This repository has been archived by the owner on Feb 11, 2021. It is now read-only.
/
SDL_blit.h
535 lines (497 loc) · 14.7 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
#ifndef _SDL_blit_h
#define _SDL_blit_h
#include "SDL_endian.h"
/* The structure passed to the low level blit functions */
30
31
32
33
34
35
36
37
38
39
40
41
42
43
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;
44
45
46
} SDL_BlitInfo;
/* The type definition for the low level blit functions */
47
typedef void (*SDL_loblit) (SDL_BlitInfo * info);
48
49
/* This is the private info structure for software accelerated blits */
50
51
52
53
struct private_swaccel
{
SDL_loblit blit;
void *aux_data;
54
55
56
};
/* Blit mapping definition */
57
58
59
60
61
62
63
64
65
66
67
typedef struct SDL_BlitMap
{
SDL_Surface *dst;
int identity;
Uint8 *table;
SDL_blit sw_blit;
struct private_swaccel *sw_data;
/* the version count matches the destination; mismatch indicates
an invalid mapping */
unsigned int format_version;
68
69
} SDL_BlitMap;
70
71
72
73
74
75
76
77
78
79
80
#define SDL_BLIT_ANY 0x00000000
#define SDL_BLIT_MMX 0x00000001
#define SDL_BLIT_SSE 0x00000002
#define SDL_BLIT_ALTIVEC_PREFETCH 0x00000004
#define SDL_BLIT_ALTIVEC_NOPREFETCH 0x00000008
typedef struct SDL_BlitEntry
{
Uint32 features;
SDL_loblit blit;
} SDL_BlitEntry;
81
82
/* Functions found in SDL_blit.c */
83
extern int SDL_CalculateBlit(SDL_Surface * surface);
84
85
/* Functions found in SDL_blit_{0,1,N,A}.c */
86
87
88
89
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);
90
91
92
93
94
95
96
97
98
99
100
/*
* 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? */
101
#define RGB_FROM_PIXEL(Pixel, fmt, r, g, b) \
102
{ \
103
104
105
r = (((Pixel&fmt->Rmask)>>fmt->Rshift)<<fmt->Rloss); \
g = (((Pixel&fmt->Gmask)>>fmt->Gshift)<<fmt->Gloss); \
b = (((Pixel&fmt->Bmask)>>fmt->Bshift)<<fmt->Bloss); \
106
}
107
#define RGB_FROM_RGB565(Pixel, r, g, b) \
108
{ \
109
110
111
r = (((Pixel&0xF800)>>11)<<3); \
g = (((Pixel&0x07E0)>>5)<<2); \
b = ((Pixel&0x001F)<<3); \
112
}
113
#define RGB_FROM_RGB555(Pixel, r, g, b) \
114
{ \
115
116
117
r = (((Pixel&0x7C00)>>10)<<3); \
g = (((Pixel&0x03E0)>>5)<<3); \
b = ((Pixel&0x001F)<<3); \
118
}
119
#define RGB_FROM_RGB888(Pixel, r, g, b) \
120
{ \
121
122
123
r = ((Pixel&0xFF0000)>>16); \
g = ((Pixel&0xFF00)>>8); \
b = (Pixel&0xFF); \
124
}
125
#define RETRIEVE_RGB_PIXEL(buf, bpp, Pixel) \
126
127
128
do { \
switch (bpp) { \
case 2: \
129
Pixel = *((Uint16 *)(buf)); \
130
131
132
133
134
break; \
\
case 3: { \
Uint8 *B = (Uint8 *)(buf); \
if(SDL_BYTEORDER == SDL_LIL_ENDIAN) { \
135
Pixel = B[0] + (B[1] << 8) + (B[2] << 16); \
136
} else { \
137
Pixel = (B[0] << 16) + (B[1] << 8) + B[2]; \
138
139
140
141
142
} \
} \
break; \
\
case 4: \
143
Pixel = *((Uint32 *)(buf)); \
144
145
146
break; \
\
default: \
147
Pixel = 0; /* appease gcc */ \
148
149
150
151
break; \
} \
} while(0)
152
#define DISEMBLE_RGB(buf, bpp, fmt, Pixel, r, g, b) \
153
154
155
do { \
switch (bpp) { \
case 2: \
156
Pixel = *((Uint16 *)(buf)); \
157
158
159
160
161
break; \
\
case 3: { \
Uint8 *B = (Uint8 *)buf; \
if(SDL_BYTEORDER == SDL_LIL_ENDIAN) { \
162
Pixel = B[0] + (B[1] << 8) + (B[2] << 16); \
163
} else { \
164
Pixel = (B[0] << 16) + (B[1] << 8) + B[2]; \
165
166
167
168
169
} \
} \
break; \
\
case 4: \
170
Pixel = *((Uint32 *)(buf)); \
171
172
173
break; \
\
default: \
174
Pixel = 0; /* prevent gcc from complaining */ \
175
176
break; \
} \
177
RGB_FROM_PIXEL(Pixel, fmt, r, g, b); \
178
179
180
} while(0)
/* Assemble R-G-B values into a specified pixel format and store them */
181
#define PIXEL_FROM_RGB(Pixel, fmt, r, g, b) \
182
{ \
183
Pixel = ((r>>fmt->Rloss)<<fmt->Rshift)| \
184
185
186
((g>>fmt->Gloss)<<fmt->Gshift)| \
((b>>fmt->Bloss)<<fmt->Bshift); \
}
187
#define RGB565_FROM_RGB(Pixel, r, g, b) \
188
{ \
189
Pixel = ((r>>3)<<11)|((g>>2)<<5)|(b>>3); \
190
}
191
#define RGB555_FROM_RGB(Pixel, r, g, b) \
192
{ \
193
Pixel = ((r>>3)<<10)|((g>>3)<<5)|(b>>3); \
194
}
195
#define RGB888_FROM_RGB(Pixel, r, g, b) \
196
{ \
197
Pixel = (r<<16)|(g<<8)|b; \
198
199
200
201
202
}
#define ASSEMBLE_RGB(buf, bpp, fmt, r, g, b) \
{ \
switch (bpp) { \
case 2: { \
203
Uint16 Pixel; \
204
\
205
206
PIXEL_FROM_RGB(Pixel, fmt, r, g, b); \
*((Uint16 *)(buf)) = Pixel; \
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
} \
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: { \
224
Uint32 Pixel; \
225
\
226
227
PIXEL_FROM_RGB(Pixel, fmt, r, g, b); \
*((Uint32 *)(buf)) = Pixel; \
228
229
230
231
232
233
234
235
236
} \
break; \
} \
}
#define ASSEMBLE_RGB_AMASK(buf, bpp, fmt, r, g, b, Amask) \
{ \
switch (bpp) { \
case 2: { \
Uint16 *bufp; \
237
Uint16 Pixel; \
238
239
\
bufp = (Uint16 *)buf; \
240
241
PIXEL_FROM_RGB(Pixel, fmt, r, g, b); \
*bufp = Pixel | (*bufp & Amask); \
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
} \
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; \
260
Uint32 Pixel; \
261
262
\
bufp = (Uint32 *)buf; \
263
264
PIXEL_FROM_RGB(Pixel, fmt, r, g, b); \
*bufp = Pixel | (*bufp & Amask); \
265
266
267
268
269
270
} \
break; \
} \
}
/* FIXME: Should we rescale alpha into 0..255 here? */
271
#define RGBA_FROM_PIXEL(Pixel, fmt, r, g, b, a) \
272
{ \
273
274
275
276
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; \
277
}
278
#define RGBA_FROM_8888(Pixel, fmt, r, g, b, a) \
279
{ \
280
281
282
283
r = (Pixel&fmt->Rmask)>>fmt->Rshift; \
g = (Pixel&fmt->Gmask)>>fmt->Gshift; \
b = (Pixel&fmt->Bmask)>>fmt->Bshift; \
a = (Pixel&fmt->Amask)>>fmt->Ashift; \
284
}
285
#define RGBA_FROM_RGBA8888(Pixel, r, g, b, a) \
286
{ \
287
288
289
290
r = (Pixel>>24); \
g = ((Pixel>>16)&0xFF); \
b = ((Pixel>>8)&0xFF); \
a = (Pixel&0xFF); \
291
}
292
#define RGBA_FROM_ARGB8888(Pixel, r, g, b, a) \
293
{ \
294
295
296
297
r = ((Pixel>>16)&0xFF); \
g = ((Pixel>>8)&0xFF); \
b = (Pixel&0xFF); \
a = (Pixel>>24); \
298
}
299
#define RGBA_FROM_ABGR8888(Pixel, r, g, b, a) \
300
{ \
301
302
303
304
r = (Pixel&0xFF); \
g = ((Pixel>>8)&0xFF); \
b = ((Pixel>>16)&0xFF); \
a = (Pixel>>24); \
305
}
306
#define DISEMBLE_RGBA(buf, bpp, fmt, Pixel, r, g, b, a) \
307
308
309
do { \
switch (bpp) { \
case 2: \
310
Pixel = *((Uint16 *)(buf)); \
311
312
313
314
315
break; \
\
case 3: {/* FIXME: broken code (no alpha) */ \
Uint8 *b = (Uint8 *)buf; \
if(SDL_BYTEORDER == SDL_LIL_ENDIAN) { \
316
Pixel = b[0] + (b[1] << 8) + (b[2] << 16); \
317
} else { \
318
Pixel = (b[0] << 16) + (b[1] << 8) + b[2]; \
319
320
321
322
323
} \
} \
break; \
\
case 4: \
324
Pixel = *((Uint32 *)(buf)); \
325
326
327
break; \
\
default: \
328
Pixel = 0; /* stop gcc complaints */ \
329
330
break; \
} \
331
332
RGBA_FROM_PIXEL(Pixel, fmt, r, g, b, a); \
Pixel &= ~fmt->Amask; \
333
334
335
} while(0)
/* FIXME: this isn't correct, especially for Alpha (maximum != 255) */
336
#define PIXEL_FROM_RGBA(Pixel, fmt, r, g, b, a) \
337
{ \
338
Pixel = ((r>>fmt->Rloss)<<fmt->Rshift)| \
339
340
((g>>fmt->Gloss)<<fmt->Gshift)| \
((b>>fmt->Bloss)<<fmt->Bshift)| \
341
((a>>fmt->Aloss)<<fmt->Ashift); \
342
343
344
345
346
}
#define ASSEMBLE_RGBA(buf, bpp, fmt, r, g, b, a) \
{ \
switch (bpp) { \
case 2: { \
347
Uint16 Pixel; \
348
\
349
350
PIXEL_FROM_RGBA(Pixel, fmt, r, g, b, a); \
*((Uint16 *)(buf)) = Pixel; \
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
} \
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: { \
368
Uint32 Pixel; \
369
\
370
371
PIXEL_FROM_RGBA(Pixel, fmt, r, g, b, a); \
*((Uint32 *)(buf)) = Pixel; \
372
373
374
375
376
} \
break; \
} \
}
377
/* Blend the RGB values of two Pixels based on a source alpha value */
378
379
380
381
382
383
384
#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)
385
/* Blend the RGB values of two Pixels based on a source alpha value */
386
387
388
389
390
391
392
393
394
395
396
397
398
#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)
399
/* This is a very useful loop for optimizing blitters */
400
401
402
#if defined(_MSC_VER) && (_MSC_VER == 1300)
/* There's a bug in the Visual C++ 7 optimizer when compiling this code */
#else
403
#define USE_DUFFS_LOOP
404
#endif
405
406
407
408
409
#ifdef USE_DUFFS_LOOP
/* 8-times unrolled loop */
#define DUFFS_LOOP8(pixel_copy_increment, width) \
{ int n = (width+7)/8; \
410
switch (width & 7) { \
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
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; \
426
switch (width & 3) { \
427
428
429
430
431
432
433
434
case 0: do { pixel_copy_increment; \
case 3: pixel_copy_increment; \
case 2: pixel_copy_increment; \
case 1: pixel_copy_increment; \
} while ( --n > 0 ); \
} \
}
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
464
465
466
467
468
469
470
471
472
473
474
475
/* 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 ); \
} \
} \
}
476
477
478
479
480
481
/* Use the 8-times version of the loop by default */
#define DUFFS_LOOP(pixel_copy_increment, width) \
DUFFS_LOOP8(pixel_copy_increment, width)
#else
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
/* 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; \
} \
}
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
/* 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 */
535
/* vi: set ts=4 sw=4 expandtab: */