This repository has been archived by the owner on Feb 11, 2021. It is now read-only.
/
SDL_blit.h
546 lines (507 loc) · 14.9 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
#ifndef _SDL_blit_h
#define _SDL_blit_h
27
28
29
30
31
32
33
#ifdef __MMX__
#include <mmintrin.h>
#endif
#ifdef __SSE__
#include <xmmintrin.h>
#endif
34
#include "SDL_cpuinfo.h"
35
36
37
#include "SDL_endian.h"
/* The structure passed to the low level blit functions */
38
39
40
41
42
43
44
45
46
47
48
49
50
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;
SDL_PixelFormat *src;
Uint8 *table;
SDL_PixelFormat *dst;
51
Uint32 ckey, cmod;
52
53
54
} SDL_BlitInfo;
/* The type definition for the low level blit functions */
55
typedef void (*SDL_loblit) (SDL_BlitInfo * info);
56
57
/* Blit mapping definition */
58
59
60
61
62
typedef struct SDL_BlitMap
{
SDL_Surface *dst;
int identity;
Uint8 *table;
63
64
65
66
SDL_blit blit;
void *data;
Uint32 ckey; /* colorkey */
Uint32 cmod; /* ARGB modulation */
67
68
69
70
/* the version count matches the destination; mismatch indicates
an invalid mapping */
unsigned int format_version;
71
72
} SDL_BlitMap;
73
74
75
76
77
78
79
80
81
82
83
#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;
84
85
/* Functions found in SDL_blit.c */
86
extern int SDL_CalculateBlit(SDL_Surface * surface);
87
88
/* Functions found in SDL_blit_{0,1,N,A}.c */
89
90
91
92
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);
93
94
95
96
97
/*
* Useful macros for blitting routines
*/
98
99
100
#if defined(__GNUC__)
#define DECLARE_ALIGNED(t,v,a) t __attribute__((aligned(a))) v
#elif defined(_MSC_VER)
101
#define DECLARE_ALIGNED(t,v,a) __declspec(align(a)) t v
102
103
104
105
#else
#define DECLARE_ALIGNED(t,v,a) t v
#endif
106
107
108
109
110
111
#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? */
112
#define RGB_FROM_PIXEL(Pixel, fmt, r, g, b) \
113
{ \
114
115
116
r = (((Pixel&fmt->Rmask)>>fmt->Rshift)<<fmt->Rloss); \
g = (((Pixel&fmt->Gmask)>>fmt->Gshift)<<fmt->Gloss); \
b = (((Pixel&fmt->Bmask)>>fmt->Bshift)<<fmt->Bloss); \
117
}
118
#define RGB_FROM_RGB565(Pixel, r, g, b) \
119
{ \
120
121
122
r = (((Pixel&0xF800)>>11)<<3); \
g = (((Pixel&0x07E0)>>5)<<2); \
b = ((Pixel&0x001F)<<3); \
123
}
124
#define RGB_FROM_RGB555(Pixel, r, g, b) \
125
{ \
126
127
128
r = (((Pixel&0x7C00)>>10)<<3); \
g = (((Pixel&0x03E0)>>5)<<3); \
b = ((Pixel&0x001F)<<3); \
129
}
130
#define RGB_FROM_RGB888(Pixel, r, g, b) \
131
{ \
132
133
134
r = ((Pixel&0xFF0000)>>16); \
g = ((Pixel&0xFF00)>>8); \
b = (Pixel&0xFF); \
135
}
136
#define RETRIEVE_RGB_PIXEL(buf, bpp, Pixel) \
137
138
139
do { \
switch (bpp) { \
case 2: \
140
Pixel = *((Uint16 *)(buf)); \
141
142
143
144
145
break; \
\
case 3: { \
Uint8 *B = (Uint8 *)(buf); \
if(SDL_BYTEORDER == SDL_LIL_ENDIAN) { \
146
Pixel = B[0] + (B[1] << 8) + (B[2] << 16); \
147
} else { \
148
Pixel = (B[0] << 16) + (B[1] << 8) + B[2]; \
149
150
151
152
153
} \
} \
break; \
\
case 4: \
154
Pixel = *((Uint32 *)(buf)); \
155
156
157
break; \
\
default: \
158
Pixel = 0; /* appease gcc */ \
159
160
161
162
break; \
} \
} while(0)
163
#define DISEMBLE_RGB(buf, bpp, fmt, Pixel, r, g, b) \
164
165
166
do { \
switch (bpp) { \
case 2: \
167
Pixel = *((Uint16 *)(buf)); \
168
169
170
171
172
break; \
\
case 3: { \
Uint8 *B = (Uint8 *)buf; \
if(SDL_BYTEORDER == SDL_LIL_ENDIAN) { \
173
Pixel = B[0] + (B[1] << 8) + (B[2] << 16); \
174
} else { \
175
Pixel = (B[0] << 16) + (B[1] << 8) + B[2]; \
176
177
178
179
180
} \
} \
break; \
\
case 4: \
181
Pixel = *((Uint32 *)(buf)); \
182
183
184
break; \
\
default: \
185
Pixel = 0; /* prevent gcc from complaining */ \
186
187
break; \
} \
188
RGB_FROM_PIXEL(Pixel, fmt, r, g, b); \
189
190
191
} while(0)
/* Assemble R-G-B values into a specified pixel format and store them */
192
#define PIXEL_FROM_RGB(Pixel, fmt, r, g, b) \
193
{ \
194
Pixel = ((r>>fmt->Rloss)<<fmt->Rshift)| \
195
196
197
((g>>fmt->Gloss)<<fmt->Gshift)| \
((b>>fmt->Bloss)<<fmt->Bshift); \
}
198
#define RGB565_FROM_RGB(Pixel, r, g, b) \
199
{ \
200
Pixel = ((r>>3)<<11)|((g>>2)<<5)|(b>>3); \
201
}
202
#define RGB555_FROM_RGB(Pixel, r, g, b) \
203
{ \
204
Pixel = ((r>>3)<<10)|((g>>3)<<5)|(b>>3); \
205
}
206
#define RGB888_FROM_RGB(Pixel, r, g, b) \
207
{ \
208
Pixel = (r<<16)|(g<<8)|b; \
209
210
211
212
213
}
#define ASSEMBLE_RGB(buf, bpp, fmt, r, g, b) \
{ \
switch (bpp) { \
case 2: { \
214
Uint16 Pixel; \
215
\
216
217
PIXEL_FROM_RGB(Pixel, fmt, r, g, b); \
*((Uint16 *)(buf)) = Pixel; \
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
} \
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: { \
235
Uint32 Pixel; \
236
\
237
238
PIXEL_FROM_RGB(Pixel, fmt, r, g, b); \
*((Uint32 *)(buf)) = Pixel; \
239
240
241
242
243
244
245
246
247
} \
break; \
} \
}
#define ASSEMBLE_RGB_AMASK(buf, bpp, fmt, r, g, b, Amask) \
{ \
switch (bpp) { \
case 2: { \
Uint16 *bufp; \
248
Uint16 Pixel; \
249
250
\
bufp = (Uint16 *)buf; \
251
252
PIXEL_FROM_RGB(Pixel, fmt, r, g, b); \
*bufp = Pixel | (*bufp & Amask); \
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
} \
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; \
271
Uint32 Pixel; \
272
273
\
bufp = (Uint32 *)buf; \
274
275
PIXEL_FROM_RGB(Pixel, fmt, r, g, b); \
*bufp = Pixel | (*bufp & Amask); \
276
277
278
279
280
281
} \
break; \
} \
}
/* FIXME: Should we rescale alpha into 0..255 here? */
282
#define RGBA_FROM_PIXEL(Pixel, fmt, r, g, b, a) \
283
{ \
284
285
286
287
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; \
288
}
289
#define RGBA_FROM_8888(Pixel, fmt, r, g, b, a) \
290
{ \
291
292
293
294
r = (Pixel&fmt->Rmask)>>fmt->Rshift; \
g = (Pixel&fmt->Gmask)>>fmt->Gshift; \
b = (Pixel&fmt->Bmask)>>fmt->Bshift; \
a = (Pixel&fmt->Amask)>>fmt->Ashift; \
295
}
296
#define RGBA_FROM_RGBA8888(Pixel, r, g, b, a) \
297
{ \
298
299
300
301
r = (Pixel>>24); \
g = ((Pixel>>16)&0xFF); \
b = ((Pixel>>8)&0xFF); \
a = (Pixel&0xFF); \
302
}
303
#define RGBA_FROM_ARGB8888(Pixel, r, g, b, a) \
304
{ \
305
306
307
308
r = ((Pixel>>16)&0xFF); \
g = ((Pixel>>8)&0xFF); \
b = (Pixel&0xFF); \
a = (Pixel>>24); \
309
}
310
#define RGBA_FROM_ABGR8888(Pixel, r, g, b, a) \
311
{ \
312
313
314
315
r = (Pixel&0xFF); \
g = ((Pixel>>8)&0xFF); \
b = ((Pixel>>16)&0xFF); \
a = (Pixel>>24); \
316
}
317
#define DISEMBLE_RGBA(buf, bpp, fmt, Pixel, r, g, b, a) \
318
319
320
do { \
switch (bpp) { \
case 2: \
321
Pixel = *((Uint16 *)(buf)); \
322
323
324
325
326
break; \
\
case 3: {/* FIXME: broken code (no alpha) */ \
Uint8 *b = (Uint8 *)buf; \
if(SDL_BYTEORDER == SDL_LIL_ENDIAN) { \
327
Pixel = b[0] + (b[1] << 8) + (b[2] << 16); \
328
} else { \
329
Pixel = (b[0] << 16) + (b[1] << 8) + b[2]; \
330
331
332
333
334
} \
} \
break; \
\
case 4: \
335
Pixel = *((Uint32 *)(buf)); \
336
337
338
break; \
\
default: \
339
Pixel = 0; /* stop gcc complaints */ \
340
341
break; \
} \
342
343
RGBA_FROM_PIXEL(Pixel, fmt, r, g, b, a); \
Pixel &= ~fmt->Amask; \
344
345
346
} while(0)
/* FIXME: this isn't correct, especially for Alpha (maximum != 255) */
347
#define PIXEL_FROM_RGBA(Pixel, fmt, r, g, b, a) \
348
{ \
349
Pixel = ((r>>fmt->Rloss)<<fmt->Rshift)| \
350
351
((g>>fmt->Gloss)<<fmt->Gshift)| \
((b>>fmt->Bloss)<<fmt->Bshift)| \
352
((a>>fmt->Aloss)<<fmt->Ashift); \
353
354
355
356
357
}
#define ASSEMBLE_RGBA(buf, bpp, fmt, r, g, b, a) \
{ \
switch (bpp) { \
case 2: { \
358
Uint16 Pixel; \
359
\
360
361
PIXEL_FROM_RGBA(Pixel, fmt, r, g, b, a); \
*((Uint16 *)(buf)) = Pixel; \
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
} \
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: { \
379
Uint32 Pixel; \
380
\
381
382
PIXEL_FROM_RGBA(Pixel, fmt, r, g, b, a); \
*((Uint32 *)(buf)) = Pixel; \
383
384
385
386
387
} \
break; \
} \
}
388
/* Blend the RGB values of two Pixels based on a source alpha value */
389
390
391
392
393
394
395
#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)
396
/* Blend the RGB values of two Pixels based on a source alpha value */
397
398
399
400
401
402
403
404
405
406
407
408
409
#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)
410
/* This is a very useful loop for optimizing blitters */
411
412
413
#if defined(_MSC_VER) && (_MSC_VER == 1300)
/* There's a bug in the Visual C++ 7 optimizer when compiling this code */
#else
414
#define USE_DUFFS_LOOP
415
#endif
416
417
418
419
420
#ifdef USE_DUFFS_LOOP
/* 8-times unrolled loop */
#define DUFFS_LOOP8(pixel_copy_increment, width) \
{ int n = (width+7)/8; \
421
switch (width & 7) { \
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
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; \
437
switch (width & 3) { \
438
439
440
441
442
443
444
445
case 0: do { pixel_copy_increment; \
case 3: pixel_copy_increment; \
case 2: pixel_copy_increment; \
case 1: pixel_copy_increment; \
} while ( --n > 0 ); \
} \
}
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
476
477
478
479
480
481
482
483
484
485
486
/* 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 ); \
} \
} \
}
487
488
489
490
491
492
/* Use the 8-times version of the loop by default */
#define DUFFS_LOOP(pixel_copy_increment, width) \
DUFFS_LOOP8(pixel_copy_increment, width)
#else
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
/* 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; \
} \
}
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
/* 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 */
546
/* vi: set ts=4 sw=4 expandtab: */