1/* 2 * Copyright (c) 2017 Google Inc. 3 * 4 * This file is part of FFmpeg. 5 * 6 * FFmpeg is free software; you can redistribute it and/or 7 * modify it under the terms of the GNU Lesser General Public 8 * License as published by the Free Software Foundation; either 9 * version 2.1 of the License, or (at your option) any later version. 10 * 11 * FFmpeg is distributed in the hope that it will be useful, 12 * but WITHOUT ANY WARRANTY; without even the implied warranty of 13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 14 * Lesser General Public License for more details. 15 * 16 * You should have received a copy of the GNU Lesser General Public 17 * License along with FFmpeg; if not, write to the Free Software 18 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 19 */ 20 21#include <stdint.h> 22 23#include "libavutil/attributes.h" 24#include "libavutil/internal.h" 25#include "libavutil/mem_internal.h" 26#include "libavutil/aarch64/cpu.h" 27#include "vp9dsp_init.h" 28 29#define declare_fpel(type, sz, suffix) \ 30void ff_vp9_##type##sz##suffix##_neon(uint8_t *dst, ptrdiff_t dst_stride, \ 31 const uint8_t *src, ptrdiff_t src_stride, \ 32 int h, int mx, int my) 33 34#define decl_mc_func(op, filter, dir, sz, bpp) \ 35void ff_vp9_##op##_##filter##sz##_##dir##_##bpp##_neon(uint8_t *dst, ptrdiff_t dst_stride, \ 36 const uint8_t *src, ptrdiff_t src_stride, \ 37 int h, int mx, int my) 38 39#define define_8tap_2d_fn(op, filter, sz, bpp) \ 40static void op##_##filter##sz##_hv_##bpp##_neon(uint8_t *dst, ptrdiff_t dst_stride, \ 41 const uint8_t *src, \ 42 ptrdiff_t src_stride, \ 43 int h, int mx, int my) \ 44{ \ 45 LOCAL_ALIGNED_16(uint8_t, temp, [((1 + (sz < 64)) * sz + 8) * sz * 2]); \ 46 /* We only need h + 7 lines, but the horizontal filter assumes an \ 47 * even number of rows, so filter h + 8 lines here. */ \ 48 ff_vp9_put_##filter##sz##_h_##bpp##_neon(temp, 2 * sz, \ 49 src - 3 * src_stride, src_stride, \ 50 h + 8, mx, 0); \ 51 ff_vp9_##op##_##filter##sz##_v_##bpp##_neon(dst, dst_stride, \ 52 temp + 3 * 2 * sz, 2 * sz, \ 53 h, 0, my); \ 54} 55 56#define decl_filter_funcs(op, dir, sz, bpp) \ 57 decl_mc_func(op, regular, dir, sz, bpp); \ 58 decl_mc_func(op, sharp, dir, sz, bpp); \ 59 decl_mc_func(op, smooth, dir, sz, bpp) 60 61#define decl_mc_funcs(sz, bpp) \ 62 decl_filter_funcs(put, h, sz, bpp); \ 63 decl_filter_funcs(avg, h, sz, bpp); \ 64 decl_filter_funcs(put, v, sz, bpp); \ 65 decl_filter_funcs(avg, v, sz, bpp); \ 66 decl_filter_funcs(put, hv, sz, bpp); \ 67 decl_filter_funcs(avg, hv, sz, bpp) 68 69#define ff_vp9_copy32_neon ff_vp9_copy32_aarch64 70#define ff_vp9_copy64_neon ff_vp9_copy64_aarch64 71#define ff_vp9_copy128_neon ff_vp9_copy128_aarch64 72 73declare_fpel(copy, 128, ); 74declare_fpel(copy, 64, ); 75declare_fpel(copy, 32, ); 76declare_fpel(copy, 16, ); 77declare_fpel(copy, 8, ); 78declare_fpel(avg, 64, _16); 79declare_fpel(avg, 32, _16); 80declare_fpel(avg, 16, _16); 81declare_fpel(avg, 8, _16); 82declare_fpel(avg, 4, _16); 83 84decl_mc_funcs(64, BPP); 85decl_mc_funcs(32, BPP); 86decl_mc_funcs(16, BPP); 87decl_mc_funcs(8, BPP); 88decl_mc_funcs(4, BPP); 89 90#define define_8tap_2d_funcs(sz, bpp) \ 91 define_8tap_2d_fn(put, regular, sz, bpp) \ 92 define_8tap_2d_fn(put, sharp, sz, bpp) \ 93 define_8tap_2d_fn(put, smooth, sz, bpp) \ 94 define_8tap_2d_fn(avg, regular, sz, bpp) \ 95 define_8tap_2d_fn(avg, sharp, sz, bpp) \ 96 define_8tap_2d_fn(avg, smooth, sz, bpp) 97 98define_8tap_2d_funcs(64, BPP) 99define_8tap_2d_funcs(32, BPP) 100define_8tap_2d_funcs(16, BPP) 101define_8tap_2d_funcs(8, BPP) 102define_8tap_2d_funcs(4, BPP) 103 104static av_cold void vp9dsp_mc_init_aarch64(VP9DSPContext *dsp) 105{ 106 int cpu_flags = av_get_cpu_flags(); 107 108#define init_fpel(idx1, idx2, sz, type, suffix) \ 109 dsp->mc[idx1][FILTER_8TAP_SMOOTH ][idx2][0][0] = \ 110 dsp->mc[idx1][FILTER_8TAP_REGULAR][idx2][0][0] = \ 111 dsp->mc[idx1][FILTER_8TAP_SHARP ][idx2][0][0] = \ 112 dsp->mc[idx1][FILTER_BILINEAR ][idx2][0][0] = ff_vp9_##type##sz##suffix 113 114#define init_copy(idx, sz, suffix) \ 115 init_fpel(idx, 0, sz, copy, suffix) 116 117#define init_avg(idx, sz, suffix) \ 118 init_fpel(idx, 1, sz, avg, suffix) 119 120#define init_copy_avg(idx, sz1, sz2) \ 121 init_copy(idx, sz2, _neon); \ 122 init_avg (idx, sz1, _16_neon) 123 124 if (have_armv8(cpu_flags)) { 125 init_copy(0, 128, _aarch64); 126 init_copy(1, 64, _aarch64); 127 init_copy(2, 32, _aarch64); 128 } 129 130 if (have_neon(cpu_flags)) { 131#define init_mc_func(idx1, idx2, op, filter, fname, dir, mx, my, sz, pfx, bpp) \ 132 dsp->mc[idx1][filter][idx2][mx][my] = pfx##op##_##fname##sz##_##dir##_##bpp##_neon 133 134#define init_mc_funcs(idx, dir, mx, my, sz, pfx, bpp) \ 135 init_mc_func(idx, 0, put, FILTER_8TAP_REGULAR, regular, dir, mx, my, sz, pfx, bpp); \ 136 init_mc_func(idx, 0, put, FILTER_8TAP_SHARP, sharp, dir, mx, my, sz, pfx, bpp); \ 137 init_mc_func(idx, 0, put, FILTER_8TAP_SMOOTH, smooth, dir, mx, my, sz, pfx, bpp); \ 138 init_mc_func(idx, 1, avg, FILTER_8TAP_REGULAR, regular, dir, mx, my, sz, pfx, bpp); \ 139 init_mc_func(idx, 1, avg, FILTER_8TAP_SHARP, sharp, dir, mx, my, sz, pfx, bpp); \ 140 init_mc_func(idx, 1, avg, FILTER_8TAP_SMOOTH, smooth, dir, mx, my, sz, pfx, bpp) 141 142#define init_mc_funcs_dirs(idx, sz, bpp) \ 143 init_mc_funcs(idx, v, 0, 1, sz, ff_vp9_, bpp); \ 144 init_mc_funcs(idx, h, 1, 0, sz, ff_vp9_, bpp); \ 145 init_mc_funcs(idx, hv, 1, 1, sz, , bpp) 146 147 148 init_avg(0, 64, _16_neon); 149 init_avg(1, 32, _16_neon); 150 init_avg(2, 16, _16_neon); 151 init_copy_avg(3, 8, 16); 152 init_copy_avg(4, 4, 8); 153 154 init_mc_funcs_dirs(0, 64, BPP); 155 init_mc_funcs_dirs(1, 32, BPP); 156 init_mc_funcs_dirs(2, 16, BPP); 157 init_mc_funcs_dirs(3, 8, BPP); 158 init_mc_funcs_dirs(4, 4, BPP); 159 } 160} 161 162#define define_itxfm2(type_a, type_b, sz, bpp) \ 163void ff_vp9_##type_a##_##type_b##_##sz##x##sz##_add_##bpp##_neon(uint8_t *_dst, \ 164 ptrdiff_t stride, \ 165 int16_t *_block, int eob) 166#define define_itxfm(type_a, type_b, sz, bpp) define_itxfm2(type_a, type_b, sz, bpp) 167 168#define define_itxfm_funcs(sz, bpp) \ 169 define_itxfm(idct, idct, sz, bpp); \ 170 define_itxfm(iadst, idct, sz, bpp); \ 171 define_itxfm(idct, iadst, sz, bpp); \ 172 define_itxfm(iadst, iadst, sz, bpp) 173 174define_itxfm_funcs(4, BPP); 175define_itxfm_funcs(8, BPP); 176define_itxfm_funcs(16, BPP); 177define_itxfm(idct, idct, 32, BPP); 178define_itxfm(iwht, iwht, 4, BPP); 179 180 181static av_cold void vp9dsp_itxfm_init_aarch64(VP9DSPContext *dsp) 182{ 183 int cpu_flags = av_get_cpu_flags(); 184 185 if (have_neon(cpu_flags)) { 186#define init_itxfm2(tx, sz, bpp) \ 187 dsp->itxfm_add[tx][DCT_DCT] = ff_vp9_idct_idct_##sz##_add_##bpp##_neon; \ 188 dsp->itxfm_add[tx][DCT_ADST] = ff_vp9_iadst_idct_##sz##_add_##bpp##_neon; \ 189 dsp->itxfm_add[tx][ADST_DCT] = ff_vp9_idct_iadst_##sz##_add_##bpp##_neon; \ 190 dsp->itxfm_add[tx][ADST_ADST] = ff_vp9_iadst_iadst_##sz##_add_##bpp##_neon 191#define init_itxfm(tx, sz, bpp) init_itxfm2(tx, sz, bpp) 192 193#define init_idct2(tx, nm, bpp) \ 194 dsp->itxfm_add[tx][DCT_DCT] = \ 195 dsp->itxfm_add[tx][ADST_DCT] = \ 196 dsp->itxfm_add[tx][DCT_ADST] = \ 197 dsp->itxfm_add[tx][ADST_ADST] = ff_vp9_##nm##_add_##bpp##_neon 198#define init_idct(tx, nm, bpp) init_idct2(tx, nm, bpp) 199 200 init_itxfm(TX_4X4, 4x4, BPP); 201 init_itxfm(TX_8X8, 8x8, BPP); 202 init_itxfm(TX_16X16, 16x16, BPP); 203 init_idct(TX_32X32, idct_idct_32x32, BPP); 204 init_idct(4, iwht_iwht_4x4, BPP); 205 } 206} 207 208#define define_loop_filter(dir, wd, size, bpp) \ 209void ff_vp9_loop_filter_##dir##_##wd##_##size##_##bpp##_neon(uint8_t *dst, ptrdiff_t stride, int E, int I, int H) 210 211#define define_loop_filters(wd, size, bpp) \ 212 define_loop_filter(h, wd, size, bpp); \ 213 define_loop_filter(v, wd, size, bpp) 214 215define_loop_filters(4, 8, BPP); 216define_loop_filters(8, 8, BPP); 217define_loop_filters(16, 8, BPP); 218 219define_loop_filters(16, 16, BPP); 220 221define_loop_filters(44, 16, BPP); 222define_loop_filters(48, 16, BPP); 223define_loop_filters(84, 16, BPP); 224define_loop_filters(88, 16, BPP); 225 226static av_cold void vp9dsp_loopfilter_init_aarch64(VP9DSPContext *dsp) 227{ 228 int cpu_flags = av_get_cpu_flags(); 229 230 if (have_neon(cpu_flags)) { 231#define init_lpf_func_8(idx1, idx2, dir, wd, bpp) \ 232 dsp->loop_filter_8[idx1][idx2] = ff_vp9_loop_filter_##dir##_##wd##_8_##bpp##_neon 233 234#define init_lpf_func_16(idx, dir, bpp) \ 235 dsp->loop_filter_16[idx] = ff_vp9_loop_filter_##dir##_16_16_##bpp##_neon 236 237#define init_lpf_func_mix2(idx1, idx2, idx3, dir, wd, bpp) \ 238 dsp->loop_filter_mix2[idx1][idx2][idx3] = ff_vp9_loop_filter_##dir##_##wd##_16_##bpp##_neon 239 240#define init_lpf_funcs_8_wd(idx, wd, bpp) \ 241 init_lpf_func_8(idx, 0, h, wd, bpp); \ 242 init_lpf_func_8(idx, 1, v, wd, bpp) 243 244#define init_lpf_funcs_16(bpp) \ 245 init_lpf_func_16(0, h, bpp); \ 246 init_lpf_func_16(1, v, bpp) 247 248#define init_lpf_funcs_mix2_wd(idx1, idx2, wd, bpp) \ 249 init_lpf_func_mix2(idx1, idx2, 0, h, wd, bpp); \ 250 init_lpf_func_mix2(idx1, idx2, 1, v, wd, bpp) 251 252#define init_lpf_funcs_8(bpp) \ 253 init_lpf_funcs_8_wd(0, 4, bpp); \ 254 init_lpf_funcs_8_wd(1, 8, bpp); \ 255 init_lpf_funcs_8_wd(2, 16, bpp) 256 257#define init_lpf_funcs_mix2(bpp) \ 258 init_lpf_funcs_mix2_wd(0, 0, 44, bpp); \ 259 init_lpf_funcs_mix2_wd(0, 1, 48, bpp); \ 260 init_lpf_funcs_mix2_wd(1, 0, 84, bpp); \ 261 init_lpf_funcs_mix2_wd(1, 1, 88, bpp) 262 263 init_lpf_funcs_8(BPP); 264 init_lpf_funcs_16(BPP); 265 init_lpf_funcs_mix2(BPP); 266 } 267} 268 269av_cold void INIT_FUNC(VP9DSPContext *dsp) 270{ 271 vp9dsp_mc_init_aarch64(dsp); 272 vp9dsp_loopfilter_init_aarch64(dsp); 273 vp9dsp_itxfm_init_aarch64(dsp); 274} 275