FFmpeg: libavcodec/rv40dsp.c Source File

FFmpeg

[フレーム]

libavcodec

rv40dsp.c

Go to the documentation of this file.

1 /*

2 * RV40 decoder motion compensation functions

4 *

5 * This file is part of FFmpeg.

6 *

7 * FFmpeg is free software; you can redistribute it and/or

8 * modify it under the terms of the GNU Lesser General Public

9 * License as published by the Free Software Foundation; either

10 * version 2.1 of the License, or (at your option) any later version.

11 *

12 * FFmpeg is distributed in the hope that it will be useful,

13 * but WITHOUT ANY WARRANTY; without even the implied warranty of

14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU

15 * Lesser General Public License for more details.

16 *

17 * You should have received a copy of the GNU Lesser General Public

18 * License along with FFmpeg; if not, write to the Free Software

19 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA

20 */

22 /**

23 * @file

24 * RV40 decoder motion compensation functions

25 */

27 #include "avcodec.h"

28 #include "dsputil.h"

29 #include "rv34dsp.h"

30 #include "libavutil/avassert.h"

31 #include "libavutil/common.h"

33 #define RV40_LOWPASS(OPNAME, OP) \

34 static av_unused void OPNAME ## rv40_qpel8_h_lowpass(uint8_t *dst, uint8_t *src, int dstStride, int srcStride,\

35 const int h, const int C1, const int C2, const int SHIFT){\

36 uint8_t *cm = ff_cropTbl + MAX_NEG_CROP;\

37 int i;\

38 for(i = 0; i < h; i++)\

39 {\

40 OP(dst[0], (src[-2] + src[ 3] - 5*(src[-1]+src[2]) + src[0]*C1 + src[1]*C2 + (1<<(SHIFT-1))) >> SHIFT);\

41 OP(dst[1], (src[-1] + src[ 4] - 5*(src[ 0]+src[3]) + src[1]*C1 + src[2]*C2 + (1<<(SHIFT-1))) >> SHIFT);\

42 OP(dst[2], (src[ 0] + src[ 5] - 5*(src[ 1]+src[4]) + src[2]*C1 + src[3]*C2 + (1<<(SHIFT-1))) >> SHIFT);\

43 OP(dst[3], (src[ 1] + src[ 6] - 5*(src[ 2]+src[5]) + src[3]*C1 + src[4]*C2 + (1<<(SHIFT-1))) >> SHIFT);\

44 OP(dst[4], (src[ 2] + src[ 7] - 5*(src[ 3]+src[6]) + src[4]*C1 + src[5]*C2 + (1<<(SHIFT-1))) >> SHIFT);\

45 OP(dst[5], (src[ 3] + src[ 8] - 5*(src[ 4]+src[7]) + src[5]*C1 + src[6]*C2 + (1<<(SHIFT-1))) >> SHIFT);\

46 OP(dst[6], (src[ 4] + src[ 9] - 5*(src[ 5]+src[8]) + src[6]*C1 + src[7]*C2 + (1<<(SHIFT-1))) >> SHIFT);\

47 OP(dst[7], (src[ 5] + src[10] - 5*(src[ 6]+src[9]) + src[7]*C1 + src[8]*C2 + (1<<(SHIFT-1))) >> SHIFT);\

48 dst += dstStride;\

49 src += srcStride;\

50 }\

51 }\

52 \

53 static void OPNAME ## rv40_qpel8_v_lowpass(uint8_t *dst, uint8_t *src, int dstStride, int srcStride,\

54 const int w, const int C1, const int C2, const int SHIFT){\

55 uint8_t *cm = ff_cropTbl + MAX_NEG_CROP;\

56 int i;\

57 for(i = 0; i < w; i++)\

58 {\

59 const int srcB = src[-2*srcStride];\

60 const int srcA = src[-1*srcStride];\

61 const int src0 = src[0 *srcStride];\

62 const int src1 = src[1 *srcStride];\

63 const int src2 = src[2 *srcStride];\

64 const int src3 = src[3 *srcStride];\

65 const int src4 = src[4 *srcStride];\

66 const int src5 = src[5 *srcStride];\

67 const int src6 = src[6 *srcStride];\

68 const int src7 = src[7 *srcStride];\

69 const int src8 = src[8 *srcStride];\

70 const int src9 = src[9 *srcStride];\

71 const int src10 = src[10*srcStride];\

72 OP(dst[0*dstStride], (srcB + src3 - 5*(srcA+src2) + src0*C1 + src1*C2 + (1<<(SHIFT-1))) >> SHIFT);\

73 OP(dst[1*dstStride], (srcA + src4 - 5*(src0+src3) + src1*C1 + src2*C2 + (1<<(SHIFT-1))) >> SHIFT);\

74 OP(dst[2*dstStride], (src0 + src5 - 5*(src1+src4) + src2*C1 + src3*C2 + (1<<(SHIFT-1))) >> SHIFT);\

75 OP(dst[3*dstStride], (src1 + src6 - 5*(src2+src5) + src3*C1 + src4*C2 + (1<<(SHIFT-1))) >> SHIFT);\

76 OP(dst[4*dstStride], (src2 + src7 - 5*(src3+src6) + src4*C1 + src5*C2 + (1<<(SHIFT-1))) >> SHIFT);\

77 OP(dst[5*dstStride], (src3 + src8 - 5*(src4+src7) + src5*C1 + src6*C2 + (1<<(SHIFT-1))) >> SHIFT);\

78 OP(dst[6*dstStride], (src4 + src9 - 5*(src5+src8) + src6*C1 + src7*C2 + (1<<(SHIFT-1))) >> SHIFT);\

79 OP(dst[7*dstStride], (src5 + src10 - 5*(src6+src9) + src7*C1 + src8*C2 + (1<<(SHIFT-1))) >> SHIFT);\

80 dst++;\

81 src++;\

82 }\

83 }\

84 \

85 static void OPNAME ## rv40_qpel16_v_lowpass(uint8_t *dst, uint8_t *src, int dstStride, int srcStride,\

86 const int w, const int C1, const int C2, const int SHIFT){\

87 OPNAME ## rv40_qpel8_v_lowpass(dst , src , dstStride, srcStride, 8, C1, C2, SHIFT);\

88 OPNAME ## rv40_qpel8_v_lowpass(dst+8, src+8, dstStride, srcStride, 8, C1, C2, SHIFT);\

89 src += 8*srcStride;\

90 dst += 8*dstStride;\

91 OPNAME ## rv40_qpel8_v_lowpass(dst , src , dstStride, srcStride, w-8, C1, C2, SHIFT);\

92 OPNAME ## rv40_qpel8_v_lowpass(dst+8, src+8, dstStride, srcStride, w-8, C1, C2, SHIFT);\

93 }\

94 \

95 static void OPNAME ## rv40_qpel16_h_lowpass(uint8_t *dst, uint8_t *src, int dstStride, int srcStride,\

96 const int h, const int C1, const int C2, const int SHIFT){\

97 OPNAME ## rv40_qpel8_h_lowpass(dst , src , dstStride, srcStride, 8, C1, C2, SHIFT);\

98 OPNAME ## rv40_qpel8_h_lowpass(dst+8, src+8, dstStride, srcStride, 8, C1, C2, SHIFT);\

99 src += 8*srcStride;\

100 dst += 8*dstStride;\

101 OPNAME ## rv40_qpel8_h_lowpass(dst , src , dstStride, srcStride, h-8, C1, C2, SHIFT);\

102 OPNAME ## rv40_qpel8_h_lowpass(dst+8, src+8, dstStride, srcStride, h-8, C1, C2, SHIFT);\

103 }\

104 \

105

106 #define RV40_MC(OPNAME, SIZE) \

107 static void OPNAME ## rv40_qpel ## SIZE ## _mc10_c(uint8_t *dst, uint8_t *src, int stride){\

108 OPNAME ## rv40_qpel ## SIZE ## _h_lowpass(dst, src, stride, stride, SIZE, 52, 20, 6);\

109 }\

110 \

111 static void OPNAME ## rv40_qpel ## SIZE ## _mc30_c(uint8_t *dst, uint8_t *src, int stride){\

112 OPNAME ## rv40_qpel ## SIZE ## _h_lowpass(dst, src, stride, stride, SIZE, 20, 52, 6);\

113 }\

114 \

115 static void OPNAME ## rv40_qpel ## SIZE ## _mc01_c(uint8_t *dst, uint8_t *src, int stride){\

116 OPNAME ## rv40_qpel ## SIZE ## _v_lowpass(dst, src, stride, stride, SIZE, 52, 20, 6);\

117 }\

118 \

119 static void OPNAME ## rv40_qpel ## SIZE ## _mc11_c(uint8_t *dst, uint8_t *src, int stride){\

120 uint8_t full[SIZE*(SIZE+5)];\

121 uint8_t * const full_mid = full + SIZE*2;\

122 put_rv40_qpel ## SIZE ## _h_lowpass(full, src - 2*stride, SIZE, stride, SIZE+5, 52, 20, 6);\

123 OPNAME ## rv40_qpel ## SIZE ## _v_lowpass(dst, full_mid, stride, SIZE, SIZE, 52, 20, 6);\

124 }\

125 \

126 static void OPNAME ## rv40_qpel ## SIZE ## _mc21_c(uint8_t *dst, uint8_t *src, int stride){\

127 uint8_t full[SIZE*(SIZE+5)];\

128 uint8_t * const full_mid = full + SIZE*2;\

129 put_rv40_qpel ## SIZE ## _h_lowpass(full, src - 2*stride, SIZE, stride, SIZE+5, 20, 20, 5);\

130 OPNAME ## rv40_qpel ## SIZE ## _v_lowpass(dst, full_mid, stride, SIZE, SIZE, 52, 20, 6);\

131 }\

132 \

133 static void OPNAME ## rv40_qpel ## SIZE ## _mc31_c(uint8_t *dst, uint8_t *src, int stride){\

134 uint8_t full[SIZE*(SIZE+5)];\

135 uint8_t * const full_mid = full + SIZE*2;\

136 put_rv40_qpel ## SIZE ## _h_lowpass(full, src - 2*stride, SIZE, stride, SIZE+5, 20, 52, 6);\

137 OPNAME ## rv40_qpel ## SIZE ## _v_lowpass(dst, full_mid, stride, SIZE, SIZE, 52, 20, 6);\

138 }\

139 \

140 static void OPNAME ## rv40_qpel ## SIZE ## _mc12_c(uint8_t *dst, uint8_t *src, int stride){\

141 uint8_t full[SIZE*(SIZE+5)];\

142 uint8_t * const full_mid = full + SIZE*2;\

143 put_rv40_qpel ## SIZE ## _h_lowpass(full, src - 2*stride, SIZE, stride, SIZE+5, 52, 20, 6);\

144 OPNAME ## rv40_qpel ## SIZE ## _v_lowpass(dst, full_mid, stride, SIZE, SIZE, 20, 20, 5);\

145 }\

146 \

147 static void OPNAME ## rv40_qpel ## SIZE ## _mc22_c(uint8_t *dst, uint8_t *src, int stride){\

148 uint8_t full[SIZE*(SIZE+5)];\

149 uint8_t * const full_mid = full + SIZE*2;\

150 put_rv40_qpel ## SIZE ## _h_lowpass(full, src - 2*stride, SIZE, stride, SIZE+5, 20, 20, 5);\

151 OPNAME ## rv40_qpel ## SIZE ## _v_lowpass(dst, full_mid, stride, SIZE, SIZE, 20, 20, 5);\

152 }\

153 \

154 static void OPNAME ## rv40_qpel ## SIZE ## _mc32_c(uint8_t *dst, uint8_t *src, int stride){\

155 uint8_t full[SIZE*(SIZE+5)];\

156 uint8_t * const full_mid = full + SIZE*2;\

157 put_rv40_qpel ## SIZE ## _h_lowpass(full, src - 2*stride, SIZE, stride, SIZE+5, 20, 52, 6);\

158 OPNAME ## rv40_qpel ## SIZE ## _v_lowpass(dst, full_mid, stride, SIZE, SIZE, 20, 20, 5);\

159 }\

160 \

161 static void OPNAME ## rv40_qpel ## SIZE ## _mc03_c(uint8_t *dst, uint8_t *src, int stride){\

162 OPNAME ## rv40_qpel ## SIZE ## _v_lowpass(dst, src, stride, stride, SIZE, 20, 52, 6);\

163 }\

164 \

165 static void OPNAME ## rv40_qpel ## SIZE ## _mc13_c(uint8_t *dst, uint8_t *src, int stride){\

166 uint8_t full[SIZE*(SIZE+5)];\

167 uint8_t * const full_mid = full + SIZE*2;\

168 put_rv40_qpel ## SIZE ## _h_lowpass(full, src - 2*stride, SIZE, stride, SIZE+5, 52, 20, 6);\

169 OPNAME ## rv40_qpel ## SIZE ## _v_lowpass(dst, full_mid, stride, SIZE, SIZE, 20, 52, 6);\

170 }\

171 \

172 static void OPNAME ## rv40_qpel ## SIZE ## _mc23_c(uint8_t *dst, uint8_t *src, int stride){\

173 uint8_t full[SIZE*(SIZE+5)];\

174 uint8_t * const full_mid = full + SIZE*2;\

175 put_rv40_qpel ## SIZE ## _h_lowpass(full, src - 2*stride, SIZE, stride, SIZE+5, 20, 20, 5);\

176 OPNAME ## rv40_qpel ## SIZE ## _v_lowpass(dst, full_mid, stride, SIZE, SIZE, 20, 52, 6);\

177 }\

178 \

179

180 #define op_avg(a, b) a = (((a)+cm[b]+1)>>1)

181 #define op_put(a, b) a = cm[b]

182

183 RV40_LOWPASS(put_ , op_put)

184 RV40_LOWPASS(avg_ , op_avg)

185

186 #undef op_avg

187 #undef op_put

188

189 RV40_MC(put_, 8)

190 RV40_MC(put_, 16)

191 RV40_MC(avg_, 8)

192 RV40_MC(avg_, 16)

193

194 static const int rv40_bias[4][4] = {

195 { 0, 16, 32, 16 },

196 { 32, 28, 32, 28 },

197 { 0, 32, 16, 32 },

198 { 32, 28, 32, 28 }

199 };

200

201 #define RV40_CHROMA_MC(OPNAME, OP)\

202 static void OPNAME ## rv40_chroma_mc4_c(uint8_t *dst/*align 8*/, uint8_t *src/*align 1*/, int stride, int h, int x, int y){\

203 const int A = (8-x) * (8-y);\

204 const int B = ( x) * (8-y);\

205 const int C = (8-x) * ( y);\

206 const int D = ( x) * ( y);\

207 int i;\

208 int bias = rv40_bias[y>>1][x>>1];\

209 \

210 av_assert2(x<8 && y<8 && x>=0 && y>=0);\

211 \

212 if(D){\

213 for(i = 0; i < h; i++){\

214 OP(dst[0], (A*src[0] + B*src[1] + C*src[stride+0] + D*src[stride+1] + bias));\

215 OP(dst[1], (A*src[1] + B*src[2] + C*src[stride+1] + D*src[stride+2] + bias));\

216 OP(dst[2], (A*src[2] + B*src[3] + C*src[stride+2] + D*src[stride+3] + bias));\

217 OP(dst[3], (A*src[3] + B*src[4] + C*src[stride+3] + D*src[stride+4] + bias));\

218 dst += stride;\

219 src += stride;\

220 }\

221 }else{\

222 const int E = B + C;\

223 const int step = C ? stride : 1;\

224 for(i = 0; i < h; i++){\

225 OP(dst[0], (A*src[0] + E*src[step+0] + bias));\

226 OP(dst[1], (A*src[1] + E*src[step+1] + bias));\

227 OP(dst[2], (A*src[2] + E*src[step+2] + bias));\

228 OP(dst[3], (A*src[3] + E*src[step+3] + bias));\

229 dst += stride;\

230 src += stride;\

231 }\

232 }\

233 }\

234 \

235 static void OPNAME ## rv40_chroma_mc8_c(uint8_t *dst/*align 8*/, uint8_t *src/*align 1*/, int stride, int h, int x, int y){\

236 const int A = (8-x) * (8-y);\

237 const int B = ( x) * (8-y);\

238 const int C = (8-x) * ( y);\

239 const int D = ( x) * ( y);\

240 int i;\

241 int bias = rv40_bias[y>>1][x>>1];\

242 \

243 av_assert2(x<8 && y<8 && x>=0 && y>=0);\

244 \

245 if(D){\

246 for(i = 0; i < h; i++){\

247 OP(dst[0], (A*src[0] + B*src[1] + C*src[stride+0] + D*src[stride+1] + bias));\

248 OP(dst[1], (A*src[1] + B*src[2] + C*src[stride+1] + D*src[stride+2] + bias));\

249 OP(dst[2], (A*src[2] + B*src[3] + C*src[stride+2] + D*src[stride+3] + bias));\

250 OP(dst[3], (A*src[3] + B*src[4] + C*src[stride+3] + D*src[stride+4] + bias));\

251 OP(dst[4], (A*src[4] + B*src[5] + C*src[stride+4] + D*src[stride+5] + bias));\

252 OP(dst[5], (A*src[5] + B*src[6] + C*src[stride+5] + D*src[stride+6] + bias));\

253 OP(dst[6], (A*src[6] + B*src[7] + C*src[stride+6] + D*src[stride+7] + bias));\

254 OP(dst[7], (A*src[7] + B*src[8] + C*src[stride+7] + D*src[stride+8] + bias));\

255 dst += stride;\

256 src += stride;\

257 }\

258 }else{\

259 const int E = B + C;\

260 const int step = C ? stride : 1;\

261 for(i = 0; i < h; i++){\

262 OP(dst[0], (A*src[0] + E*src[step+0] + bias));\

263 OP(dst[1], (A*src[1] + E*src[step+1] + bias));\

264 OP(dst[2], (A*src[2] + E*src[step+2] + bias));\

265 OP(dst[3], (A*src[3] + E*src[step+3] + bias));\

266 OP(dst[4], (A*src[4] + E*src[step+4] + bias));\

267 OP(dst[5], (A*src[5] + E*src[step+5] + bias));\

268 OP(dst[6], (A*src[6] + E*src[step+6] + bias));\

269 OP(dst[7], (A*src[7] + E*src[step+7] + bias));\

270 dst += stride;\

271 src += stride;\

272 }\

273 }\

274 }

275

276 #define op_avg(a, b) a = (((a)+((b)>>6)+1)>>1)

277 #define op_put(a, b) a = ((b)>>6)

278

279 RV40_CHROMA_MC(put_, op_put)

280 RV40_CHROMA_MC(avg_, op_avg)

281

282 #define RV40_WEIGHT_FUNC(size) \

283 static void rv40_weight_func_rnd_ ## size (uint8_t *dst, uint8_t *src1, uint8_t *src2, int w1, int w2, ptrdiff_t stride)\

284 {\

285 int i, j;\

286 \

287 for (j = 0; j < size; j++) {\

288 for (i = 0; i < size; i++)\

289 dst[i] = (((w2 * src1[i]) >> 9) + ((w1 * src2[i]) >> 9) + 0x10) >> 5;\

290 src1 += stride;\

291 src2 += stride;\

292 dst += stride;\

293 }\

294 }\

295 static void rv40_weight_func_nornd_ ## size (uint8_t *dst, uint8_t *src1, uint8_t *src2, int w1, int w2, ptrdiff_t stride)\

296 {\

297 int i, j;\

298 \

299 for (j = 0; j < size; j++) {\

300 for (i = 0; i < size; i++)\

301 dst[i] = (w2 * src1[i] + w1 * src2[i] + 0x10) >> 5;\

302 src1 += stride;\

303 src2 += stride;\

304 dst += stride;\

305 }\

306 }

307

308 RV40_WEIGHT_FUNC(16)

309 RV40_WEIGHT_FUNC(8)

310

311 /**

312 * dither values for deblocking filter - left/top values

313 */

314 static const uint8_t rv40_dither_l[16] = {

315 0x40, 0x50, 0x20, 0x60, 0x30, 0x50, 0x40, 0x30,

316 0x50, 0x40, 0x50, 0x30, 0x60, 0x20, 0x50, 0x40

317 };

318

319 /**

320 * dither values for deblocking filter - right/bottom values

321 */

322 static const uint8_t rv40_dither_r[16] = {

323 0x40, 0x30, 0x60, 0x20, 0x50, 0x30, 0x30, 0x40,

324 0x40, 0x40, 0x50, 0x30, 0x20, 0x60, 0x30, 0x40

325 };

326

327 #define CLIP_SYMM(a, b) av_clip(a, -(b), b)

328 /**

329 * weaker deblocking very similar to the one described in 4.4.2 of JVT-A003r1

330 */

331 static av_always_inline void rv40_weak_loop_filter(uint8_t *src,

332 const int step,

333 const ptrdiff_t stride,

334 const int filter_p1,

335 const int filter_q1,

336 const int alpha,

337 const int beta,

338 const int lim_p0q0,

339 const int lim_q1,

340 const int lim_p1)

341 {

342 uint8_t *cm = ff_cropTbl + MAX_NEG_CROP;

343 int i, t, u, diff;

344

345 for (i = 0; i < 4; i++, src += stride) {

346 int diff_p1p0 = src[-2*step] - src[-1*step];

347 int diff_q1q0 = src[ 1*step] - src[ 0*step];

348 int diff_p1p2 = src[-2*step] - src[-3*step];

349 int diff_q1q2 = src[ 1*step] - src[ 2*step];

350

351 t = src[0*step] - src[-1*step];

352 if (!t)

353 continue;

354

355 u = (alpha * FFABS(t)) >> 7;

356 if (u > 3 - (filter_p1 && filter_q1))

357 continue;

358

359 t <<= 2;

360 if (filter_p1 && filter_q1)

361 t += src[-2*step] - src[1*step];

362

363 diff = CLIP_SYMM((t + 4) >> 3, lim_p0q0);

364 src[-1*step] = cm[src[-1*step] + diff];

365 src[ 0*step] = cm[src[ 0*step] - diff];

366

367 if (filter_p1 && FFABS(diff_p1p2) <= beta) {

368 t = (diff_p1p0 + diff_p1p2 - diff) >> 1;

369 src[-2*step] = cm[src[-2*step] - CLIP_SYMM(t, lim_p1)];

370 }

371

372 if (filter_q1 && FFABS(diff_q1q2) <= beta) {

373 t = (diff_q1q0 + diff_q1q2 + diff) >> 1;

374 src[ 1*step] = cm[src[ 1*step] - CLIP_SYMM(t, lim_q1)];

375 }

376 }

377 }

378

379 static void rv40_h_weak_loop_filter(uint8_t *src, const ptrdiff_t stride,

380 const int filter_p1, const int filter_q1,

381 const int alpha, const int beta,

382 const int lim_p0q0, const int lim_q1,

383 const int lim_p1)

384 {

385 rv40_weak_loop_filter(src, stride, 1, filter_p1, filter_q1,

386 alpha, beta, lim_p0q0, lim_q1, lim_p1);

387 }

388

389 static void rv40_v_weak_loop_filter(uint8_t *src, const ptrdiff_t stride,

390 const int filter_p1, const int filter_q1,

391 const int alpha, const int beta,

392 const int lim_p0q0, const int lim_q1,

393 const int lim_p1)

394 {

395 rv40_weak_loop_filter(src, 1, stride, filter_p1, filter_q1,

396 alpha, beta, lim_p0q0, lim_q1, lim_p1);

397 }

398

399 static av_always_inline void rv40_strong_loop_filter(uint8_t *src,

400 const int step,

401 const ptrdiff_t stride,

402 const int alpha,

403 const int lims,

404 const int dmode,

405 const int chroma)

406 {

407 int i;

408

409 for(i = 0; i < 4; i++, src += stride){

410 int sflag, p0, q0, p1, q1;

411 int t = src[0*step] - src[-1*step];

412

413 if (!t)

414 continue;

415

416 sflag = (alpha * FFABS(t)) >> 7;

417 if (sflag > 1)

418 continue;

419

420 p0 = (25*src[-3*step] + 26*src[-2*step] + 26*src[-1*step] +

421 26*src[ 0*step] + 25*src[ 1*step] +

422 rv40_dither_l[dmode + i]) >> 7;

423

424 q0 = (25*src[-2*step] + 26*src[-1*step] + 26*src[ 0*step] +

425 26*src[ 1*step] + 25*src[ 2*step] +

426 rv40_dither_r[dmode + i]) >> 7;

427

428 if (sflag) {

429 p0 = av_clip(p0, src[-1*step] - lims, src[-1*step] + lims);

430 q0 = av_clip(q0, src[ 0*step] - lims, src[ 0*step] + lims);

431 }

432

433 p1 = (25*src[-4*step] + 26*src[-3*step] + 26*src[-2*step] + 26*p0 +

434 25*src[ 0*step] + rv40_dither_l[dmode + i]) >> 7;

435 q1 = (25*src[-1*step] + 26*q0 + 26*src[ 1*step] + 26*src[ 2*step] +

436 25*src[ 3*step] + rv40_dither_r[dmode + i]) >> 7;

437

438 if (sflag) {

439 p1 = av_clip(p1, src[-2*step] - lims, src[-2*step] + lims);

440 q1 = av_clip(q1, src[ 1*step] - lims, src[ 1*step] + lims);

441 }

442

443 src[-2*step] = p1;

444 src[-1*step] = p0;

445 src[ 0*step] = q0;

446 src[ 1*step] = q1;

447

448 if(!chroma){

449 src[-3*step] = (25*src[-1*step] + 26*src[-2*step] +

450 51*src[-3*step] + 26*src[-4*step] + 64) >> 7;

451 src[ 2*step] = (25*src[ 0*step] + 26*src[ 1*step] +

452 51*src[ 2*step] + 26*src[ 3*step] + 64) >> 7;

453 }

454 }

455 }

456

457 static void rv40_h_strong_loop_filter(uint8_t *src, const ptrdiff_t stride,

458 const int alpha, const int lims,

459 const int dmode, const int chroma)

460 {

461 rv40_strong_loop_filter(src, stride, 1, alpha, lims, dmode, chroma);

462 }

463

464 static void rv40_v_strong_loop_filter(uint8_t *src, const ptrdiff_t stride,

465 const int alpha, const int lims,

466 const int dmode, const int chroma)

467 {

468 rv40_strong_loop_filter(src, 1, stride, alpha, lims, dmode, chroma);

469 }

470

471 static av_always_inline int rv40_loop_filter_strength(uint8_t *src,

472 int step, ptrdiff_t stride,

473 int beta, int beta2,

474 int edge,

475 int *p1, int *q1)

476 {

477 int sum_p1p0 = 0, sum_q1q0 = 0, sum_p1p2 = 0, sum_q1q2 = 0;

478 int strong0 = 0, strong1 = 0;

479 uint8_t *ptr;

480 int i;

481

482 for (i = 0, ptr = src; i < 4; i++, ptr += stride) {

483 sum_p1p0 += ptr[-2*step] - ptr[-1*step];

484 sum_q1q0 += ptr[ 1*step] - ptr[ 0*step];

485 }

486

487 *p1 = FFABS(sum_p1p0) < (beta << 2);

488 *q1 = FFABS(sum_q1q0) < (beta << 2);

489

490 if(!*p1 && !*q1)

491 return 0;

492

493 if (!edge)

494 return 0;

495

496 for (i = 0, ptr = src; i < 4; i++, ptr += stride) {

497 sum_p1p2 += ptr[-2*step] - ptr[-3*step];

498 sum_q1q2 += ptr[ 1*step] - ptr[ 2*step];

499 }

500

501 strong0 = *p1 && (FFABS(sum_p1p2) < beta2);

502 strong1 = *q1 && (FFABS(sum_q1q2) < beta2);

503

504 return strong0 && strong1;

505 }

506

507 static int rv40_h_loop_filter_strength(uint8_t *src, ptrdiff_t stride,

508 int beta, int beta2, int edge,

509 int *p1, int *q1)

510 {

511 return rv40_loop_filter_strength(src, stride, 1, beta, beta2, edge, p1, q1);

512 }

513

514 static int rv40_v_loop_filter_strength(uint8_t *src, ptrdiff_t stride,

515 int beta, int beta2, int edge,

516 int *p1, int *q1)

517 {

518 return rv40_loop_filter_strength(src, 1, stride, beta, beta2, edge, p1, q1);

519 }

520

521 av_cold void ff_rv40dsp_init(RV34DSPContext *c, DSPContext* dsp) {

522

523 ff_rv34dsp_init(c, dsp);

524

525 c->put_pixels_tab[0][ 0] = dsp->put_h264_qpel_pixels_tab[0][0];

526 c->put_pixels_tab[0][ 1] = put_rv40_qpel16_mc10_c;

527 c->put_pixels_tab[0][ 2] = dsp->put_h264_qpel_pixels_tab[0][2];

528 c->put_pixels_tab[0][ 3] = put_rv40_qpel16_mc30_c;

529 c->put_pixels_tab[0][ 4] = put_rv40_qpel16_mc01_c;

530 c->put_pixels_tab[0][ 5] = put_rv40_qpel16_mc11_c;

531 c->put_pixels_tab[0][ 6] = put_rv40_qpel16_mc21_c;

532 c->put_pixels_tab[0][ 7] = put_rv40_qpel16_mc31_c;

533 c->put_pixels_tab[0][ 8] = dsp->put_h264_qpel_pixels_tab[0][8];

534 c->put_pixels_tab[0][ 9] = put_rv40_qpel16_mc12_c;

535 c->put_pixels_tab[0][10] = put_rv40_qpel16_mc22_c;

536 c->put_pixels_tab[0][11] = put_rv40_qpel16_mc32_c;

537 c->put_pixels_tab[0][12] = put_rv40_qpel16_mc03_c;

538 c->put_pixels_tab[0][13] = put_rv40_qpel16_mc13_c;

539 c->put_pixels_tab[0][14] = put_rv40_qpel16_mc23_c;

540 c->put_pixels_tab[0][15] = ff_put_rv40_qpel16_mc33_c;

541 c->avg_pixels_tab[0][ 0] = dsp->avg_h264_qpel_pixels_tab[0][0];

542 c->avg_pixels_tab[0][ 1] = avg_rv40_qpel16_mc10_c;

543 c->avg_pixels_tab[0][ 2] = dsp->avg_h264_qpel_pixels_tab[0][2];

544 c->avg_pixels_tab[0][ 3] = avg_rv40_qpel16_mc30_c;

545 c->avg_pixels_tab[0][ 4] = avg_rv40_qpel16_mc01_c;

546 c->avg_pixels_tab[0][ 5] = avg_rv40_qpel16_mc11_c;

547 c->avg_pixels_tab[0][ 6] = avg_rv40_qpel16_mc21_c;

548 c->avg_pixels_tab[0][ 7] = avg_rv40_qpel16_mc31_c;

549 c->avg_pixels_tab[0][ 8] = dsp->avg_h264_qpel_pixels_tab[0][8];

550 c->avg_pixels_tab[0][ 9] = avg_rv40_qpel16_mc12_c;

551 c->avg_pixels_tab[0][10] = avg_rv40_qpel16_mc22_c;

552 c->avg_pixels_tab[0][11] = avg_rv40_qpel16_mc32_c;

553 c->avg_pixels_tab[0][12] = avg_rv40_qpel16_mc03_c;

554 c->avg_pixels_tab[0][13] = avg_rv40_qpel16_mc13_c;

555 c->avg_pixels_tab[0][14] = avg_rv40_qpel16_mc23_c;

556 c->avg_pixels_tab[0][15] = ff_avg_rv40_qpel16_mc33_c;

557 c->put_pixels_tab[1][ 0] = dsp->put_h264_qpel_pixels_tab[1][0];

558 c->put_pixels_tab[1][ 1] = put_rv40_qpel8_mc10_c;

559 c->put_pixels_tab[1][ 2] = dsp->put_h264_qpel_pixels_tab[1][2];

560 c->put_pixels_tab[1][ 3] = put_rv40_qpel8_mc30_c;

561 c->put_pixels_tab[1][ 4] = put_rv40_qpel8_mc01_c;

562 c->put_pixels_tab[1][ 5] = put_rv40_qpel8_mc11_c;

563 c->put_pixels_tab[1][ 6] = put_rv40_qpel8_mc21_c;

564 c->put_pixels_tab[1][ 7] = put_rv40_qpel8_mc31_c;

565 c->put_pixels_tab[1][ 8] = dsp->put_h264_qpel_pixels_tab[1][8];

566 c->put_pixels_tab[1][ 9] = put_rv40_qpel8_mc12_c;

567 c->put_pixels_tab[1][10] = put_rv40_qpel8_mc22_c;

568 c->put_pixels_tab[1][11] = put_rv40_qpel8_mc32_c;

569 c->put_pixels_tab[1][12] = put_rv40_qpel8_mc03_c;

570 c->put_pixels_tab[1][13] = put_rv40_qpel8_mc13_c;

571 c->put_pixels_tab[1][14] = put_rv40_qpel8_mc23_c;

572 c->put_pixels_tab[1][15] = ff_put_rv40_qpel8_mc33_c;

573 c->avg_pixels_tab[1][ 0] = dsp->avg_h264_qpel_pixels_tab[1][0];

574 c->avg_pixels_tab[1][ 1] = avg_rv40_qpel8_mc10_c;

575 c->avg_pixels_tab[1][ 2] = dsp->avg_h264_qpel_pixels_tab[1][2];

576 c->avg_pixels_tab[1][ 3] = avg_rv40_qpel8_mc30_c;

577 c->avg_pixels_tab[1][ 4] = avg_rv40_qpel8_mc01_c;

578 c->avg_pixels_tab[1][ 5] = avg_rv40_qpel8_mc11_c;

579 c->avg_pixels_tab[1][ 6] = avg_rv40_qpel8_mc21_c;

580 c->avg_pixels_tab[1][ 7] = avg_rv40_qpel8_mc31_c;

581 c->avg_pixels_tab[1][ 8] = dsp->avg_h264_qpel_pixels_tab[1][8];

582 c->avg_pixels_tab[1][ 9] = avg_rv40_qpel8_mc12_c;

583 c->avg_pixels_tab[1][10] = avg_rv40_qpel8_mc22_c;

584 c->avg_pixels_tab[1][11] = avg_rv40_qpel8_mc32_c;

585 c->avg_pixels_tab[1][12] = avg_rv40_qpel8_mc03_c;

586 c->avg_pixels_tab[1][13] = avg_rv40_qpel8_mc13_c;

587 c->avg_pixels_tab[1][14] = avg_rv40_qpel8_mc23_c;

588 c->avg_pixels_tab[1][15] = ff_avg_rv40_qpel8_mc33_c;

589

590 c->put_chroma_pixels_tab[0] = put_rv40_chroma_mc8_c;

591 c->put_chroma_pixels_tab[1] = put_rv40_chroma_mc4_c;

592 c->avg_chroma_pixels_tab[0] = avg_rv40_chroma_mc8_c;

593 c->avg_chroma_pixels_tab[1] = avg_rv40_chroma_mc4_c;

594

595 c->rv40_weight_pixels_tab[0][0] = rv40_weight_func_rnd_16;

596 c->rv40_weight_pixels_tab[0][1] = rv40_weight_func_rnd_8;

597 c->rv40_weight_pixels_tab[1][0] = rv40_weight_func_nornd_16;

598 c->rv40_weight_pixels_tab[1][1] = rv40_weight_func_nornd_8;

599

600 c->rv40_weak_loop_filter[0] = rv40_h_weak_loop_filter;

601 c->rv40_weak_loop_filter[1] = rv40_v_weak_loop_filter;

602 c->rv40_strong_loop_filter[0] = rv40_h_strong_loop_filter;

603 c->rv40_strong_loop_filter[1] = rv40_v_strong_loop_filter;

604 c->rv40_loop_filter_strength[0] = rv40_h_loop_filter_strength;

605 c->rv40_loop_filter_strength[1] = rv40_v_loop_filter_strength;

606

607 if (ARCH_X86)

608 ff_rv40dsp_init_x86(c, dsp);

609 if (ARCH_ARM)

610 ff_rv40dsp_init_arm(c, dsp);

611 }

Generated on Sat May 25 2013 03:58:40 for FFmpeg by doxygen 1.8.2