FFmpeg
mdct15_init.c
Go to the documentation of this file.
1 /*
2  * SIMD optimized non-power-of-two MDCT functions
3  *
4  * Copyright (C) 2017 Rostislav Pehlivanov <atomnuker@gmail.com>
5  *
6  * This file is part of FFmpeg.
7  *
8  * FFmpeg is free software; you can redistribute it and/or
9  * modify it under the terms of the GNU Lesser General Public
10  * License as published by the Free Software Foundation; either
11  * version 2.1 of the License, or (at your option) any later version.
12  *
13  * FFmpeg is distributed in the hope that it will be useful,
14  * but WITHOUT ANY WARRANTY; without even the implied warranty of
15  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16  * Lesser General Public License for more details.
17  *
18  * You should have received a copy of the GNU Lesser General Public
19  * License along with FFmpeg; if not, write to the Free Software
20  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
21  */
22 
23 #include "config.h"
24 
25 #include "libavutil/x86/cpu.h"
26 #include "libavcodec/mdct15.h"
27 
28 void ff_mdct15_postreindex_sse3(FFTComplex *out, FFTComplex *in, FFTComplex *exp, int *lut, ptrdiff_t len8);
29 void ff_mdct15_postreindex_avx2(FFTComplex *out, FFTComplex *in, FFTComplex *exp, int *lut, ptrdiff_t len8);
30 
32 
34 {
35  int k;
36  FFTComplex tmp[30];
37 
38  /* 5-point FFT twiddles */
39  s->exptab[60].re = s->exptab[60].im = s->exptab[19].re;
40  s->exptab[61].re = s->exptab[61].im = s->exptab[19].im;
41  s->exptab[62].re = s->exptab[62].im = s->exptab[20].re;
42  s->exptab[63].re = s->exptab[63].im = s->exptab[20].im;
43 
44  /* 15-point FFT twiddles */
45  for (k = 0; k < 5; k++) {
46  tmp[6*k + 0] = s->exptab[k + 0];
47  tmp[6*k + 2] = s->exptab[k + 5];
48  tmp[6*k + 4] = s->exptab[k + 10];
49 
50  tmp[6*k + 1] = s->exptab[2 * (k + 0)];
51  tmp[6*k + 3] = s->exptab[2 * (k + 5)];
52  tmp[6*k + 5] = s->exptab[2 * k + 5 ];
53  }
54 
55  for (k = 0; k < 6; k++) {
56  FFTComplex ac_exp[] = {
57  { tmp[6*1 + k].re, tmp[6*1 + k].re },
58  { tmp[6*2 + k].re, tmp[6*2 + k].re },
59  { tmp[6*3 + k].re, tmp[6*3 + k].re },
60  { tmp[6*4 + k].re, tmp[6*4 + k].re },
61  { tmp[6*1 + k].im, -tmp[6*1 + k].im },
62  { tmp[6*2 + k].im, -tmp[6*2 + k].im },
63  { tmp[6*3 + k].im, -tmp[6*3 + k].im },
64  { tmp[6*4 + k].im, -tmp[6*4 + k].im },
65  };
66  memcpy(s->exptab + 8*k, ac_exp, 8*sizeof(FFTComplex));
67  }
68 
69  /* Specialcase when k = 0 */
70  for (k = 0; k < 3; k++) {
71  FFTComplex dc_exp[] = {
72  { tmp[2*k + 0].re, -tmp[2*k + 0].im },
73  { tmp[2*k + 0].im, tmp[2*k + 0].re },
74  { tmp[2*k + 1].re, -tmp[2*k + 1].im },
75  { tmp[2*k + 1].im, tmp[2*k + 1].re },
76  };
77  memcpy(s->exptab + 8*6 + 4*k, dc_exp, 4*sizeof(FFTComplex));
78  }
79 }
80 
82 {
83  int adjust_twiddles = 0;
85 
87  s->postreindex = ff_mdct15_postreindex_sse3;
88 
89  if (ARCH_X86_64 && EXTERNAL_AVX(cpu_flags)) {
90  s->fft15 = ff_fft15_avx;
91  adjust_twiddles = 1;
92  }
93 
94  if (ARCH_X86_64 && EXTERNAL_AVX2_FAST(cpu_flags))
95  s->postreindex = ff_mdct15_postreindex_avx2;
96 
97  if (adjust_twiddles)
99 }
stride
int stride
Definition: mace.c:144
cpu.h
out
FILE * out
Definition: movenc.c:54
ff_mdct15_postreindex_avx2
void ff_mdct15_postreindex_avx2(FFTComplex *out, FFTComplex *in, FFTComplex *exp, int *lut, ptrdiff_t len8)
EXTERNAL_AVX2_FAST
#define EXTERNAL_AVX2_FAST(flags)
Definition: cpu.h:79
tmp
static uint8_t tmp[11]
Definition: aes_ctr.c:27
mdct15.h
av_get_cpu_flags
int av_get_cpu_flags(void)
Return the flags which specify extensions supported by the CPU.
Definition: cpu.c:95
perm_twiddles
static void perm_twiddles(MDCT15Context *s)
Definition: mdct15_init.c:33
cpu_flags
static atomic_int cpu_flags
Definition: cpu.c:50
av_cold
#define av_cold
Definition: attributes.h:90
s
#define s(width, name)
Definition: cbs_vp9.c:257
exptab
static struct @135 * exptab
MDCT15Context
Definition: mdct15.h:30
EXTERNAL_SSE3
#define EXTERNAL_SSE3(flags)
Definition: cpu.h:62
exp
int8_t exp
Definition: eval.c:72
ff_mdct15_init_x86
av_cold void ff_mdct15_init_x86(MDCT15Context *s)
Definition: mdct15_init.c:81
in
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
Definition: audio_convert.c:326
ff_mdct15_postreindex_sse3
void ff_mdct15_postreindex_sse3(FFTComplex *out, FFTComplex *in, FFTComplex *exp, int *lut, ptrdiff_t len8)
ff_fft15_avx
void ff_fft15_avx(FFTComplex *out, FFTComplex *in, FFTComplex *exptab, ptrdiff_t stride)
EXTERNAL_AVX
#define EXTERNAL_AVX(flags)
Definition: cpu.h:70
FFTComplex
Definition: avfft.h:37