CONVERT("quad", "stereo");
SDL_assert(format == AUDIO_F32SYS);
for (i = cvt->len_cvt / (sizeof (float) * 4); i; --i, src += 4, dst += 2) {
dst[0] = (src[0] + src[2]) * 0.5f; /* left */
dst[1] = (src[1] + src[3]) * 0.5f; /* right */
}
cvt->len_cvt /= 3;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
/* Convert from 7.1 to 5.1. Distribute sides across front and back. */
static void SDLCALL
SDL_Convert71To51(SDL_AudioCVT * cvt, SDL_AudioFormat format)
{
float *dst = (float *) cvt->buf;
const float *src = dst;
int i;
LOG_DEBUG_CONVERT("7.1", "5.1");
SDL_assert(format == AUDIO_F32SYS);
for (i = cvt->len_cvt / (sizeof (float) * 8); i; --i, src += 8, dst += 6) {
const float surround_left_distributed = src[6] * 0.5f;
const float surround_right_distributed = src[7] * 0.5f;
dst[0] = (src[0] + surround_left_distributed) / 1.5f; /* FL */
dst[1] = (src[1] + surround_right_distributed) / 1.5f; /* FR */
dst[2] = src[2] / 1.5f; /* CC */
dst[3] = src[3] / 1.5f; /* LFE */
dst[4] = (src[4] + surround_left_distributed) / 1.5f; /* BL */
dst[5] = (src[5] + surround_right_distributed) / 1.5f; /* BR */
}
cvt->len_cvt /= 8;
cvt->len_cvt *= 6;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
/* Convert from 5.1 to quad. Distribute center across front, discard LFE. */
175
static void SDLCALL
176
SDL_Convert51ToQuad(SDL_AudioCVT * cvt, SDL_AudioFormat format)
177
{
178
179
float *dst = (float *) cvt->buf;
const float *src = dst;
180
181
int i;
182
LOG_DEBUG_CONVERT("5.1", "quad");
183
SDL_assert(format == AUDIO_F32SYS);
184
185
186
/* SDL's 4.0 layout: FL+FR+BL+BR */
/* SDL's 5.1 layout: FL+FR+FC+LFE+BL+BR */
187
for (i = cvt->len_cvt / (sizeof (float) * 6); i; --i, src += 6, dst += 4) {
188
189
190
191
192
const float front_center_distributed = src[2] * 0.5f;
dst[0] = (src[0] + front_center_distributed) / 1.5f; /* FL */
dst[1] = (src[1] + front_center_distributed) / 1.5f; /* FR */
dst[2] = src[4] / 1.5f; /* BL */
dst[3] = src[5] / 1.5f; /* BR */
193
194
195
196
197
198
199
200
201
}
cvt->len_cvt /= 6;
cvt->len_cvt *= 4;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
202
203
/* Upmix mono to stereo (by duplication) */
204
static void SDLCALL
205
SDL_ConvertMonoToStereo(SDL_AudioCVT * cvt, SDL_AudioFormat format)
206
{
207
208
const float *src = (const float *) (cvt->buf + cvt->len_cvt);
float *dst = (float *) (cvt->buf + cvt->len_cvt * 2);
209
210
int i;
211
212
LOG_DEBUG_CONVERT("mono", "stereo");
SDL_assert(format == AUDIO_F32SYS);
213
214
215
216
217
for (i = cvt->len_cvt / sizeof (float); i; --i) {
src--;
dst -= 2;
dst[0] = dst[1] = *src;
218
219
220
221
222
223
224
225
226
}
cvt->len_cvt *= 2;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
227
/* Upmix stereo to a pseudo-5.1 stream */
228
static void SDLCALL
229
SDL_ConvertStereoTo51(SDL_AudioCVT * cvt, SDL_AudioFormat format)
230
231
{
int i;
232
233
234
235
236
237
238
float lf, rf, ce;
const float *src = (const float *) (cvt->buf + cvt->len_cvt);
float *dst = (float *) (cvt->buf + cvt->len_cvt * 3);
LOG_DEBUG_CONVERT("stereo", "5.1");
SDL_assert(format == AUDIO_F32SYS);
239
for (i = cvt->len_cvt / (sizeof(float) * 2); i; --i) {
240
241
242
243
dst -= 6;
src -= 2;
lf = src[0];
rf = src[1];
244
ce = (lf + rf) * 0.5f;
245
/* !!! FIXME: FL and FR may clip */
246
247
248
dst[0] = lf + (lf - ce); /* FL */
dst[1] = rf + (rf - ce); /* FR */
dst[2] = ce; /* FC */
249
dst[3] = 0; /* LFE (only meant for special LFE effects) */
250
251
dst[4] = lf; /* BL */
dst[5] = rf; /* BR */
252
}
253
254
255
256
257
258
259
260
cvt->len_cvt *= 3;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
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
/* Upmix quad to a pseudo-5.1 stream */
static void SDLCALL
SDL_ConvertQuadTo51(SDL_AudioCVT * cvt, SDL_AudioFormat format)
{
int i;
float lf, rf, lb, rb, ce;
const float *src = (const float *) (cvt->buf + cvt->len_cvt);
float *dst = (float *) (cvt->buf + cvt->len_cvt * 3 / 2);
LOG_DEBUG_CONVERT("quad", "5.1");
SDL_assert(format == AUDIO_F32SYS);
SDL_assert(cvt->len_cvt % (sizeof(float) * 4) == 0);
for (i = cvt->len_cvt / (sizeof(float) * 4); i; --i) {
dst -= 6;
src -= 4;
lf = src[0];
rf = src[1];
lb = src[2];
rb = src[3];
ce = (lf + rf) * 0.5f;
/* !!! FIXME: FL and FR may clip */
dst[0] = lf + (lf - ce); /* FL */
dst[1] = rf + (rf - ce); /* FR */
dst[2] = ce; /* FC */
dst[3] = 0; /* LFE (only meant for special LFE effects) */
dst[4] = lb; /* BL */
dst[5] = rb; /* BR */
}
cvt->len_cvt = cvt->len_cvt * 3 / 2;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
/* Upmix stereo to a pseudo-4.0 stream (by duplication) */
299
static void SDLCALL
300
SDL_ConvertStereoToQuad(SDL_AudioCVT * cvt, SDL_AudioFormat format)
301
{
302
303
const float *src = (const float *) (cvt->buf + cvt->len_cvt);
float *dst = (float *) (cvt->buf + cvt->len_cvt * 2);
304
float lf, rf;
305
306
int i;
307
308
309
LOG_DEBUG_CONVERT("stereo", "quad");
SDL_assert(format == AUDIO_F32SYS);
310
for (i = cvt->len_cvt / (sizeof(float) * 2); i; --i) {
311
312
313
314
dst -= 4;
src -= 2;
lf = src[0];
rf = src[1];
315
316
317
318
dst[0] = lf; /* FL */
dst[1] = rf; /* FR */
dst[2] = lf; /* BL */
dst[3] = rf; /* BR */
319
}
320
321
322
323
324
325
326
cvt->len_cvt *= 2;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
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
/* Upmix 5.1 to 7.1 */
static void SDLCALL
SDL_Convert51To71(SDL_AudioCVT * cvt, SDL_AudioFormat format)
{
float lf, rf, lb, rb, ls, rs;
int i;
const float *src = (const float *) (cvt->buf + cvt->len_cvt);
float *dst = (float *) (cvt->buf + cvt->len_cvt * 4 / 3);
LOG_DEBUG_CONVERT("5.1", "7.1");
SDL_assert(format == AUDIO_F32SYS);
SDL_assert(cvt->len_cvt % (sizeof(float) * 6) == 0);
for (i = cvt->len_cvt / (sizeof(float) * 6); i; --i) {
dst -= 8;
src -= 6;
lf = src[0];
rf = src[1];
lb = src[4];
rb = src[5];
ls = (lf + lb) * 0.5f;
rs = (rf + rb) * 0.5f;
/* !!! FIXME: these four may clip */
lf += lf - ls;
rf += rf - ls;
lb += lb - ls;
rb += rb - ls;
dst[3] = src[3]; /* LFE */
dst[2] = src[2]; /* FC */
dst[7] = rs; /* SR */
dst[6] = ls; /* SL */
dst[5] = rb; /* BR */
dst[4] = lb; /* BL */
dst[1] = rf; /* FR */
dst[0] = lf; /* FL */
}
cvt->len_cvt = cvt->len_cvt * 4 / 3;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
372
373
/* SDL's resampler uses a "bandlimited interpolation" algorithm:
https://ccrma.stanford.edu/~jos/resample/ */
374
375
376
377
378
#define RESAMPLER_ZERO_CROSSINGS 5
#define RESAMPLER_BITS_PER_SAMPLE 16
#define RESAMPLER_SAMPLES_PER_ZERO_CROSSING (1 << ((RESAMPLER_BITS_PER_SAMPLE / 2) + 1))
#define RESAMPLER_FILTER_SIZE ((RESAMPLER_SAMPLES_PER_ZERO_CROSSING * RESAMPLER_ZERO_CROSSINGS) + 1)
379
380
381
382
383
384
385
386
387
388
389
390
391
392
/* This is a "modified" bessel function, so you can't use POSIX j0() */
static double
bessel(const double x)
{
const double xdiv2 = x / 2.0;
double i0 = 1.0f;
double f = 1.0f;
int i = 1;
while (SDL_TRUE) {
const double diff = SDL_pow(xdiv2, i * 2) / SDL_pow(f, 2);
if (diff < 1.0e-21f) {
break;
393
}
394
395
396
397
i0 += diff;
i++;
f *= (double) i;
}
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
return i0;
}
/* build kaiser table with cardinal sine applied to it, and array of differences between elements. */
static void
kaiser_and_sinc(float *table, float *diffs, const int tablelen, const double beta)
{
const int lenm1 = tablelen - 1;
const int lenm1div2 = lenm1 / 2;
int i;
table[0] = 1.0f;
for (i = 1; i < tablelen; i++) {
const double kaiser = bessel(beta * SDL_sqrt(1.0 - SDL_pow(((i - lenm1) / 2.0) / lenm1div2, 2.0))) / bessel(beta);
table[tablelen - i] = (float) kaiser;
414
415
}
416
417
418
419
420
421
for (i = 1; i < tablelen; i++) {
const float x = (((float) i) / ((float) RESAMPLER_SAMPLES_PER_ZERO_CROSSING)) * ((float) M_PI);
table[i] *= SDL_sinf(x) / x;
diffs[i - 1] = table[i] - table[i - 1];
}
diffs[lenm1] = 0.0f;
422
423
}
424
425
426
427
428
429
430
static SDL_SpinLock ResampleFilterSpinlock = 0;
static float *ResamplerFilter = NULL;
static float *ResamplerFilterDifference = NULL;
int
SDL_PrepareResampleFilter(void)
431
{
432
433
434
435
436
437
438
439
440
441
442
SDL_AtomicLock(&ResampleFilterSpinlock);
if (!ResamplerFilter) {
/* if dB > 50, beta=(0.1102 * (dB - 8.7)), according to Matlab. */
const double dB = 80.0;
const double beta = 0.1102 * (dB - 8.7);
const size_t alloclen = RESAMPLER_FILTER_SIZE * sizeof (float);
ResamplerFilter = (float *) SDL_malloc(alloclen);
if (!ResamplerFilter) {
SDL_AtomicUnlock(&ResampleFilterSpinlock);
return SDL_OutOfMemory();
443
444
}
445
446
447
448
449
450
ResamplerFilterDifference = (float *) SDL_malloc(alloclen);
if (!ResamplerFilterDifference) {
SDL_free(ResamplerFilter);
ResamplerFilter = NULL;
SDL_AtomicUnlock(&ResampleFilterSpinlock);
return SDL_OutOfMemory();
451
}
452
kaiser_and_sinc(ResamplerFilter, ResamplerFilterDifference, RESAMPLER_FILTER_SIZE, beta);
453
}
454
455
SDL_AtomicUnlock(&ResampleFilterSpinlock);
return 0;
456
457
}
458
459
void
SDL_FreeResampleFilter(void)
460
{
461
462
463
464
465
SDL_free(ResamplerFilter);
SDL_free(ResamplerFilterDifference);
ResamplerFilter = NULL;
ResamplerFilterDifference = NULL;
}
466
467
468
469
470
471
static int
ResamplerPadding(const int inrate, const int outrate)
{
return (inrate > outrate) ? (int) SDL_ceil(((float) (RESAMPLER_SAMPLES_PER_ZERO_CROSSING * inrate) / ((float) outrate))) : RESAMPLER_SAMPLES_PER_ZERO_CROSSING;
}
472
473
/* lpadding and rpadding are expected to be buffers of (ResamplePadding(inrate, outrate) * chans * sizeof (float)) bytes. */
474
475
static int
SDL_ResampleAudio(const int chans, const int inrate, const int outrate,
476
float *lpadding, float *rpadding, const float *inbuf,
477
478
479
480
const int inbuflen, float *outbuf, const int outbuflen)
{
const float outtimeincr = 1.0f / ((float) outrate);
const float ratio = ((float) outrate) / ((float) inrate);
481
const int paddinglen = ResamplerPadding(inrate, outrate);
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
const int framelen = chans * (int)sizeof (float);
const int inframes = inbuflen / framelen;
const int wantedoutframes = (int) ((inbuflen / framelen) * ratio); /* outbuflen isn't total to write, it's total available. */
const int maxoutframes = outbuflen / framelen;
const int outframes = (wantedoutframes < maxoutframes) ? wantedoutframes : maxoutframes;
float *dst = outbuf;
float outtime = 0.0f;
int i, j, chan;
for (i = 0; i < outframes; i++) {
const int srcindex = (int) (outtime * inrate);
const float finrate = (float) inrate;
const float intime = ((float) srcindex) / finrate;
const float innexttime = ((float) (srcindex + 1)) / finrate;
const float interpolation1 = 1.0f - (innexttime - outtime) / (innexttime - intime);
const int filterindex1 = (int) (interpolation1 * RESAMPLER_SAMPLES_PER_ZERO_CROSSING);
const float interpolation2 = 1.0f - interpolation1;
const int filterindex2 = interpolation2 * RESAMPLER_SAMPLES_PER_ZERO_CROSSING;
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. */
/* !!! FIXME: do both wings in one loop */
for (j = 0; (filterindex1 + (j * RESAMPLER_SAMPLES_PER_ZERO_CROSSING)) < RESAMPLER_FILTER_SIZE; j++) {
const int srcframe = srcindex - j;
509
510
/* !!! 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];
511
512
outsample += (insample * (ResamplerFilter[filterindex1 + (j * RESAMPLER_SAMPLES_PER_ZERO_CROSSING)] + (interpolation1 * ResamplerFilterDifference[filterindex1 + (j * RESAMPLER_SAMPLES_PER_ZERO_CROSSING)])));
}
513
514
515
for (j = 0; (filterindex2 + (j * RESAMPLER_SAMPLES_PER_ZERO_CROSSING)) < RESAMPLER_FILTER_SIZE; j++) {
const int srcframe = srcindex + 1 + j;
516
517
/* !!! 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];
518
519
520
521
522
523
outsample += (insample * (ResamplerFilter[filterindex2 + (j * RESAMPLER_SAMPLES_PER_ZERO_CROSSING)] + (interpolation2 * ResamplerFilterDifference[filterindex2 + (j * RESAMPLER_SAMPLES_PER_ZERO_CROSSING)])));
}
*(dst++) = outsample;
}
outtime += outtimeincr;
524
525
}
526
527
return outframes * chans * sizeof (float);
}
528
529
530
531
532
533
534
535
536
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) {
537
return SDL_SetError("No buffer allocated for conversion");
538
}
539
540
541
542
/* Return okay if no conversion is necessary */
cvt->len_cvt = cvt->len;
if (cvt->filters[0] == NULL) {
543
return 0;
544
545
546
547
548
}
/* Set up the conversion and go! */
cvt->filter_index = 0;
cvt->filters[0] (cvt, cvt->src_format);
549
return 0;
550
551
}
552
553
static void SDLCALL
SDL_Convert_Byteswap(SDL_AudioCVT *cvt, SDL_AudioFormat format)
554
{
555
556
557
#if DEBUG_CONVERT
printf("Converting byte order\n");
#endif
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
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;
}
578
579
580
581
582
583
584
585
586
587
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);
}
588
589
}
590
591
592
593
594
595
596
597
598
599
600
601
602
static int
SDL_AddAudioCVTFilter(SDL_AudioCVT *cvt, const 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);
}
if (filter == NULL) {
return SDL_SetError("Audio filter pointer is NULL");
}
cvt->filters[cvt->filter_index++] = filter;
cvt->filters[cvt->filter_index] = NULL; /* Moving terminator */
return 0;
}
603
604
static int
605
SDL_BuildAudioTypeCVTToFloat(SDL_AudioCVT *cvt, const SDL_AudioFormat src_fmt)
606
{
607
int retval = 0; /* 0 == no conversion necessary. */
608
609
if ((SDL_AUDIO_ISBIGENDIAN(src_fmt) != 0) == (SDL_BYTEORDER == SDL_LIL_ENDIAN)) {
610
611
612
if (SDL_AddAudioCVTFilter(cvt, SDL_Convert_Byteswap) < 0) {
return -1;
}
613
614
retval = 1; /* added a converter. */
}
615
616
if (!SDL_AUDIO_ISFLOAT(src_fmt)) {
617
618
const Uint16 src_bitsize = SDL_AUDIO_BITSIZE(src_fmt);
const Uint16 dst_bitsize = 32;
619
SDL_AudioFilter filter = NULL;
620
621
622
623
624
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;
625
case AUDIO_U16: filter = SDL_Convert_U16_to_F32; break;
626
627
case AUDIO_S32: filter = SDL_Convert_S32_to_F32; break;
default: SDL_assert(!"Unexpected audio format!"); break;
628
629
}
630
if (!filter) {
631
return SDL_SetError("No conversion from source format to float available");
632
633
}
634
635
636
if (SDL_AddAudioCVTFilter(cvt, filter) < 0) {
return -1;
}
637
638
639
640
641
642
643
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) {
cvt->len_ratio /= (src_bitsize / dst_bitsize);
}
644
645
retval = 1; /* added a converter. */
646
647
}
648
return retval;
649
650
}
651
652
static int
SDL_BuildAudioTypeCVTFromFloat(SDL_AudioCVT *cvt, const SDL_AudioFormat dst_fmt)
653
{
654
655
656
int retval = 0; /* 0 == no conversion necessary. */
if (!SDL_AUDIO_ISFLOAT(dst_fmt)) {
657
658
const Uint16 dst_bitsize = SDL_AUDIO_BITSIZE(dst_fmt);
const Uint16 src_bitsize = 32;
659
660
661
662
663
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;
664
case AUDIO_U16: filter = SDL_Convert_F32_to_U16; break;
665
666
667
668
669
case AUDIO_S32: filter = SDL_Convert_F32_to_S32; break;
default: SDL_assert(!"Unexpected audio format!"); break;
}
if (!filter) {
670
return SDL_SetError("No conversion from float to destination format available");
671
}
672
673
674
675
if (SDL_AddAudioCVTFilter(cvt, filter) < 0) {
return -1;
}
676
677
678
679
680
681
682
683
684
685
686
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) {
cvt->len_ratio /= (src_bitsize / dst_bitsize);
}
retval = 1; /* added a converter. */
}
if ((SDL_AUDIO_ISBIGENDIAN(dst_fmt) != 0) == (SDL_BYTEORDER == SDL_LIL_ENDIAN)) {
687
688
689
if (SDL_AddAudioCVTFilter(cvt, SDL_Convert_Byteswap) < 0) {
return -1;
}
690
691
692
693
retval = 1; /* added a converter. */
}
return retval;
694
695
}
696
697
698
static void
SDL_ResampleCVT(SDL_AudioCVT *cvt, const int chans, const SDL_AudioFormat format)
{
699
700
701
/* !!! 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. :( */
702
703
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];
704
705
const float *src = (const float *) cvt->buf;
const int srclen = cvt->len_cvt;
706
707
708
709
710
/*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;
711
712
const int paddingsamples = (ResamplerPadding(inrate, outrate) * chans);
float *padding = SDL_stack_alloc(float, paddingsamples);
713
714
715
SDL_assert(format == AUDIO_F32SYS);
716
717
/* we keep no streaming state here, so pad with silence on both ends. */
SDL_memset(padding, '\0', paddingsamples * sizeof (float));
718
719
cvt->len_cvt = SDL_ResampleAudio(chans, inrate, outrate, padding, padding, src, srclen, dst, dstlen);
720
721
SDL_memcpy(cvt->buf, dst, cvt->len_cvt); /* !!! FIXME: remove this if we can get the resampler to work in-place again. */
722
723
724
725
726
727
728
729
730
731
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. */
732
733
#define RESAMPLER_FUNCS(chans) \
static void SDLCALL \
734
735
SDL_ResampleCVT_c##chans(SDL_AudioCVT *cvt, SDL_AudioFormat format) { \
SDL_ResampleCVT(cvt, chans, format); \
736
737
738
739
740
741
742
743
}
RESAMPLER_FUNCS(1)
RESAMPLER_FUNCS(2)
RESAMPLER_FUNCS(4)
RESAMPLER_FUNCS(6)
RESAMPLER_FUNCS(8)
#undef RESAMPLER_FUNCS
744
static SDL_AudioFilter
745
ChooseCVTResampler(const int dst_channels)
746
{
747
748
749
750
751
752
753
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;
754
755
}
756
return NULL;
757
758
759
760
761
762
763
764
765
766
767
768
}
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. */
}
769
filter = ChooseCVTResampler(dst_channels);
770
771
772
if (filter == NULL) {
return SDL_SetError("No conversion available for these rates");
}
773
774
775
776
777
if (SDL_PrepareResampleFilter() < 0) {
return -1;
}
778
/* Update (cvt) with filter details... */
779
780
781
if (SDL_AddAudioCVTFilter(cvt, filter) < 0) {
return -1;
}
782
783
784
785
786
787
788
789
790
791
/* !!! 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) (size_t) src_rate;
cvt->filters[SDL_AUDIOCVT_MAX_FILTERS] = (SDL_AudioFilter) (size_t) dst_rate;
792
793
794
795
796
797
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);
798
799
}
800
801
802
803
804
/* !!! 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;
805
return 1; /* added a converter. */
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
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)
{
switch (channels) {
case 1: /* mono */
case 2: /* stereo */
case 4: /* quad */
case 6: /* 5.1 */
839
840
case 8: /* 7.1 */
return SDL_TRUE; /* supported. */
841
842
843
844
845
846
847
848
default:
break;
}
return SDL_FALSE; /* unsupported. */
}
849
850
/* Creates a set of audio filters to convert from one format to another.
851
852
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.
853
854
855
856
857
858
859
860
861
862
863
864
*/
int
SDL_BuildAudioCVT(SDL_AudioCVT * cvt,
SDL_AudioFormat src_fmt, Uint8 src_channels, int src_rate,
SDL_AudioFormat dst_fmt, Uint8 dst_channels, int dst_rate)
{
/* Sanity check target pointer */
if (cvt == NULL) {
return SDL_InvalidParamError("cvt");
}
865
866
867
/* Make sure we zero out the audio conversion before error checking */
SDL_zerop(cvt);
868
if (!SDL_SupportedAudioFormat(src_fmt)) {
869
return SDL_SetError("Invalid source format");
870
} else if (!SDL_SupportedAudioFormat(dst_fmt)) {
871
return SDL_SetError("Invalid destination format");
872
873
874
875
876
877
878
879
} else if (!SDL_SupportedChannelCount(src_channels)) {
return SDL_SetError("Invalid source channels");
} else if (!SDL_SupportedChannelCount(dst_channels)) {
return SDL_SetError("Invalid destination channels");
} else if (src_rate == 0) {
return SDL_SetError("Source rate is zero");
} else if (dst_rate == 0) {
return SDL_SetError("Destination rate is zero");
880
881
}
882
#if DEBUG_CONVERT
883
884
885
886
887
888
889
890
891
printf("Build format %04x->%04x, channels %u->%u, rate %d->%d\n",
src_fmt, dst_fmt, src_channels, dst_channels, src_rate, dst_rate);
#endif
/* Start off with no conversion necessary */
cvt->src_format = src_fmt;
cvt->dst_format = dst_fmt;
cvt->needed = 0;
cvt->filter_index = 0;
892
SDL_zero(cvt->filters);
893
894
895
896
cvt->len_mult = 1;
cvt->len_ratio = 1.0;
cvt->rate_incr = ((double) dst_rate) / ((double) src_rate);
897
898
899
/* Make sure we've chosen audio conversion functions (MMX, scalar, etc.) */
SDL_ChooseAudioConverters();
900
901
902
903
904
905
906
907
908
/* 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 back to native 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
909
buffer is likely to be CPU cache-friendly, avoiding the
910
911
912
913
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. */
914
915
916
917
918
919
920
921
/* see if we can skip float conversion entirely. */
if (src_rate == dst_rate && src_channels == dst_channels) {
if (src_fmt == dst_fmt) {
return 0;
}
/* just a byteswap needed? */
if ((src_fmt & ~SDL_AUDIO_MASK_ENDIAN) == (dst_fmt & ~SDL_AUDIO_MASK_ENDIAN)) {
922
923
924
if (SDL_AddAudioCVTFilter(cvt, SDL_Convert_Byteswap) < 0) {
return -1;
}
925
926
927
cvt->needed = 1;
return 1;
}
928
929
}
930
/* Convert data types, if necessary. Updates (cvt). */
931
if (SDL_BuildAudioTypeCVTToFloat(cvt, src_fmt) < 0) {
932
933
934
935
return -1; /* shouldn't happen, but just in case... */
}
/* Channel conversion */
936
937
938
if (src_channels < dst_channels) {
/* Upmixing */
/* Mono -> Stereo [-> ...] */
939
if ((src_channels == 1) && (dst_channels > 1)) {
940
941
942
if (SDL_AddAudioCVTFilter(cvt, SDL_ConvertMonoToStereo) < 0) {
return -1;
}
943
944
945
946
cvt->len_mult *= 2;
src_channels = 2;
cvt->len_ratio *= 2;
}
947
948
/* [Mono ->] Stereo -> 5.1 [-> 7.1] */
if ((src_channels == 2) && (dst_channels >= 6)) {
949
950
951
if (SDL_AddAudioCVTFilter(cvt, SDL_ConvertStereoTo51) < 0) {
return -1;
}
952
953
954
955
src_channels = 6;
cvt->len_mult *= 3;
cvt->len_ratio *= 3;
}
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
/* Quad -> 5.1 [-> 7.1] */
if ((src_channels == 4) && (dst_channels >= 6)) {
if (SDL_AddAudioCVTFilter(cvt, SDL_ConvertQuadTo51) < 0) {
return -1;
}
src_channels = 6;
cvt->len_mult = (cvt->len_mult * 3 + 1) / 2;
cvt->len_ratio *= 1.5;
}
/* [[Mono ->] Stereo ->] 5.1 -> 7.1 */
if ((src_channels == 6) && (dst_channels == 8)) {
if (SDL_AddAudioCVTFilter(cvt, SDL_Convert51To71) < 0) {
return -1;
}
src_channels = 8;
cvt->len_mult = (cvt->len_mult * 4 + 2) / 3;
/* Should be numerically exact with every valid input to this
function */
cvt->len_ratio = cvt->len_ratio * 4 / 3;
}
/* [Mono ->] Stereo -> Quad */
977
if ((src_channels == 2) && (dst_channels == 4)) {
978
979
980
if (SDL_AddAudioCVTFilter(cvt, SDL_ConvertStereoToQuad) < 0) {
return -1;
}
981
982
983
984
src_channels = 4;
cvt->len_mult *= 2;
cvt->len_ratio *= 2;
}
985
986
987
988
989
990
} else if (src_channels > dst_channels) {
/* Downmixing */
/* 7.1 -> 5.1 [-> Stereo [-> Mono]] */
/* 7.1 -> 5.1 [-> Quad] */
if ((src_channels == 8) && (dst_channels <= 6)) {
if (SDL_AddAudioCVTFilter(cvt, SDL_Convert71To51) < 0) {
991
992
return -1;
}
993
994
src_channels = 6;
cvt->len_ratio *= 0.75;
995
}
996
/* [7.1 ->] 5.1 -> Stereo [-> Mono] */
997
if ((src_channels == 6) && (dst_channels <= 2)) {
998
999
1000
if (SDL_AddAudioCVTFilter(cvt, SDL_Convert51ToStereo) < 0) {
return -1;
}