2 * ARM NEON optimised DSP functions
3 * Copyright (c) 2008 Mans Rullgard <mans@mansr.com>
5 * This file is part of FFmpeg.
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.
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.
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
24 #include "libavutil/attributes.h"
25 #include "libavcodec/avcodec.h"
26 #include "dsputil_arm.h"
28 void ff_simple_idct_neon(int16_t *data);
29 void ff_simple_idct_put_neon(uint8_t *dest, int line_size, int16_t *data);
30 void ff_simple_idct_add_neon(uint8_t *dest, int line_size, int16_t *data);
32 void ff_clear_block_neon(int16_t *block);
33 void ff_clear_blocks_neon(int16_t *blocks);
35 void ff_add_pixels_clamped_neon(const int16_t *, uint8_t *, int);
36 void ff_put_pixels_clamped_neon(const int16_t *, uint8_t *, int);
37 void ff_put_signed_pixels_clamped_neon(const int16_t *, uint8_t *, int);
39 void ff_vector_clipf_neon(float *dst, const float *src, float min, float max,
41 void ff_vector_clip_int32_neon(int32_t *dst, const int32_t *src, int32_t min,
42 int32_t max, unsigned int len);
44 int32_t ff_scalarproduct_int16_neon(const int16_t *v1, const int16_t *v2, int len);
45 int32_t ff_scalarproduct_and_madd_int16_neon(int16_t *v1, const int16_t *v2,
46 const int16_t *v3, int len, int mul);
48 av_cold void ff_dsputil_init_neon(DSPContext *c, AVCodecContext *avctx)
50 const int high_bit_depth = avctx->bits_per_raw_sample > 8;
52 if (!avctx->lowres && avctx->bits_per_raw_sample <= 8) {
53 if (avctx->idct_algo == FF_IDCT_AUTO ||
54 avctx->idct_algo == FF_IDCT_SIMPLENEON) {
55 c->idct_put = ff_simple_idct_put_neon;
56 c->idct_add = ff_simple_idct_add_neon;
57 c->idct = ff_simple_idct_neon;
58 c->idct_permutation_type = FF_PARTTRANS_IDCT_PERM;
62 if (!high_bit_depth) {
63 c->clear_block = ff_clear_block_neon;
64 c->clear_blocks = ff_clear_blocks_neon;
67 c->add_pixels_clamped = ff_add_pixels_clamped_neon;
68 c->put_pixels_clamped = ff_put_pixels_clamped_neon;
69 c->put_signed_pixels_clamped = ff_put_signed_pixels_clamped_neon;
71 c->vector_clipf = ff_vector_clipf_neon;
72 c->vector_clip_int32 = ff_vector_clip_int32_neon;
74 c->scalarproduct_int16 = ff_scalarproduct_int16_neon;
75 c->scalarproduct_and_madd_int16 = ff_scalarproduct_and_madd_int16_neon;