| 1 | /* |
| 2 | * This file is part of FFmpeg. |
| 3 | * |
| 4 | * FFmpeg is free software; you can redistribute it and/or |
| 5 | * modify it under the terms of the GNU Lesser General Public |
| 6 | * License as published by the Free Software Foundation; either |
| 7 | * version 2.1 of the License, or (at your option) any later version. |
| 8 | * |
| 9 | * FFmpeg is distributed in the hope that it will be useful, |
| 10 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 11 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 12 | * Lesser General Public License for more details. |
| 13 | * |
| 14 | * You should have received a copy of the GNU Lesser General Public |
| 15 | * License along with FFmpeg; if not, write to the Free Software |
| 16 | * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA |
| 17 | */ |
| 18 | |
| 19 | #include <stdint.h> |
| 20 | |
| 21 | #include "libavutil/attributes.h" |
| 22 | #include "libavcodec/vc1dsp.h" |
| 23 | #include "vc1dsp.h" |
| 24 | |
| 25 | #include "config.h" |
| 26 | |
| 27 | void ff_vc1_inv_trans_8x8_neon(int16_t *block); |
| 28 | void ff_vc1_inv_trans_4x8_neon(uint8_t *dest, int linesize, int16_t *block); |
| 29 | void ff_vc1_inv_trans_8x4_neon(uint8_t *dest, int linesize, int16_t *block); |
| 30 | void ff_vc1_inv_trans_4x4_neon(uint8_t *dest, int linesize, int16_t *block); |
| 31 | |
| 32 | void ff_vc1_inv_trans_8x8_dc_neon(uint8_t *dest, int linesize, int16_t *block); |
| 33 | void ff_vc1_inv_trans_4x8_dc_neon(uint8_t *dest, int linesize, int16_t *block); |
| 34 | void ff_vc1_inv_trans_8x4_dc_neon(uint8_t *dest, int linesize, int16_t *block); |
| 35 | void ff_vc1_inv_trans_4x4_dc_neon(uint8_t *dest, int linesize, int16_t *block); |
| 36 | |
| 37 | void ff_put_pixels8x8_neon(uint8_t *block, const uint8_t *pixels, |
| 38 | ptrdiff_t line_size, int rnd); |
| 39 | |
| 40 | #define DECL_PUT(X, Y) \ |
| 41 | void ff_put_vc1_mspel_mc##X##Y##_neon(uint8_t *dst, const uint8_t *src, \ |
| 42 | ptrdiff_t stride, int rnd); \ |
| 43 | static void ff_put_vc1_mspel_mc##X##Y##_16_neon(uint8_t *dst, const uint8_t *src, \ |
| 44 | ptrdiff_t stride, int rnd) \ |
| 45 | { \ |
| 46 | ff_put_vc1_mspel_mc##X##Y##_neon(dst+0, src+0, stride, rnd); \ |
| 47 | ff_put_vc1_mspel_mc##X##Y##_neon(dst+8, src+8, stride, rnd); \ |
| 48 | dst += 8*stride; src += 8*stride; \ |
| 49 | ff_put_vc1_mspel_mc##X##Y##_neon(dst+0, src+0, stride, rnd); \ |
| 50 | ff_put_vc1_mspel_mc##X##Y##_neon(dst+8, src+8, stride, rnd); \ |
| 51 | } |
| 52 | |
| 53 | DECL_PUT(1, 0) |
| 54 | DECL_PUT(2, 0) |
| 55 | DECL_PUT(3, 0) |
| 56 | |
| 57 | DECL_PUT(0, 1) |
| 58 | DECL_PUT(0, 2) |
| 59 | DECL_PUT(0, 3) |
| 60 | |
| 61 | DECL_PUT(1, 1) |
| 62 | DECL_PUT(1, 2) |
| 63 | DECL_PUT(1, 3) |
| 64 | |
| 65 | DECL_PUT(2, 1) |
| 66 | DECL_PUT(2, 2) |
| 67 | DECL_PUT(2, 3) |
| 68 | |
| 69 | DECL_PUT(3, 1) |
| 70 | DECL_PUT(3, 2) |
| 71 | DECL_PUT(3, 3) |
| 72 | |
| 73 | void ff_put_vc1_chroma_mc8_neon(uint8_t *dst, uint8_t *src, int stride, int h, |
| 74 | int x, int y); |
| 75 | void ff_avg_vc1_chroma_mc8_neon(uint8_t *dst, uint8_t *src, int stride, int h, |
| 76 | int x, int y); |
| 77 | void ff_put_vc1_chroma_mc4_neon(uint8_t *dst, uint8_t *src, int stride, int h, |
| 78 | int x, int y); |
| 79 | void ff_avg_vc1_chroma_mc4_neon(uint8_t *dst, uint8_t *src, int stride, int h, |
| 80 | int x, int y); |
| 81 | |
| 82 | #define FN_ASSIGN(X, Y) \ |
| 83 | dsp->put_vc1_mspel_pixels_tab[0][X+4*Y] = ff_put_vc1_mspel_mc##X##Y##_16_neon; \ |
| 84 | dsp->put_vc1_mspel_pixels_tab[1][X+4*Y] = ff_put_vc1_mspel_mc##X##Y##_neon |
| 85 | |
| 86 | av_cold void ff_vc1dsp_init_neon(VC1DSPContext *dsp) |
| 87 | { |
| 88 | dsp->vc1_inv_trans_8x8 = ff_vc1_inv_trans_8x8_neon; |
| 89 | dsp->vc1_inv_trans_4x8 = ff_vc1_inv_trans_4x8_neon; |
| 90 | dsp->vc1_inv_trans_8x4 = ff_vc1_inv_trans_8x4_neon; |
| 91 | dsp->vc1_inv_trans_4x4 = ff_vc1_inv_trans_4x4_neon; |
| 92 | dsp->vc1_inv_trans_8x8_dc = ff_vc1_inv_trans_8x8_dc_neon; |
| 93 | dsp->vc1_inv_trans_4x8_dc = ff_vc1_inv_trans_4x8_dc_neon; |
| 94 | dsp->vc1_inv_trans_8x4_dc = ff_vc1_inv_trans_8x4_dc_neon; |
| 95 | dsp->vc1_inv_trans_4x4_dc = ff_vc1_inv_trans_4x4_dc_neon; |
| 96 | |
| 97 | dsp->put_vc1_mspel_pixels_tab[1][ 0] = ff_put_pixels8x8_neon; |
| 98 | if (HAVE_AS_DN_DIRECTIVE) { |
| 99 | FN_ASSIGN(1, 0); |
| 100 | FN_ASSIGN(2, 0); |
| 101 | FN_ASSIGN(3, 0); |
| 102 | |
| 103 | FN_ASSIGN(0, 1); |
| 104 | FN_ASSIGN(1, 1); |
| 105 | FN_ASSIGN(2, 1); |
| 106 | FN_ASSIGN(3, 1); |
| 107 | |
| 108 | FN_ASSIGN(0, 2); |
| 109 | FN_ASSIGN(1, 2); |
| 110 | FN_ASSIGN(2, 2); |
| 111 | FN_ASSIGN(3, 2); |
| 112 | |
| 113 | FN_ASSIGN(0, 3); |
| 114 | FN_ASSIGN(1, 3); |
| 115 | FN_ASSIGN(2, 3); |
| 116 | FN_ASSIGN(3, 3); |
| 117 | } |
| 118 | |
| 119 | dsp->put_no_rnd_vc1_chroma_pixels_tab[0] = ff_put_vc1_chroma_mc8_neon; |
| 120 | dsp->avg_no_rnd_vc1_chroma_pixels_tab[0] = ff_avg_vc1_chroma_mc8_neon; |
| 121 | dsp->put_no_rnd_vc1_chroma_pixels_tab[1] = ff_put_vc1_chroma_mc4_neon; |
| 122 | dsp->avg_no_rnd_vc1_chroma_pixels_tab[1] = ff_avg_vc1_chroma_mc4_neon; |
| 123 | } |