| 1 | /* |
| 2 | * Bink DSP routines |
| 3 | * Copyright (c) 2009 Konstantin Shishkov |
| 4 | * |
| 5 | * This file is part of FFmpeg. |
| 6 | * |
| 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. |
| 11 | * |
| 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. |
| 16 | * |
| 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 |
| 20 | */ |
| 21 | |
| 22 | /** |
| 23 | * @file |
| 24 | * Bink DSP routines |
| 25 | */ |
| 26 | |
| 27 | #include "config.h" |
| 28 | #include "libavutil/attributes.h" |
| 29 | #include "binkdsp.h" |
| 30 | |
| 31 | #define A1 2896 /* (1/sqrt(2))<<12 */ |
| 32 | #define A2 2217 |
| 33 | #define A3 3784 |
| 34 | #define A4 -5352 |
| 35 | |
| 36 | #define IDCT_TRANSFORM(dest,s0,s1,s2,s3,s4,s5,s6,s7,d0,d1,d2,d3,d4,d5,d6,d7,munge,src) {\ |
| 37 | const int a0 = (src)[s0] + (src)[s4]; \ |
| 38 | const int a1 = (src)[s0] - (src)[s4]; \ |
| 39 | const int a2 = (src)[s2] + (src)[s6]; \ |
| 40 | const int a3 = (A1*((src)[s2] - (src)[s6])) >> 11; \ |
| 41 | const int a4 = (src)[s5] + (src)[s3]; \ |
| 42 | const int a5 = (src)[s5] - (src)[s3]; \ |
| 43 | const int a6 = (src)[s1] + (src)[s7]; \ |
| 44 | const int a7 = (src)[s1] - (src)[s7]; \ |
| 45 | const int b0 = a4 + a6; \ |
| 46 | const int b1 = (A3*(a5 + a7)) >> 11; \ |
| 47 | const int b2 = ((A4*a5) >> 11) - b0 + b1; \ |
| 48 | const int b3 = (A1*(a6 - a4) >> 11) - b2; \ |
| 49 | const int b4 = ((A2*a7) >> 11) + b3 - b1; \ |
| 50 | (dest)[d0] = munge(a0+a2 +b0); \ |
| 51 | (dest)[d1] = munge(a1+a3-a2+b2); \ |
| 52 | (dest)[d2] = munge(a1-a3+a2+b3); \ |
| 53 | (dest)[d3] = munge(a0-a2 -b4); \ |
| 54 | (dest)[d4] = munge(a0-a2 +b4); \ |
| 55 | (dest)[d5] = munge(a1-a3+a2-b3); \ |
| 56 | (dest)[d6] = munge(a1+a3-a2-b2); \ |
| 57 | (dest)[d7] = munge(a0+a2 -b0); \ |
| 58 | } |
| 59 | /* end IDCT_TRANSFORM macro */ |
| 60 | |
| 61 | #define MUNGE_NONE(x) (x) |
| 62 | #define IDCT_COL(dest,src) IDCT_TRANSFORM(dest,0,8,16,24,32,40,48,56,0,8,16,24,32,40,48,56,MUNGE_NONE,src) |
| 63 | |
| 64 | #define MUNGE_ROW(x) (((x) + 0x7F)>>8) |
| 65 | #define IDCT_ROW(dest,src) IDCT_TRANSFORM(dest,0,1,2,3,4,5,6,7,0,1,2,3,4,5,6,7,MUNGE_ROW,src) |
| 66 | |
| 67 | static inline void bink_idct_col(int *dest, const int32_t *src) |
| 68 | { |
| 69 | if ((src[8]|src[16]|src[24]|src[32]|src[40]|src[48]|src[56])==0) { |
| 70 | dest[0] = |
| 71 | dest[8] = |
| 72 | dest[16] = |
| 73 | dest[24] = |
| 74 | dest[32] = |
| 75 | dest[40] = |
| 76 | dest[48] = |
| 77 | dest[56] = src[0]; |
| 78 | } else { |
| 79 | IDCT_COL(dest, src); |
| 80 | } |
| 81 | } |
| 82 | |
| 83 | static void bink_idct_c(int32_t *block) |
| 84 | { |
| 85 | int i; |
| 86 | int temp[64]; |
| 87 | |
| 88 | for (i = 0; i < 8; i++) |
| 89 | bink_idct_col(&temp[i], &block[i]); |
| 90 | for (i = 0; i < 8; i++) { |
| 91 | IDCT_ROW( (&block[8*i]), (&temp[8*i]) ); |
| 92 | } |
| 93 | } |
| 94 | |
| 95 | static void bink_idct_add_c(uint8_t *dest, int linesize, int32_t *block) |
| 96 | { |
| 97 | int i, j; |
| 98 | |
| 99 | bink_idct_c(block); |
| 100 | for (i = 0; i < 8; i++, dest += linesize, block += 8) |
| 101 | for (j = 0; j < 8; j++) |
| 102 | dest[j] += block[j]; |
| 103 | } |
| 104 | |
| 105 | static void bink_idct_put_c(uint8_t *dest, int linesize, int32_t *block) |
| 106 | { |
| 107 | int i; |
| 108 | int temp[64]; |
| 109 | for (i = 0; i < 8; i++) |
| 110 | bink_idct_col(&temp[i], &block[i]); |
| 111 | for (i = 0; i < 8; i++) { |
| 112 | IDCT_ROW( (&dest[i*linesize]), (&temp[8*i]) ); |
| 113 | } |
| 114 | } |
| 115 | |
| 116 | static void scale_block_c(const uint8_t src[64]/*align 8*/, uint8_t *dst/*align 8*/, int linesize) |
| 117 | { |
| 118 | int i, j; |
| 119 | uint16_t *dst1 = (uint16_t *) dst; |
| 120 | uint16_t *dst2 = (uint16_t *)(dst + linesize); |
| 121 | |
| 122 | for (j = 0; j < 8; j++) { |
| 123 | for (i = 0; i < 8; i++) { |
| 124 | dst1[i] = dst2[i] = src[i] * 0x0101; |
| 125 | } |
| 126 | src += 8; |
| 127 | dst1 += linesize; |
| 128 | dst2 += linesize; |
| 129 | } |
| 130 | } |
| 131 | |
| 132 | static void add_pixels8_c(uint8_t *av_restrict pixels, int16_t *block, |
| 133 | int line_size) |
| 134 | { |
| 135 | int i; |
| 136 | |
| 137 | for (i = 0; i < 8; i++) { |
| 138 | pixels[0] += block[0]; |
| 139 | pixels[1] += block[1]; |
| 140 | pixels[2] += block[2]; |
| 141 | pixels[3] += block[3]; |
| 142 | pixels[4] += block[4]; |
| 143 | pixels[5] += block[5]; |
| 144 | pixels[6] += block[6]; |
| 145 | pixels[7] += block[7]; |
| 146 | pixels += line_size; |
| 147 | block += 8; |
| 148 | } |
| 149 | } |
| 150 | |
| 151 | av_cold void ff_binkdsp_init(BinkDSPContext *c) |
| 152 | { |
| 153 | c->idct_add = bink_idct_add_c; |
| 154 | c->idct_put = bink_idct_put_c; |
| 155 | c->scale_block = scale_block_c; |
| 156 | c->add_pixels8 = add_pixels8_c; |
| 157 | } |