1/* 2 * Copyright (c) 2004 Romain Dolbeau <romain@dolbeau.org> 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 "config.h" 22 23#include "libavutil/attributes.h" 24#include "libavutil/cpu.h" 25#include "libavutil/intreadwrite.h" 26#include "libavutil/mem_internal.h" 27#include "libavutil/ppc/cpu.h" 28#include "libavutil/ppc/util_altivec.h" 29 30#include "libavcodec/h264qpel.h" 31 32#include "hpeldsp_altivec.h" 33 34#if HAVE_ALTIVEC 35 36#define PUT_OP_U8_ALTIVEC(d, s, dst) d = s 37#define AVG_OP_U8_ALTIVEC(d, s, dst) d = vec_avg(dst, s) 38 39#define OP_U8_ALTIVEC PUT_OP_U8_ALTIVEC 40#define PREFIX_h264_qpel16_h_lowpass_altivec put_h264_qpel16_h_lowpass_altivec 41#define PREFIX_h264_qpel16_h_lowpass_num altivec_put_h264_qpel16_h_lowpass_num 42#define PREFIX_h264_qpel16_v_lowpass_altivec put_h264_qpel16_v_lowpass_altivec 43#define PREFIX_h264_qpel16_v_lowpass_num altivec_put_h264_qpel16_v_lowpass_num 44#define PREFIX_h264_qpel16_hv_lowpass_altivec put_h264_qpel16_hv_lowpass_altivec 45#define PREFIX_h264_qpel16_hv_lowpass_num altivec_put_h264_qpel16_hv_lowpass_num 46#include "h264qpel_template.c" 47#undef OP_U8_ALTIVEC 48#undef PREFIX_h264_qpel16_h_lowpass_altivec 49#undef PREFIX_h264_qpel16_h_lowpass_num 50#undef PREFIX_h264_qpel16_v_lowpass_altivec 51#undef PREFIX_h264_qpel16_v_lowpass_num 52#undef PREFIX_h264_qpel16_hv_lowpass_altivec 53#undef PREFIX_h264_qpel16_hv_lowpass_num 54 55#define OP_U8_ALTIVEC AVG_OP_U8_ALTIVEC 56#define PREFIX_h264_qpel16_h_lowpass_altivec avg_h264_qpel16_h_lowpass_altivec 57#define PREFIX_h264_qpel16_h_lowpass_num altivec_avg_h264_qpel16_h_lowpass_num 58#define PREFIX_h264_qpel16_v_lowpass_altivec avg_h264_qpel16_v_lowpass_altivec 59#define PREFIX_h264_qpel16_v_lowpass_num altivec_avg_h264_qpel16_v_lowpass_num 60#define PREFIX_h264_qpel16_hv_lowpass_altivec avg_h264_qpel16_hv_lowpass_altivec 61#define PREFIX_h264_qpel16_hv_lowpass_num altivec_avg_h264_qpel16_hv_lowpass_num 62#include "h264qpel_template.c" 63#undef OP_U8_ALTIVEC 64#undef PREFIX_h264_qpel16_h_lowpass_altivec 65#undef PREFIX_h264_qpel16_h_lowpass_num 66#undef PREFIX_h264_qpel16_v_lowpass_altivec 67#undef PREFIX_h264_qpel16_v_lowpass_num 68#undef PREFIX_h264_qpel16_hv_lowpass_altivec 69#undef PREFIX_h264_qpel16_hv_lowpass_num 70 71#define H264_MC(OPNAME, SIZE, CODETYPE) \ 72static void OPNAME ## h264_qpel ## SIZE ## _mc00_ ## CODETYPE (uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 73{\ 74 ff_ ## OPNAME ## pixels ## SIZE ## _ ## CODETYPE(dst, src, stride, SIZE);\ 75}\ 76\ 77static void OPNAME ## h264_qpel ## SIZE ## _mc10_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 78{ \ 79 DECLARE_ALIGNED(16, uint8_t, half)[SIZE*SIZE];\ 80 put_h264_qpel ## SIZE ## _h_lowpass_ ## CODETYPE(half, src, SIZE, stride);\ 81 OPNAME ## pixels ## SIZE ## _l2_ ## CODETYPE(dst, src, half, stride, stride, SIZE);\ 82}\ 83\ 84static void OPNAME ## h264_qpel ## SIZE ## _mc20_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 85{\ 86 OPNAME ## h264_qpel ## SIZE ## _h_lowpass_ ## CODETYPE(dst, src, stride, stride);\ 87}\ 88\ 89static void OPNAME ## h264_qpel ## SIZE ## _mc30_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 90{\ 91 DECLARE_ALIGNED(16, uint8_t, half)[SIZE*SIZE];\ 92 put_h264_qpel ## SIZE ## _h_lowpass_ ## CODETYPE(half, src, SIZE, stride);\ 93 OPNAME ## pixels ## SIZE ## _l2_ ## CODETYPE(dst, src+1, half, stride, stride, SIZE);\ 94}\ 95\ 96static void OPNAME ## h264_qpel ## SIZE ## _mc01_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 97{\ 98 DECLARE_ALIGNED(16, uint8_t, half)[SIZE*SIZE];\ 99 put_h264_qpel ## SIZE ## _v_lowpass_ ## CODETYPE(half, src, SIZE, stride);\ 100 OPNAME ## pixels ## SIZE ## _l2_ ## CODETYPE(dst, src, half, stride, stride, SIZE);\ 101}\ 102\ 103static void OPNAME ## h264_qpel ## SIZE ## _mc02_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 104{\ 105 OPNAME ## h264_qpel ## SIZE ## _v_lowpass_ ## CODETYPE(dst, src, stride, stride);\ 106}\ 107\ 108static void OPNAME ## h264_qpel ## SIZE ## _mc03_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 109{\ 110 DECLARE_ALIGNED(16, uint8_t, half)[SIZE*SIZE];\ 111 put_h264_qpel ## SIZE ## _v_lowpass_ ## CODETYPE(half, src, SIZE, stride);\ 112 OPNAME ## pixels ## SIZE ## _l2_ ## CODETYPE(dst, src+stride, half, stride, stride, SIZE);\ 113}\ 114\ 115static void OPNAME ## h264_qpel ## SIZE ## _mc11_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 116{\ 117 DECLARE_ALIGNED(16, uint8_t, halfH)[SIZE*SIZE];\ 118 DECLARE_ALIGNED(16, uint8_t, halfV)[SIZE*SIZE];\ 119 put_h264_qpel ## SIZE ## _h_lowpass_ ## CODETYPE(halfH, src, SIZE, stride);\ 120 put_h264_qpel ## SIZE ## _v_lowpass_ ## CODETYPE(halfV, src, SIZE, stride);\ 121 OPNAME ## pixels ## SIZE ## _l2_ ## CODETYPE(dst, halfH, halfV, stride, SIZE, SIZE);\ 122}\ 123\ 124static void OPNAME ## h264_qpel ## SIZE ## _mc31_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 125{\ 126 DECLARE_ALIGNED(16, uint8_t, halfH)[SIZE*SIZE];\ 127 DECLARE_ALIGNED(16, uint8_t, halfV)[SIZE*SIZE];\ 128 put_h264_qpel ## SIZE ## _h_lowpass_ ## CODETYPE(halfH, src, SIZE, stride);\ 129 put_h264_qpel ## SIZE ## _v_lowpass_ ## CODETYPE(halfV, src+1, SIZE, stride);\ 130 OPNAME ## pixels ## SIZE ## _l2_ ## CODETYPE(dst, halfH, halfV, stride, SIZE, SIZE);\ 131}\ 132\ 133static void OPNAME ## h264_qpel ## SIZE ## _mc13_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 134{\ 135 DECLARE_ALIGNED(16, uint8_t, halfH)[SIZE*SIZE];\ 136 DECLARE_ALIGNED(16, uint8_t, halfV)[SIZE*SIZE];\ 137 put_h264_qpel ## SIZE ## _h_lowpass_ ## CODETYPE(halfH, src + stride, SIZE, stride);\ 138 put_h264_qpel ## SIZE ## _v_lowpass_ ## CODETYPE(halfV, src, SIZE, stride);\ 139 OPNAME ## pixels ## SIZE ## _l2_ ## CODETYPE(dst, halfH, halfV, stride, SIZE, SIZE);\ 140}\ 141\ 142static void OPNAME ## h264_qpel ## SIZE ## _mc33_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 143{\ 144 DECLARE_ALIGNED(16, uint8_t, halfH)[SIZE*SIZE];\ 145 DECLARE_ALIGNED(16, uint8_t, halfV)[SIZE*SIZE];\ 146 put_h264_qpel ## SIZE ## _h_lowpass_ ## CODETYPE(halfH, src + stride, SIZE, stride);\ 147 put_h264_qpel ## SIZE ## _v_lowpass_ ## CODETYPE(halfV, src+1, SIZE, stride);\ 148 OPNAME ## pixels ## SIZE ## _l2_ ## CODETYPE(dst, halfH, halfV, stride, SIZE, SIZE);\ 149}\ 150\ 151static void OPNAME ## h264_qpel ## SIZE ## _mc22_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 152{\ 153 DECLARE_ALIGNED(16, int16_t, tmp)[SIZE*(SIZE+8)];\ 154 OPNAME ## h264_qpel ## SIZE ## _hv_lowpass_ ## CODETYPE(dst, tmp, src, stride, SIZE, stride);\ 155}\ 156\ 157static void OPNAME ## h264_qpel ## SIZE ## _mc21_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 158{\ 159 DECLARE_ALIGNED(16, uint8_t, halfH)[SIZE*SIZE];\ 160 DECLARE_ALIGNED(16, uint8_t, halfHV)[SIZE*SIZE];\ 161 DECLARE_ALIGNED(16, int16_t, tmp)[SIZE*(SIZE+8)];\ 162 put_h264_qpel ## SIZE ## _h_lowpass_ ## CODETYPE(halfH, src, SIZE, stride);\ 163 put_h264_qpel ## SIZE ## _hv_lowpass_ ## CODETYPE(halfHV, tmp, src, SIZE, SIZE, stride);\ 164 OPNAME ## pixels ## SIZE ## _l2_ ## CODETYPE(dst, halfH, halfHV, stride, SIZE, SIZE);\ 165}\ 166\ 167static void OPNAME ## h264_qpel ## SIZE ## _mc23_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 168{\ 169 DECLARE_ALIGNED(16, uint8_t, halfH)[SIZE*SIZE];\ 170 DECLARE_ALIGNED(16, uint8_t, halfHV)[SIZE*SIZE];\ 171 DECLARE_ALIGNED(16, int16_t, tmp)[SIZE*(SIZE+8)];\ 172 put_h264_qpel ## SIZE ## _h_lowpass_ ## CODETYPE(halfH, src + stride, SIZE, stride);\ 173 put_h264_qpel ## SIZE ## _hv_lowpass_ ## CODETYPE(halfHV, tmp, src, SIZE, SIZE, stride);\ 174 OPNAME ## pixels ## SIZE ## _l2_ ## CODETYPE(dst, halfH, halfHV, stride, SIZE, SIZE);\ 175}\ 176\ 177static void OPNAME ## h264_qpel ## SIZE ## _mc12_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 178{\ 179 DECLARE_ALIGNED(16, uint8_t, halfV)[SIZE*SIZE];\ 180 DECLARE_ALIGNED(16, uint8_t, halfHV)[SIZE*SIZE];\ 181 DECLARE_ALIGNED(16, int16_t, tmp)[SIZE*(SIZE+8)];\ 182 put_h264_qpel ## SIZE ## _v_lowpass_ ## CODETYPE(halfV, src, SIZE, stride);\ 183 put_h264_qpel ## SIZE ## _hv_lowpass_ ## CODETYPE(halfHV, tmp, src, SIZE, SIZE, stride);\ 184 OPNAME ## pixels ## SIZE ## _l2_ ## CODETYPE(dst, halfV, halfHV, stride, SIZE, SIZE);\ 185}\ 186\ 187static void OPNAME ## h264_qpel ## SIZE ## _mc32_ ## CODETYPE(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\ 188{\ 189 DECLARE_ALIGNED(16, uint8_t, halfV)[SIZE*SIZE];\ 190 DECLARE_ALIGNED(16, uint8_t, halfHV)[SIZE*SIZE];\ 191 DECLARE_ALIGNED(16, int16_t, tmp)[SIZE*(SIZE+8)];\ 192 put_h264_qpel ## SIZE ## _v_lowpass_ ## CODETYPE(halfV, src+1, SIZE, stride);\ 193 put_h264_qpel ## SIZE ## _hv_lowpass_ ## CODETYPE(halfHV, tmp, src, SIZE, SIZE, stride);\ 194 OPNAME ## pixels ## SIZE ## _l2_ ## CODETYPE(dst, halfV, halfHV, stride, SIZE, SIZE);\ 195}\ 196 197#if HAVE_BIGENDIAN 198#define put_unligned_store(s, dest) { \ 199 tmp1 = vec_ld(0, dest); \ 200 mask = vec_lvsl(0, dest); \ 201 tmp2 = vec_ld(15, dest); \ 202 edges = vec_perm(tmp2, tmp1, mask); \ 203 align = vec_lvsr(0, dest); \ 204 tmp2 = vec_perm(s, edges, align); \ 205 tmp1 = vec_perm(edges, s, align); \ 206 vec_st(tmp2, 15, dest); \ 207 vec_st(tmp1, 0 , dest); \ 208 } 209#else 210#define put_unligned_store(s, dest) vec_vsx_st(s, 0, dest); 211#endif /* HAVE_BIGENDIAN */ 212 213static inline void put_pixels16_l2_altivec( uint8_t * dst, const uint8_t * src1, 214 const uint8_t * src2, int dst_stride, 215 int src_stride1, int h) 216{ 217 int i; 218 vec_u8 a, b, d, mask_; 219#if HAVE_BIGENDIAN 220 vec_u8 tmp1, tmp2, mask, edges, align; 221 mask_ = vec_lvsl(0, src2); 222#endif 223 224 for (i = 0; i < h; i++) { 225 a = unaligned_load(i * src_stride1, src1); 226 b = load_with_perm_vec(i * 16, src2, mask_); 227 d = vec_avg(a, b); 228 put_unligned_store(d, dst); 229 dst += dst_stride; 230 } 231} 232 233#if HAVE_BIGENDIAN 234#define avg_unligned_store(s, dest){ \ 235 tmp1 = vec_ld(0, dest); \ 236 mask = vec_lvsl(0, dest); \ 237 tmp2 = vec_ld(15, dest); \ 238 a = vec_avg(vec_perm(tmp1, tmp2, mask), s); \ 239 edges = vec_perm(tmp2, tmp1, mask); \ 240 align = vec_lvsr(0, dest); \ 241 tmp2 = vec_perm(a, edges, align); \ 242 tmp1 = vec_perm(edges, a, align); \ 243 vec_st(tmp2, 15, dest); \ 244 vec_st(tmp1, 0 , dest); \ 245 } 246#else 247#define avg_unligned_store(s, dest){ \ 248 a = vec_avg(vec_vsx_ld(0, dst), s); \ 249 vec_vsx_st(a, 0, dst); \ 250 } 251#endif /* HAVE_BIGENDIAN */ 252 253static inline void avg_pixels16_l2_altivec( uint8_t * dst, const uint8_t * src1, 254 const uint8_t * src2, int dst_stride, 255 int src_stride1, int h) 256{ 257 int i; 258 vec_u8 a, b, d, mask_; 259 260#if HAVE_BIGENDIAN 261 vec_u8 tmp1, tmp2, mask, edges, align; 262 mask_ = vec_lvsl(0, src2); 263#endif 264 265 for (i = 0; i < h; i++) { 266 a = unaligned_load(i * src_stride1, src1); 267 b = load_with_perm_vec(i * 16, src2, mask_); 268 d = vec_avg(a, b); 269 avg_unligned_store(d, dst); 270 dst += dst_stride; 271 } 272} 273 274/* Implemented but could be faster 275#define put_pixels16_l2_altivec(d,s1,s2,ds,s1s,h) put_pixels16_l2(d,s1,s2,ds,s1s,16,h) 276#define avg_pixels16_l2_altivec(d,s1,s2,ds,s1s,h) avg_pixels16_l2(d,s1,s2,ds,s1s,16,h) 277 */ 278 279H264_MC(put_, 16, altivec) 280H264_MC(avg_, 16, altivec) 281#endif /* HAVE_ALTIVEC */ 282 283av_cold void ff_h264qpel_init_ppc(H264QpelContext *c, int bit_depth) 284{ 285#if HAVE_ALTIVEC 286 const int high_bit_depth = bit_depth > 8; 287 288 if (!PPC_ALTIVEC(av_get_cpu_flags())) 289 return; 290 291 if (!high_bit_depth) { 292#define dspfunc(PFX, IDX, NUM) \ 293 c->PFX ## _pixels_tab[IDX][ 0] = PFX ## NUM ## _mc00_altivec; \ 294 c->PFX ## _pixels_tab[IDX][ 1] = PFX ## NUM ## _mc10_altivec; \ 295 c->PFX ## _pixels_tab[IDX][ 2] = PFX ## NUM ## _mc20_altivec; \ 296 c->PFX ## _pixels_tab[IDX][ 3] = PFX ## NUM ## _mc30_altivec; \ 297 c->PFX ## _pixels_tab[IDX][ 4] = PFX ## NUM ## _mc01_altivec; \ 298 c->PFX ## _pixels_tab[IDX][ 5] = PFX ## NUM ## _mc11_altivec; \ 299 c->PFX ## _pixels_tab[IDX][ 6] = PFX ## NUM ## _mc21_altivec; \ 300 c->PFX ## _pixels_tab[IDX][ 7] = PFX ## NUM ## _mc31_altivec; \ 301 c->PFX ## _pixels_tab[IDX][ 8] = PFX ## NUM ## _mc02_altivec; \ 302 c->PFX ## _pixels_tab[IDX][ 9] = PFX ## NUM ## _mc12_altivec; \ 303 c->PFX ## _pixels_tab[IDX][10] = PFX ## NUM ## _mc22_altivec; \ 304 c->PFX ## _pixels_tab[IDX][11] = PFX ## NUM ## _mc32_altivec; \ 305 c->PFX ## _pixels_tab[IDX][12] = PFX ## NUM ## _mc03_altivec; \ 306 c->PFX ## _pixels_tab[IDX][13] = PFX ## NUM ## _mc13_altivec; \ 307 c->PFX ## _pixels_tab[IDX][14] = PFX ## NUM ## _mc23_altivec; \ 308 c->PFX ## _pixels_tab[IDX][15] = PFX ## NUM ## _mc33_altivec 309 310 dspfunc(put_h264_qpel, 0, 16); 311 dspfunc(avg_h264_qpel, 0, 16); 312#undef dspfunc 313 } 314#endif /* HAVE_ALTIVEC */ 315} 316