1 /*
2  * Copyright (c) 2011 Mans Rullgard <mans@mansr.com>
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 <stdint.h>
22 
23 #include "libavutil/arm/cpu.h"
24 #include "libavutil/attributes.h"
25 #include "libavcodec/ac3dsp.h"
26 #include "config.h"
27 
28 void ff_ac3_exponent_min_neon(uint8_t *exp, int num_reuse_blocks, int nb_coefs);
29 int ff_ac3_max_msb_abs_int16_neon(const int16_t *src, int len);
30 void ff_ac3_lshift_int16_neon(int16_t *src, unsigned len, unsigned shift);
31 void ff_ac3_rshift_int32_neon(int32_t *src, unsigned len, unsigned shift);
32 void ff_float_to_fixed24_neon(int32_t *dst, const float *src, unsigned int len);
33 void ff_ac3_extract_exponents_neon(uint8_t *exp, int32_t *coef, int nb_coefs);
34 void ff_apply_window_int16_neon(int16_t *dst, const int16_t *src,
35                                 const int16_t *window, unsigned n);
36 void ff_ac3_sum_square_butterfly_int32_neon(int64_t sum[4],
37                                             const int32_t *coef0,
38                                             const int32_t *coef1,
39                                             int len);
40 void ff_ac3_sum_square_butterfly_float_neon(float sum[4],
41                                             const float *coef0,
42                                             const float *coef1,
43                                             int len);
44 
45 void ff_ac3_bit_alloc_calc_bap_armv6(int16_t *mask, int16_t *psd,
46                                      int start, int end,
47                                      int snr_offset, int floor,
48                                      const uint8_t *bap_tab, uint8_t *bap);
49 
50 void ff_ac3_update_bap_counts_arm(uint16_t mant_cnt[16], uint8_t *bap, int len);
51 
ff_ac3dsp_init_arm(AC3DSPContext * c,int bit_exact)52 av_cold void ff_ac3dsp_init_arm(AC3DSPContext *c, int bit_exact)
53 {
54     int cpu_flags = av_get_cpu_flags();
55 
56     c->update_bap_counts         = ff_ac3_update_bap_counts_arm;
57 
58     if (have_armv6(cpu_flags)) {
59         c->bit_alloc_calc_bap    = ff_ac3_bit_alloc_calc_bap_armv6;
60     }
61 
62     if (have_neon(cpu_flags)) {
63         c->ac3_exponent_min      = ff_ac3_exponent_min_neon;
64         c->ac3_max_msb_abs_int16 = ff_ac3_max_msb_abs_int16_neon;
65         c->ac3_lshift_int16      = ff_ac3_lshift_int16_neon;
66         c->ac3_rshift_int32      = ff_ac3_rshift_int32_neon;
67         c->float_to_fixed24      = ff_float_to_fixed24_neon;
68         c->extract_exponents     = ff_ac3_extract_exponents_neon;
69         c->apply_window_int16    = ff_apply_window_int16_neon;
70         c->sum_square_butterfly_int32 = ff_ac3_sum_square_butterfly_int32_neon;
71         c->sum_square_butterfly_float = ff_ac3_sum_square_butterfly_float_neon;
72     }
73 }
74