1 /*****************************************************************************
2 * dct.h: aarch64 transform and zigzag
3 *****************************************************************************
4 * Copyright (C) 2009-2016 x264 project
6 * Authors: David Conrad <lessen42@gmail.com>
7 * Janne Grunau <janne-x264@jannau.net>
9 * This program is free software; you can redistribute it and/or modify
10 * it under the terms of the GNU General Public License as published by
11 * the Free Software Foundation; either version 2 of the License, or
12 * (at your option) any later version.
14 * This program is distributed in the hope that it will be useful,
15 * but WITHOUT ANY WARRANTY; without even the implied warranty of
16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
17 * GNU General Public License for more details.
19 * You should have received a copy of the GNU General Public License
20 * along with this program; if not, write to the Free Software
21 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
23 * This program is also available under a commercial proprietary license.
24 * For more information, contact us at licensing@x264.com.
25 *****************************************************************************/
27 #ifndef X264_AARCH64_DCT_H
28 #define X264_AARCH64_DCT_H
30 void x264_dct4x4dc_neon( int16_t d[16] );
31 void x264_idct4x4dc_neon( int16_t d[16] );
33 void x264_sub4x4_dct_neon( int16_t dct[16], uint8_t *pix1, uint8_t *pix2 );
34 void x264_sub8x8_dct_neon( int16_t dct[4][16], uint8_t *pix1, uint8_t *pix2 );
35 void x264_sub16x16_dct_neon( int16_t dct[16][16], uint8_t *pix1, uint8_t *pix2 );
37 void x264_add4x4_idct_neon( uint8_t *p_dst, int16_t dct[16] );
38 void x264_add8x8_idct_neon( uint8_t *p_dst, int16_t dct[4][16] );
39 void x264_add16x16_idct_neon( uint8_t *p_dst, int16_t dct[16][16] );
41 void x264_add8x8_idct_dc_neon( uint8_t *p_dst, int16_t dct[4] );
42 void x264_add16x16_idct_dc_neon( uint8_t *p_dst, int16_t dct[16] );
43 void x264_sub8x8_dct_dc_neon( int16_t dct[4], uint8_t *pix1, uint8_t *pix2 );
44 void x264_sub8x16_dct_dc_neon( int16_t dct[8], uint8_t *pix1, uint8_t *pix2 );
46 void x264_sub8x8_dct8_neon( int16_t dct[64], uint8_t *pix1, uint8_t *pix2 );
47 void x264_sub16x16_dct8_neon( int16_t dct[4][64], uint8_t *pix1, uint8_t *pix2 );
49 void x264_add8x8_idct8_neon( uint8_t *p_dst, int16_t dct[64] );
50 void x264_add16x16_idct8_neon( uint8_t *p_dst, int16_t dct[4][64] );
52 void x264_zigzag_scan_4x4_frame_neon( int16_t level[16], int16_t dct[16] );
53 void x264_zigzag_scan_4x4_field_neon( int16_t level[16], int16_t dct[16] );
54 void x264_zigzag_scan_8x8_frame_neon( int16_t level[64], int16_t dct[64] );
55 void x264_zigzag_scan_8x8_field_neon( int16_t level[64], int16_t dct[64] );
57 int x264_zigzag_sub_4x4_field_neon( dctcoef level[16], const pixel *p_src, pixel *p_dst );
58 int x264_zigzag_sub_4x4ac_field_neon( dctcoef level[16], const pixel *p_src, pixel *p_dst, dctcoef *dc );
59 int x264_zigzag_sub_4x4_frame_neon( dctcoef level[16], const pixel *p_src, pixel *p_dst );
60 int x264_zigzag_sub_4x4ac_frame_neon( dctcoef level[16], const pixel *p_src, pixel *p_dst, dctcoef *dc );
62 int x264_zigzag_sub_8x8_field_neon( dctcoef level[16], const pixel *p_src, pixel *p_dst );
63 int x264_zigzag_sub_8x8_frame_neon( dctcoef level[16], const pixel *p_src, pixel *p_dst );
65 void x264_zigzag_interleave_8x8_cavlc_neon( dctcoef *dst, dctcoef *src, uint8_t *nnz );