1 /* Copyright (c) 2014, Cisco Systems, INC 2 Written by XiangMingZhu WeiZhou MinPeng YanWang 3 4 Redistribution and use in source and binary forms, with or without 5 modification, are permitted provided that the following conditions 6 are met: 7 8 - Redistributions of source code must retain the above copyright 9 notice, this list of conditions and the following disclaimer. 10 11 - Redistributions in binary form must reproduce the above copyright 12 notice, this list of conditions and the following disclaimer in the 13 documentation and/or other materials provided with the distribution. 14 15 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 16 ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 17 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 18 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER 19 OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, 20 EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 21 PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 22 PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 23 LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 24 NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 25 SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 26 */ 27 28 #ifndef SIGPROC_FIX_SSE_H 29 # define SIGPROC_FIX_SSE_H 30 31 # ifdef HAVE_CONFIG_H 32 # include "config.h" 33 # endif 34 35 # if defined(OPUS_X86_MAY_HAVE_SSE4_1) 36 void silk_burg_modified_sse4_1( 37 opus_int32 *res_nrg, /* O Residual energy */ 38 opus_int *res_nrg_Q, /* O Residual energy Q value */ 39 opus_int32 A_Q16[], /* O Prediction coefficients (length order) */ 40 const opus_int16 x[], /* I Input signal, length: nb_subfr * ( D + subfr_length ) */ 41 const opus_int32 minInvGain_Q30, /* I Inverse of max prediction gain */ 42 const opus_int subfr_length, /* I Input signal subframe length (incl. D preceding samples) */ 43 const opus_int nb_subfr, /* I Number of subframes stacked in x */ 44 const opus_int D, /* I Order */ 45 int arch /* I Run-time architecture */ 46 ); 47 48 # if defined(OPUS_X86_PRESUME_SSE4_1) 49 50 # define OVERRIDE_silk_burg_modified 51 # define silk_burg_modified(res_nrg, res_nrg_Q, A_Q16, x, minInvGain_Q30, subfr_length, nb_subfr, D, arch) \ 52 ((void)(arch), silk_burg_modified_sse4_1(res_nrg, res_nrg_Q, A_Q16, x, minInvGain_Q30, subfr_length, nb_subfr, D, arch)) 53 54 # elif defined(OPUS_HAVE_RTCD) 55 56 extern void (*const SILK_BURG_MODIFIED_IMPL[OPUS_ARCHMASK + 1])( 57 opus_int32 *res_nrg, /* O Residual energy */ 58 opus_int *res_nrg_Q, /* O Residual energy Q value */ 59 opus_int32 A_Q16[], /* O Prediction coefficients (length order) */ 60 const opus_int16 x[], /* I Input signal, length: nb_subfr * ( D + subfr_length ) */ 61 const opus_int32 minInvGain_Q30, /* I Inverse of max prediction gain */ 62 const opus_int subfr_length, /* I Input signal subframe length (incl. D preceding samples) */ 63 const opus_int nb_subfr, /* I Number of subframes stacked in x */ 64 const opus_int D, /* I Order */ 65 int arch /* I Run-time architecture */); 66 67 # define OVERRIDE_silk_burg_modified 68 # define silk_burg_modified(res_nrg, res_nrg_Q, A_Q16, x, minInvGain_Q30, subfr_length, nb_subfr, D, arch) \ 69 ((*SILK_BURG_MODIFIED_IMPL[(arch) & OPUS_ARCHMASK])(res_nrg, res_nrg_Q, A_Q16, x, minInvGain_Q30, subfr_length, nb_subfr, D, arch)) 70 71 # endif 72 73 opus_int64 silk_inner_prod16_sse4_1( 74 const opus_int16 *inVec1, 75 const opus_int16 *inVec2, 76 const opus_int len 77 ); 78 79 80 # if defined(OPUS_X86_PRESUME_SSE4_1) 81 82 # define OVERRIDE_silk_inner_prod16 83 # define silk_inner_prod16(inVec1, inVec2, len, arch) \ 84 ((void)(arch),silk_inner_prod16_sse4_1(inVec1, inVec2, len)) 85 86 # elif defined(OPUS_HAVE_RTCD) 87 88 extern opus_int64 (*const SILK_INNER_PROD16_IMPL[OPUS_ARCHMASK + 1])( 89 const opus_int16 *inVec1, 90 const opus_int16 *inVec2, 91 const opus_int len); 92 93 # define OVERRIDE_silk_inner_prod16 94 # define silk_inner_prod16(inVec1, inVec2, len, arch) \ 95 ((*SILK_INNER_PROD16_IMPL[(arch) & OPUS_ARCHMASK])(inVec1, inVec2, len)) 96 97 # endif 98 # endif 99 #endif 100