aboutsummaryrefslogtreecommitdiff
path: root/libavcodec/dcadsp.c
blob: 412c1dcf1f219e3b946bb53a5533e4265377748a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
/*
 * Copyright (c) 2004 Gildas Bazin
 * Copyright (c) 2010 Mans Rullgard <mans@mansr.com>
 *
 * This file is part of FFmpeg.
 *
 * FFmpeg is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * FFmpeg is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with FFmpeg; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

#include "config.h"

#include "libavutil/attributes.h"
#include "libavutil/intreadwrite.h"

#include "dcadsp.h"
#include "dcamath.h"

static void decode_hf_c(float dst[DCA_SUBBANDS][8],
                        const int32_t vq_num[DCA_SUBBANDS],
                        const int8_t hf_vq[1024][32], intptr_t vq_offset,
                        int32_t scale[DCA_SUBBANDS][2],
                        intptr_t start, intptr_t end)
{
    int i, l;

    for (l = start; l < end; l++) {
        /* 1 vector -> 32 samples but we only need the 8 samples
         * for this subsubframe. */
        const int8_t *ptr = &hf_vq[vq_num[l]][vq_offset];
        float fscale = scale[l][0] * (1 / 16.0);
        for (i = 0; i < 8; i++)
            dst[l][i] = ptr[i] * fscale;
    }
}

static void decode_hf_int_c(int32_t dst[DCA_SUBBANDS][8],
                            const int32_t vq_num[DCA_SUBBANDS],
                            const int8_t hf_vq[1024][32], intptr_t vq_offset,
                            int32_t scale[DCA_SUBBANDS][2],
                            intptr_t start, intptr_t end)
{
    int i, j;

    for (j = start; j < end; j++) {
        const int8_t *ptr = &hf_vq[vq_num[j]][vq_offset];
        for (i = 0; i < 8; i++)
            dst[j][i] = ptr[i] * scale[j][0] + 8 >> 4;
    }
}

static inline void dca_lfe_fir(float *out, const float *in, const float *coefs,
                               int decifactor)
{
    float *out2    = out + 2 * decifactor - 1;
    int num_coeffs = 256 / decifactor;
    int j, k;

    /* One decimated sample generates 2*decifactor interpolated ones */
    for (k = 0; k < decifactor; k++) {
        float v0 = 0.0;
        float v1 = 0.0;
        for (j = 0; j < num_coeffs; j++, coefs++) {
            v0 += in[-j]                 * *coefs;
            v1 += in[j + 1 - num_coeffs] * *coefs;
        }
        *out++  = v0;
        *out2-- = v1;
    }
}

static void dca_qmf_32_subbands(float samples_in[32][8], int sb_act,
                                SynthFilterContext *synth, FFTContext *imdct,
                                float synth_buf_ptr[512],
                                int *synth_buf_offset, float synth_buf2[32],
                                const float window[512], float *samples_out,
                                float raXin[32], float scale)
{
    int i;
    int subindex;

    for (i = sb_act; i < 32; i++)
        raXin[i] = 0.0;

    /* Reconstructed channel sample index */
    for (subindex = 0; subindex < 8; subindex++) {
        /* Load in one sample from each subband and clear inactive subbands */
        for (i = 0; i < sb_act; i++) {
            unsigned sign = (i - 1) & 2;
            uint32_t v    = AV_RN32A(&samples_in[i][subindex]) ^ sign << 30;
            AV_WN32A(&raXin[i], v);
        }

        synth->synth_filter_float(imdct, synth_buf_ptr, synth_buf_offset,
                                  synth_buf2, window, samples_out, raXin,
                                  scale);
        samples_out += 32;
    }
}

static void dequantize_c(int32_t *samples, uint32_t step_size, uint32_t scale)
{
    int64_t step = (int64_t)step_size * scale;
    int shift, i;
    int32_t step_scale;

    if (step > (1 << 23))
        shift = av_log2(step >> 23) + 1;
    else
        shift = 0;
    step_scale = (int32_t)(step >> shift);

    for (i = 0; i < 8; i++)
        samples[i] = dca_clip23(dca_norm((int64_t)samples[i] * step_scale, 22 - shift));
}

static void dca_lfe_fir0_c(float *out, const float *in, const float *coefs)
{
    dca_lfe_fir(out, in, coefs, 32);
}

static void dca_lfe_fir1_c(float *out, const float *in, const float *coefs)
{
    dca_lfe_fir(out, in, coefs, 64);
}

av_cold void ff_dcadsp_init(DCADSPContext *s)
{
    s->lfe_fir[0]      = dca_lfe_fir0_c;
    s->lfe_fir[1]      = dca_lfe_fir1_c;
    s->qmf_32_subbands = dca_qmf_32_subbands;
    s->decode_hf       = decode_hf_c;
    s->decode_hf_int   = decode_hf_int_c;
    s->dequantize      = dequantize_c;

    if (ARCH_AARCH64)
        ff_dcadsp_init_aarch64(s);
    if (ARCH_ARM)
        ff_dcadsp_init_arm(s);
    if (ARCH_X86)
        ff_dcadsp_init_x86(s);
}