2 * ARM NEON optimised DSP functions
3 * Copyright (c) 2008 Mans Rullgard <mans@mansr.com>
5 * This file is part of Libav.
7 * Libav 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 * Libav 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 Libav; 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 "libavcodec/dsputil.h"
27 #include "dsputil_arm.h"
29 void ff_simple_idct_neon(int16_t *data
);
30 void ff_simple_idct_put_neon(uint8_t *dest
, int line_size
, int16_t *data
);
31 void ff_simple_idct_add_neon(uint8_t *dest
, int line_size
, int16_t *data
);
33 void ff_add_pixels_clamped_neon(const int16_t *, uint8_t *, int);
34 void ff_put_pixels_clamped_neon(const int16_t *, uint8_t *, int);
35 void ff_put_signed_pixels_clamped_neon(const int16_t *, uint8_t *, int);
37 void ff_vector_clipf_neon(float *dst
, const float *src
, float min
, float max
,
39 void ff_vector_clip_int32_neon(int32_t *dst
, const int32_t *src
, int32_t min
,
40 int32_t max
, unsigned int len
);
42 int32_t ff_scalarproduct_int16_neon(const int16_t *v1
, const int16_t *v2
, int len
);
44 av_cold
void ff_dsputil_init_neon(DSPContext
*c
, AVCodecContext
*avctx
,
45 unsigned high_bit_depth
)
47 if (!high_bit_depth
) {
48 if (avctx
->idct_algo
== FF_IDCT_AUTO
||
49 avctx
->idct_algo
== FF_IDCT_SIMPLENEON
) {
50 c
->idct_put
= ff_simple_idct_put_neon
;
51 c
->idct_add
= ff_simple_idct_add_neon
;
52 c
->idct
= ff_simple_idct_neon
;
53 c
->idct_permutation_type
= FF_PARTTRANS_IDCT_PERM
;
57 c
->add_pixels_clamped
= ff_add_pixels_clamped_neon
;
58 c
->put_pixels_clamped
= ff_put_pixels_clamped_neon
;
59 c
->put_signed_pixels_clamped
= ff_put_signed_pixels_clamped_neon
;
61 c
->vector_clipf
= ff_vector_clipf_neon
;
62 c
->vector_clip_int32
= ff_vector_clip_int32_neon
;
64 c
->scalarproduct_int16
= ff_scalarproduct_int16_neon
;