1;****************************************************************************** 2;* SIMD optimized AAC encoder DSP functions 3;* 4;* Copyright (C) 2016 Rostislav Pehlivanov <atomnuker@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%include "libavutil/x86/x86util.asm" 24 25SECTION_RODATA 26 27float_abs_mask: times 4 dd 0x7fffffff 28 29SECTION .text 30 31;******************************************************************* 32;void ff_abs_pow34(float *out, const float *in, const int size); 33;******************************************************************* 34INIT_XMM sse 35cglobal abs_pow34, 3, 3, 3, out, in, size 36 mova m2, [float_abs_mask] 37 shl sizeq, 2 38 add inq, sizeq 39 add outq, sizeq 40 neg sizeq 41.loop: 42 andps m0, m2, [inq+sizeq] 43 sqrtps m1, m0 44 mulps m0, m1 45 sqrtps m0, m0 46 mova [outq+sizeq], m0 47 add sizeq, mmsize 48 jl .loop 49 RET 50 51;******************************************************************* 52;void ff_aac_quantize_bands(int *out, const float *in, const float *scaled, 53; int size, int is_signed, int maxval, const float Q34, 54; const float rounding) 55;******************************************************************* 56INIT_XMM sse2 57cglobal aac_quantize_bands, 5, 5, 6, out, in, scaled, size, is_signed, maxval, Q34, rounding 58%if UNIX64 == 0 59 movss m0, Q34m 60 movss m1, roundingm 61 cvtsi2ss m3, dword maxvalm 62%else 63 cvtsi2ss m3, maxvald 64%endif 65 shufps m0, m0, 0 66 shufps m1, m1, 0 67 shufps m3, m3, 0 68 shl is_signedd, 31 69 movd m4, is_signedd 70 shufps m4, m4, 0 71 shl sized, 2 72 add inq, sizeq 73 add outq, sizeq 74 add scaledq, sizeq 75 neg sizeq 76.loop: 77 mulps m2, m0, [scaledq+sizeq] 78 addps m2, m1 79 minps m2, m3 80 andps m5, m4, [inq+sizeq] 81 orps m2, m5 82 cvttps2dq m2, m2 83 mova [outq+sizeq], m2 84 add sizeq, mmsize 85 jl .loop 86 RET 87