1/*
2 * Audio resampling
3 *
4 * Copyright (c) 2004-2012 Michael Niedermayer <michaelni@gmx.at>
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/attributes.h"
26#include "libavutil/cpu.h"
27#include "libavutil/avassert.h"
28
29#include "libavutil/aarch64/cpu.h"
30#include "libswresample/resample.h"
31
32#define DECLARE_RESAMPLE_COMMON_TEMPLATE(TYPE, DELEM, FELEM, FELEM2, OUT)                         \
33                                                                                                  \
34void ff_resample_common_apply_filter_x4_##TYPE##_neon(FELEM2 *acc, const DELEM *src,              \
35                                                      const FELEM *filter, int length);           \
36                                                                                                  \
37void ff_resample_common_apply_filter_x8_##TYPE##_neon(FELEM2 *acc, const DELEM *src,              \
38                                                      const FELEM *filter, int length);           \
39                                                                                                  \
40static int ff_resample_common_##TYPE##_neon(ResampleContext *c, void *dest, const void *source,   \
41                                            int n, int update_ctx)                                \
42{                                                                                                 \
43    DELEM *dst = dest;                                                                            \
44    const DELEM *src = source;                                                                    \
45    int dst_index;                                                                                \
46    int index = c->index;                                                                         \
47    int frac = c->frac;                                                                           \
48    int sample_index = 0;                                                                         \
49    int x4_aligned_filter_length = c->filter_length & ~3;                                         \
50    int x8_aligned_filter_length = c->filter_length & ~7;                                         \
51                                                                                                  \
52    while (index >= c->phase_count) {                                                             \
53        sample_index++;                                                                           \
54        index -= c->phase_count;                                                                  \
55    }                                                                                             \
56                                                                                                  \
57    for (dst_index = 0; dst_index < n; dst_index++) {                                             \
58        FELEM *filter = ((FELEM *) c->filter_bank) + c->filter_alloc * index;                     \
59                                                                                                  \
60        FELEM2 val = 0;                                                                             \
61        int i = 0;                                                                                \
62        if (x8_aligned_filter_length >= 8) {                                                      \
63            ff_resample_common_apply_filter_x8_##TYPE##_neon(&val, &src[sample_index],            \
64                                                             filter, x8_aligned_filter_length);   \
65            i += x8_aligned_filter_length;                                                        \
66                                                                                                  \
67        } else if (x4_aligned_filter_length >= 4) {                                               \
68            ff_resample_common_apply_filter_x4_##TYPE##_neon(&val, &src[sample_index],            \
69                                                             filter, x4_aligned_filter_length);   \
70            i += x4_aligned_filter_length;                                                        \
71        }                                                                                         \
72        for (; i < c->filter_length; i++) {                                                       \
73            val += src[sample_index + i] * (FELEM2)filter[i];                                     \
74        }                                                                                         \
75        OUT(dst[dst_index], val);                                                                 \
76                                                                                                  \
77        frac  += c->dst_incr_mod;                                                                 \
78        index += c->dst_incr_div;                                                                 \
79        if (frac >= c->src_incr) {                                                                \
80            frac -= c->src_incr;                                                                  \
81            index++;                                                                              \
82        }                                                                                         \
83                                                                                                  \
84        while (index >= c->phase_count) {                                                         \
85            sample_index++;                                                                       \
86            index -= c->phase_count;                                                              \
87        }                                                                                         \
88    }                                                                                             \
89                                                                                                  \
90    if (update_ctx) {                                                                             \
91        c->frac = frac;                                                                           \
92        c->index = index;                                                                         \
93    }                                                                                             \
94                                                                                                  \
95    return sample_index;                                                                          \
96}                                                                                                 \
97
98#define OUT(d, v) d = v
99DECLARE_RESAMPLE_COMMON_TEMPLATE(float, float, float, float, OUT)
100#undef OUT
101
102#define OUT(d, v) (v) = ((v) + (1<<(14)))>>15; (d) = av_clip_int16(v)
103DECLARE_RESAMPLE_COMMON_TEMPLATE(s16, int16_t, int16_t, int32_t, OUT)
104#undef OUT
105
106av_cold void swri_resample_dsp_aarch64_init(ResampleContext *c)
107{
108    int cpu_flags = av_get_cpu_flags();
109
110    if (!have_neon(cpu_flags))
111        return;
112
113    switch(c->format) {
114    case AV_SAMPLE_FMT_FLTP:
115        c->dsp.resample_common = ff_resample_common_float_neon;
116        break;
117    case AV_SAMPLE_FMT_S16P:
118        c->dsp.resample_common = ff_resample_common_s16_neon;
119        break;
120    }
121}
122