1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
|
/*
* software RGB to RGB converter
* pluralize by software PAL8 to RGB converter
* software YUV to YUV converter
* software YUV to RGB converter
* Written by Nick Kurshev.
* palette & YUV & runtime CPU stuff by Michael (michaelni@gmx.at)
*
* This file is part of Libav.
*
* Libav is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* Libav is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with Libav; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include <inttypes.h>
#include "config.h"
#include "libavutil/x86_cpu.h"
#include "libavutil/bswap.h"
#include "rgb2rgb.h"
#include "swscale.h"
#include "swscale_internal.h"
void (*rgb24tobgr32)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb24tobgr16)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb24tobgr15)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb32tobgr24)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb32to16)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb32to15)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb15to16)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb15tobgr24)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb15to32)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb16to15)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb16tobgr24)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb16to32)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb24tobgr24)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb24to16)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb24to15)(const uint8_t *src, uint8_t *dst, long src_size);
void (*shuffle_bytes_2103)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb32tobgr16)(const uint8_t *src, uint8_t *dst, long src_size);
void (*rgb32tobgr15)(const uint8_t *src, uint8_t *dst, long src_size);
void (*yv12toyuy2)(const uint8_t *ysrc, const uint8_t *usrc, const uint8_t *vsrc, uint8_t *dst,
long width, long height,
long lumStride, long chromStride, long dstStride);
void (*yv12touyvy)(const uint8_t *ysrc, const uint8_t *usrc, const uint8_t *vsrc, uint8_t *dst,
long width, long height,
long lumStride, long chromStride, long dstStride);
void (*yuv422ptoyuy2)(const uint8_t *ysrc, const uint8_t *usrc, const uint8_t *vsrc, uint8_t *dst,
long width, long height,
long lumStride, long chromStride, long dstStride);
void (*yuv422ptouyvy)(const uint8_t *ysrc, const uint8_t *usrc, const uint8_t *vsrc, uint8_t *dst,
long width, long height,
long lumStride, long chromStride, long dstStride);
void (*yuy2toyv12)(const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
long width, long height,
long lumStride, long chromStride, long srcStride);
void (*rgb24toyv12)(const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
long width, long height,
long lumStride, long chromStride, long srcStride);
void (*planar2x)(const uint8_t *src, uint8_t *dst, long width, long height,
long srcStride, long dstStride);
void (*interleaveBytes)(const uint8_t *src1, const uint8_t *src2, uint8_t *dst,
long width, long height, long src1Stride,
long src2Stride, long dstStride);
void (*vu9_to_vu12)(const uint8_t *src1, const uint8_t *src2,
uint8_t *dst1, uint8_t *dst2,
long width, long height,
long srcStride1, long srcStride2,
long dstStride1, long dstStride2);
void (*yvu9_to_yuy2)(const uint8_t *src1, const uint8_t *src2, const uint8_t *src3,
uint8_t *dst,
long width, long height,
long srcStride1, long srcStride2,
long srcStride3, long dstStride);
void (*uyvytoyuv420)(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, const uint8_t *src,
long width, long height,
long lumStride, long chromStride, long srcStride);
void (*uyvytoyuv422)(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, const uint8_t *src,
long width, long height,
long lumStride, long chromStride, long srcStride);
void (*yuyvtoyuv420)(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, const uint8_t *src,
long width, long height,
long lumStride, long chromStride, long srcStride);
void (*yuyvtoyuv422)(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, const uint8_t *src,
long width, long height,
long lumStride, long chromStride, long srcStride);
#if ARCH_X86
DECLARE_ASM_CONST(8, uint64_t, mmx_ff) = 0x00000000000000FFULL;
DECLARE_ASM_CONST(8, uint64_t, mmx_null) = 0x0000000000000000ULL;
DECLARE_ASM_CONST(8, uint64_t, mmx_one) = 0xFFFFFFFFFFFFFFFFULL;
DECLARE_ASM_CONST(8, uint64_t, mask32b) = 0x000000FF000000FFULL;
DECLARE_ASM_CONST(8, uint64_t, mask32g) = 0x0000FF000000FF00ULL;
DECLARE_ASM_CONST(8, uint64_t, mask32r) = 0x00FF000000FF0000ULL;
DECLARE_ASM_CONST(8, uint64_t, mask32a) = 0xFF000000FF000000ULL;
DECLARE_ASM_CONST(8, uint64_t, mask32) = 0x00FFFFFF00FFFFFFULL;
DECLARE_ASM_CONST(8, uint64_t, mask3216br) = 0x00F800F800F800F8ULL;
DECLARE_ASM_CONST(8, uint64_t, mask3216g) = 0x0000FC000000FC00ULL;
DECLARE_ASM_CONST(8, uint64_t, mask3215g) = 0x0000F8000000F800ULL;
DECLARE_ASM_CONST(8, uint64_t, mul3216) = 0x2000000420000004ULL;
DECLARE_ASM_CONST(8, uint64_t, mul3215) = 0x2000000820000008ULL;
DECLARE_ASM_CONST(8, uint64_t, mask24b) = 0x00FF0000FF0000FFULL;
DECLARE_ASM_CONST(8, uint64_t, mask24g) = 0xFF0000FF0000FF00ULL;
DECLARE_ASM_CONST(8, uint64_t, mask24r) = 0x0000FF0000FF0000ULL;
DECLARE_ASM_CONST(8, uint64_t, mask24l) = 0x0000000000FFFFFFULL;
DECLARE_ASM_CONST(8, uint64_t, mask24h) = 0x0000FFFFFF000000ULL;
DECLARE_ASM_CONST(8, uint64_t, mask24hh) = 0xffff000000000000ULL;
DECLARE_ASM_CONST(8, uint64_t, mask24hhh) = 0xffffffff00000000ULL;
DECLARE_ASM_CONST(8, uint64_t, mask24hhhh) = 0xffffffffffff0000ULL;
DECLARE_ASM_CONST(8, uint64_t, mask15b) = 0x001F001F001F001FULL; /* 00000000 00011111 xxB */
DECLARE_ASM_CONST(8, uint64_t, mask15rg) = 0x7FE07FE07FE07FE0ULL; /* 01111111 11100000 RGx */
DECLARE_ASM_CONST(8, uint64_t, mask15s) = 0xFFE0FFE0FFE0FFE0ULL;
DECLARE_ASM_CONST(8, uint64_t, mask15g) = 0x03E003E003E003E0ULL;
DECLARE_ASM_CONST(8, uint64_t, mask15r) = 0x7C007C007C007C00ULL;
#define mask16b mask15b
DECLARE_ASM_CONST(8, uint64_t, mask16g) = 0x07E007E007E007E0ULL;
DECLARE_ASM_CONST(8, uint64_t, mask16r) = 0xF800F800F800F800ULL;
DECLARE_ASM_CONST(8, uint64_t, red_16mask) = 0x0000f8000000f800ULL;
DECLARE_ASM_CONST(8, uint64_t, green_16mask) = 0x000007e0000007e0ULL;
DECLARE_ASM_CONST(8, uint64_t, blue_16mask) = 0x0000001f0000001fULL;
DECLARE_ASM_CONST(8, uint64_t, red_15mask) = 0x00007c0000007c00ULL;
DECLARE_ASM_CONST(8, uint64_t, green_15mask) = 0x000003e0000003e0ULL;
DECLARE_ASM_CONST(8, uint64_t, blue_15mask) = 0x0000001f0000001fULL;
#endif /* ARCH_X86 */
#define RGB2YUV_SHIFT 8
#define BY ((int)( 0.098*(1<<RGB2YUV_SHIFT)+0.5))
#define BV ((int)(-0.071*(1<<RGB2YUV_SHIFT)+0.5))
#define BU ((int)( 0.439*(1<<RGB2YUV_SHIFT)+0.5))
#define GY ((int)( 0.504*(1<<RGB2YUV_SHIFT)+0.5))
#define GV ((int)(-0.368*(1<<RGB2YUV_SHIFT)+0.5))
#define GU ((int)(-0.291*(1<<RGB2YUV_SHIFT)+0.5))
#define RY ((int)( 0.257*(1<<RGB2YUV_SHIFT)+0.5))
#define RV ((int)( 0.439*(1<<RGB2YUV_SHIFT)+0.5))
#define RU ((int)(-0.148*(1<<RGB2YUV_SHIFT)+0.5))
//Note: We have C, MMX, MMX2, 3DNOW versions, there is no 3DNOW + MMX2 one.
//plain C versions
#define COMPILE_TEMPLATE_MMX 0
#define COMPILE_TEMPLATE_MMX2 0
#define COMPILE_TEMPLATE_AMD3DNOW 0
#define COMPILE_TEMPLATE_SSE2 0
#define RENAME(a) a ## _C
#include "rgb2rgb_template.c"
#if ARCH_X86
//MMX versions
#undef RENAME
#undef COMPILE_TEMPLATE_MMX
#define COMPILE_TEMPLATE_MMX 1
#define RENAME(a) a ## _MMX
#include "rgb2rgb_template.c"
//MMX2 versions
#undef RENAME
#undef COMPILE_TEMPLATE_MMX2
#define COMPILE_TEMPLATE_MMX2 1
#define RENAME(a) a ## _MMX2
#include "rgb2rgb_template.c"
//SSE2 versions
#undef RENAME
#undef COMPILE_TEMPLATE_SSE2
#define COMPILE_TEMPLATE_SSE2 1
#define RENAME(a) a ## _SSE2
#include "rgb2rgb_template.c"
//3DNOW versions
#undef RENAME
#undef COMPILE_TEMPLATE_MMX2
#undef COMPILE_TEMPLATE_SSE2
#undef COMPILE_TEMPLATE_AMD3DNOW
#define COMPILE_TEMPLATE_MMX2 0
#define COMPILE_TEMPLATE_SSE2 1
#define COMPILE_TEMPLATE_AMD3DNOW 1
#define RENAME(a) a ## _3DNOW
#include "rgb2rgb_template.c"
#endif //ARCH_X86 || ARCH_X86_64
/*
RGB15->RGB16 original by Strepto/Astral
ported to gcc & bugfixed : A'rpi
MMX2, 3DNOW optimization by Nick Kurshev
32-bit C version, and and&add trick by Michael Niedermayer
*/
void sws_rgb2rgb_init(int flags)
{
#if HAVE_MMX2 || HAVE_AMD3DNOW || HAVE_MMX
if (flags & SWS_CPU_CAPS_SSE2)
rgb2rgb_init_SSE2();
else if (flags & SWS_CPU_CAPS_MMX2)
rgb2rgb_init_MMX2();
else if (flags & SWS_CPU_CAPS_3DNOW)
rgb2rgb_init_3DNOW();
else if (flags & SWS_CPU_CAPS_MMX)
rgb2rgb_init_MMX();
else
#endif /* HAVE_MMX2 || HAVE_AMD3DNOW || HAVE_MMX */
rgb2rgb_init_C();
}
#if LIBSWSCALE_VERSION_MAJOR < 1
void palette8topacked32(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette)
{
sws_convertPalette8ToPacked32(src, dst, num_pixels, palette);
}
void palette8topacked24(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette)
{
sws_convertPalette8ToPacked24(src, dst, num_pixels, palette);
}
/**
* Palette is assumed to contain BGR16, see rgb32to16 to convert the palette.
*/
void palette8torgb16(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette)
{
long i;
for (i=0; i<num_pixels; i++)
((uint16_t *)dst)[i] = ((const uint16_t *)palette)[src[i]];
}
void palette8tobgr16(const uint8_t *src, uint8_t *dst, long num_pixels, const uint8_t *palette)
{
long i;
for (i=0; i<num_pixels; i++)
((uint16_t *)dst)[i] = av_bswap16(((const uint16_t *)palette)[src[i]]);
}
#endif
void rgb32to24(const uint8_t *src, uint8_t *dst, long src_size)
{
long i;
long num_pixels = src_size >> 2;
for (i=0; i<num_pixels; i++) {
#if HAVE_BIGENDIAN
/* RGB32 (= A,B,G,R) -> BGR24 (= B,G,R) */
dst[3*i + 0] = src[4*i + 1];
dst[3*i + 1] = src[4*i + 2];
dst[3*i + 2] = src[4*i + 3];
#else
dst[3*i + 0] = src[4*i + 2];
dst[3*i + 1] = src[4*i + 1];
dst[3*i + 2] = src[4*i + 0];
#endif
}
}
void rgb24to32(const uint8_t *src, uint8_t *dst, long src_size)
{
long i;
for (i=0; 3*i<src_size; i++) {
#if HAVE_BIGENDIAN
/* RGB24 (= R,G,B) -> BGR32 (= A,R,G,B) */
dst[4*i + 0] = 255;
dst[4*i + 1] = src[3*i + 0];
dst[4*i + 2] = src[3*i + 1];
dst[4*i + 3] = src[3*i + 2];
#else
dst[4*i + 0] = src[3*i + 2];
dst[4*i + 1] = src[3*i + 1];
dst[4*i + 2] = src[3*i + 0];
dst[4*i + 3] = 255;
#endif
}
}
void rgb16tobgr32(const uint8_t *src, uint8_t *dst, long src_size)
{
const uint16_t *end;
uint8_t *d = dst;
const uint16_t *s = (const uint16_t *)src;
end = s + src_size/2;
while (s < end) {
register uint16_t bgr;
bgr = *s++;
#if HAVE_BIGENDIAN
*d++ = 255;
*d++ = (bgr&0x1F)<<3;
*d++ = (bgr&0x7E0)>>3;
*d++ = (bgr&0xF800)>>8;
#else
*d++ = (bgr&0xF800)>>8;
*d++ = (bgr&0x7E0)>>3;
*d++ = (bgr&0x1F)<<3;
*d++ = 255;
#endif
}
}
void rgb16to24(const uint8_t *src, uint8_t *dst, long src_size)
{
const uint16_t *end;
uint8_t *d = dst;
const uint16_t *s = (const uint16_t *)src;
end = s + src_size/2;
while (s < end) {
register uint16_t bgr;
bgr = *s++;
*d++ = (bgr&0xF800)>>8;
*d++ = (bgr&0x7E0)>>3;
*d++ = (bgr&0x1F)<<3;
}
}
void rgb16tobgr16(const uint8_t *src, uint8_t *dst, long src_size)
{
long i;
long num_pixels = src_size >> 1;
for (i=0; i<num_pixels; i++) {
unsigned rgb = ((const uint16_t*)src)[i];
((uint16_t*)dst)[i] = (rgb>>11) | (rgb&0x7E0) | (rgb<<11);
}
}
void rgb16tobgr15(const uint8_t *src, uint8_t *dst, long src_size)
{
long i;
long num_pixels = src_size >> 1;
for (i=0; i<num_pixels; i++) {
unsigned rgb = ((const uint16_t*)src)[i];
((uint16_t*)dst)[i] = (rgb>>11) | ((rgb&0x7C0)>>1) | ((rgb&0x1F)<<10);
}
}
void rgb15tobgr32(const uint8_t *src, uint8_t *dst, long src_size)
{
const uint16_t *end;
uint8_t *d = dst;
const uint16_t *s = (const uint16_t *)src;
end = s + src_size/2;
while (s < end) {
register uint16_t bgr;
bgr = *s++;
#if HAVE_BIGENDIAN
*d++ = 255;
*d++ = (bgr&0x1F)<<3;
*d++ = (bgr&0x3E0)>>2;
*d++ = (bgr&0x7C00)>>7;
#else
*d++ = (bgr&0x7C00)>>7;
*d++ = (bgr&0x3E0)>>2;
*d++ = (bgr&0x1F)<<3;
*d++ = 255;
#endif
}
}
void rgb15to24(const uint8_t *src, uint8_t *dst, long src_size)
{
const uint16_t *end;
uint8_t *d = dst;
const uint16_t *s = (const uint16_t *)src;
end = s + src_size/2;
while (s < end) {
register uint16_t bgr;
bgr = *s++;
*d++ = (bgr&0x7C00)>>7;
*d++ = (bgr&0x3E0)>>2;
*d++ = (bgr&0x1F)<<3;
}
}
void rgb15tobgr16(const uint8_t *src, uint8_t *dst, long src_size)
{
long i;
long num_pixels = src_size >> 1;
for (i=0; i<num_pixels; i++) {
unsigned rgb = ((const uint16_t*)src)[i];
((uint16_t*)dst)[i] = ((rgb&0x7C00)>>10) | ((rgb&0x3E0)<<1) | (rgb<<11);
}
}
void rgb15tobgr15(const uint8_t *src, uint8_t *dst, long src_size)
{
long i;
long num_pixels = src_size >> 1;
for (i=0; i<num_pixels; i++) {
unsigned br;
unsigned rgb = ((const uint16_t*)src)[i];
br = rgb&0x7c1F;
((uint16_t*)dst)[i] = (br>>10) | (rgb&0x3E0) | (br<<10);
}
}
void bgr8torgb8(const uint8_t *src, uint8_t *dst, long src_size)
{
long i;
long num_pixels = src_size;
for (i=0; i<num_pixels; i++) {
unsigned b,g,r;
register uint8_t rgb;
rgb = src[i];
r = (rgb&0x07);
g = (rgb&0x38)>>3;
b = (rgb&0xC0)>>6;
dst[i] = ((b<<1)&0x07) | ((g&0x07)<<3) | ((r&0x03)<<6);
}
}
#define DEFINE_SHUFFLE_BYTES(a, b, c, d) \
void shuffle_bytes_##a##b##c##d(const uint8_t *src, uint8_t *dst, long src_size) \
{ \
long i; \
\
for (i = 0; i < src_size; i+=4) { \
dst[i + 0] = src[i + a]; \
dst[i + 1] = src[i + b]; \
dst[i + 2] = src[i + c]; \
dst[i + 3] = src[i + d]; \
} \
}
DEFINE_SHUFFLE_BYTES(0, 3, 2, 1);
DEFINE_SHUFFLE_BYTES(1, 2, 3, 0);
DEFINE_SHUFFLE_BYTES(3, 0, 1, 2);
DEFINE_SHUFFLE_BYTES(3, 2, 1, 0);
|