| 1 | /* |
| 2 | * AAC Spectral Band Replication decoding functions |
| 3 | * Copyright (c) 2012 Christophe Gisquet <christophe.gisquet@gmail.com> |
| 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 | #include "config.h" |
| 23 | #include "libavutil/attributes.h" |
| 24 | #include "libavutil/cpu.h" |
| 25 | #include "libavutil/x86/cpu.h" |
| 26 | #include "libavcodec/sbrdsp.h" |
| 27 | |
| 28 | float ff_sbr_sum_square_sse(float (*x)[2], int n); |
| 29 | void ff_sbr_sum64x5_sse(float *z); |
| 30 | void ff_sbr_hf_g_filt_sse(float (*Y)[2], const float (*X_high)[40][2], |
| 31 | const float *g_filt, int m_max, intptr_t ixh); |
| 32 | void ff_sbr_hf_gen_sse(float (*X_high)[2], const float (*X_low)[2], |
| 33 | const float alpha0[2], const float alpha1[2], |
| 34 | float bw, int start, int end); |
| 35 | void ff_sbr_neg_odd_64_sse(float *z); |
| 36 | void ff_sbr_qmf_post_shuffle_sse(float W[32][2], const float *z); |
| 37 | void ff_sbr_qmf_deint_bfly_sse(float *v, const float *src0, const float *src1); |
| 38 | void ff_sbr_qmf_deint_bfly_sse2(float *v, const float *src0, const float *src1); |
| 39 | void ff_sbr_qmf_pre_shuffle_sse2(float *z); |
| 40 | |
| 41 | void ff_sbr_hf_apply_noise_0_sse2(float (*Y)[2], const float *s_m, |
| 42 | const float *q_filt, int noise, |
| 43 | int kx, int m_max); |
| 44 | void ff_sbr_hf_apply_noise_1_sse2(float (*Y)[2], const float *s_m, |
| 45 | const float *q_filt, int noise, |
| 46 | int kx, int m_max); |
| 47 | void ff_sbr_hf_apply_noise_2_sse2(float (*Y)[2], const float *s_m, |
| 48 | const float *q_filt, int noise, |
| 49 | int kx, int m_max); |
| 50 | void ff_sbr_hf_apply_noise_3_sse2(float (*Y)[2], const float *s_m, |
| 51 | const float *q_filt, int noise, |
| 52 | int kx, int m_max); |
| 53 | |
| 54 | void ff_sbr_qmf_deint_neg_sse(float *v, const float *src); |
| 55 | |
| 56 | av_cold void ff_sbrdsp_init_x86(SBRDSPContext *s) |
| 57 | { |
| 58 | int cpu_flags = av_get_cpu_flags(); |
| 59 | |
| 60 | if (EXTERNAL_SSE(cpu_flags)) { |
| 61 | s->neg_odd_64 = ff_sbr_neg_odd_64_sse; |
| 62 | s->sum_square = ff_sbr_sum_square_sse; |
| 63 | s->sum64x5 = ff_sbr_sum64x5_sse; |
| 64 | s->hf_g_filt = ff_sbr_hf_g_filt_sse; |
| 65 | s->hf_gen = ff_sbr_hf_gen_sse; |
| 66 | s->qmf_post_shuffle = ff_sbr_qmf_post_shuffle_sse; |
| 67 | s->qmf_deint_bfly = ff_sbr_qmf_deint_bfly_sse; |
| 68 | s->qmf_deint_neg = ff_sbr_qmf_deint_neg_sse; |
| 69 | } |
| 70 | |
| 71 | if (EXTERNAL_SSE2(cpu_flags)) { |
| 72 | s->qmf_deint_bfly = ff_sbr_qmf_deint_bfly_sse2; |
| 73 | s->qmf_pre_shuffle = ff_sbr_qmf_pre_shuffle_sse2; |
| 74 | s->hf_apply_noise[0] = ff_sbr_hf_apply_noise_0_sse2; |
| 75 | s->hf_apply_noise[1] = ff_sbr_hf_apply_noise_1_sse2; |
| 76 | s->hf_apply_noise[2] = ff_sbr_hf_apply_noise_2_sse2; |
| 77 | s->hf_apply_noise[3] = ff_sbr_hf_apply_noise_3_sse2; |
| 78 | } |
| 79 | } |