1/* 2 * Canopus HQ/HQA decoder 3 * 4 * This file is part of FFmpeg. 5 * 6 * FFmpeg is free software; you can redistribute it and/or 7 * modify it under the terms of the GNU Lesser General Public 8 * License as published by the Free Software Foundation; either 9 * version 2.1 of the License, or (at your option) any later version. 10 * 11 * FFmpeg is distributed in the hope that it will be useful, 12 * but WITHOUT ANY WARRANTY; without even the implied warranty of 13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 14 * Lesser General Public License for more details. 15 * 16 * You should have received a copy of the GNU Lesser General Public 17 * License along with FFmpeg; if not, write to the Free Software 18 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 19 */ 20 21#include <stdint.h> 22 23#include "libavutil/attributes.h" 24#include "libavutil/common.h" 25 26#include "hq_hqadsp.h" 27 28#define FIX_1_082 17734 29#define FIX_1_847 30274 30#define FIX_1_414 23170 31#define FIX_2_613 21407 // divided by two to fit the range 32 33#define IDCTMUL(a, b) ((int)((a) * (unsigned)(b)) >> 16) 34 35static inline void idct_row(int16_t *blk) 36{ 37 int tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7, tmp8, tmp9, tmpA; 38 int tmpB, tmpC, tmpD, tmpE, tmpF, tmp10, tmp11, tmp12, tmp13, tmp14; 39 40 tmp0 = blk[5] - blk[3]; 41 tmp1 = blk[5] + blk[3]; 42 tmp2 = blk[1] - blk[7]; 43 tmp3 = blk[1] + blk[7]; 44 tmp4 = tmp3 - tmp1; 45 tmp5 = IDCTMUL(tmp0 + tmp2, FIX_1_847); 46 tmp6 = IDCTMUL(tmp2, FIX_1_082) - tmp5; 47 tmp7 = tmp5 - IDCTMUL(tmp0, FIX_2_613) * 2; 48 tmp8 = tmp3 + tmp1; 49 tmp9 = tmp7 * 4 - tmp8; 50 tmpA = IDCTMUL(tmp4, FIX_1_414) * 4 - tmp9; 51 tmpB = tmp6 * 4 + tmpA; 52 tmpC = blk[2] + blk[6]; 53 tmpD = blk[2] - blk[6]; 54 tmpE = blk[0] - blk[4]; 55 tmpF = blk[0] + blk[4]; 56 57 tmp10 = IDCTMUL(tmpD, FIX_1_414) * 4 - tmpC; 58 tmp11 = tmpE - tmp10; 59 tmp12 = tmpF - tmpC; 60 tmp13 = tmpE + tmp10; 61 tmp14 = tmpF + tmpC; 62 63 blk[0] = tmp14 + tmp8; 64 blk[1] = tmp13 + tmp9; 65 blk[2] = tmp11 + tmpA; 66 blk[3] = tmp12 - tmpB; 67 blk[4] = tmp12 + tmpB; 68 blk[5] = tmp11 - tmpA; 69 blk[6] = tmp13 - tmp9; 70 blk[7] = tmp14 - tmp8; 71} 72 73static inline void idct_col(int16_t *blk) 74{ 75 int tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7, tmp8, tmp9, tmpA; 76 int tmpB, tmpC, tmpD, tmpE, tmpF, tmp10, tmp11, tmp12, tmp13, tmp14; 77 78 tmp0 = blk[5 * 8] - blk[3 * 8]; 79 tmp1 = blk[5 * 8] + blk[3 * 8]; 80 tmp2 = blk[1 * 8] * 2 - (blk[7 * 8] >> 2); 81 tmp3 = blk[1 * 8] * 2 + (blk[7 * 8] >> 2); 82 tmp4 = tmp3 - tmp1; 83 tmp5 = IDCTMUL(tmp0 + tmp2, FIX_1_847); 84 tmp6 = IDCTMUL(tmp2, FIX_1_082) - tmp5; 85 tmp7 = tmp5 - IDCTMUL(tmp0, FIX_2_613) * 2; 86 tmp8 = (tmp3 + tmp1) >> 1; 87 tmp9 = tmp7 * 2 - tmp8; 88 tmpA = IDCTMUL(tmp4, FIX_1_414) * 2 - tmp9; 89 tmpB = tmp6 * 2 + tmpA; 90 tmpC = blk[2 * 8] + (blk[6 * 8] >> 1) >> 1; 91 tmpD = blk[2 * 8] - (blk[6 * 8] >> 1); 92 tmpE = (blk[0 * 8] >> 1) - (blk[4 * 8] >> 1) + 0x2020; 93 tmpF = (blk[0 * 8] >> 1) + (blk[4 * 8] >> 1) + 0x2020; 94 95 tmp10 = IDCTMUL(tmpD, FIX_1_414) * 2 - tmpC; 96 tmp11 = tmpE - tmp10; 97 tmp12 = tmpF - tmpC; 98 tmp13 = tmpE + tmp10; 99 tmp14 = tmpF + tmpC; 100 101 blk[0 * 8] = (tmp14 + tmp8) >> 6; 102 blk[1 * 8] = (tmp13 + tmp9) >> 6; 103 blk[2 * 8] = (tmp11 + tmpA) >> 6; 104 blk[3 * 8] = (tmp12 - tmpB) >> 6; 105 blk[4 * 8] = (tmp12 + tmpB) >> 6; 106 blk[5 * 8] = (tmp11 - tmpA) >> 6; 107 blk[6 * 8] = (tmp13 - tmp9) >> 6; 108 blk[7 * 8] = (tmp14 - tmp8) >> 6; 109} 110 111static void hq_idct_put(uint8_t *dst, int stride, int16_t *block) 112{ 113 int i, j; 114 115 for (i = 0; i < 8; i++) 116 idct_row(block + i * 8); 117 for (i = 0; i < 8; i++) 118 idct_col(block + i); 119 120 for (i = 0; i < 8; i++) { 121 for (j = 0; j < 8; j++) 122 dst[j] = av_clip_uint8(block[j + i * 8]); 123 dst += stride; 124 } 125} 126 127av_cold void ff_hqdsp_init(HQDSPContext *c) 128{ 129 c->idct_put = hq_idct_put; 130} 131