Skip to content

F
ffmpeg.wasm-core
Switch branch/tag
Find file
Normal viewHistoryPermalink
vp8dsp_mips.h 16 KB
Newer Older
Shivraj Patil's avatar
avcodec/mips: MSA (MIPS-SIMD-Arch) optimizations for VP8 functions
dec16372
 
Shivraj Patil committed
1 2 
/*
 * Copyright (c) 2015 Manojkumar Bhosale (Manojkumar.Bhosale@imgtec.com)
Zhou Xiaoyong's avatar
avcodec/mips: version 1 of vp8dsp optimizations for loongson mmi
c5c6e307
 
Zhou Xiaoyong committed
3 
 * Copyright (c) 2016 Zhou Xiaoyong <zhouxiaoyong@loongson.cn>
Shivraj Patil's avatar
avcodec/mips: MSA (MIPS-SIMD-Arch) optimizations for VP8 functions
dec16372
 
Shivraj Patil committed
4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 
 *
 * This file is part of FFmpeg.
 *
 * FFmpeg is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * FFmpeg is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with FFmpeg; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

#ifndef AVCODEC_MIPS_VP8DSP_MIPS_H
#define AVCODEC_MIPS_VP8DSP_MIPS_H
Zhou Xiaoyong's avatar
avcodec/mips: version 1 of vp8dsp optimizations for loongson mmi
c5c6e307
 
Zhou Xiaoyong committed
25 26 27 28 29 
#include "libavutil/mem.h"
#include "libavcodec/vp8dsp.h"
#include "libavcodec/mathops.h"
#include "constants.h"
Shivraj Patil's avatar
avcodec/mips: MSA (MIPS-SIMD-Arch) optimizations for VP8 functions
dec16372
 
Shivraj Patil committed
30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 
void ff_put_vp8_pixels4_msa(uint8_t *dst, ptrdiff_t dststride,
                            uint8_t *src, ptrdiff_t srcstride,
                            int h, int x, int y);
void ff_put_vp8_pixels8_msa(uint8_t *dst, ptrdiff_t dststride,
                            uint8_t *src, ptrdiff_t srcstride,
                            int h, int x, int y);
void ff_put_vp8_pixels16_msa(uint8_t *dst, ptrdiff_t dststride,
                             uint8_t *src, ptrdiff_t srcstride,
                             int h, int x, int y);

void ff_put_vp8_epel16_h4_msa(uint8_t *dst, ptrdiff_t dststride,
                              uint8_t *src, ptrdiff_t srcstride,
                              int h, int mx, int my);
void ff_put_vp8_epel16_h6_msa(uint8_t *dst, ptrdiff_t dststride,
                              uint8_t *src, ptrdiff_t srcstride,
                              int h, int mx, int my);
void ff_put_vp8_epel16_v4_msa(uint8_t *dst, ptrdiff_t dststride,
                              uint8_t *src, ptrdiff_t srcstride,
                              int h, int mx, int my);
void ff_put_vp8_epel16_v6_msa(uint8_t *dst, ptrdiff_t dststride,
                              uint8_t *src, ptrdiff_t srcstride,
                              int h, int mx, int my);
void ff_put_vp8_epel16_h4v4_msa(uint8_t *dst, ptrdiff_t dststride,
                                uint8_t *src, ptrdiff_t srcstride,
                                int h, int mx, int my);
void ff_put_vp8_epel16_h6v4_msa(uint8_t *dst, ptrdiff_t dststride,
                                uint8_t *src, ptrdiff_t srcstride,
                                int h, int mx, int my);
void ff_put_vp8_epel16_h4v6_msa(uint8_t *dst, ptrdiff_t dststride,
                                uint8_t *src, ptrdiff_t srcstride,
                                int h, int mx, int my);
void ff_put_vp8_epel16_h6v6_msa(uint8_t *dst, ptrdiff_t dststride,
                                uint8_t *src, ptrdiff_t srcstride,
                                int h, int mx, int my);

void ff_put_vp8_epel8_h4_msa(uint8_t *dst, ptrdiff_t dststride,
                             uint8_t *src, ptrdiff_t srcstride,
                             int h, int mx, int my);
void ff_put_vp8_epel8_h6_msa(uint8_t *dst, ptrdiff_t dststride,
                             uint8_t *src, ptrdiff_t srcstride,
                             int h, int mx, int my);
void ff_put_vp8_epel8_v4_msa(uint8_t *dst, ptrdiff_t dststride,
                             uint8_t *src, ptrdiff_t srcstride,
                             int h, int mx, int my);
void ff_put_vp8_epel8_v6_msa(uint8_t *dst, ptrdiff_t dststride,
                             uint8_t *src, ptrdiff_t srcstride,
                             int h, int mx, int my);
void ff_put_vp8_epel8_h4v4_msa(uint8_t *dst, ptrdiff_t dststride,
                               uint8_t *src, ptrdiff_t srcstride,
                               int h, int mx, int my);
void ff_put_vp8_epel8_h6v4_msa(uint8_t *dst, ptrdiff_t dststride,
                               uint8_t *src, ptrdiff_t srcstride,
                               int h, int mx, int my);
void ff_put_vp8_epel8_h4v6_msa(uint8_t *dst, ptrdiff_t dststride,
                               uint8_t *src, ptrdiff_t srcstride,
                               int h, int mx, int my);
void ff_put_vp8_epel8_h6v6_msa(uint8_t *dst, ptrdiff_t dststride,
                               uint8_t *src, ptrdiff_t srcstride,
                               int h, int mx, int my);

void ff_put_vp8_epel4_h4_msa(uint8_t *dst, ptrdiff_t dststride,
                             uint8_t *src, ptrdiff_t srcstride,
                             int h, int mx, int my);
void ff_put_vp8_epel4_h6_msa(uint8_t *dst, ptrdiff_t dststride,
                             uint8_t *src, ptrdiff_t srcstride,
                             int h, int mx, int my);
void ff_put_vp8_epel4_v4_msa(uint8_t *dst, ptrdiff_t dststride,
                             uint8_t *src, ptrdiff_t srcstride,
                             int h, int mx, int my);
void ff_put_vp8_epel4_v6_msa(uint8_t *dst, ptrdiff_t dststride,
                             uint8_t *src, ptrdiff_t srcstride,
                             int h, int mx, int my);
void ff_put_vp8_epel4_h4v4_msa(uint8_t *dst, ptrdiff_t dststride,
                               uint8_t *src, ptrdiff_t srcstride,
                               int h, int mx, int my);
void ff_put_vp8_epel4_h6v4_msa(uint8_t *dst, ptrdiff_t dststride,
                               uint8_t *src, ptrdiff_t srcstride,
                               int h, int mx, int my);
void ff_put_vp8_epel4_h4v6_msa(uint8_t *dst, ptrdiff_t dststride,
                               uint8_t *src, ptrdiff_t srcstride,
                               int h, int mx, int my);
void ff_put_vp8_epel4_h6v6_msa(uint8_t *dst, ptrdiff_t dststride,
                               uint8_t *src, ptrdiff_t srcstride,
                               int h, int mx, int my);

void ff_put_vp8_bilinear16_h_msa(uint8_t *dst, ptrdiff_t dststride,
                                 uint8_t *src, ptrdiff_t srcstride,
                                 int h, int mx, int my);
void ff_put_vp8_bilinear16_v_msa(uint8_t *dst, ptrdiff_t dststride,
                                 uint8_t *src, ptrdiff_t srcstride,
                                 int h, int mx, int my);
void ff_put_vp8_bilinear16_hv_msa(uint8_t *dst, ptrdiff_t dststride,
                                  uint8_t *src, ptrdiff_t srcstride,
                                  int h, int mx, int my);

void ff_put_vp8_bilinear8_h_msa(uint8_t *dst, ptrdiff_t dststride,
                                uint8_t *src, ptrdiff_t srcstride,
                                int h, int mx, int my);
void ff_put_vp8_bilinear8_v_msa(uint8_t *dst, ptrdiff_t dststride,
                                uint8_t *src, ptrdiff_t srcstride,
                                int h, int mx, int my);
void ff_put_vp8_bilinear8_hv_msa(uint8_t *dst, ptrdiff_t dststride,
                                 uint8_t *src, ptrdiff_t srcstride,
                                 int h, int mx, int my);

void ff_put_vp8_bilinear4_h_msa(uint8_t *dst, ptrdiff_t dststride,
                                uint8_t *src, ptrdiff_t srcstride,
                                int h, int mx, int my);
void ff_put_vp8_bilinear4_v_msa(uint8_t *dst, ptrdiff_t dststride,
                                uint8_t *src, ptrdiff_t srcstride,
                                int h, int mx, int my);
void ff_put_vp8_bilinear4_hv_msa(uint8_t *dst, ptrdiff_t dststride,
                                 uint8_t *src, ptrdiff_t srcstride,
                                 int h, int mx, int my);

/* loop filter */
void ff_vp8_h_loop_filter16_inner_msa(uint8_t *dst, ptrdiff_t stride,
                                      int32_t e, int32_t i, int32_t h);
void ff_vp8_v_loop_filter16_inner_msa(uint8_t *dst, ptrdiff_t stride,
                                      int32_t e, int32_t i, int32_t h);
void ff_vp8_h_loop_filter8uv_inner_msa(uint8_t *dst_u, uint8_t *dst_v,
                                       ptrdiff_t stride,
                                       int flim_e, int flim_i, int hev_thresh);
void ff_vp8_v_loop_filter8uv_inner_msa(uint8_t *dst_u, uint8_t *dst_v,
                                       ptrdiff_t stride,
                                       int flim_e, int flim_i, int hev_thresh);
void ff_vp8_h_loop_filter16_msa(uint8_t *dst, ptrdiff_t stride,
                                int flim_e, int flim_i, int hev_thresh);
void ff_vp8_v_loop_filter16_msa(uint8_t *dst, ptrdiff_t stride,
                                int flim_e, int flim_i, int hev_thresh);
void ff_vp8_h_loop_filter8uv_msa(uint8_t *dst_u, uint8_t *dst_v,
                                 ptrdiff_t stride,
                                 int flim_e, int flim_i, int hev_thresh);
void ff_vp8_v_loop_filter8uv_msa(uint8_t *dst_u, uint8_t *dst_v,
                                 ptrdiff_t stride,
                                 int flim_e, int flim_i, int hev_thresh);
void ff_vp8_h_loop_filter_simple_msa(uint8_t *dst, ptrdiff_t stride, int flim);
void ff_vp8_v_loop_filter_simple_msa(uint8_t *dst, ptrdiff_t stride, int flim);

/* Idct functions */
void ff_vp8_luma_dc_wht_msa(int16_t block[4][4][16], int16_t dc[16]);
void ff_vp8_idct_add_msa(uint8_t *dst, int16_t block[16], ptrdiff_t stride);
void ff_vp8_idct_dc_add_msa(uint8_t *dst, int16_t block[16], ptrdiff_t stride);
void ff_vp8_idct_dc_add4uv_msa(uint8_t *dst, int16_t block[4][16],
                               ptrdiff_t stride);
void ff_vp8_idct_dc_add4y_msa(uint8_t *dst, int16_t block[4][16],
                              ptrdiff_t stride);
Zhou Xiaoyong's avatar
avcodec/mips: version 1 of vp8dsp optimizations for loongson mmi
c5c6e307
 
Zhou Xiaoyong committed
178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 
void ff_vp8_luma_dc_wht_mmi(int16_t block[4][4][16], int16_t dc[16]);
void ff_vp8_luma_dc_wht_dc_mmi(int16_t block[4][4][16], int16_t dc[16]);
void ff_vp8_idct_add_mmi(uint8_t *dst, int16_t block[16], ptrdiff_t stride);
void ff_vp8_idct_dc_add_mmi(uint8_t *dst, int16_t block[16], ptrdiff_t stride);
void ff_vp8_idct_dc_add4y_mmi(uint8_t *dst, int16_t block[4][16],
        ptrdiff_t stride);
void ff_vp8_idct_dc_add4uv_mmi(uint8_t *dst, int16_t block[4][16],
        ptrdiff_t stride);

void ff_put_vp8_pixels4_mmi(uint8_t *dst, ptrdiff_t dststride, uint8_t *src,
        ptrdiff_t srcstride, int h, int x, int y);
void ff_put_vp8_pixels8_mmi(uint8_t *dst, ptrdiff_t dststride, uint8_t *src,
        ptrdiff_t srcstride, int h, int x, int y);
void ff_put_vp8_pixels16_mmi(uint8_t *dst, ptrdiff_t dststride, uint8_t *src,
        ptrdiff_t srcstride, int h, int x, int y);

void ff_put_vp8_epel16_h4_mmi(uint8_t *dst, ptrdiff_t dststride, uint8_t *src,
        ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel16_h6_mmi(uint8_t *dst, ptrdiff_t dststride, uint8_t *src,
        ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel16_v4_mmi(uint8_t *dst, ptrdiff_t dststride, uint8_t *src,
        ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel16_v6_mmi(uint8_t *dst, ptrdiff_t dststride, uint8_t *src,
        ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel16_h4v4_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel16_h6v4_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel16_h4v6_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel16_h6v6_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);

void ff_put_vp8_epel8_h4_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel8_h6_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel8_v4_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel8_v6_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel8_h4v4_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel8_h6v4_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel8_h4v6_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel8_h6v6_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);

void ff_put_vp8_epel4_h4_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel4_h6_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel4_v4_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel4_v6_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel4_h4v4_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel4_h6v4_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel4_h4v6_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_epel4_h6v6_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);

void ff_put_vp8_bilinear16_h_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_bilinear16_v_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_bilinear16_hv_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);

void ff_put_vp8_bilinear8_h_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_bilinear8_v_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_bilinear8_hv_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);

void ff_put_vp8_bilinear4_h_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_bilinear4_v_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);
void ff_put_vp8_bilinear4_hv_mmi(uint8_t *dst, ptrdiff_t dststride,
        uint8_t *src, ptrdiff_t srcstride, int h, int mx, int my);

// loop filter applied to edges between macroblocks
void ff_vp8_v_loop_filter16_mmi(uint8_t *dst, ptrdiff_t stride, int flim_E,
        int flim_I, int hev_thresh);
void ff_vp8_h_loop_filter16_mmi(uint8_t *dst, ptrdiff_t stride, int flim_E,
        int flim_I, int hev_thresh);
void ff_vp8_v_loop_filter8uv_mmi(uint8_t *dstU, uint8_t *dstV, ptrdiff_t stride,
        int flim_E, int flim_I, int hev_thresh);
void ff_vp8_h_loop_filter8uv_mmi(uint8_t *dstU, uint8_t *dstV, ptrdiff_t stride,
        int flim_E, int flim_I, int hev_thresh);

// loop filter applied to inner macroblock edges
void ff_vp8_v_loop_filter16_inner_mmi(uint8_t *dst, ptrdiff_t stride,
        int flim_E, int flim_I, int hev_thresh);
void ff_vp8_h_loop_filter16_inner_mmi(uint8_t *dst, ptrdiff_t stride,
        int flim_E, int flim_I, int hev_thresh);
void ff_vp8_v_loop_filter8uv_inner_mmi(uint8_t *dstU, uint8_t *dstV,
        ptrdiff_t stride, int flim_E, int flim_I, int hev_thresh);
void ff_vp8_h_loop_filter8uv_inner_mmi(uint8_t *dstU, uint8_t *dstV,
        ptrdiff_t stride, int flim_E, int flim_I, int hev_thresh);

void ff_vp8_v_loop_filter_simple_mmi(uint8_t *dst, ptrdiff_t stride, int flim);
void ff_vp8_h_loop_filter_simple_mmi(uint8_t *dst, ptrdiff_t stride, int flim);
Shivraj Patil's avatar
avcodec/mips: MSA (MIPS-SIMD-Arch) optimizations for VP8 functions
dec16372
 
Shivraj Patil committed
289 
#endif  // #ifndef AVCODEC_MIPS_VP8DSP_MIPS_H