FFmpeg: libswscale/ppc/swscale_altivec.c Source File

FFmpeg

[フレーム]

swscale_altivec.c

Go to the documentation of this file.

1 /*

2 * AltiVec-enhanced yuv2yuvX

3 *

5 * based on the equivalent C code in swscale.c

6 *

7 * This file is part of FFmpeg.

8 *

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

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

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

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

13 *

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

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

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

17 * Lesser General Public License for more details.

18 *

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

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

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

22 */

24 #include <inttypes.h>

26 #include "config.h"

27 #include "libswscale/swscale.h"

28 #include "libswscale/swscale_internal.h"

29 #include "libavutil/attributes.h"

30 #include "libavutil/cpu.h"

31 #include "yuv2rgb_altivec.h"

33 #define vzero vec_splat_s32(0)

35 #define yuv2planeX_8(d1, d2, l1, src, x, perm, filter) do { \

36 vector signed short l2 = vec_ld(((x) << 1) + 16, src); \

37 vector signed short ls = vec_perm(l1, l2, perm); \

38 vector signed int i1 = vec_mule(filter, ls); \

39 vector signed int i2 = vec_mulo(filter, ls); \

40 vector signed int vf1 = vec_mergeh(i1, i2); \

41 vector signed int vf2 = vec_mergel(i1, i2); \

42 d1 = vec_add(d1, vf1); \

43 d2 = vec_add(d2, vf2); \

44 l1 = l2; \

45 } while (0)

47 static void yuv2planeX_16_altivec(const int16_t *filter, int filterSize,

48 const int16_t **src, uint8_t *dest,

49 const uint8_t *dither, int offset, int x)

50 {

51 register int i, j;

52 DECLARE_ALIGNED(16, int, val)[16];

53 vector signed int vo1, vo2, vo3, vo4;

54 vector unsigned short vs1, vs2;

55 vector unsigned char vf;

56 vector unsigned int altivec_vectorShiftInt19 =

57 vec_add(vec_splat_u32(10), vec_splat_u32(9));

59 for (i = 0; i < 16; i++)

60 val[i] = dither[(x + i + offset) & 7] << 12;

62 vo1 = vec_ld(0, val);

63 vo2 = vec_ld(16, val);

64 vo3 = vec_ld(32, val);

65 vo4 = vec_ld(48, val);

67 for (j = 0; j < filterSize; j++) {

68 vector signed short l1, vLumFilter = vec_ld(j << 1, filter);

69 vector unsigned char perm, perm0 = vec_lvsl(j << 1, filter);

70 vLumFilter = vec_perm(vLumFilter, vLumFilter, perm0);

71 vLumFilter = vec_splat(vLumFilter, 0); // lumFilter[j] is loaded 8 times in vLumFilter

73 perm = vec_lvsl(x << 1, src[j]);

74 l1 = vec_ld(x << 1, src[j]);

76 yuv2planeX_8(vo1, vo2, l1, src[j], x, perm, vLumFilter);

77 yuv2planeX_8(vo3, vo4, l1, src[j], x + 8, perm, vLumFilter);

78 }

80 vo1 = vec_sra(vo1, altivec_vectorShiftInt19);

81 vo2 = vec_sra(vo2, altivec_vectorShiftInt19);

82 vo3 = vec_sra(vo3, altivec_vectorShiftInt19);

83 vo4 = vec_sra(vo4, altivec_vectorShiftInt19);

84 vs1 = vec_packsu(vo1, vo2);

85 vs2 = vec_packsu(vo3, vo4);

86 vf = vec_packsu(vs1, vs2);

87 vec_st(vf, 0, dest);

88 }

90 static inline void yuv2planeX_u(const int16_t *filter, int filterSize,

91 const int16_t **src, uint8_t *dest, int dstW,

92 const uint8_t *dither, int offset, int x)

93 {

94 int i, j;

96 for (i = x; i < dstW; i++) {

97 int t = dither[(i + offset) & 7] << 12;

98 for (j = 0; j < filterSize; j++)

99 t += src[j][i] * filter[j];

100 dest[i] = av_clip_uint8(t >> 19);

101 }

102 }

103

104 static void yuv2planeX_altivec(const int16_t *filter, int filterSize,

105 const int16_t **src, uint8_t *dest, int dstW,

106 const uint8_t *dither, int offset)

107 {

108 int dst_u = -(uintptr_t)dest & 15;

109 int i;

110

111 yuv2planeX_u(filter, filterSize, src, dest, dst_u, dither, offset, 0);

112

113 for (i = dst_u; i < dstW - 15; i += 16)

114 yuv2planeX_16_altivec(filter, filterSize, src, dest + i, dither,

115 offset, i);

116

117 yuv2planeX_u(filter, filterSize, src, dest, dstW, dither, offset, i);

118 }

119

120 static void hScale_altivec_real(SwsContext *c, int16_t *dst, int dstW,

121 const uint8_t *src, const int16_t *filter,

122 const int32_t *filterPos, int filterSize)

123 {

124 register int i;

125 DECLARE_ALIGNED(16, int, tempo)[4];

126

127 if (filterSize % 4) {

128 for (i = 0; i < dstW; i++) {

129 register int j;

130 register int srcPos = filterPos[i];

131 register int val = 0;

132 for (j = 0; j < filterSize; j++)

133 val += ((int)src[srcPos + j]) * filter[filterSize * i + j];

134 dst[i] = FFMIN(val >> 7, (1 << 15) - 1);

135 }

136 } else

137 switch (filterSize) {

138 case 4:

139 for (i = 0; i < dstW; i++) {

140 register int srcPos = filterPos[i];

141

142 vector unsigned char src_v0 = vec_ld(srcPos, src);

143 vector unsigned char src_v1, src_vF;

144 vector signed short src_v, filter_v;

145 vector signed int val_vEven, val_s;

146 if ((((uintptr_t)src + srcPos) % 16) > 12) {

147 src_v1 = vec_ld(srcPos + 16, src);

148 }

149 src_vF = vec_perm(src_v0, src_v1, vec_lvsl(srcPos, src));

150

151 src_v = // vec_unpackh sign-extends...

152 (vector signed short)(vec_mergeh((vector unsigned char)vzero, src_vF));

153 // now put our elements in the even slots

154 src_v = vec_mergeh(src_v, (vector signed short)vzero);

155

156 filter_v = vec_ld(i << 3, filter);

157 // The 3 above is 2 (filterSize == 4) + 1 (sizeof(short) == 2).

158

159 // The neat trick: We only care for half the elements,

160 // high or low depending on (i<<3)%16 (it's 0 or 8 here),

161 // and we're going to use vec_mule, so we choose

162 // carefully how to "unpack" the elements into the even slots.

163 if ((i << 3) % 16)

164 filter_v = vec_mergel(filter_v, (vector signed short)vzero);

165 else

166 filter_v = vec_mergeh(filter_v, (vector signed short)vzero);

167

168 val_vEven = vec_mule(src_v, filter_v);

169 val_s = vec_sums(val_vEven, vzero);

170 vec_st(val_s, 0, tempo);

171 dst[i] = FFMIN(tempo[3] >> 7, (1 << 15) - 1);

172 }

173 break;

174

175 case 8:

176 for (i = 0; i < dstW; i++) {

177 register int srcPos = filterPos[i];

178

179 vector unsigned char src_v0 = vec_ld(srcPos, src);

180 vector unsigned char src_v1, src_vF;

181 vector signed short src_v, filter_v;

182 vector signed int val_v, val_s;

183 if ((((uintptr_t)src + srcPos) % 16) > 8) {

184 src_v1 = vec_ld(srcPos + 16, src);

185 }

186 src_vF = vec_perm(src_v0, src_v1, vec_lvsl(srcPos, src));

187

188 src_v = // vec_unpackh sign-extends...

189 (vector signed short)(vec_mergeh((vector unsigned char)vzero, src_vF));

190 filter_v = vec_ld(i << 4, filter);

191 // the 4 above is 3 (filterSize == 8) + 1 (sizeof(short) == 2)

192

193 val_v = vec_msums(src_v, filter_v, (vector signed int)vzero);

194 val_s = vec_sums(val_v, vzero);

195 vec_st(val_s, 0, tempo);

196 dst[i] = FFMIN(tempo[3] >> 7, (1 << 15) - 1);

197 }

198 break;

199

200 case 16:

201 for (i = 0; i < dstW; i++) {

202 register int srcPos = filterPos[i];

203

204 vector unsigned char src_v0 = vec_ld(srcPos, src);

205 vector unsigned char src_v1 = vec_ld(srcPos + 16, src);

206 vector unsigned char src_vF = vec_perm(src_v0, src_v1, vec_lvsl(srcPos, src));

207

208 vector signed short src_vA = // vec_unpackh sign-extends...

209 (vector signed short)(vec_mergeh((vector unsigned char)vzero, src_vF));

210 vector signed short src_vB = // vec_unpackh sign-extends...

211 (vector signed short)(vec_mergel((vector unsigned char)vzero, src_vF));

212

213 vector signed short filter_v0 = vec_ld(i << 5, filter);

214 vector signed short filter_v1 = vec_ld((i << 5) + 16, filter);

215 // the 5 above are 4 (filterSize == 16) + 1 (sizeof(short) == 2)

216

217 vector signed int val_acc = vec_msums(src_vA, filter_v0, (vector signed int)vzero);

218 vector signed int val_v = vec_msums(src_vB, filter_v1, val_acc);

219

220 vector signed int val_s = vec_sums(val_v, vzero);

221

222 vec_st(val_s, 0, tempo);

223 dst[i] = FFMIN(tempo[3] >> 7, (1 << 15) - 1);

224 }

225 break;

226

227 default:

228 for (i = 0; i < dstW; i++) {

229 register int j;

230 register int srcPos = filterPos[i];

231

232 vector signed int val_s, val_v = (vector signed int)vzero;

233 vector signed short filter_v0R = vec_ld(i * 2 * filterSize, filter);

234 vector unsigned char permF = vec_lvsl((i * 2 * filterSize), filter);

235

236 vector unsigned char src_v0 = vec_ld(srcPos, src);

237 vector unsigned char permS = vec_lvsl(srcPos, src);

238

239 for (j = 0; j < filterSize - 15; j += 16) {

240 vector unsigned char src_v1 = vec_ld(srcPos + j + 16, src);

241 vector unsigned char src_vF = vec_perm(src_v0, src_v1, permS);

242

243 vector signed short src_vA = // vec_unpackh sign-extends...

244 (vector signed short)(vec_mergeh((vector unsigned char)vzero, src_vF));

245 vector signed short src_vB = // vec_unpackh sign-extends...

246 (vector signed short)(vec_mergel((vector unsigned char)vzero, src_vF));

247

248 vector signed short filter_v1R = vec_ld((i * 2 * filterSize) + (j * 2) + 16, filter);

249 vector signed short filter_v2R = vec_ld((i * 2 * filterSize) + (j * 2) + 32, filter);

250 vector signed short filter_v0 = vec_perm(filter_v0R, filter_v1R, permF);

251 vector signed short filter_v1 = vec_perm(filter_v1R, filter_v2R, permF);

252

253 vector signed int val_acc = vec_msums(src_vA, filter_v0, val_v);

254 val_v = vec_msums(src_vB, filter_v1, val_acc);

255

256 filter_v0R = filter_v2R;

257 src_v0 = src_v1;

258 }

259

260 if (j < filterSize - 7) {

261 // loading src_v0 is useless, it's already done above

262 // vector unsigned char src_v0 = vec_ld(srcPos + j, src);

263 vector unsigned char src_v1, src_vF;

264 vector signed short src_v, filter_v1R, filter_v;

265 if ((((uintptr_t)src + srcPos) % 16) > 8) {

266 src_v1 = vec_ld(srcPos + j + 16, src);

267 }

268 src_vF = vec_perm(src_v0, src_v1, permS);

269

270 src_v = // vec_unpackh sign-extends...

271 (vector signed short)(vec_mergeh((vector unsigned char)vzero, src_vF));

272 // loading filter_v0R is useless, it's already done above

273 // vector signed short filter_v0R = vec_ld((i * 2 * filterSize) + j, filter);

274 filter_v1R = vec_ld((i * 2 * filterSize) + (j * 2) + 16, filter);

275 filter_v = vec_perm(filter_v0R, filter_v1R, permF);

276

277 val_v = vec_msums(src_v, filter_v, val_v);

278 }

279

280 val_s = vec_sums(val_v, vzero);

281

282 vec_st(val_s, 0, tempo);

283 dst[i] = FFMIN(tempo[3] >> 7, (1 << 15) - 1);

284 }

285 }

286 }

287

288 av_cold void ff_sws_init_swScale_altivec(SwsContext *c)

289 {

290 enum AVPixelFormat dstFormat = c->dstFormat;

291

292 if (!(av_get_cpu_flags() & AV_CPU_FLAG_ALTIVEC))

293 return;

294

295 if (c->srcBpc == 8 && c->dstBpc <= 14) {

296 c->hyScale = c->hcScale = hScale_altivec_real;

297 }

298 if (!is16BPS(dstFormat) && !is9_OR_10BPS(dstFormat) &&

299 dstFormat != AV_PIX_FMT_NV12 && dstFormat != AV_PIX_FMT_NV21 &&

300 !c->alpPixBuf) {

301 c->yuv2planeX = yuv2planeX_altivec;

302 }

303

304 /* The following list of supported dstFormat values should

305 * match what's found in the body of ff_yuv2packedX_altivec() */

306 if (!(c->flags & (SWS_BITEXACT | SWS_FULL_CHR_H_INT)) && !c->alpPixBuf) {

307 switch (c->dstFormat) {

308 case AV_PIX_FMT_ABGR:

309 c->yuv2packedX = ff_yuv2abgr_X_altivec;

310 break;

311 case AV_PIX_FMT_BGRA:

312 c->yuv2packedX = ff_yuv2bgra_X_altivec;

313 break;

314 case AV_PIX_FMT_ARGB:

315 c->yuv2packedX = ff_yuv2argb_X_altivec;

316 break;

317 case AV_PIX_FMT_RGBA:

318 c->yuv2packedX = ff_yuv2rgba_X_altivec;

319 break;

320 case AV_PIX_FMT_BGR24:

321 c->yuv2packedX = ff_yuv2bgr24_X_altivec;

322 break;

323 case AV_PIX_FMT_RGB24:

324 c->yuv2packedX = ff_yuv2rgb24_X_altivec;

325 break;

326 }

327 }

328 }

Generated on Sat May 25 2013 04:01:21 for FFmpeg by doxygen 1.8.2