| Line | Branch | Exec | Source |
|---|---|---|---|
| 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 | #include "mem.h" | ||
| 51 | |||
| 52 | 2398466 | static void vector_fmul_add_c(int *dst, const int *src0, const int *src1, const int *src2, int len){ | |
| 53 | int i; | ||
| 54 | int64_t accu; | ||
| 55 | |||
| 56 |
2/2✓ Branch 0 taken 132342272 times.
✓ Branch 1 taken 2398466 times.
|
134740738 | for (i=0; i<len; i++) { |
| 57 | 132342272 | accu = (int64_t)src0[i] * src1[i]; | |
| 58 | 132342272 | dst[i] = src2[i] + (int)((accu + 0x40000000) >> 31); | |
| 59 | } | ||
| 60 | 2398466 | } | |
| 61 | |||
| 62 | 274061 | static void vector_fmul_reverse_c(int *dst, const int *src0, const int *src1, int len) | |
| 63 | { | ||
| 64 | int i; | ||
| 65 | int64_t accu; | ||
| 66 | |||
| 67 | 274061 | src1 += len-1; | |
| 68 |
2/2✓ Branch 0 taken 87971584 times.
✓ Branch 1 taken 274061 times.
|
88245645 | for (i=0; i<len; i++) { |
| 69 | 87971584 | accu = (int64_t)src0[i] * src1[-i]; | |
| 70 | 87971584 | dst[i] = (int)((accu+0x40000000) >> 31); | |
| 71 | } | ||
| 72 | 274061 | } | |
| 73 | |||
| 74 | 2927 | static void vector_fmul_window_scaled_c(int16_t *dst, const int32_t *src0, | |
| 75 | const int32_t *src1, const int32_t *win, | ||
| 76 | int len, uint8_t bits) | ||
| 77 | { | ||
| 78 | int32_t s0, s1, wi, wj, i,j, round; | ||
| 79 | |||
| 80 | 2927 | dst += len; | |
| 81 | 2927 | win += len; | |
| 82 | 2927 | src0+= len; | |
| 83 |
1/2✓ Branch 0 taken 2927 times.
✗ Branch 1 not taken.
|
2927 | round = bits? 1 << (bits-1) : 0; |
| 84 | |||
| 85 |
2/2✓ Branch 0 taken 374656 times.
✓ Branch 1 taken 2927 times.
|
377583 | for (i=-len, j=len-1; i<0; i++, j--) { |
| 86 | 374656 | s0 = src0[i]; | |
| 87 | 374656 | s1 = src1[j]; | |
| 88 | 374656 | wi = win[i]; | |
| 89 | 374656 | wj = win[j]; | |
| 90 | 374656 | dst[i] = av_clip_int16(((((int64_t)s0*wj - (int64_t)s1*wi + 0x40000000) >> 31) + round) >> bits); | |
| 91 | 374656 | dst[j] = av_clip_int16(((((int64_t)s0*wi + (int64_t)s1*wj + 0x40000000) >> 31) + round) >> bits); | |
| 92 | } | ||
| 93 | 2927 | } | |
| 94 | |||
| 95 | 24628 | static void vector_fmul_window_c(int32_t *dst, const int32_t *src0, | |
| 96 | const int32_t *src1, const int32_t *win, | ||
| 97 | int len) | ||
| 98 | { | ||
| 99 | int32_t s0, s1, wi, wj, i, j; | ||
| 100 | |||
| 101 | 24628 | dst += len; | |
| 102 | 24628 | win += len; | |
| 103 | 24628 | src0+= len; | |
| 104 | |||
| 105 |
2/2✓ Branch 0 taken 9336256 times.
✓ Branch 1 taken 24628 times.
|
9360884 | for (i=-len, j=len-1; i<0; i++, j--) { |
| 106 | 9336256 | s0 = src0[i]; | |
| 107 | 9336256 | s1 = src1[j]; | |
| 108 | 9336256 | wi = win[i]; | |
| 109 | 9336256 | wj = win[j]; | |
| 110 | 9336256 | dst[i] = ((int64_t)s0*wj - (int64_t)s1*wi + 0x40000000) >> 31; | |
| 111 | 9336256 | dst[j] = ((int64_t)s0*wi + (int64_t)s1*wj + 0x40000000) >> 31; | |
| 112 | } | ||
| 113 | 24628 | } | |
| 114 | |||
| 115 | 272279 | static void vector_fmul_c(int *dst, const int *src0, const int *src1, int len) | |
| 116 | { | ||
| 117 | int i; | ||
| 118 | int64_t accu; | ||
| 119 | |||
| 120 |
2/2✓ Branch 0 taken 16486016 times.
✓ Branch 1 taken 272279 times.
|
16758295 | for (i = 0; i < len; i++){ |
| 121 | 16486016 | accu = (int64_t)src0[i] * src1[i]; | |
| 122 | 16486016 | dst[i] = (int)((accu+0x40000000) >> 31); | |
| 123 | } | ||
| 124 | 272279 | } | |
| 125 | |||
| 126 | 137933 | static int scalarproduct_fixed_c(const int *v1, const int *v2, int len) | |
| 127 | { | ||
| 128 | /** p is initialized with 0x40000000 so that the proper rounding will occur | ||
| 129 | * at the end */ | ||
| 130 | 137933 | int64_t p = 0x40000000; | |
| 131 | int i; | ||
| 132 | |||
| 133 |
2/2✓ Branch 0 taken 2883988 times.
✓ Branch 1 taken 137933 times.
|
3021921 | for (i = 0; i < len; i++) |
| 134 | 2883988 | p += (int64_t)v1[i] * v2[i]; | |
| 135 | |||
| 136 | 137933 | return (int)(p >> 31); | |
| 137 | } | ||
| 138 | |||
| 139 | 256657 | static void butterflies_fixed_c(int *restrict v1s, int *restrict v2, int len) | |
| 140 | { | ||
| 141 | int i; | ||
| 142 | 256657 | unsigned int *v1 = v1s; | |
| 143 | |||
| 144 |
2/2✓ Branch 0 taken 3433068 times.
✓ Branch 1 taken 256657 times.
|
3689725 | for (i = 0; i < len; i++){ |
| 145 | 3433068 | int t = v1[i] - v2[i]; | |
| 146 | 3433068 | v1[i] += v2[i]; | |
| 147 | 3433068 | v2[i] = t; | |
| 148 | } | ||
| 149 | 256657 | } | |
| 150 | |||
| 151 | 150 | AVFixedDSPContext * avpriv_alloc_fixed_dsp(int bit_exact) | |
| 152 | { | ||
| 153 | 150 | AVFixedDSPContext * fdsp = av_malloc(sizeof(AVFixedDSPContext)); | |
| 154 | |||
| 155 |
1/2✗ Branch 0 not taken.
✓ Branch 1 taken 150 times.
|
150 | if (!fdsp) |
| 156 | ✗ | return NULL; | |
| 157 | |||
| 158 | 150 | fdsp->vector_fmul_window_scaled = vector_fmul_window_scaled_c; | |
| 159 | 150 | fdsp->vector_fmul_window = vector_fmul_window_c; | |
| 160 | 150 | fdsp->vector_fmul = vector_fmul_c; | |
| 161 | 150 | fdsp->vector_fmul_add = vector_fmul_add_c; | |
| 162 | 150 | fdsp->vector_fmul_reverse = vector_fmul_reverse_c; | |
| 163 | 150 | fdsp->butterflies_fixed = butterflies_fixed_c; | |
| 164 | 150 | fdsp->scalarproduct_fixed = scalarproduct_fixed_c; | |
| 165 | |||
| 166 | #if ARCH_RISCV | ||
| 167 | ff_fixed_dsp_init_riscv(fdsp); | ||
| 168 | #elif ARCH_X86 | ||
| 169 | 150 | ff_fixed_dsp_init_x86(fdsp); | |
| 170 | #endif | ||
| 171 | |||
| 172 | 150 | return fdsp; | |
| 173 | } | ||
| 174 |