FFmpeg
 All Data Structures Namespaces Files Functions Variables Typedefs Enumerations Enumerator Macros Groups Pages
float_dsp_init.c
Go to the documentation of this file.
1 /*
2  * This file is part of FFmpeg.
3  *
4  * FFmpeg is free software; you can redistribute it and/or
5  * modify it under the terms of the GNU Lesser General Public
6  * License as published by the Free Software Foundation; either
7  * version 2.1 of the License, or (at your option) any later version.
8  *
9  * FFmpeg is distributed in the hope that it will be useful,
10  * but WITHOUT ANY WARRANTY; without even the implied warranty of
11  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
12  * Lesser General Public License for more details.
13  *
14  * You should have received a copy of the GNU Lesser General Public
15  * License along with FFmpeg; if not, write to the Free Software
16  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
17  */
18 
19 #include "config.h"
20 
21 #include "libavutil/attributes.h"
22 #include "libavutil/cpu.h"
23 #include "libavutil/float_dsp.h"
24 #include "cpu.h"
25 #include "asm.h"
26 
27 void ff_vector_fmul_sse(float *dst, const float *src0, const float *src1,
28  int len);
29 void ff_vector_fmul_avx(float *dst, const float *src0, const float *src1,
30  int len);
31 
32 void ff_vector_fmac_scalar_sse(float *dst, const float *src, float mul,
33  int len);
34 void ff_vector_fmac_scalar_avx(float *dst, const float *src, float mul,
35  int len);
36 void ff_vector_fmac_scalar_fma3(float *dst, const float *src, float mul,
37  int len);
38 
39 void ff_vector_fmul_scalar_sse(float *dst, const float *src, float mul,
40  int len);
41 
42 void ff_vector_dmul_scalar_sse2(double *dst, const double *src,
43  double mul, int len);
44 void ff_vector_dmul_scalar_avx(double *dst, const double *src,
45  double mul, int len);
46 
47 void ff_vector_fmul_window_3dnowext(float *dst, const float *src0,
48  const float *src1, const float *win, int len);
49 void ff_vector_fmul_window_sse(float *dst, const float *src0,
50  const float *src1, const float *win, int len);
51 
52 void ff_vector_fmul_add_sse(float *dst, const float *src0, const float *src1,
53  const float *src2, int len);
54 void ff_vector_fmul_add_avx(float *dst, const float *src0, const float *src1,
55  const float *src2, int len);
56 void ff_vector_fmul_add_fma3(float *dst, const float *src0, const float *src1,
57  const float *src2, int len);
58 
59 void ff_vector_fmul_reverse_sse(float *dst, const float *src0,
60  const float *src1, int len);
61 void ff_vector_fmul_reverse_avx(float *dst, const float *src0,
62  const float *src1, int len);
63 
64 float ff_scalarproduct_float_sse(const float *v1, const float *v2, int order);
65 
66 void ff_butterflies_float_sse(float *src0, float *src1, int len);
67 
69 {
70  int cpu_flags = av_get_cpu_flags();
71 
72  if (EXTERNAL_AMD3DNOWEXT(cpu_flags)) {
74  }
75  if (EXTERNAL_SSE(cpu_flags)) {
84  }
85  if (EXTERNAL_SSE2(cpu_flags)) {
87  }
88  if (EXTERNAL_AVX_FAST(cpu_flags)) {
94  }
95  if (EXTERNAL_FMA3(cpu_flags) && !(cpu_flags & AV_CPU_FLAG_AVXSLOW)) {
98  }
99 }
float(* scalarproduct_float)(const float *v1, const float *v2, int len)
Calculate the scalar product of two vectors of floats.
Definition: float_dsp.h:159
void(* vector_fmul_reverse)(float *dst, const float *src0, const float *src1, int len)
Calculate the entry wise product of two vectors of floats, and store the result in a vector of floats...
Definition: float_dsp.h:138
#define EXTERNAL_SSE(flags)
Definition: cpu.h:55
Macro definitions for various function/variable attributes.
void(* vector_fmac_scalar)(float *dst, const float *src, float mul, int len)
Multiply a vector of floats by a scalar float and add to destination vector.
Definition: float_dsp.h:54
void(* vector_fmul_window)(float *dst, const float *src0, const float *src1, const float *win, int len)
Overlap/add with window function.
Definition: float_dsp.h:103
void ff_vector_fmul_window_sse(float *dst, const float *src0, const float *src1, const float *win, int len)
#define av_cold
Definition: attributes.h:74
void ff_vector_fmul_reverse_avx(float *dst, const float *src0, const float *src1, int len)
av_cold void ff_float_dsp_init_x86(AVFloatDSPContext *fdsp)
void ff_vector_fmul_window_3dnowext(float *dst, const float *src0, const float *src1, const float *win, int len)
float ff_scalarproduct_float_sse(const float *v1, const float *v2, int order)
#define EXTERNAL_AVX_FAST(flags)
Definition: cpu.h:66
#define EXTERNAL_SSE2(flags)
Definition: cpu.h:56
void(* vector_fmul)(float *dst, const float *src0, const float *src1, int len)
Calculate the entry wise product of two vectors of floats and store the result in a vector of floats...
Definition: float_dsp.h:38
void(* butterflies_float)(float *av_restrict v1, float *av_restrict v2, int len)
Calculate the sum and difference of two vectors of floats.
Definition: float_dsp.h:148
void ff_vector_fmul_add_avx(float *dst, const float *src0, const float *src1, const float *src2, int len)
void(* vector_dmul_scalar)(double *dst, const double *src, double mul, int len)
Multiply a vector of double by a scalar double.
Definition: float_dsp.h:84
#define EXTERNAL_AMD3DNOWEXT(flags)
Definition: cpu.h:52
void(* vector_fmul_scalar)(float *dst, const float *src, float mul, int len)
Multiply a vector of floats by a scalar float.
Definition: float_dsp.h:69
void ff_vector_fmac_scalar_avx(float *dst, const float *src, float mul, int len)
void ff_vector_dmul_scalar_sse2(double *dst, const double *src, double mul, int len)
AVS_Value src
Definition: avisynth_c.h:482
#define AV_CPU_FLAG_AVXSLOW
AVX supported, but slow when using YMM registers (e.g. Bulldozer)
Definition: cpu.h:46
void ff_butterflies_float_sse(float *src0, float *src1, int len)
void(* vector_fmul_add)(float *dst, const float *src0, const float *src1, const float *src2, int len)
Calculate the entry wise product of two vectors of floats, add a third vector of floats and store the...
Definition: float_dsp.h:121
void ff_vector_dmul_scalar_avx(double *dst, const double *src, double mul, int len)
int av_get_cpu_flags(void)
Return the flags which specify extensions supported by the CPU.
Definition: cpu.c:76
void ff_vector_fmul_sse(float *dst, const float *src0, const float *src1, int len)
void ff_vector_fmac_scalar_sse(float *dst, const float *src, float mul, int len)
void ff_vector_fmul_scalar_sse(float *dst, const float *src, float mul, int len)
void ff_vector_fmul_reverse_sse(float *dst, const float *src0, const float *src1, int len)
void ff_vector_fmul_add_sse(float *dst, const float *src0, const float *src1, const float *src2, int len)
#define EXTERNAL_FMA3(flags)
Definition: cpu.h:69
int len
void ff_vector_fmac_scalar_fma3(float *dst, const float *src, float mul, int len)
void ff_vector_fmul_avx(float *dst, const float *src0, const float *src1, int len)
void ff_vector_fmul_add_fma3(float *dst, const float *src0, const float *src1, const float *src2, int len)