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 * Author: Nedeljko Babic (nedeljko.babic imgtec com) 30 * 31 * This file is part of FFmpeg. 32 * 33 * FFmpeg is free software; you can redistribute it and/or 34 * modify it under the terms of the GNU Lesser General Public 35 * License as published by the Free Software Foundation; either 36 * version 2.1 of the License, or (at your option) any later version. 37 * 38 * FFmpeg is distributed in the hope that it will be useful, 39 * but WITHOUT ANY WARRANTY; without even the implied warranty of 40 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 41 * Lesser General Public License for more details. 42 * 43 * You should have received a copy of the GNU Lesser General Public 44 * License along with FFmpeg; if not, write to the Free Software 45 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 46 */ 47 48#include "common.h" 49#include "fixed_dsp.h" 50 51static void vector_fmul_add_c(int *dst, const int *src0, const int *src1, const int *src2, int len){ 52 int i; 53 int64_t accu; 54 55 for (i=0; i<len; i++) { 56 accu = (int64_t)src0[i] * src1[i]; 57 dst[i] = src2[i] + (int)((accu + 0x40000000) >> 31); 58 } 59} 60 61static void vector_fmul_reverse_c(int *dst, const int *src0, const int *src1, int len) 62{ 63 int i; 64 int64_t accu; 65 66 src1 += len-1; 67 for (i=0; i<len; i++) { 68 accu = (int64_t)src0[i] * src1[-i]; 69 dst[i] = (int)((accu+0x40000000) >> 31); 70 } 71} 72 73static void vector_fmul_window_scaled_c(int16_t *dst, const int32_t *src0, 74 const int32_t *src1, const int32_t *win, 75 int len, uint8_t bits) 76{ 77 int32_t s0, s1, wi, wj, i,j, round; 78 79 dst += len; 80 win += len; 81 src0+= len; 82 round = bits? 1 << (bits-1) : 0; 83 84 for (i=-len, j=len-1; i<0; i++, j--) { 85 s0 = src0[i]; 86 s1 = src1[j]; 87 wi = win[i]; 88 wj = win[j]; 89 dst[i] = av_clip_int16(((((int64_t)s0*wj - (int64_t)s1*wi + 0x40000000) >> 31) + round) >> bits); 90 dst[j] = av_clip_int16(((((int64_t)s0*wi + (int64_t)s1*wj + 0x40000000) >> 31) + round) >> bits); 91 } 92} 93 94static void vector_fmul_window_c(int32_t *dst, const int32_t *src0, 95 const int32_t *src1, const int32_t *win, 96 int len) 97{ 98 int32_t s0, s1, wi, wj, i, j; 99 100 dst += len; 101 win += len; 102 src0+= len; 103 104 for (i=-len, j=len-1; i<0; i++, j--) { 105 s0 = src0[i]; 106 s1 = src1[j]; 107 wi = win[i]; 108 wj = win[j]; 109 dst[i] = ((int64_t)s0*wj - (int64_t)s1*wi + 0x40000000) >> 31; 110 dst[j] = ((int64_t)s0*wi + (int64_t)s1*wj + 0x40000000) >> 31; 111 } 112} 113 114static void vector_fmul_c(int *dst, const int *src0, const int *src1, int len) 115{ 116 int i; 117 int64_t accu; 118 119 for (i = 0; i < len; i++){ 120 accu = (int64_t)src0[i] * src1[i]; 121 dst[i] = (int)((accu+0x40000000) >> 31); 122 } 123} 124 125static int scalarproduct_fixed_c(const int *v1, const int *v2, int len) 126{ 127 /** p is initialized with 0x40000000 so that the proper rounding will occur 128 * at the end */ 129 int64_t p = 0x40000000; 130 int i; 131 132 for (i = 0; i < len; i++) 133 p += (int64_t)v1[i] * v2[i]; 134 135 return (int)(p >> 31); 136} 137 138static void butterflies_fixed_c(int *v1s, int *v2, int len) 139{ 140 int i; 141 unsigned int *v1 = v1s; 142 143 for (i = 0; i < len; i++){ 144 int t = v1[i] - v2[i]; 145 v1[i] += v2[i]; 146 v2[i] = t; 147 } 148} 149 150AVFixedDSPContext * avpriv_alloc_fixed_dsp(int bit_exact) 151{ 152 AVFixedDSPContext * fdsp = av_malloc(sizeof(AVFixedDSPContext)); 153 154 if (!fdsp) 155 return NULL; 156 157 fdsp->vector_fmul_window_scaled = vector_fmul_window_scaled_c; 158 fdsp->vector_fmul_window = vector_fmul_window_c; 159 fdsp->vector_fmul = vector_fmul_c; 160 fdsp->vector_fmul_add = vector_fmul_add_c; 161 fdsp->vector_fmul_reverse = vector_fmul_reverse_c; 162 fdsp->butterflies_fixed = butterflies_fixed_c; 163 fdsp->scalarproduct_fixed = scalarproduct_fixed_c; 164 165#if ARCH_X86 166 ff_fixed_dsp_init_x86(fdsp); 167#endif 168 169 return fdsp; 170} 171