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 "h264qpel.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 const 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 const 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, ptrdiff_t stride)\

108 {\

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

110 }\

111 \

112 static void OPNAME ## rv40_qpel ## SIZE ## _mc30_c(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\

113 {\

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

115 }\

116 \

117 static void OPNAME ## rv40_qpel ## SIZE ## _mc01_c(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\

118 {\

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

120 }\

121 \

122 static void OPNAME ## rv40_qpel ## SIZE ## _mc11_c(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\

123 {\

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

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

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

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

128 }\

129 \

130 static void OPNAME ## rv40_qpel ## SIZE ## _mc21_c(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\

131 {\

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

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

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

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

136 }\

137 \

138 static void OPNAME ## rv40_qpel ## SIZE ## _mc31_c(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\

139 {\

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

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

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

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

144 }\

145 \

146 static void OPNAME ## rv40_qpel ## SIZE ## _mc12_c(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\

147 {\

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, 52, 20, 6);\

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 ## _mc22_c(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\

155 {\

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

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

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

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

160 }\

161 \

162 static void OPNAME ## rv40_qpel ## SIZE ## _mc32_c(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\

163 {\

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

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

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

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

168 }\

169 \

170 static void OPNAME ## rv40_qpel ## SIZE ## _mc03_c(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\

171 {\

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

173 }\

174 \

175 static void OPNAME ## rv40_qpel ## SIZE ## _mc13_c(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\

176 {\

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

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

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

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

181 }\

182 \

183 static void OPNAME ## rv40_qpel ## SIZE ## _mc23_c(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\

184 {\

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

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

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

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

189 }\

190 \

191

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

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

194

195 RV40_LOWPASS(put_ , op_put)

196 RV40_LOWPASS(avg_ , op_avg)

197

198 #undef op_avg

199 #undef op_put

200

201 RV40_MC(put_, 8)

202 RV40_MC(put_, 16)

203 RV40_MC(avg_, 8)

204 RV40_MC(avg_, 16)

205

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

207 { 0, 16, 32, 16 },

208 { 32, 28, 32, 28 },

209 { 0, 32, 16, 32 },

210 { 32, 28, 32, 28 }

211 };

212

213 #define RV40_CHROMA_MC(OPNAME, OP)\

214 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){\

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

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

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

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

219 int i;\

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

221 \

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

223 \

224 if(D){\

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

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

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

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

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

230 dst += stride;\

231 src += stride;\

232 }\

233 }else{\

234 const int E = B + C;\

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

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

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

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

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

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

241 dst += stride;\

242 src += stride;\

243 }\

244 }\

245 }\

246 \

247 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){\

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

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

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

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

252 int i;\

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

254 \

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

256 \

257 if(D){\

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

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

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

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

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

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

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

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

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

267 dst += stride;\

268 src += stride;\

269 }\

270 }else{\

271 const int E = B + C;\

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

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

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

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

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

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

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

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

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

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

282 dst += stride;\

283 src += stride;\

284 }\

285 }\

286 }

287

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

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

290

291 RV40_CHROMA_MC(put_, op_put)

292 RV40_CHROMA_MC(avg_, op_avg)

293

294 #define RV40_WEIGHT_FUNC(size) \

295 static void rv40_weight_func_rnd_ ## 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]) >> 9) + ((w1 * src2[i]) >> 9) + 0x10) >> 5;\

302 src1 += stride;\

303 src2 += stride;\

304 dst += stride;\

305 }\

306 }\

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

308 {\

309 int i, j;\

310 \

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

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

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

314 src1 += stride;\

315 src2 += stride;\

316 dst += stride;\

317 }\

318 }

319

320 RV40_WEIGHT_FUNC(16)

321 RV40_WEIGHT_FUNC(8)

322

323 /**

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

325 */

326 static const uint8_t rv40_dither_l[16] = {

327 0x40, 0x50, 0x20, 0x60, 0x30, 0x50, 0x40, 0x30,

328 0x50, 0x40, 0x50, 0x30, 0x60, 0x20, 0x50, 0x40

329 };

330

331 /**

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

333 */

334 static const uint8_t rv40_dither_r[16] = {

335 0x40, 0x30, 0x60, 0x20, 0x50, 0x30, 0x30, 0x40,

336 0x40, 0x40, 0x50, 0x30, 0x20, 0x60, 0x30, 0x40

337 };

338

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

340 /**

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

342 */

343 static av_always_inline void rv40_weak_loop_filter(uint8_t *src,

344 const int step,

345 const ptrdiff_t stride,

346 const int filter_p1,

347 const int filter_q1,

348 const int alpha,

349 const int beta,

350 const int lim_p0q0,

351 const int lim_q1,

352 const int lim_p1)

353 {

354 const uint8_t *cm = ff_cropTbl + MAX_NEG_CROP;

355 int i, t, u, diff;

356

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

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

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

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

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

362

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

364 if (!t)

365 continue;

366

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

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

369 continue;

370

371 t <<= 2;

372 if (filter_p1 && filter_q1)

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

374

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

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

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

378

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

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

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

382 }

383

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

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

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

387 }

388 }

389 }

390

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

392 const int filter_p1, const int filter_q1,

393 const int alpha, const int beta,

394 const int lim_p0q0, const int lim_q1,

395 const int lim_p1)

396 {

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

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

399 }

400

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

402 const int filter_p1, const int filter_q1,

403 const int alpha, const int beta,

404 const int lim_p0q0, const int lim_q1,

405 const int lim_p1)

406 {

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

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

409 }

410

411 static av_always_inline void rv40_strong_loop_filter(uint8_t *src,

412 const int step,

413 const ptrdiff_t stride,

414 const int alpha,

415 const int lims,

416 const int dmode,

417 const int chroma)

418 {

419 int i;

420

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

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

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

424

425 if (!t)

426 continue;

427

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

429 if (sflag > 1)

430 continue;

431

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

433 26*src[ 0*step] + 25*src[ 1*step] +

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

435

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

437 26*src[ 1*step] + 25*src[ 2*step] +

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

439

440 if (sflag) {

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

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

443 }

444

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

446 25*src[ 0*step] + rv40_dither_l[dmode + i]) >> 7;

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

448 25*src[ 3*step] + rv40_dither_r[dmode + i]) >> 7;

449

450 if (sflag) {

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

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

453 }

454

455 src[-2*step] = p1;

456 src[-1*step] = p0;

457 src[ 0*step] = q0;

458 src[ 1*step] = q1;

459

460 if(!chroma){

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

462 51*src[-3*step] + 26*src[-4*step] + 64) >> 7;

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

464 51*src[ 2*step] + 26*src[ 3*step] + 64) >> 7;

465 }

466 }

467 }

468

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

470 const int alpha, const int lims,

471 const int dmode, const int chroma)

472 {

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

474 }

475

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

477 const int alpha, const int lims,

478 const int dmode, const int chroma)

479 {

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

481 }

482

483 static av_always_inline int rv40_loop_filter_strength(uint8_t *src,

484 int step, ptrdiff_t stride,

485 int beta, int beta2,

486 int edge,

487 int *p1, int *q1)

488 {

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

490 int strong0 = 0, strong1 = 0;

491 uint8_t *ptr;

492 int i;

493

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

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

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

497 }

498

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

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

501

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

503 return 0;

504

505 if (!edge)

506 return 0;

507

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

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

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

511 }

512

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

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

515

516 return strong0 && strong1;

517 }

518

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

520 int beta, int beta2, int edge,

521 int *p1, int *q1)

522 {

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

524 }

525

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

527 int beta, int beta2, int edge,

528 int *p1, int *q1)

529 {

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

531 }

532

533 av_cold void ff_rv40dsp_init(RV34DSPContext *c)

534 {

535 H264QpelContext qpel;

536

537 ff_rv34dsp_init(c);

538 ff_h264qpel_init(&qpel, 8);

539

540 c->put_pixels_tab[0][ 0] = qpel.put_h264_qpel_pixels_tab[0][0];

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

542 c->put_pixels_tab[0][ 2] = qpel.put_h264_qpel_pixels_tab[0][2];

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

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

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

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

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

548 c->put_pixels_tab[0][ 8] = qpel.put_h264_qpel_pixels_tab[0][8];

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

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

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

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

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

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

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

556 c->avg_pixels_tab[0][ 0] = qpel.avg_h264_qpel_pixels_tab[0][0];

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

558 c->avg_pixels_tab[0][ 2] = qpel.avg_h264_qpel_pixels_tab[0][2];

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

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

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

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

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

564 c->avg_pixels_tab[0][ 8] = qpel.avg_h264_qpel_pixels_tab[0][8];

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

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

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

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

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

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

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

572 c->put_pixels_tab[1][ 0] = qpel.put_h264_qpel_pixels_tab[1][0];

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

574 c->put_pixels_tab[1][ 2] = qpel.put_h264_qpel_pixels_tab[1][2];

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

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

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

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

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

580 c->put_pixels_tab[1][ 8] = qpel.put_h264_qpel_pixels_tab[1][8];

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

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

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

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

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

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

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

588 c->avg_pixels_tab[1][ 0] = qpel.avg_h264_qpel_pixels_tab[1][0];

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

590 c->avg_pixels_tab[1][ 2] = qpel.avg_h264_qpel_pixels_tab[1][2];

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

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

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

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

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

596 c->avg_pixels_tab[1][ 8] = qpel.avg_h264_qpel_pixels_tab[1][8];

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

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

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

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

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

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

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

604

605 c->put_chroma_pixels_tab[0] = put_rv40_chroma_mc8_c;

606 c->put_chroma_pixels_tab[1] = put_rv40_chroma_mc4_c;

607 c->avg_chroma_pixels_tab[0] = avg_rv40_chroma_mc8_c;

608 c->avg_chroma_pixels_tab[1] = avg_rv40_chroma_mc4_c;

609

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

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

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

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

614

615 c->rv40_weak_loop_filter[0] = rv40_h_weak_loop_filter;

616 c->rv40_weak_loop_filter[1] = rv40_v_weak_loop_filter;

617 c->rv40_strong_loop_filter[0] = rv40_h_strong_loop_filter;

618 c->rv40_strong_loop_filter[1] = rv40_v_strong_loop_filter;

619 c->rv40_loop_filter_strength[0] = rv40_h_loop_filter_strength;

620 c->rv40_loop_filter_strength[1] = rv40_v_loop_filter_strength;

621

622 if (ARCH_ARM)

623 ff_rv40dsp_init_arm(c);

624 if (ARCH_X86)

625 ff_rv40dsp_init_x86(c);

626 }

Generated on Sat Jan 25 2014 19:51:54 for FFmpeg by doxygen 1.8.2