re_rav1d 0.1.2

Rust port of the dav1d AV1 decoder
Documentation 
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

/*
 * Copyright © 2018, VideoLAN and dav1d authors
 * Copyright © 2018, Two Orioles, LLC
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright notice, this
 *    list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright notice,
 *    this list of conditions and the following disclaimer in the documentation
 *    and/or other materials provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
 * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
 * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include "config.h"

#include "src/mc.h"
#include "src/cpu.h"

#define decl_8tap_gen(decl_name, fn_name, opt) \
    decl_##decl_name##_fn(BF(dav1d_##fn_name##_8tap_regular,        opt)); \
    decl_##decl_name##_fn(BF(dav1d_##fn_name##_8tap_regular_smooth, opt)); \
    decl_##decl_name##_fn(BF(dav1d_##fn_name##_8tap_regular_sharp,  opt)); \
    decl_##decl_name##_fn(BF(dav1d_##fn_name##_8tap_smooth_regular, opt)); \
    decl_##decl_name##_fn(BF(dav1d_##fn_name##_8tap_smooth,         opt)); \
    decl_##decl_name##_fn(BF(dav1d_##fn_name##_8tap_smooth_sharp,   opt)); \
    decl_##decl_name##_fn(BF(dav1d_##fn_name##_8tap_sharp_regular,  opt)); \
    decl_##decl_name##_fn(BF(dav1d_##fn_name##_8tap_sharp_smooth,   opt)); \
    decl_##decl_name##_fn(BF(dav1d_##fn_name##_8tap_sharp,          opt))

#define decl_8tap_fns(opt) \
    decl_8tap_gen(mc,  put,  opt); \
    decl_8tap_gen(mct, prep, opt)

#define init_8tap_gen(name, opt) \
    init_##name##_fn(FILTER_2D_8TAP_REGULAR,        8tap_regular,        opt); \
    init_##name##_fn(FILTER_2D_8TAP_REGULAR_SMOOTH, 8tap_regular_smooth, opt); \
    init_##name##_fn(FILTER_2D_8TAP_REGULAR_SHARP,  8tap_regular_sharp,  opt); \
    init_##name##_fn(FILTER_2D_8TAP_SMOOTH_REGULAR, 8tap_smooth_regular, opt); \
    init_##name##_fn(FILTER_2D_8TAP_SMOOTH,         8tap_smooth,         opt); \
    init_##name##_fn(FILTER_2D_8TAP_SMOOTH_SHARP,   8tap_smooth_sharp,   opt); \
    init_##name##_fn(FILTER_2D_8TAP_SHARP_REGULAR,  8tap_sharp_regular,  opt); \
    init_##name##_fn(FILTER_2D_8TAP_SHARP_SMOOTH,   8tap_sharp_smooth,   opt); \
    init_##name##_fn(FILTER_2D_8TAP_SHARP,          8tap_sharp,          opt)

#define init_8tap_fns(opt) \
    init_8tap_gen(mc,  opt); \
    init_8tap_gen(mct, opt)

decl_8tap_fns(neon);
decl_8tap_fns(neon_dotprod);
decl_8tap_fns(neon_i8mm);

decl_mc_fn(BF(dav1d_put_bilin, neon));
decl_mct_fn(BF(dav1d_prep_bilin, neon));

decl_avg_fn(BF(dav1d_avg, neon));
decl_w_avg_fn(BF(dav1d_w_avg, neon));
decl_mask_fn(BF(dav1d_mask, neon));
decl_blend_fn(BF(dav1d_blend, neon));
decl_blend_dir_fn(BF(dav1d_blend_h, neon));
decl_blend_dir_fn(BF(dav1d_blend_v, neon));

decl_w_mask_fn(BF(dav1d_w_mask_444, neon));
decl_w_mask_fn(BF(dav1d_w_mask_422, neon));
decl_w_mask_fn(BF(dav1d_w_mask_420, neon));

decl_warp8x8_fn(BF(dav1d_warp_affine_8x8, neon));
decl_warp8x8t_fn(BF(dav1d_warp_affine_8x8t, neon));

decl_emu_edge_fn(BF(dav1d_emu_edge, neon));

static ALWAYS_INLINE void mc_dsp_init_arm(Dav1dMCDSPContext *const c) {
#define init_mc_fn(type, name, suffix) \
    c->mc[type] = BF(dav1d_put_##name, suffix)
#define init_mct_fn(type, name, suffix) \
    c->mct[type] = BF(dav1d_prep_##name, suffix)
    const unsigned flags = dav1d_get_cpu_flags();

    if (!(flags & DAV1D_ARM_CPU_FLAG_NEON)) return;

    init_8tap_fns(neon);

    init_mc_fn (FILTER_2D_BILINEAR, bilin, neon);
    init_mct_fn(FILTER_2D_BILINEAR, bilin, neon);

    c->avg = BF(dav1d_avg, neon);
    c->w_avg = BF(dav1d_w_avg, neon);
    c->mask = BF(dav1d_mask, neon);
    c->blend = BF(dav1d_blend, neon);
    c->blend_h = BF(dav1d_blend_h, neon);
    c->blend_v = BF(dav1d_blend_v, neon);
    c->w_mask[0] = BF(dav1d_w_mask_444, neon);
    c->w_mask[1] = BF(dav1d_w_mask_422, neon);
    c->w_mask[2] = BF(dav1d_w_mask_420, neon);
    c->warp8x8 = BF(dav1d_warp_affine_8x8, neon);
    c->warp8x8t = BF(dav1d_warp_affine_8x8t, neon);
    c->emu_edge = BF(dav1d_emu_edge, neon);

#if ARCH_AARCH64 && BITDEPTH == 8
#if HAVE_DOTPROD
    if (!(flags & DAV1D_ARM_CPU_FLAG_DOTPROD)) return;

    init_8tap_fns(neon_dotprod);
#endif  // HAVE_DOTPROD

#if HAVE_I8MM
    if (!(flags & DAV1D_ARM_CPU_FLAG_I8MM)) return;

    init_8tap_fns(neon_i8mm);
#endif  // HAVE_I8MM
#endif  // ARCH_AARCH64 && BITDEPTH == 8
}