/
SDL_blit.h
522 lines (485 loc) · 14.3 KB
1
2
/*
SDL - Simple DirectMedia Layer
3
Copyright (C) 1997-2006 Sam Lantinga
4
5
This library is free software; you can redistribute it and/or
6
modify it under the terms of the GNU Lesser General Public
7
License as published by the Free Software Foundation; either
8
version 2.1 of the License, or (at your option) any later version.
9
10
11
12
This library 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
13
Lesser General Public License for more details.
14
15
16
17
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
18
19
Sam Lantinga
20
slouken@libsdl.org
21
*/
22
#include "SDL_config.h"
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
#ifndef _SDL_blit_h
#define _SDL_blit_h
#include "SDL_endian.h"
/* The structure passed to the low level blit functions */
typedef struct {
Uint8 *s_pixels;
int s_width;
int s_height;
int s_skip;
Uint8 *d_pixels;
int d_width;
int d_height;
int d_skip;
void *aux_data;
SDL_PixelFormat *src;
Uint8 *table;
SDL_PixelFormat *dst;
} SDL_BlitInfo;
/* The type definition for the low level blit functions */
typedef void (*SDL_loblit)(SDL_BlitInfo *info);
/* This is the private info structure for software accelerated blits */
struct private_swaccel {
SDL_loblit blit;
void *aux_data;
};
/* Blit mapping definition */
typedef struct SDL_BlitMap {
SDL_Surface *dst;
int identity;
Uint8 *table;
SDL_blit hw_blit;
SDL_blit sw_blit;
struct private_hwaccel *hw_data;
struct private_swaccel *sw_data;
/* the version count matches the destination; mismatch indicates
an invalid mapping */
unsigned int format_version;
} SDL_BlitMap;
/* Functions found in SDL_blit.c */
extern int SDL_CalculateBlit(SDL_Surface *surface);
/* Functions found in SDL_blit_{0,1,N,A}.c */
extern SDL_loblit SDL_CalculateBlit0(SDL_Surface *surface, int complex);
extern SDL_loblit SDL_CalculateBlit1(SDL_Surface *surface, int complex);
extern SDL_loblit SDL_CalculateBlitN(SDL_Surface *surface, int complex);
extern SDL_loblit SDL_CalculateAlphaBlit(SDL_Surface *surface, int complex);
/*
* Useful macros for blitting routines
*/
#define FORMAT_EQUAL(A, B) \
((A)->BitsPerPixel == (B)->BitsPerPixel \
&& ((A)->Rmask == (B)->Rmask) && ((A)->Amask == (B)->Amask))
/* Load pixel of the specified format from a buffer and get its R-G-B values */
/* FIXME: rescale values to 0..255 here? */
89
#define RGB_FROM_PIXEL(Pixel, fmt, r, g, b) \
90
{ \
91
92
93
r = (((Pixel&fmt->Rmask)>>fmt->Rshift)<<fmt->Rloss); \
g = (((Pixel&fmt->Gmask)>>fmt->Gshift)<<fmt->Gloss); \
b = (((Pixel&fmt->Bmask)>>fmt->Bshift)<<fmt->Bloss); \
94
}
95
#define RGB_FROM_RGB565(Pixel, r, g, b) \
96
{ \
97
98
99
r = (((Pixel&0xF800)>>11)<<3); \
g = (((Pixel&0x07E0)>>5)<<2); \
b = ((Pixel&0x001F)<<3); \
100
}
101
#define RGB_FROM_RGB555(Pixel, r, g, b) \
102
{ \
103
104
105
r = (((Pixel&0x7C00)>>10)<<3); \
g = (((Pixel&0x03E0)>>5)<<3); \
b = ((Pixel&0x001F)<<3); \
106
}
107
#define RGB_FROM_RGB888(Pixel, r, g, b) \
108
{ \
109
110
111
r = ((Pixel&0xFF0000)>>16); \
g = ((Pixel&0xFF00)>>8); \
b = (Pixel&0xFF); \
112
}
113
#define RETRIEVE_RGB_PIXEL(buf, bpp, Pixel) \
114
115
116
do { \
switch (bpp) { \
case 2: \
117
Pixel = *((Uint16 *)(buf)); \
118
119
120
121
122
break; \
\
case 3: { \
Uint8 *B = (Uint8 *)(buf); \
if(SDL_BYTEORDER == SDL_LIL_ENDIAN) { \
123
Pixel = B[0] + (B[1] << 8) + (B[2] << 16); \
124
} else { \
125
Pixel = (B[0] << 16) + (B[1] << 8) + B[2]; \
126
127
128
129
130
} \
} \
break; \
\
case 4: \
131
Pixel = *((Uint32 *)(buf)); \
132
133
134
break; \
\
default: \
135
Pixel = 0; /* appease gcc */ \
136
137
138
139
break; \
} \
} while(0)
140
#define DISEMBLE_RGB(buf, bpp, fmt, Pixel, r, g, b) \
141
142
143
do { \
switch (bpp) { \
case 2: \
144
Pixel = *((Uint16 *)(buf)); \
145
146
147
148
149
break; \
\
case 3: { \
Uint8 *B = (Uint8 *)buf; \
if(SDL_BYTEORDER == SDL_LIL_ENDIAN) { \
150
Pixel = B[0] + (B[1] << 8) + (B[2] << 16); \
151
} else { \
152
Pixel = (B[0] << 16) + (B[1] << 8) + B[2]; \
153
154
155
156
157
} \
} \
break; \
\
case 4: \
158
Pixel = *((Uint32 *)(buf)); \
159
160
161
break; \
\
default: \
162
Pixel = 0; /* prevent gcc from complaining */ \
163
164
break; \
} \
165
RGB_FROM_PIXEL(Pixel, fmt, r, g, b); \
166
167
168
} while(0)
/* Assemble R-G-B values into a specified pixel format and store them */
169
#define PIXEL_FROM_RGB(Pixel, fmt, r, g, b) \
170
{ \
171
Pixel = ((r>>fmt->Rloss)<<fmt->Rshift)| \
172
173
174
((g>>fmt->Gloss)<<fmt->Gshift)| \
((b>>fmt->Bloss)<<fmt->Bshift); \
}
175
#define RGB565_FROM_RGB(Pixel, r, g, b) \
176
{ \
177
Pixel = ((r>>3)<<11)|((g>>2)<<5)|(b>>3); \
178
}
179
#define RGB555_FROM_RGB(Pixel, r, g, b) \
180
{ \
181
Pixel = ((r>>3)<<10)|((g>>3)<<5)|(b>>3); \
182
}
183
#define RGB888_FROM_RGB(Pixel, r, g, b) \
184
{ \
185
Pixel = (r<<16)|(g<<8)|b; \
186
187
188
189
190
}
#define ASSEMBLE_RGB(buf, bpp, fmt, r, g, b) \
{ \
switch (bpp) { \
case 2: { \
191
Uint16 Pixel; \
192
\
193
194
PIXEL_FROM_RGB(Pixel, fmt, r, g, b); \
*((Uint16 *)(buf)) = Pixel; \
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
} \
break; \
\
case 3: { \
if(SDL_BYTEORDER == SDL_LIL_ENDIAN) { \
*((buf)+fmt->Rshift/8) = r; \
*((buf)+fmt->Gshift/8) = g; \
*((buf)+fmt->Bshift/8) = b; \
} else { \
*((buf)+2-fmt->Rshift/8) = r; \
*((buf)+2-fmt->Gshift/8) = g; \
*((buf)+2-fmt->Bshift/8) = b; \
} \
} \
break; \
\
case 4: { \
212
Uint32 Pixel; \
213
\
214
215
PIXEL_FROM_RGB(Pixel, fmt, r, g, b); \
*((Uint32 *)(buf)) = Pixel; \
216
217
218
219
220
221
222
223
224
} \
break; \
} \
}
#define ASSEMBLE_RGB_AMASK(buf, bpp, fmt, r, g, b, Amask) \
{ \
switch (bpp) { \
case 2: { \
Uint16 *bufp; \
225
Uint16 Pixel; \
226
227
\
bufp = (Uint16 *)buf; \
228
229
PIXEL_FROM_RGB(Pixel, fmt, r, g, b); \
*bufp = Pixel | (*bufp & Amask); \
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
} \
break; \
\
case 3: { \
if(SDL_BYTEORDER == SDL_LIL_ENDIAN) { \
*((buf)+fmt->Rshift/8) = r; \
*((buf)+fmt->Gshift/8) = g; \
*((buf)+fmt->Bshift/8) = b; \
} else { \
*((buf)+2-fmt->Rshift/8) = r; \
*((buf)+2-fmt->Gshift/8) = g; \
*((buf)+2-fmt->Bshift/8) = b; \
} \
} \
break; \
\
case 4: { \
Uint32 *bufp; \
248
Uint32 Pixel; \
249
250
\
bufp = (Uint32 *)buf; \
251
252
PIXEL_FROM_RGB(Pixel, fmt, r, g, b); \
*bufp = Pixel | (*bufp & Amask); \
253
254
255
256
257
258
} \
break; \
} \
}
/* FIXME: Should we rescale alpha into 0..255 here? */
259
#define RGBA_FROM_PIXEL(Pixel, fmt, r, g, b, a) \
260
{ \
261
262
263
264
r = ((Pixel&fmt->Rmask)>>fmt->Rshift)<<fmt->Rloss; \
g = ((Pixel&fmt->Gmask)>>fmt->Gshift)<<fmt->Gloss; \
b = ((Pixel&fmt->Bmask)>>fmt->Bshift)<<fmt->Bloss; \
a = ((Pixel&fmt->Amask)>>fmt->Ashift)<<fmt->Aloss; \
265
}
266
#define RGBA_FROM_8888(Pixel, fmt, r, g, b, a) \
267
{ \
268
269
270
271
r = (Pixel&fmt->Rmask)>>fmt->Rshift; \
g = (Pixel&fmt->Gmask)>>fmt->Gshift; \
b = (Pixel&fmt->Bmask)>>fmt->Bshift; \
a = (Pixel&fmt->Amask)>>fmt->Ashift; \
272
}
273
#define RGBA_FROM_RGBA8888(Pixel, r, g, b, a) \
274
{ \
275
276
277
278
r = (Pixel>>24); \
g = ((Pixel>>16)&0xFF); \
b = ((Pixel>>8)&0xFF); \
a = (Pixel&0xFF); \
279
}
280
#define RGBA_FROM_ARGB8888(Pixel, r, g, b, a) \
281
{ \
282
283
284
285
r = ((Pixel>>16)&0xFF); \
g = ((Pixel>>8)&0xFF); \
b = (Pixel&0xFF); \
a = (Pixel>>24); \
286
}
287
#define RGBA_FROM_ABGR8888(Pixel, r, g, b, a) \
288
{ \
289
290
291
292
r = (Pixel&0xFF); \
g = ((Pixel>>8)&0xFF); \
b = ((Pixel>>16)&0xFF); \
a = (Pixel>>24); \
293
}
294
#define DISEMBLE_RGBA(buf, bpp, fmt, Pixel, r, g, b, a) \
295
296
297
do { \
switch (bpp) { \
case 2: \
298
Pixel = *((Uint16 *)(buf)); \
299
300
301
302
303
break; \
\
case 3: {/* FIXME: broken code (no alpha) */ \
Uint8 *b = (Uint8 *)buf; \
if(SDL_BYTEORDER == SDL_LIL_ENDIAN) { \
304
Pixel = b[0] + (b[1] << 8) + (b[2] << 16); \
305
} else { \
306
Pixel = (b[0] << 16) + (b[1] << 8) + b[2]; \
307
308
309
310
311
} \
} \
break; \
\
case 4: \
312
Pixel = *((Uint32 *)(buf)); \
313
314
315
break; \
\
default: \
316
Pixel = 0; /* stop gcc complaints */ \
317
318
break; \
} \
319
320
RGBA_FROM_PIXEL(Pixel, fmt, r, g, b, a); \
Pixel &= ~fmt->Amask; \
321
322
323
} while(0)
/* FIXME: this isn't correct, especially for Alpha (maximum != 255) */
324
#define PIXEL_FROM_RGBA(Pixel, fmt, r, g, b, a) \
325
{ \
326
Pixel = ((r>>fmt->Rloss)<<fmt->Rshift)| \
327
328
((g>>fmt->Gloss)<<fmt->Gshift)| \
((b>>fmt->Bloss)<<fmt->Bshift)| \
329
((a>>fmt->Aloss)<<fmt->Ashift); \
330
331
332
333
334
}
#define ASSEMBLE_RGBA(buf, bpp, fmt, r, g, b, a) \
{ \
switch (bpp) { \
case 2: { \
335
Uint16 Pixel; \
336
\
337
338
PIXEL_FROM_RGBA(Pixel, fmt, r, g, b, a); \
*((Uint16 *)(buf)) = Pixel; \
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
} \
break; \
\
case 3: { /* FIXME: broken code (no alpha) */ \
if(SDL_BYTEORDER == SDL_LIL_ENDIAN) { \
*((buf)+fmt->Rshift/8) = r; \
*((buf)+fmt->Gshift/8) = g; \
*((buf)+fmt->Bshift/8) = b; \
} else { \
*((buf)+2-fmt->Rshift/8) = r; \
*((buf)+2-fmt->Gshift/8) = g; \
*((buf)+2-fmt->Bshift/8) = b; \
} \
} \
break; \
\
case 4: { \
356
Uint32 Pixel; \
357
\
358
359
PIXEL_FROM_RGBA(Pixel, fmt, r, g, b, a); \
*((Uint32 *)(buf)) = Pixel; \
360
361
362
363
364
} \
break; \
} \
}
365
/* Blend the RGB values of two Pixels based on a source alpha value */
366
367
368
369
370
371
372
#define ALPHA_BLEND(sR, sG, sB, A, dR, dG, dB) \
do { \
dR = (((sR-dR)*(A))>>8)+dR; \
dG = (((sG-dG)*(A))>>8)+dG; \
dB = (((sB-dB)*(A))>>8)+dB; \
} while(0)
373
/* Blend the RGB values of two Pixels based on a source alpha value */
374
375
376
377
378
379
380
381
382
383
384
385
386
#define ACCURATE_ALPHA_BLEND(sR, sG, sB, sA, dR, dG, dB) \
do { \
unsigned tR, tG, tB, tA; \
tA = 255 - sA; \
tR = 1 + (sR * sA) + (dR * tA); \
dR = (tR + (tR >> 8)) >> 8; \
tG = 1 + (sG * sA) + (dG * tA); \
dG = (tG + (tG >> 8)) >> 8; \
tB = 1 + (sB * sA) + (dB * tA); \
dB = (tB + (tB >> 8)) >> 8; \
} while(0)
387
/* This is a very useful loop for optimizing blitters */
388
389
390
#if defined(_MSC_VER) && (_MSC_VER == 1300)
/* There's a bug in the Visual C++ 7 optimizer when compiling this code */
#else
391
#define USE_DUFFS_LOOP
392
#endif
393
394
395
396
397
#ifdef USE_DUFFS_LOOP
/* 8-times unrolled loop */
#define DUFFS_LOOP8(pixel_copy_increment, width) \
{ int n = (width+7)/8; \
398
switch (width & 7) { \
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
case 0: do { pixel_copy_increment; \
case 7: pixel_copy_increment; \
case 6: pixel_copy_increment; \
case 5: pixel_copy_increment; \
case 4: pixel_copy_increment; \
case 3: pixel_copy_increment; \
case 2: pixel_copy_increment; \
case 1: pixel_copy_increment; \
} while ( --n > 0 ); \
} \
}
/* 4-times unrolled loop */
#define DUFFS_LOOP4(pixel_copy_increment, width) \
{ int n = (width+3)/4; \
414
switch (width & 3) { \
415
416
417
418
419
420
421
422
case 0: do { pixel_copy_increment; \
case 3: pixel_copy_increment; \
case 2: pixel_copy_increment; \
case 1: pixel_copy_increment; \
} while ( --n > 0 ); \
} \
}
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
/* 2 - times unrolled loop */
#define DUFFS_LOOP_DOUBLE2(pixel_copy_increment, \
double_pixel_copy_increment, width) \
{ int n, w = width; \
if( w & 1 ) { \
pixel_copy_increment; \
w--; \
} \
if ( w > 0 ) { \
n = ( w + 2) / 4; \
switch( w & 2 ) { \
case 0: do { double_pixel_copy_increment; \
case 2: double_pixel_copy_increment; \
} while ( --n > 0 ); \
} \
} \
}
/* 2 - times unrolled loop 4 pixels */
#define DUFFS_LOOP_QUATRO2(pixel_copy_increment, \
double_pixel_copy_increment, \
quatro_pixel_copy_increment, width) \
{ int n, w = width; \
if(w & 1) { \
pixel_copy_increment; \
w--; \
} \
if(w & 2) { \
double_pixel_copy_increment; \
w -= 2; \
} \
if ( w > 0 ) { \
n = ( w + 7 ) / 8; \
switch( w & 4 ) { \
case 0: do { quatro_pixel_copy_increment; \
case 4: quatro_pixel_copy_increment; \
} while ( --n > 0 ); \
} \
} \
}
464
465
466
467
468
469
/* Use the 8-times version of the loop by default */
#define DUFFS_LOOP(pixel_copy_increment, width) \
DUFFS_LOOP8(pixel_copy_increment, width)
#else
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
/* Don't use Duff's device to unroll loops */
#define DUFFS_LOOP_DOUBLE2(pixel_copy_increment, \
double_pixel_copy_increment, width) \
{ int n = width; \
if( n & 1 ) { \
pixel_copy_increment; \
n--; \
} \
n=n>>1; \
for(; n > 0; --n) { \
double_pixel_copy_increment; \
} \
}
/* Don't use Duff's device to unroll loops */
#define DUFFS_LOOP_QUATRO2(pixel_copy_increment, \
double_pixel_copy_increment, \
quatro_pixel_copy_increment, width) \
{ int n = width; \
if(n & 1) { \
pixel_copy_increment; \
n--; \
} \
if(n & 2) { \
double_pixel_copy_increment; \
n -= 2; \
} \
n=n>>2; \
for(; n > 0; --n) { \
quatro_pixel_copy_increment; \
} \
}
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
/* Don't use Duff's device to unroll loops */
#define DUFFS_LOOP(pixel_copy_increment, width) \
{ int n; \
for ( n=width; n > 0; --n ) { \
pixel_copy_increment; \
} \
}
#define DUFFS_LOOP8(pixel_copy_increment, width) \
DUFFS_LOOP(pixel_copy_increment, width)
#define DUFFS_LOOP4(pixel_copy_increment, width) \
DUFFS_LOOP(pixel_copy_increment, width)
#endif /* USE_DUFFS_LOOP */
/* Prevent Visual C++ 6.0 from printing out stupid warnings */
#if defined(_MSC_VER) && (_MSC_VER >= 600)
#pragma warning(disable: 4550)
#endif
#endif /* _SDL_blit_h */