1/*
2 * x86-optimized AC-3 DSP functions
3 * Copyright (c) 2011 Justin Ruggles
4 *
5 * This file is part of FFmpeg.
6 *
7 * FFmpeg is free software; you can redistribute it and/or
8 * modify it under the terms of the GNU Lesser General Public
9 * License as published by the Free Software Foundation; either
10 * version 2.1 of the License, or (at your option) any later version.
11 *
12 * FFmpeg is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
15 * Lesser General Public License for more details.
16 *
17 * You should have received a copy of the GNU Lesser General Public
18 * License along with FFmpeg; if not, write to the Free Software
19 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20 */
21
22#include "libavutil/attributes.h"
23#include "libavutil/x86/asm.h"
24#include "libavutil/x86/cpu.h"
25#include "libavcodec/ac3dsp.h"
26
27void ff_ac3_exponent_min_sse2  (uint8_t *exp, int num_reuse_blocks, int nb_coefs);
28
29void ff_float_to_fixed24_sse2 (int32_t *dst, const float *src, unsigned int len);
30
31int ff_ac3_compute_mantissa_size_sse2(uint16_t mant_cnt[6][16]);
32
33void ff_ac3_extract_exponents_sse2 (uint8_t *exp, int32_t *coef, int nb_coefs);
34void ff_ac3_extract_exponents_ssse3(uint8_t *exp, int32_t *coef, int nb_coefs);
35
36av_cold void ff_ac3dsp_init_x86(AC3DSPContext *c, int bit_exact)
37{
38    int cpu_flags = av_get_cpu_flags();
39
40    if (EXTERNAL_SSE2(cpu_flags)) {
41        c->ac3_exponent_min = ff_ac3_exponent_min_sse2;
42        c->float_to_fixed24 = ff_float_to_fixed24_sse2;
43        c->compute_mantissa_size = ff_ac3_compute_mantissa_size_sse2;
44        c->extract_exponents = ff_ac3_extract_exponents_sse2;
45    }
46
47    if (EXTERNAL_SSSE3(cpu_flags)) {
48        if (!(cpu_flags & AV_CPU_FLAG_ATOM))
49            c->extract_exponents = ff_ac3_extract_exponents_ssse3;
50    }
51}
52
53#define DOWNMIX_FUNC_OPT(ch, opt)                                       \
54void ff_ac3_downmix_ ## ch ## _to_1_ ## opt(float **samples,            \
55                                            float **matrix, int len);   \
56void ff_ac3_downmix_ ## ch ## _to_2_ ## opt(float **samples,            \
57                                            float **matrix, int len);
58
59#define DOWNMIX_FUNCS(opt)   \
60    DOWNMIX_FUNC_OPT(3, opt) \
61    DOWNMIX_FUNC_OPT(4, opt) \
62    DOWNMIX_FUNC_OPT(5, opt) \
63    DOWNMIX_FUNC_OPT(6, opt)
64
65DOWNMIX_FUNCS(sse)
66DOWNMIX_FUNCS(avx)
67DOWNMIX_FUNCS(fma3)
68
69void ff_ac3dsp_set_downmix_x86(AC3DSPContext *c)
70{
71    int cpu_flags = av_get_cpu_flags();
72
73#define SET_DOWNMIX(ch, suf, SUF)                                       \
74    if (ch == c->in_channels) {                                         \
75        if (EXTERNAL_ ## SUF (cpu_flags)) {                             \
76            if (c->out_channels == 1)                                   \
77                c->downmix = ff_ac3_downmix_ ## ch ## _to_1_ ## suf;    \
78            else                                                        \
79                c->downmix = ff_ac3_downmix_ ## ch ## _to_2_ ## suf;    \
80        }                                                               \
81    }
82
83#define SET_DOWNMIX_ALL(suf, SUF)                   \
84    SET_DOWNMIX(3, suf, SUF)                        \
85    SET_DOWNMIX(4, suf, SUF)                        \
86    SET_DOWNMIX(5, suf, SUF)                        \
87    SET_DOWNMIX(6, suf, SUF)
88
89    SET_DOWNMIX_ALL(sse,  SSE)
90    if (!(cpu_flags & AV_CPU_FLAG_AVXSLOW)) {
91        SET_DOWNMIX_ALL(avx,  AVX)
92        SET_DOWNMIX_ALL(fma3, FMA3)
93    }
94}
95