xref: /third_party/ffmpeg/libavcodec/ppc/hevcdsp.c (revision cabdff1a)
1/*
2 * SIMD-optimized IDCT functions for HEVC decoding
3 * Copyright (c) Alexandra Hajkova
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 "config.h"
23
24#include "libavutil/attributes.h"
25#include "libavutil/cpu.h"
26#include "libavutil/ppc/cpu.h"
27#include "libavutil/ppc/util_altivec.h"
28
29#include "libavcodec/hevcdsp.h"
30
31#if HAVE_ALTIVEC
32static const vec_s16 trans4[4] = {
33    { 64,  64, 64,  64, 64,  64, 64,  64 },
34    { 83,  36, 83,  36, 83,  36, 83,  36 },
35    { 64, -64, 64, -64, 64, -64, 64, -64 },
36    { 36, -83, 36, -83, 36, -83, 36, -83 },
37};
38
39static const vec_u8 mask[2] = {
40    { 0x00, 0x01, 0x08, 0x09, 0x10, 0x11, 0x18, 0x19, 0x02, 0x03, 0x0A, 0x0B, 0x12, 0x13, 0x1A, 0x1B },
41    { 0x04, 0x05, 0x0C, 0x0D, 0x14, 0x15, 0x1C, 0x1D, 0x06, 0x07, 0x0E, 0x0F, 0x16, 0x17, 0x1E, 0x1F },
42};
43
44static av_always_inline void transform4x4(vec_s16 src_01, vec_s16 src_23,
45                                          vec_s32 res[4], const int shift,
46                                          int16_t *coeffs)
47{
48    vec_s16 src_02, src_13;
49    vec_s32 zero = vec_splat_s32(0);
50    vec_s32 e0, o0, e1, o1;
51    vec_s32 add;
52
53    src_13 = vec_mergel(src_01, src_23);
54    src_02 = vec_mergeh(src_01, src_23);
55
56    e0 = vec_msums(src_02, trans4[0], zero);
57    o0 = vec_msums(src_13, trans4[1], zero);
58    e1 = vec_msums(src_02, trans4[2], zero);
59    o1 = vec_msums(src_13, trans4[3], zero);
60
61    switch(shift) {
62    case  7: add = vec_sl(vec_splat_s32(1), vec_splat_u32( 7 - 1)); break;
63    case 10: add = vec_sl(vec_splat_s32(1), vec_splat_u32(10 - 1)); break;
64    case 12: add = vec_sl(vec_splat_s32(1), vec_splat_u32(12 - 1)); break;
65    default: abort();
66    }
67
68    e0 = vec_add(e0, add);
69    e1 = vec_add(e1, add);
70
71    res[0] = vec_add(e0, o0);
72    res[1] = vec_add(e1, o1);
73    res[2] = vec_sub(e1, o1);
74    res[3] = vec_sub(e0, o0);
75}
76
77static av_always_inline void scale(vec_s32 res[4], vec_s16 res_packed[2],
78                                   const int shift)
79{
80    int i;
81    vec_u32 v_shift;
82
83    switch(shift) {
84    case  7: v_shift = vec_splat_u32(7) ; break;
85    case 10: v_shift = vec_splat_u32(10); break;
86    case 12: v_shift = vec_splat_u32(12); break;
87    default: abort();
88    }
89
90    for (i = 0; i < 4; i++)
91        res[i] = vec_sra(res[i], v_shift);
92
93    // clip16
94    res_packed[0] = vec_packs(res[0], res[1]);
95    res_packed[1] = vec_packs(res[2], res[3]);
96}
97
98#define FUNCDECL(a, depth) a ## _ ## depth ## _altivec
99#define FUNC(a, b) FUNCDECL(a, b)
100
101#define BIT_DEPTH 8
102#include "hevcdsp_template.c"
103#undef BIT_DEPTH
104
105#define BIT_DEPTH 10
106#include "hevcdsp_template.c"
107#undef BIT_DEPTH
108#endif /* HAVE_ALTIVEC */
109
110av_cold void ff_hevc_dsp_init_ppc(HEVCDSPContext *c, const int bit_depth)
111{
112#if HAVE_ALTIVEC
113    if (!PPC_ALTIVEC(av_get_cpu_flags()))
114        return;
115
116    if (bit_depth == 8)
117        c->idct[0] = ff_hevc_idct_4x4_8_altivec;
118    if (bit_depth == 10)
119        c->idct[0] = ff_hevc_idct_4x4_10_altivec;
120#endif /* HAVE_ALTIVEC */
121}
122