FFmpeg
aacpsdsp_init.c
Go to the documentation of this file.
1 /*
2  * SIMD optimized MPEG-4 Parametric Stereo decoding functions
3  *
4  * This file is part of FFmpeg.
5  *
6  * FFmpeg 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  * FFmpeg 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 FFmpeg; if not, write to the Free Software
18  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19  */
20 
21 #include <stddef.h>
22 
23 #include "config.h"
24 
25 #include "libavutil/x86/cpu.h"
26 #include "libavutil/attributes.h"
27 #include "libavcodec/aacpsdsp.h"
28 
29 void ff_ps_add_squares_sse (float *dst, const float (*src)[2], int n);
30 void ff_ps_add_squares_sse3 (float *dst, const float (*src)[2], int n);
31 void ff_ps_mul_pair_single_sse (float (*dst)[2], float (*src0)[2],
32  float *src1, int n);
33 void ff_ps_hybrid_analysis_sse (float (*out)[2], float (*in)[2],
34  const float (*filter)[8][2],
35  ptrdiff_t stride, int n);
36 void ff_ps_hybrid_analysis_sse3(float (*out)[2], float (*in)[2],
37  const float (*filter)[8][2],
38  ptrdiff_t stride, int n);
39 void ff_ps_stereo_interpolate_sse3(float (*l)[2], float (*r)[2],
40  float h[2][4], float h_step[2][4],
41  int len);
42 void ff_ps_stereo_interpolate_ipdopd_sse3(float (*l)[2], float (*r)[2],
43  float h[2][4], float h_step[2][4],
44  int len);
45 void ff_ps_hybrid_synthesis_deint_sse(float out[2][38][64], float (*in)[32][2],
46  int i, int len);
47 void ff_ps_hybrid_synthesis_deint_sse4(float out[2][38][64], float (*in)[32][2],
48  int i, int len);
49 void ff_ps_hybrid_analysis_ileave_sse(float (*out)[32][2], float L[2][38][64],
50  int i, int len);
51 
53 {
55 
56  if (EXTERNAL_SSE(cpu_flags)) {
62  }
63  if (EXTERNAL_SSE3(cpu_flags)) {
68  }
69  if (EXTERNAL_SSE4(cpu_flags)) {
71  }
72 }
void(* mul_pair_single)(INTFLOAT(*dst)[2], INTFLOAT(*src0)[2], INTFLOAT *src1, int n)
Definition: aacpsdsp.h:34
static atomic_int cpu_flags
Definition: cpu.c:50
#define EXTERNAL_SSE(flags)
Definition: cpu.h:58
#define src
Definition: vp8dsp.c:254
void(* hybrid_synthesis_deint)(INTFLOAT out[2][38][64], INTFLOAT(*in)[32][2], int i, int len)
Definition: aacpsdsp.h:41
Macro definitions for various function/variable attributes.
#define EXTERNAL_SSE4(flags)
Definition: cpu.h:68
#define av_cold
Definition: attributes.h:82
void(* add_squares)(INTFLOAT *dst, const INTFLOAT(*src)[2], int n)
Definition: aacpsdsp.h:33
#define EXTERNAL_SSE3(flags)
Definition: cpu.h:62
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:259
void ff_ps_add_squares_sse3(float *dst, const float(*src)[2], int n)
filter_frame For filters that do not use the this method is called when a frame is pushed to the filter s input It can be called at any time except in a reentrant way If the input frame is enough to produce then the filter should push the output frames on the output link immediately As an exception to the previous rule if the input frame is enough to produce several output frames then the filter needs output only at least one per link The additional frames can be left buffered in the filter
const char * r
Definition: vf_curves.c:114
void(* hybrid_analysis)(INTFLOAT(*out)[2], INTFLOAT(*in)[2], const INTFLOAT(*filter)[8][2], ptrdiff_t stride, int n)
Definition: aacpsdsp.h:36
void ff_ps_hybrid_synthesis_deint_sse4(float out[2][38][64], float(*in)[32][2], int i, int len)
void(* stereo_interpolate[2])(INTFLOAT(*l)[2], INTFLOAT(*r)[2], INTFLOAT h[2][4], INTFLOAT h_step[2][4], int len)
Definition: aacpsdsp.h:49
#define s(width, name)
Definition: cbs_vp9.c:257
int n
Definition: avisynth_c.h:760
void ff_ps_mul_pair_single_sse(float(*dst)[2], float(*src0)[2], float *src1, int n)
#define L(x)
Definition: vp56_arith.h:36
void ff_ps_hybrid_analysis_sse(float(*out)[2], float(*in)[2], const float(*filter)[8][2], ptrdiff_t stride, int n)
void ff_ps_add_squares_sse(float *dst, const float(*src)[2], int n)
#define src1
Definition: h264pred.c:139
void ff_ps_hybrid_analysis_sse3(float(*out)[2], float(*in)[2], const float(*filter)[8][2], ptrdiff_t stride, int n)
void ff_ps_hybrid_analysis_ileave_sse(float(*out)[32][2], float L[2][38][64], int i, int len)
uint8_t pi<< 24) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi-0x80)*(1.0f/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi-0x80)*(1.0/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16, int16_t,(*(const int16_t *) pi >> 8)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16, int16_t,*(const int16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16, int16_t,*(const int16_t *) pi *(1.0/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32, int32_t,(*(const int32_t *) pi >> 24)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32, int32_t,*(const int32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32, int32_t,*(const int32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, float, av_clip_uint8(lrintf(*(const float *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, float, av_clip_int16(lrintf(*(const float *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, float, av_clipl_int32(llrintf(*(const float *) pi *(1U<< 31)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, double, av_clip_uint8(lrint(*(const double *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, double, av_clip_int16(lrint(*(const double *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, double, av_clipl_int32(llrint(*(const double *) pi *(1U<< 31))))#define SET_CONV_FUNC_GROUP(ofmt, ifmt) static void set_generic_function(AudioConvert *ac){}void ff_audio_convert_free(AudioConvert **ac){if(!*ac) return;ff_dither_free(&(*ac) ->dc);av_freep(ac);}AudioConvert *ff_audio_convert_alloc(AVAudioResampleContext *avr, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels, int sample_rate, int apply_map){AudioConvert *ac;int in_planar, out_planar;ac=av_mallocz(sizeof(*ac));if(!ac) return NULL;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);return NULL;}return ac;}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;}else if(in_planar) ac->func_type=CONV_FUNC_TYPE_INTERLEAVE;else ac->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);return ac;}int ff_audio_convert(AudioConvert *ac, AudioData *out, AudioData *in){int use_generic=1;int len=in->nb_samples;int p;if(ac->dc){av_log(ac->avr, AV_LOG_TRACE,"%d samples - audio_convert: %s to %s (dithered)\n", len, av_get_sample_fmt_name(ac->in_fmt), av_get_sample_fmt_name(ac->out_fmt));return ff_convert_dither(ac-> in
av_cold void ff_psdsp_init_x86(PSDSPContext *s)
Definition: aacpsdsp_init.c:52
void ff_ps_stereo_interpolate_ipdopd_sse3(float(*l)[2], float(*r)[2], float h[2][4], float h_step[2][4], int len)
#define src0
Definition: h264pred.c:138
int av_get_cpu_flags(void)
Return the flags which specify extensions supported by the CPU.
Definition: cpu.c:93
GLint GLenum GLboolean GLsizei stride
Definition: opengl_enc.c:104
void ff_ps_hybrid_synthesis_deint_sse(float out[2][38][64], float(*in)[32][2], int i, int len)
void(* hybrid_analysis_ileave)(INTFLOAT(*out)[32][2], INTFLOAT L[2][38][64], int i, int len)
Definition: aacpsdsp.h:39
int len
void ff_ps_stereo_interpolate_sse3(float(*l)[2], float(*r)[2], float h[2][4], float h_step[2][4], int len)
FILE * out
Definition: movenc.c:54