1 /*
2 * ARM-NEON-optimized IDCT functions
3 * Copyright (c) 2008 Mans Rullgard <mans@mansr.com>
4 * Copyright (c) 2017 Matthieu Bouron <matthieu.bouron@gmail.com>
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 "libavutil/attributes.h"
24 #include "libavutil/cpu.h"
25 #include "libavutil/arm/cpu.h"
26 #include "libavcodec/avcodec.h"
27 #include "libavcodec/idctdsp.h"
28 #include "idct.h"
29
30 void ff_put_pixels_clamped_neon(const int16_t *, uint8_t *, ptrdiff_t);
31 void ff_put_signed_pixels_clamped_neon(const int16_t *, uint8_t *, ptrdiff_t);
32 void ff_add_pixels_clamped_neon(const int16_t *, uint8_t *, ptrdiff_t);
33
ff_idctdsp_init_aarch64(IDCTDSPContext * c,AVCodecContext * avctx,unsigned high_bit_depth)34 av_cold void ff_idctdsp_init_aarch64(IDCTDSPContext *c, AVCodecContext *avctx,
35 unsigned high_bit_depth)
36 {
37 int cpu_flags = av_get_cpu_flags();
38
39 if (have_neon(cpu_flags)) {
40 if (!avctx->lowres && !high_bit_depth) {
41 if (avctx->idct_algo == FF_IDCT_AUTO ||
42 avctx->idct_algo == FF_IDCT_SIMPLEAUTO ||
43 avctx->idct_algo == FF_IDCT_SIMPLENEON) {
44 c->idct_put = ff_simple_idct_put_neon;
45 c->idct_add = ff_simple_idct_add_neon;
46 c->idct = ff_simple_idct_neon;
47 c->perm_type = FF_IDCT_PERM_PARTTRANS;
48 }
49 }
50
51 c->add_pixels_clamped = ff_add_pixels_clamped_neon;
52 c->put_pixels_clamped = ff_put_pixels_clamped_neon;
53 c->put_signed_pixels_clamped = ff_put_signed_pixels_clamped_neon;
54 }
55 }
56