1/* 2 * AAC Spectral Band Replication decoding functions 3 * Copyright (c) 2008-2009 Robert Swain ( rob opendot cl ) 4 * Copyright (c) 2009-2010 Alex Converse <alex.converse@gmail.com> 5 * 6 * This file is part of FFmpeg. 7 * 8 * FFmpeg is free software; you can redistribute it and/or 9 * modify it under the terms of the GNU Lesser General Public 10 * License as published by the Free Software Foundation; either 11 * version 2.1 of the License, or (at your option) any later version. 12 * 13 * FFmpeg is distributed in the hope that it will be useful, 14 * but WITHOUT ANY WARRANTY; without even the implied warranty of 15 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 16 * Lesser General Public License for more details. 17 * 18 * You should have received a copy of the GNU Lesser General Public 19 * License along with FFmpeg; if not, write to the Free Software 20 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 21 */ 22 23#define USE_FIXED 0 24 25#include "aac.h" 26#include "config.h" 27#include "libavutil/attributes.h" 28#include "libavutil/intfloat.h" 29#include "sbrdsp.h" 30 31static float sbr_sum_square_c(float (*x)[2], int n) 32{ 33 float sum0 = 0.0f, sum1 = 0.0f; 34 int i; 35 36 for (i = 0; i < n; i += 2) 37 { 38 sum0 += x[i + 0][0] * x[i + 0][0]; 39 sum1 += x[i + 0][1] * x[i + 0][1]; 40 sum0 += x[i + 1][0] * x[i + 1][0]; 41 sum1 += x[i + 1][1] * x[i + 1][1]; 42 } 43 44 return sum0 + sum1; 45} 46 47static void sbr_neg_odd_64_c(float *x) 48{ 49 union av_intfloat32 *xi = (union av_intfloat32*) x; 50 int i; 51 for (i = 1; i < 64; i += 4) { 52 xi[i + 0].i ^= 1U << 31; 53 xi[i + 2].i ^= 1U << 31; 54 } 55} 56 57static void sbr_qmf_pre_shuffle_c(float *z) 58{ 59 union av_intfloat32 *zi = (union av_intfloat32*) z; 60 int k; 61 zi[64].i = zi[0].i; 62 zi[65].i = zi[1].i; 63 for (k = 1; k < 31; k += 2) { 64 zi[64 + 2 * k + 0].i = zi[64 - k].i ^ (1U << 31); 65 zi[64 + 2 * k + 1].i = zi[ k + 1].i; 66 zi[64 + 2 * k + 2].i = zi[63 - k].i ^ (1U << 31); 67 zi[64 + 2 * k + 3].i = zi[ k + 2].i; 68 } 69 70 zi[64 + 2 * 31 + 0].i = zi[64 - 31].i ^ (1U << 31); 71 zi[64 + 2 * 31 + 1].i = zi[31 + 1].i; 72} 73 74static void sbr_qmf_post_shuffle_c(float W[32][2], const float *z) 75{ 76 const union av_intfloat32 *zi = (const union av_intfloat32*) z; 77 union av_intfloat32 *Wi = (union av_intfloat32*) W; 78 int k; 79 for (k = 0; k < 32; k += 2) { 80 Wi[2 * k + 0].i = zi[63 - k].i ^ (1U << 31); 81 Wi[2 * k + 1].i = zi[ k + 0].i; 82 Wi[2 * k + 2].i = zi[62 - k].i ^ (1U << 31); 83 Wi[2 * k + 3].i = zi[ k + 1].i; 84 } 85} 86 87static void sbr_qmf_deint_neg_c(float *v, const float *src) 88{ 89 const union av_intfloat32 *si = (const union av_intfloat32*)src; 90 union av_intfloat32 *vi = (union av_intfloat32*)v; 91 int i; 92 for (i = 0; i < 32; i++) { 93 vi[ i].i = si[63 - 2 * i ].i; 94 vi[63 - i].i = si[63 - 2 * i - 1].i ^ (1U << 31); 95 } 96} 97 98#if 0 99 /* This code is slower because it multiplies memory accesses. 100 * It is left for educational purposes and because it may offer 101 * a better reference for writing arch-specific DSP functions. */ 102static av_always_inline void autocorrelate(const float x[40][2], 103 float phi[3][2][2], int lag) 104{ 105 int i; 106 float real_sum = 0.0f; 107 float imag_sum = 0.0f; 108 if (lag) { 109 for (i = 1; i < 38; i++) { 110 real_sum += x[i][0] * x[i+lag][0] + x[i][1] * x[i+lag][1]; 111 imag_sum += x[i][0] * x[i+lag][1] - x[i][1] * x[i+lag][0]; 112 } 113 phi[2-lag][1][0] = real_sum + x[ 0][0] * x[lag][0] + x[ 0][1] * x[lag][1]; 114 phi[2-lag][1][1] = imag_sum + x[ 0][0] * x[lag][1] - x[ 0][1] * x[lag][0]; 115 if (lag == 1) { 116 phi[0][0][0] = real_sum + x[38][0] * x[39][0] + x[38][1] * x[39][1]; 117 phi[0][0][1] = imag_sum + x[38][0] * x[39][1] - x[38][1] * x[39][0]; 118 } 119 } else { 120 for (i = 1; i < 38; i++) { 121 real_sum += x[i][0] * x[i][0] + x[i][1] * x[i][1]; 122 } 123 phi[2][1][0] = real_sum + x[ 0][0] * x[ 0][0] + x[ 0][1] * x[ 0][1]; 124 phi[1][0][0] = real_sum + x[38][0] * x[38][0] + x[38][1] * x[38][1]; 125 } 126} 127 128static void sbr_autocorrelate_c(const float x[40][2], float phi[3][2][2]) 129{ 130 autocorrelate(x, phi, 0); 131 autocorrelate(x, phi, 1); 132 autocorrelate(x, phi, 2); 133} 134#else 135static void sbr_autocorrelate_c(const float x[40][2], float phi[3][2][2]) 136{ 137 float real_sum2 = x[0][0] * x[2][0] + x[0][1] * x[2][1]; 138 float imag_sum2 = x[0][0] * x[2][1] - x[0][1] * x[2][0]; 139 float real_sum1 = 0.0f, imag_sum1 = 0.0f, real_sum0 = 0.0f; 140 int i; 141 for (i = 1; i < 38; i++) { 142 real_sum0 += x[i][0] * x[i ][0] + x[i][1] * x[i ][1]; 143 real_sum1 += x[i][0] * x[i + 1][0] + x[i][1] * x[i + 1][1]; 144 imag_sum1 += x[i][0] * x[i + 1][1] - x[i][1] * x[i + 1][0]; 145 real_sum2 += x[i][0] * x[i + 2][0] + x[i][1] * x[i + 2][1]; 146 imag_sum2 += x[i][0] * x[i + 2][1] - x[i][1] * x[i + 2][0]; 147 } 148 phi[2 - 2][1][0] = real_sum2; 149 phi[2 - 2][1][1] = imag_sum2; 150 phi[2 ][1][0] = real_sum0 + x[ 0][0] * x[ 0][0] + x[ 0][1] * x[ 0][1]; 151 phi[1 ][0][0] = real_sum0 + x[38][0] * x[38][0] + x[38][1] * x[38][1]; 152 phi[2 - 1][1][0] = real_sum1 + x[ 0][0] * x[ 1][0] + x[ 0][1] * x[ 1][1]; 153 phi[2 - 1][1][1] = imag_sum1 + x[ 0][0] * x[ 1][1] - x[ 0][1] * x[ 1][0]; 154 phi[0 ][0][0] = real_sum1 + x[38][0] * x[39][0] + x[38][1] * x[39][1]; 155 phi[0 ][0][1] = imag_sum1 + x[38][0] * x[39][1] - x[38][1] * x[39][0]; 156} 157#endif 158 159static void sbr_hf_gen_c(float (*X_high)[2], const float (*X_low)[2], 160 const float alpha0[2], const float alpha1[2], 161 float bw, int start, int end) 162{ 163 float alpha[4]; 164 int i; 165 166 alpha[0] = alpha1[0] * bw * bw; 167 alpha[1] = alpha1[1] * bw * bw; 168 alpha[2] = alpha0[0] * bw; 169 alpha[3] = alpha0[1] * bw; 170 171 for (i = start; i < end; i++) { 172 X_high[i][0] = 173 X_low[i - 2][0] * alpha[0] - 174 X_low[i - 2][1] * alpha[1] + 175 X_low[i - 1][0] * alpha[2] - 176 X_low[i - 1][1] * alpha[3] + 177 X_low[i][0]; 178 X_high[i][1] = 179 X_low[i - 2][1] * alpha[0] + 180 X_low[i - 2][0] * alpha[1] + 181 X_low[i - 1][1] * alpha[2] + 182 X_low[i - 1][0] * alpha[3] + 183 X_low[i][1]; 184 } 185} 186 187static void sbr_hf_g_filt_c(float (*Y)[2], const float (*X_high)[40][2], 188 const float *g_filt, int m_max, intptr_t ixh) 189{ 190 int m; 191 192 for (m = 0; m < m_max; m++) { 193 Y[m][0] = X_high[m][ixh][0] * g_filt[m]; 194 Y[m][1] = X_high[m][ixh][1] * g_filt[m]; 195 } 196} 197 198static av_always_inline void sbr_hf_apply_noise(float (*Y)[2], 199 const float *s_m, 200 const float *q_filt, 201 int noise, 202 float phi_sign0, 203 float phi_sign1, 204 int m_max) 205{ 206 int m; 207 208 for (m = 0; m < m_max; m++) { 209 float y0 = Y[m][0]; 210 float y1 = Y[m][1]; 211 noise = (noise + 1) & 0x1ff; 212 if (s_m[m]) { 213 y0 += s_m[m] * phi_sign0; 214 y1 += s_m[m] * phi_sign1; 215 } else { 216 y0 += q_filt[m] * ff_sbr_noise_table[noise][0]; 217 y1 += q_filt[m] * ff_sbr_noise_table[noise][1]; 218 } 219 Y[m][0] = y0; 220 Y[m][1] = y1; 221 phi_sign1 = -phi_sign1; 222 } 223} 224 225#include "sbrdsp_template.c" 226