1/* 2 * Copyright (c) 2012 3 * MIPS Technologies, Inc., California. 4 * 5 * Redistribution and use in source and binary forms, with or without 6 * modification, are permitted provided that the following conditions 7 * are met: 8 * 1. Redistributions of source code must retain the above copyright 9 * notice, this list of conditions and the following disclaimer. 10 * 2. Redistributions in binary form must reproduce the above copyright 11 * notice, this list of conditions and the following disclaimer in the 12 * documentation and/or other materials provided with the distribution. 13 * 3. Neither the name of the MIPS Technologies, Inc., nor the names of its 14 * contributors may be used to endorse or promote products derived from 15 * this software without specific prior written permission. 16 * 17 * THIS SOFTWARE IS PROVIDED BY THE MIPS TECHNOLOGIES, INC. ``AS IS'' AND 18 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 19 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 20 * ARE DISCLAIMED. IN NO EVENT SHALL THE MIPS TECHNOLOGIES, INC. BE LIABLE 21 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 22 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 23 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 24 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 25 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 26 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 27 * SUCH DAMAGE. 28 * 29 * Authors: Darko Laus (darko@mips.com) 30 * Djordje Pesut (djordje@mips.com) 31 * Mirjana Vulin (mvulin@mips.com) 32 * 33 * This file is part of FFmpeg. 34 * 35 * FFmpeg is free software; you can redistribute it and/or 36 * modify it under the terms of the GNU Lesser General Public 37 * License as published by the Free Software Foundation; either 38 * version 2.1 of the License, or (at your option) any later version. 39 * 40 * FFmpeg is distributed in the hope that it will be useful, 41 * but WITHOUT ANY WARRANTY; without even the implied warranty of 42 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 43 * Lesser General Public License for more details. 44 * 45 * You should have received a copy of the GNU Lesser General Public 46 * License along with FFmpeg; if not, write to the Free Software 47 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 48 */ 49 50/** 51 * @file 52 * Reference: libavcodec/aacpsdsp.c 53 */ 54 55#include "config.h" 56#include "libavcodec/aacpsdsp.h" 57#include "libavutil/mips/asmdefs.h" 58 59#if HAVE_INLINE_ASM 60#if HAVE_MIPSFPU 61static void ps_hybrid_analysis_ileave_mips(float (*out)[32][2], float L[2][38][64], 62 int i, int len) 63{ 64 int temp0, temp1, temp2, temp3; 65 int temp4, temp5, temp6, temp7; 66 float *out1=&out[i][0][0]; 67 float *L1=&L[0][0][i]; 68 float *j=out1+ len*2; 69 70 for (; i < 64; i++) { 71 72 /* loop unrolled 8 times */ 73 __asm__ volatile ( 74 "1: \n\t" 75 "lw %[temp0], 0(%[L1]) \n\t" 76 "lw %[temp1], 9728(%[L1]) \n\t" 77 "lw %[temp2], 256(%[L1]) \n\t" 78 "lw %[temp3], 9984(%[L1]) \n\t" 79 "lw %[temp4], 512(%[L1]) \n\t" 80 "lw %[temp5], 10240(%[L1]) \n\t" 81 "lw %[temp6], 768(%[L1]) \n\t" 82 "lw %[temp7], 10496(%[L1]) \n\t" 83 "sw %[temp0], 0(%[out1]) \n\t" 84 "sw %[temp1], 4(%[out1]) \n\t" 85 "sw %[temp2], 8(%[out1]) \n\t" 86 "sw %[temp3], 12(%[out1]) \n\t" 87 "sw %[temp4], 16(%[out1]) \n\t" 88 "sw %[temp5], 20(%[out1]) \n\t" 89 "sw %[temp6], 24(%[out1]) \n\t" 90 "sw %[temp7], 28(%[out1]) \n\t" 91 PTR_ADDIU "%[out1], %[out1], 32 \n\t" 92 PTR_ADDIU "%[L1], %[L1], 1024 \n\t" 93 "bne %[out1], %[j], 1b \n\t" 94 95 : [out1]"+r"(out1), [L1]"+r"(L1), [j]"+r"(j), 96 [temp0]"=&r"(temp0), [temp1]"=&r"(temp1), 97 [temp2]"=&r"(temp2), [temp3]"=&r"(temp3), 98 [temp4]"=&r"(temp4), [temp5]"=&r"(temp5), 99 [temp6]"=&r"(temp6), [temp7]"=&r"(temp7) 100 : [len]"r"(len) 101 : "memory" 102 ); 103 out1-=(len<<1)-64; 104 L1-=(len<<6)-1; 105 j+=len*2; 106 } 107} 108 109static void ps_hybrid_synthesis_deint_mips(float out[2][38][64], 110 float (*in)[32][2], 111 int i, int len) 112{ 113 int n; 114 int temp0, temp1, temp2, temp3, temp4, temp5, temp6, temp7; 115 float *out1 = (float*)out + i; 116 float *out2 = (float*)out + 2432 + i; 117 float *in1 = (float*)in + 64 * i; 118 float *in2 = (float*)in + 64 * i + 1; 119 120 for (; i < 64; i++) { 121 for (n = 0; n < 7; n++) { 122 123 /* loop unrolled 8 times */ 124 __asm__ volatile ( 125 "lw %[temp0], 0(%[in1]) \n\t" 126 "lw %[temp1], 0(%[in2]) \n\t" 127 "lw %[temp2], 8(%[in1]) \n\t" 128 "lw %[temp3], 8(%[in2]) \n\t" 129 "lw %[temp4], 16(%[in1]) \n\t" 130 "lw %[temp5], 16(%[in2]) \n\t" 131 "lw %[temp6], 24(%[in1]) \n\t" 132 "lw %[temp7], 24(%[in2]) \n\t" 133 PTR_ADDIU "%[out1], %[out1], 1024 \n\t" 134 PTR_ADDIU "%[out2], %[out2], 1024 \n\t" 135 PTR_ADDIU "%[in1], %[in1], 32 \n\t" 136 PTR_ADDIU "%[in2], %[in2], 32 \n\t" 137 "sw %[temp0], -1024(%[out1]) \n\t" 138 "sw %[temp1], -1024(%[out2]) \n\t" 139 "sw %[temp2], -768(%[out1]) \n\t" 140 "sw %[temp3], -768(%[out2]) \n\t" 141 "sw %[temp4], -512(%[out1]) \n\t" 142 "sw %[temp5], -512(%[out2]) \n\t" 143 "sw %[temp6], -256(%[out1]) \n\t" 144 "sw %[temp7], -256(%[out2]) \n\t" 145 146 : [temp0]"=&r"(temp0), [temp1]"=&r"(temp1), 147 [temp2]"=&r"(temp2), [temp3]"=&r"(temp3), 148 [temp4]"=&r"(temp4), [temp5]"=&r"(temp5), 149 [temp6]"=&r"(temp6), [temp7]"=&r"(temp7), 150 [out1]"+r"(out1), [out2]"+r"(out2), 151 [in1]"+r"(in1), [in2]"+r"(in2) 152 : 153 : "memory" 154 ); 155 } 156 /* loop unrolled 8 times */ 157 __asm__ volatile ( 158 "lw %[temp0], 0(%[in1]) \n\t" 159 "lw %[temp1], 0(%[in2]) \n\t" 160 "lw %[temp2], 8(%[in1]) \n\t" 161 "lw %[temp3], 8(%[in2]) \n\t" 162 "lw %[temp4], 16(%[in1]) \n\t" 163 "lw %[temp5], 16(%[in2]) \n\t" 164 "lw %[temp6], 24(%[in1]) \n\t" 165 "lw %[temp7], 24(%[in2]) \n\t" 166 PTR_ADDIU "%[out1], %[out1], -7164 \n\t" 167 PTR_ADDIU "%[out2], %[out2], -7164 \n\t" 168 PTR_ADDIU "%[in1], %[in1], 32 \n\t" 169 PTR_ADDIU "%[in2], %[in2], 32 \n\t" 170 "sw %[temp0], 7164(%[out1]) \n\t" 171 "sw %[temp1], 7164(%[out2]) \n\t" 172 "sw %[temp2], 7420(%[out1]) \n\t" 173 "sw %[temp3], 7420(%[out2]) \n\t" 174 "sw %[temp4], 7676(%[out1]) \n\t" 175 "sw %[temp5], 7676(%[out2]) \n\t" 176 "sw %[temp6], 7932(%[out1]) \n\t" 177 "sw %[temp7], 7932(%[out2]) \n\t" 178 179 : [temp0]"=&r"(temp0), [temp1]"=&r"(temp1), 180 [temp2]"=&r"(temp2), [temp3]"=&r"(temp3), 181 [temp4]"=&r"(temp4), [temp5]"=&r"(temp5), 182 [temp6]"=&r"(temp6), [temp7]"=&r"(temp7), 183 [out1]"+r"(out1), [out2]"+r"(out2), 184 [in1]"+r"(in1), [in2]"+r"(in2) 185 : 186 : "memory" 187 ); 188 } 189} 190 191#if !HAVE_MIPS32R6 && !HAVE_MIPS64R6 192static void ps_add_squares_mips(float *dst, const float (*src)[2], int n) 193{ 194 int i; 195 float temp0, temp1, temp2, temp3, temp4, temp5; 196 float temp6, temp7, temp8, temp9, temp10, temp11; 197 float *src0 = (float*)&src[0][0]; 198 float *dst0 = &dst[0]; 199 200 for (i = 0; i < 8; i++) { 201 /* loop unrolled 4 times */ 202 __asm__ volatile ( 203 "lwc1 %[temp0], 0(%[src0]) \n\t" 204 "lwc1 %[temp1], 4(%[src0]) \n\t" 205 "lwc1 %[temp2], 8(%[src0]) \n\t" 206 "lwc1 %[temp3], 12(%[src0]) \n\t" 207 "lwc1 %[temp4], 16(%[src0]) \n\t" 208 "lwc1 %[temp5], 20(%[src0]) \n\t" 209 "lwc1 %[temp6], 24(%[src0]) \n\t" 210 "lwc1 %[temp7], 28(%[src0]) \n\t" 211 "lwc1 %[temp8], 0(%[dst0]) \n\t" 212 "lwc1 %[temp9], 4(%[dst0]) \n\t" 213 "lwc1 %[temp10], 8(%[dst0]) \n\t" 214 "lwc1 %[temp11], 12(%[dst0]) \n\t" 215 "mul.s %[temp1], %[temp1], %[temp1] \n\t" 216 "mul.s %[temp3], %[temp3], %[temp3] \n\t" 217 "mul.s %[temp5], %[temp5], %[temp5] \n\t" 218 "mul.s %[temp7], %[temp7], %[temp7] \n\t" 219 "madd.s %[temp0], %[temp1], %[temp0], %[temp0] \n\t" 220 "madd.s %[temp2], %[temp3], %[temp2], %[temp2] \n\t" 221 "madd.s %[temp4], %[temp5], %[temp4], %[temp4] \n\t" 222 "madd.s %[temp6], %[temp7], %[temp6], %[temp6] \n\t" 223 "add.s %[temp0], %[temp8], %[temp0] \n\t" 224 "add.s %[temp2], %[temp9], %[temp2] \n\t" 225 "add.s %[temp4], %[temp10], %[temp4] \n\t" 226 "add.s %[temp6], %[temp11], %[temp6] \n\t" 227 "swc1 %[temp0], 0(%[dst0]) \n\t" 228 "swc1 %[temp2], 4(%[dst0]) \n\t" 229 "swc1 %[temp4], 8(%[dst0]) \n\t" 230 "swc1 %[temp6], 12(%[dst0]) \n\t" 231 PTR_ADDIU "%[dst0], %[dst0], 16 \n\t" 232 PTR_ADDIU "%[src0], %[src0], 32 \n\t" 233 234 : [temp0]"=&f"(temp0), [temp1]"=&f"(temp1), [temp2]"=&f"(temp2), 235 [temp3]"=&f"(temp3), [temp4]"=&f"(temp4), [temp5]"=&f"(temp5), 236 [temp6]"=&f"(temp6), [temp7]"=&f"(temp7), [temp8]"=&f"(temp8), 237 [temp9]"=&f"(temp9), [dst0]"+r"(dst0), [src0]"+r"(src0), 238 [temp10]"=&f"(temp10), [temp11]"=&f"(temp11) 239 : 240 : "memory" 241 ); 242 } 243} 244 245static void ps_mul_pair_single_mips(float (*dst)[2], float (*src0)[2], float *src1, 246 int n) 247{ 248 float temp0, temp1, temp2; 249 float *p_d, *p_s0, *p_s1, *end; 250 p_d = &dst[0][0]; 251 p_s0 = &src0[0][0]; 252 p_s1 = &src1[0]; 253 end = p_s1 + n; 254 255 __asm__ volatile( 256 ".set push \n\t" 257 ".set noreorder \n\t" 258 "1: \n\t" 259 "lwc1 %[temp2], 0(%[p_s1]) \n\t" 260 "lwc1 %[temp0], 0(%[p_s0]) \n\t" 261 "lwc1 %[temp1], 4(%[p_s0]) \n\t" 262 PTR_ADDIU "%[p_d], %[p_d], 8 \n\t" 263 "mul.s %[temp0], %[temp0], %[temp2] \n\t" 264 "mul.s %[temp1], %[temp1], %[temp2] \n\t" 265 PTR_ADDIU "%[p_s0], %[p_s0], 8 \n\t" 266 "swc1 %[temp0], -8(%[p_d]) \n\t" 267 "swc1 %[temp1], -4(%[p_d]) \n\t" 268 "bne %[p_s1], %[end], 1b \n\t" 269 PTR_ADDIU "%[p_s1], %[p_s1], 4 \n\t" 270 ".set pop \n\t" 271 272 : [temp0]"=&f"(temp0), [temp1]"=&f"(temp1), 273 [temp2]"=&f"(temp2), [p_d]"+r"(p_d), 274 [p_s0]"+r"(p_s0), [p_s1]"+r"(p_s1) 275 : [end]"r"(end) 276 : "memory" 277 ); 278} 279 280static void ps_decorrelate_mips(float (*out)[2], float (*delay)[2], 281 float (*ap_delay)[PS_QMF_TIME_SLOTS + PS_MAX_AP_DELAY][2], 282 const float phi_fract[2], const float (*Q_fract)[2], 283 const float *transient_gain, 284 float g_decay_slope, 285 int len) 286{ 287 float *p_delay = &delay[0][0]; 288 float *p_out = &out[0][0]; 289 float *p_ap_delay = &ap_delay[0][0][0]; 290 const float *p_t_gain = transient_gain; 291 const float *p_Q_fract = &Q_fract[0][0]; 292 float ag0, ag1, ag2; 293 float phi_fract0 = phi_fract[0]; 294 float phi_fract1 = phi_fract[1]; 295 float temp0, temp1, temp2, temp3, temp4, temp5, temp6, temp7, temp8, temp9; 296 float f1, f2, f3; 297 298 float *p_delay_end = (p_delay + (len << 1)); 299 300 /* merged 2 loops */ 301 f1 = 0.65143905753106; 302 f2 = 0.56471812200776; 303 f3 = 0.48954165955695; 304 __asm__ volatile( 305 ".set push \n\t" 306 ".set noreorder \n\t" 307 "mul.s %[ag0], %[ag0], %[g_decay_slope] \n\t" 308 "mul.s %[ag1], %[ag1], %[g_decay_slope] \n\t" 309 "mul.s %[ag2], %[ag2], %[g_decay_slope] \n\t" 310 "1: \n\t" 311 "lwc1 %[temp0], 0(%[p_delay]) \n\t" 312 "lwc1 %[temp1], 4(%[p_delay]) \n\t" 313 "lwc1 %[temp4], 16(%[p_ap_delay]) \n\t" 314 "lwc1 %[temp5], 20(%[p_ap_delay]) \n\t" 315 "mul.s %[temp3], %[temp0], %[phi_fract1] \n\t" 316 "lwc1 %[temp6], 0(%[p_Q_fract]) \n\t" 317 "mul.s %[temp2], %[temp1], %[phi_fract1] \n\t" 318 "lwc1 %[temp7], 4(%[p_Q_fract]) \n\t" 319 "madd.s %[temp3], %[temp3], %[temp1], %[phi_fract0] \n\t" 320 "msub.s %[temp2], %[temp2], %[temp0], %[phi_fract0] \n\t" 321 "mul.s %[temp8], %[temp5], %[temp7] \n\t" 322 "mul.s %[temp9], %[temp4], %[temp7] \n\t" 323 "lwc1 %[temp7], 12(%[p_Q_fract]) \n\t" 324 "mul.s %[temp0], %[ag0], %[temp2] \n\t" 325 "mul.s %[temp1], %[ag0], %[temp3] \n\t" 326 "msub.s %[temp8], %[temp8], %[temp4], %[temp6] \n\t" 327 "lwc1 %[temp4], 304(%[p_ap_delay]) \n\t" 328 "madd.s %[temp9], %[temp9], %[temp5], %[temp6] \n\t" 329 "lwc1 %[temp5], 308(%[p_ap_delay]) \n\t" 330 "sub.s %[temp0], %[temp8], %[temp0] \n\t" 331 "sub.s %[temp1], %[temp9], %[temp1] \n\t" 332 "madd.s %[temp2], %[temp2], %[ag0], %[temp0] \n\t" 333 "lwc1 %[temp6], 8(%[p_Q_fract]) \n\t" 334 "madd.s %[temp3], %[temp3], %[ag0], %[temp1] \n\t" 335 "mul.s %[temp8], %[temp5], %[temp7] \n\t" 336 "mul.s %[temp9], %[temp4], %[temp7] \n\t" 337 "lwc1 %[temp7], 20(%[p_Q_fract]) \n\t" 338 "msub.s %[temp8], %[temp8], %[temp4], %[temp6] \n\t" 339 "swc1 %[temp2], 40(%[p_ap_delay]) \n\t" 340 "mul.s %[temp2], %[ag1], %[temp0] \n\t" 341 "swc1 %[temp3], 44(%[p_ap_delay]) \n\t" 342 "mul.s %[temp3], %[ag1], %[temp1] \n\t" 343 "lwc1 %[temp4], 592(%[p_ap_delay]) \n\t" 344 "madd.s %[temp9], %[temp9], %[temp5], %[temp6] \n\t" 345 "lwc1 %[temp5], 596(%[p_ap_delay]) \n\t" 346 "sub.s %[temp2], %[temp8], %[temp2] \n\t" 347 "sub.s %[temp3], %[temp9], %[temp3] \n\t" 348 "lwc1 %[temp6], 16(%[p_Q_fract]) \n\t" 349 "madd.s %[temp0], %[temp0], %[ag1], %[temp2] \n\t" 350 "madd.s %[temp1], %[temp1], %[ag1], %[temp3] \n\t" 351 "mul.s %[temp8], %[temp5], %[temp7] \n\t" 352 "mul.s %[temp9], %[temp4], %[temp7] \n\t" 353 "msub.s %[temp8], %[temp8], %[temp4], %[temp6] \n\t" 354 "madd.s %[temp9], %[temp9], %[temp5], %[temp6] \n\t" 355 "swc1 %[temp0], 336(%[p_ap_delay]) \n\t" 356 "mul.s %[temp0], %[ag2], %[temp2] \n\t" 357 "swc1 %[temp1], 340(%[p_ap_delay]) \n\t" 358 "mul.s %[temp1], %[ag2], %[temp3] \n\t" 359 "lwc1 %[temp4], 0(%[p_t_gain]) \n\t" 360 "sub.s %[temp0], %[temp8], %[temp0] \n\t" 361 PTR_ADDIU "%[p_ap_delay], %[p_ap_delay], 8 \n\t" 362 "sub.s %[temp1], %[temp9], %[temp1] \n\t" 363 PTR_ADDIU "%[p_t_gain], %[p_t_gain], 4 \n\t" 364 "madd.s %[temp2], %[temp2], %[ag2], %[temp0] \n\t" 365 PTR_ADDIU "%[p_delay], %[p_delay], 8 \n\t" 366 "madd.s %[temp3], %[temp3], %[ag2], %[temp1] \n\t" 367 PTR_ADDIU "%[p_out], %[p_out], 8 \n\t" 368 "mul.s %[temp5], %[temp4], %[temp0] \n\t" 369 "mul.s %[temp6], %[temp4], %[temp1] \n\t" 370 "swc1 %[temp2], 624(%[p_ap_delay]) \n\t" 371 "swc1 %[temp3], 628(%[p_ap_delay]) \n\t" 372 "swc1 %[temp5], -8(%[p_out]) \n\t" 373 "swc1 %[temp6], -4(%[p_out]) \n\t" 374 "bne %[p_delay], %[p_delay_end],1b \n\t" 375 " swc1 %[temp6], -4(%[p_out]) \n\t" 376 ".set pop \n\t" 377 378 : [temp0]"=&f"(temp0), [temp1]"=&f"(temp1), [temp2]"=&f"(temp2), 379 [temp3]"=&f"(temp3), [temp4]"=&f"(temp4), [temp5]"=&f"(temp5), 380 [temp6]"=&f"(temp6), [temp7]"=&f"(temp7), [temp8]"=&f"(temp8), 381 [temp9]"=&f"(temp9), [p_delay]"+r"(p_delay), [p_ap_delay]"+r"(p_ap_delay), 382 [p_Q_fract]"+r"(p_Q_fract), [p_t_gain]"+r"(p_t_gain), [p_out]"+r"(p_out) 383 : [phi_fract0]"f"(phi_fract0), [phi_fract1]"f"(phi_fract1), 384 [p_delay_end]"r"(p_delay_end), [g_decay_slope]"f"(g_decay_slope), 385 [ag0]"f"(f1), [ag1]"f"(f2), [ag2]"f"(f3) 386 : "memory" 387 ); 388} 389 390static void ps_stereo_interpolate_mips(float (*l)[2], float (*r)[2], 391 float h[2][4], float h_step[2][4], 392 int len) 393{ 394 float h0 = h[0][0]; 395 float h1 = h[0][1]; 396 float h2 = h[0][2]; 397 float h3 = h[0][3]; 398 float hs0 = h_step[0][0]; 399 float hs1 = h_step[0][1]; 400 float hs2 = h_step[0][2]; 401 float hs3 = h_step[0][3]; 402 float temp0, temp1, temp2, temp3; 403 float l_re, l_im, r_re, r_im; 404 405 float *l_end = ((float *)l + (len << 1)); 406 407 __asm__ volatile( 408 ".set push \n\t" 409 ".set noreorder \n\t" 410 "1: \n\t" 411 "add.s %[h0], %[h0], %[hs0] \n\t" 412 "lwc1 %[l_re], 0(%[l]) \n\t" 413 "add.s %[h1], %[h1], %[hs1] \n\t" 414 "lwc1 %[r_re], 0(%[r]) \n\t" 415 "add.s %[h2], %[h2], %[hs2] \n\t" 416 "lwc1 %[l_im], 4(%[l]) \n\t" 417 "add.s %[h3], %[h3], %[hs3] \n\t" 418 "lwc1 %[r_im], 4(%[r]) \n\t" 419 "mul.s %[temp0], %[h0], %[l_re] \n\t" 420 PTR_ADDIU "%[l], %[l], 8 \n\t" 421 "mul.s %[temp2], %[h1], %[l_re] \n\t" 422 PTR_ADDIU "%[r], %[r], 8 \n\t" 423 "madd.s %[temp0], %[temp0], %[h2], %[r_re] \n\t" 424 "madd.s %[temp2], %[temp2], %[h3], %[r_re] \n\t" 425 "mul.s %[temp1], %[h0], %[l_im] \n\t" 426 "mul.s %[temp3], %[h1], %[l_im] \n\t" 427 "madd.s %[temp1], %[temp1], %[h2], %[r_im] \n\t" 428 "madd.s %[temp3], %[temp3], %[h3], %[r_im] \n\t" 429 "swc1 %[temp0], -8(%[l]) \n\t" 430 "swc1 %[temp2], -8(%[r]) \n\t" 431 "swc1 %[temp1], -4(%[l]) \n\t" 432 "bne %[l], %[l_end], 1b \n\t" 433 " swc1 %[temp3], -4(%[r]) \n\t" 434 ".set pop \n\t" 435 436 : [temp0]"=&f"(temp0), [temp1]"=&f"(temp1), 437 [temp2]"=&f"(temp2), [temp3]"=&f"(temp3), 438 [h0]"+f"(h0), [h1]"+f"(h1), [h2]"+f"(h2), 439 [h3]"+f"(h3), [l]"+r"(l), [r]"+r"(r), 440 [l_re]"=&f"(l_re), [l_im]"=&f"(l_im), 441 [r_re]"=&f"(r_re), [r_im]"=&f"(r_im) 442 : [hs0]"f"(hs0), [hs1]"f"(hs1), [hs2]"f"(hs2), 443 [hs3]"f"(hs3), [l_end]"r"(l_end) 444 : "memory" 445 ); 446} 447#endif /* !HAVE_MIPS32R6 && !HAVE_MIPS64R6 */ 448#endif /* HAVE_MIPSFPU */ 449#endif /* HAVE_INLINE_ASM */ 450 451void ff_psdsp_init_mips(PSDSPContext *s) 452{ 453#if HAVE_INLINE_ASM 454#if HAVE_MIPSFPU 455 s->hybrid_analysis_ileave = ps_hybrid_analysis_ileave_mips; 456 s->hybrid_synthesis_deint = ps_hybrid_synthesis_deint_mips; 457#if !HAVE_MIPS32R6 && !HAVE_MIPS64R6 458 s->add_squares = ps_add_squares_mips; 459 s->mul_pair_single = ps_mul_pair_single_mips; 460 s->decorrelate = ps_decorrelate_mips; 461 s->stereo_interpolate[0] = ps_stereo_interpolate_mips; 462#endif /* !HAVE_MIPS32R6 && !HAVE_MIPS64R6 */ 463#endif /* HAVE_MIPSFPU */ 464#endif /* HAVE_INLINE_ASM */ 465} 466