1 /*
2 * Copyright (C) 2011-2013 Michael Niedermayer (michaelni@gmx.at)
3 *
4 * This file is part of libswresample
5 *
6 * libswresample is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public
8 * License as published by the Free Software Foundation; either
9 * version 2.1 of the License, or (at your option) any later version.
10 *
11 * libswresample is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 * Lesser General Public License for more details.
15 *
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with libswresample; if not, write to the Free Software
18 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19 */
20
21 #ifndef SWRESAMPLE_SWRESAMPLE_INTERNAL_H
22 #define SWRESAMPLE_SWRESAMPLE_INTERNAL_H
23
27
29
30 #define SQRT3_2 1.22474487139158904909 /* sqrt(3/2) */
31
33
34 #if ARCH_X86_64
36 #else
38 #endif
39
42
44
49 int bps;
///< bytes per sample
50 int count;
///< number of samples
51 int planar;
///< 1 if planar audio, 0 otherwise
54
60 int ns_taps;
///< Noise shaping dither taps
61 float ns_scale;
///< Noise shaping dither scale
63 int ns_pos;
///< Noise shaping dither position
67 AudioData temp;
///< temporary storage when writing into the input buffer isn't possible
69 };
70
80
90 };
91
94
98 void *
log_ctx;
///< parent logging context
106 int flags;
///< miscellaneous flags such as SWR_FLAG_RESAMPLE
107 float slev;
///< surround mixing level
108 float clev;
///< center mixing level
113 const int *
channel_map;
///< channel index (or -1 if muted channel) map
114 int used_ch_count;
///< number of used input channels (mapped channel count if channel_map, otherwise in.ch_count)
116
124
126
127 int filter_size;
/**< length of each FIR filter in the resampling filterbank relative to the cutoff frequency */
128 int phase_shift;
/**< log2 of the number of entries in the resampling polyphase filterbank */
129 int linear_interp;
/**< if 1 then the resampling FIR filter will be linearly interpolated */
131 double cutoff;
/**< resampling cutoff frequency (swr: 6dB point; soxr: 0dB point). 1.0 corresponds to half the output sample rate */
133 double kaiser_beta;
/**< swr beta value for Kaiser window (only applicable if filter_type == AV_FILTER_TYPE_KAISER) */
134 double precision;
/**< soxr resampling precision (in bits) */
135 int cheby;
/**< soxr: if 1 then passband rolloff will be none (Chebyshev) & irrational ratio approximation precision will be higher */
136
141 float async;
///< swr simple 1 parameter async, similar to ffmpegs -async
143
145 int rematrix;
///< flag to indicate if rematrixing is needed (basically if input and output layouts mismatch)
147
159 int flushed;
///< 1 if data is to be flushed and no further input is expected
164
170
181
184
186
187 /* TODO: callbacks for ASM optimizations */
188 };
189
192
197
203
208
212 int channels);
216 int channels);
220 int channels);
221
222 #endif
struct AudioConvert * in_convert
input conversion context
const AVClass * av_class
AVClass used for AVOption and av_log()
struct AudioConvert * full_convert
full conversion context (single conversion for input and output)
int(* set_compensation_func)(struct ResampleContext *c, int sample_delta, int compensation_distance)
int user_dither_method
User set dither method.
AudioData temp
temporary storage when writing into the input buffer isn't possible
int out_sample_rate
output sample rate
enum AVSampleFormat int_sample_fmt
internal sample format (AV_SAMPLE_FMT_FLTP or AV_SAMPLE_FMT_S16P)
Audio buffer used for intermediate storage between conversion phases.
multiple_resample_func multiple_resample
static int linear(InterplayACMContext *s, unsigned ind, unsigned col)
struct Resampler const swri_resampler
int count
number of samples
int ch_count
number of channels
void( mix_2_1_func_type)(void *out, const void *in1, const void *in2, void *coeffp, integer index1, integer index2, integer len)
float soft_compensation_duration
swr duration over which soft compensation is applied
int rematrix_custom
flag to indicate that a custom matrix has been defined
SwrFilterType
Resampling Filter Types.
double delayed_samples_fixup
soxr 0.1.1: needed to fixup delayed_samples after flush has been called.
int in_buffer_index
cached buffer position
void( mix_1_1_func_type)(void *out, const void *in, void *coeffp, integer index, integer len)
AudioData in_buffer
cached audio data (convert and resample purpose)
int resample_in_constraint
1 if the input end was reach before the output end, 0 otherwise
struct ResampleContext * resample
resampling context
float ns_scale
Noise shaping dither scale.
float ns_coeffs[NS_TAPS]
Noise shaping filter coefficients.
float async
swr simple 1 parameter async, similar to ffmpegs -async
const int * channel_map
channel index (or -1 if muted channel) map
int(* multiple_resample_func)(struct ResampleContext *c, AudioData *dst, int dst_size, AudioData *src, int src_size, int *consumed)
int log_level_offset
logging level offset
struct Resampler const * resampler
resampler virtual function table
float ns_errors[SWR_CH_MAX][2 *NS_TAPS]
float max_soft_compensation
swr maximum soft compensation in seconds over soft_compensation_duration
int user_out_ch_count
User set output channel count.
enum AVSampleFormat fmt
sample format
void * log_ctx
parent logging context
void swri_rematrix_free(SwrContext *s)
void swri_audio_convert_init_arm(struct AudioConvert *ac, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels)
AudioData out
converted output audio data
int phase_shift
log2 of the number of entries in the resampling polyphase filterbank
int compensation_distance
AudioData in
input audio data
uint8_t * native_simd_one
invert_initial_buffer_func invert_initial_buffer
float min_hard_compensation
swr minimum below which no silence inject / sample drop will happen
enum AVResampleFilterType filter_type
enum AVSampleFormat out_sample_fmt
output sample format
void(* resample_free_func)(struct ResampleContext **c)
int in_buffer_count
cached buffer length
libswresample public header
AudioData postin
post-input audio data: used for rematrix/resample
int matrix_encoding
matrixed stereo encoding
float slev
surround mixing level
int output_sample_bits
the number of used output bits, needed to scale dither correctly
int64_t user_in_ch_layout
User set input channel layout.
av_warn_unused_result int swri_realloc_audio(AudioData *a, int count)
av_warn_unused_result int swri_get_dither(SwrContext *s, void *dst, int len, unsigned seed, enum AVSampleFormat noise_fmt)
The libswresample context.
int swri_rematrix_init_x86(struct SwrContext *s)
double cutoff
resampling cutoff frequency (swr: 6dB point; soxr: 0dB point).
float clev
center mixing level
void swri_audio_convert_init_x86(struct AudioConvert *ac, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels)
mix_2_1_func_type * mix_2_1_simd
resample_flush_func flush
int64_t firstpts
first PTS
AudioData preout
pre-output audio data: used for rematrix/resample
int32_t matrix32[SWR_CH_MAX][SWR_CH_MAX]
17.15 fixed point rematrixing coefficients
AudioData midbuf
intermediate audio data (postin/preout)
audio channel layout utility functions
int flags
miscellaneous flags such as SWR_FLAG_RESAMPLE
int filter_type
swr resampling filter type
int drop_output
number of output samples to drop
int linear_interp
if 1 then the resampling FIR filter will be linearly interpolated
mix_1_1_func_type * mix_1_1_f
void swri_noise_shaping_int32(SwrContext *s, AudioData *dsts, const AudioData *srcs, const AudioData *noises, int count)
typedef void(APIENTRY *FF_PFNGLACTIVETEXTUREPROC)(GLenum texture)
double precision
soxr resampling precision (in bits)
mix_1_1_func_type * mix_1_1_simd
AudioData noise
noise used for dithering
int64_t out_ch_layout
output channel layout
int in_sample_rate
input sample rate
av_warn_unused_result int swri_dither_init(SwrContext *s, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt)
int(* resample_flush_func)(struct SwrContext *c)
int rematrix
flag to indicate if rematrixing is needed (basically if input and output layouts mismatch) ...
mix_any_func_type * mix_any_f
int64_t(* get_delay_func)(struct SwrContext *s, int64_t base)
set_compensation_func set_compensation
int64_t(* get_out_samples_func)(struct SwrContext *s, int in_samples)
float ns_scale_1
Noise shaping dither scale^-1.
float noise_scale
Noise scale.
void swri_noise_shaping_double(SwrContext *s, AudioData *dsts, const AudioData *srcs, const AudioData *noises, int count)
int user_in_ch_count
User set input channel count.
enum AVSampleFormat user_int_sample_fmt
User set internal sample format.
AVSampleFormat
Audio sample formats.
int user_used_ch_count
User set used channel count.
int filter_size
length of each FIR filter in the resampling filterbank relative to the cutoff frequency ...
uint8_t * data[AVRESAMPLE_MAX_CHANNELS]
data plane pointers
double kaiser_beta
swr beta value for Kaiser window (only applicable if filter_type == AV_FILTER_TYPE_KAISER) ...
float min_compensation
swr minimum below which no compensation will happen
uint8_t pi<< 24) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8, uint8_t,(*(constuint8_t *) pi-0x80)*(1.0f/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8, uint8_t,(*(constuint8_t *) pi-0x80)*(1.0/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16, int16_t,(*(constint16_t *) pi >>8)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16, int16_t,*(constint16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16, int16_t,*(constint16_t *) pi *(1.0/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32, int32_t,(*(constint32_t *) pi >>24)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32, int32_t,*(constint32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32, int32_t,*(constint32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, float, av_clip_uint8(lrintf(*(constfloat *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, float, av_clip_int16(lrintf(*(constfloat *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, float, av_clipl_int32(llrintf(*(constfloat *) pi *(1U<< 31)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, double, av_clip_uint8(lrint(*(constdouble *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, double, av_clip_int16(lrint(*(constdouble *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, double, av_clipl_int32(llrint(*(constdouble *) pi *(1U<< 31))))#defineSET_CONV_FUNC_GROUP(ofmt, ifmt) staticvoidset_generic_function(AudioConvert *ac){}voidff_audio_convert_free(AudioConvert **ac){if(!*ac) return;ff_dither_free(&(*ac) ->dc);av_freep(ac);}AudioConvert *ff_audio_convert_alloc(AVAudioResampleContext *avr, enumAVSampleFormatout_fmt, enumAVSampleFormatin_fmt, intchannels, intsample_rate, intapply_map){AudioConvert *ac;intin_planar, out_planar;ac=av_mallocz(sizeof(*ac));if(!ac) returnNULL;ac->avr=avr;ac->out_fmt=out_fmt;ac->in_fmt=in_fmt;ac->channels=channels;ac->apply_map=apply_map;if(avr->dither_method!=AV_RESAMPLE_DITHER_NONE &&av_get_packed_sample_fmt(out_fmt)==AV_SAMPLE_FMT_S16 &&av_get_bytes_per_sample(in_fmt)>2){ac->dc=ff_dither_alloc(avr, out_fmt, in_fmt, channels, sample_rate, apply_map);if(!ac->dc){av_free(ac);returnNULL;}returnac;}in_planar=ff_sample_fmt_is_planar(in_fmt, channels);out_planar=ff_sample_fmt_is_planar(out_fmt, channels);if(in_planar==out_planar){ac->func_type=CONV_FUNC_TYPE_FLAT;ac->planes=in_planar?ac->channels:1;}elseif(in_planar) ac->func_type=CONV_FUNC_TYPE_INTERLEAVE;elseac->func_type=CONV_FUNC_TYPE_DEINTERLEAVE;set_generic_function(ac);if(ARCH_AARCH64) ff_audio_convert_init_aarch64(ac);if(ARCH_ARM) ff_audio_convert_init_arm(ac);if(ARCH_X86) ff_audio_convert_init_x86(ac);returnac;}intff_audio_convert(AudioConvert *ac, AudioData *out, AudioData *in){intuse_generic=1;intlen=in->nb_samples;intp;if(ac->dc){av_log(ac->avr, AV_LOG_TRACE,"%dsamples-audio_convert:%sto%s(dithered)\n", len, av_get_sample_fmt_name(ac->in_fmt), av_get_sample_fmt_name(ac->out_fmt));returnff_convert_dither(ac-> in
int ns_pos
Noise shaping dither position.
static const char * format
Describe the class of an AVClass context structure.
struct DitherContext dither
void swri_noise_shaping_float(SwrContext *s, AudioData *dsts, const AudioData *srcs, const AudioData *noises, int count)
get_out_samples_func get_out_samples
av_warn_unused_result int swri_rematrix_init(SwrContext *s)
enum AVSampleFormat in_sample_fmt
input sample format
struct Resampler const swri_soxr_resampler
int(* invert_initial_buffer_func)(struct ResampleContext *c, AudioData *dst, const AudioData *src, int src_size, int *dst_idx, int *dst_count)
float matrix_flt[SWR_CH_MAX][SWR_CH_MAX]
single precision floating point rematrixing coefficients
int swri_rematrix(SwrContext *s, AudioData *out, AudioData *in, int len, int mustcopy)
double matrix[SWR_CH_MAX][SWR_CH_MAX]
floating point rematrixing coefficients
#define av_warn_unused_result
int flushed
1 if data is to be flushed and no further input is expected
int64_t in_ch_layout
input channel layout
uint8_t * native_simd_matrix
int cheby
soxr: if 1 then passband rolloff will be none (Chebyshev) & irrational ratio approximation precision ...
float lfe_mix_level
LFE mixing level.
void( mix_any_func_type)(uint8_t **out, const uint8_t **in1, void *coeffp, integer len)
void swri_noise_shaping_int16(SwrContext *s, AudioData *dsts, const AudioData *srcs, const AudioData *noises, int count)
float rematrix_maxval
maximum value for rematrixing output
struct AudioConvert * out_convert
output conversion context
float rematrix_volume
rematrixing volume coefficient
mix_2_1_func_type * mix_2_1_f
int64_t firstpts_in_samples
swr first pts in samples
int planar
1 if planar audio, 0 otherwise
AudioData drop_temp
temporary used to discard output
int exact_rational
if 1 then enable non power of 2 phase_count
uint8_t matrix_ch[SWR_CH_MAX][SWR_CH_MAX+1]
Lists of input channels per output channel that have non zero rematrixing coefficients.
uint8_t * ch[SWR_CH_MAX]
samples buffer per channel
int used_ch_count
number of used input channels (mapped channel count if channel_map, otherwise in.ch_count) ...
void swri_audio_convert_init_aarch64(struct AudioConvert *ac, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels)
int64_t user_out_ch_layout
User set output channel layout.
AudioData silence
temporary with silence
int resample_first
1 if resampling must come first, 0 if rematrixing
int ns_taps
Noise shaping dither taps.