summaryrefslogtreecommitdiff
path: root/src/mesa/main/imports.h
blob: 17a9bd09986b2140d95aad8549abbfcf09331126 (plain)
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
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
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
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
/*
 * Mesa 3-D graphics library
 *
 * Copyright (C) 1999-2008  Brian Paul   All Rights Reserved.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included
 * in all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
 * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 * OTHER DEALINGS IN THE SOFTWARE.
 */


/**
 * \file imports.h
 * Standard C library function wrappers.
 *
 * This file provides wrappers for all the standard C library functions
 * like malloc(), free(), printf(), getenv(), etc.
 */


#ifndef IMPORTS_H
#define IMPORTS_H


#include "compiler.h"
#include "glheader.h"
#include "errors.h"

#ifdef __cplusplus
extern "C" {
#endif


/**********************************************************************/
/** Memory macros */
/*@{*/

/** Allocate a structure of type \p T */
#define MALLOC_STRUCT(T)   (struct T *) malloc(sizeof(struct T))
/** Allocate and zero a structure of type \p T */
#define CALLOC_STRUCT(T)   (struct T *) calloc(1, sizeof(struct T))

/*@}*/


/*
 * For GL_ARB_vertex_buffer_object we need to treat vertex array pointers
 * as offsets into buffer stores.  Since the vertex array pointer and
 * buffer store pointer are both pointers and we need to add them, we use
 * this macro.
 * Both pointers/offsets are expressed in bytes.
 */
#define ADD_POINTERS(A, B)  ( (GLubyte *) (A) + (uintptr_t) (B) )


/**
 * Sometimes we treat GLfloats as GLints.  On x86 systems, moving a float
 * as a int (thereby using integer registers instead of FP registers) is
 * a performance win.  Typically, this can be done with ordinary casts.
 * But with gcc's -fstrict-aliasing flag (which defaults to on in gcc 3.0)
 * these casts generate warnings.
 * The following union typedef is used to solve that.
 */
typedef union { GLfloat f; GLint i; GLuint u; } fi_type;



/**********************************************************************
 * Math macros
 */

#define MAX_GLUSHORT	0xffff
#define MAX_GLUINT	0xffffffff

/* Degrees to radians conversion: */
#define DEG2RAD (M_PI/180.0)


/**
 * \name Work-arounds for platforms that lack C99 math functions
 */
/*@{*/
#if (!defined(_XOPEN_SOURCE) || (_XOPEN_SOURCE < 600)) && !defined(_ISOC99_SOURCE) \
   && (!defined(__STDC_VERSION__) || (__STDC_VERSION__ < 199901L)) \
   && (!defined(_MSC_VER) || (_MSC_VER < 1400))
#define acosf(f) ((float) acos(f))
#define asinf(f) ((float) asin(f))
#define atan2f(x,y) ((float) atan2(x,y))
#define atanf(f) ((float) atan(f))
#define ceilf(f) ((float) ceil(f))
#define cosf(f) ((float) cos(f))
#define coshf(f) ((float) cosh(f))
#define expf(f) ((float) exp(f))
#define exp2f(f) ((float) exp2(f))
#define floorf(f) ((float) floor(f))
#define logf(f) ((float) log(f))

#ifdef ANDROID
#define log2f(f) (logf(f) * (float) (1.0 / M_LN2))
#else
#define log2f(f) ((float) log2(f))
#endif

#define powf(x,y) ((float) pow(x,y))
#define sinf(f) ((float) sin(f))
#define sinhf(f) ((float) sinh(f))
#define sqrtf(f) ((float) sqrt(f))
#define tanf(f) ((float) tan(f))
#define tanhf(f) ((float) tanh(f))
#define acoshf(f) ((float) acosh(f))
#define asinhf(f) ((float) asinh(f))
#define atanhf(f) ((float) atanh(f))
#endif

#if defined(_MSC_VER) && (_MSC_VER < 1800)  /* Not req'd on VS2013 and above */
static inline float truncf(float x) { return x < 0.0f ? ceilf(x) : floorf(x); }
static inline float exp2f(float x) { return powf(2.0f, x); }
static inline float log2f(float x) { return logf(x) * 1.442695041f; }
static inline float asinhf(float x) { return logf(x + sqrtf(x * x + 1.0f)); }
static inline float acoshf(float x) { return logf(x + sqrtf(x * x - 1.0f)); }
static inline float atanhf(float x) { return (logf(1.0f + x) - logf(1.0f - x)) / 2.0f; }
static inline int isblank(int ch) { return ch == ' ' || ch == '\t'; }
#define strtoll(p, e, b) _strtoi64(p, e, b)
#define strcasecmp(s1, s2) _stricmp(s1, s2)
#endif
/*@}*/


/*
 * signbit() is a macro on Linux.  Not available on Windows.
 */
#ifndef signbit
#define signbit(x) ((x) < 0.0f)
#endif


/** single-precision inverse square root */
static inline float
INV_SQRTF(float x)
{
   /* XXX we could try Quake's fast inverse square root function here */
   return 1.0F / sqrtf(x);
}


/***
 *** LOG2: Log base 2 of float
 ***/
static inline GLfloat LOG2(GLfloat x)
{
#ifdef USE_IEEE
#if 0
   /* This is pretty fast, but not accurate enough (only 2 fractional bits).
    * Based on code from http://www.stereopsis.com/log2.html
    */
   const GLfloat y = x * x * x * x;
   const GLuint ix = *((GLuint *) &y);
   const GLuint exp = (ix >> 23) & 0xFF;
   const GLint log2 = ((GLint) exp) - 127;
   return (GLfloat) log2 * (1.0 / 4.0);  /* 4, because of x^4 above */
#endif
   /* Pretty fast, and accurate.
    * Based on code from http://www.flipcode.com/totd/
    */
   fi_type num;
   GLint log_2;
   num.f = x;
   log_2 = ((num.i >> 23) & 255) - 128;
   num.i &= ~(255 << 23);
   num.i += 127 << 23;
   num.f = ((-1.0f/3) * num.f + 2) * num.f - 2.0f/3;
   return num.f + log_2;
#else
   /*
    * NOTE: log_base_2(x) = log(x) / log(2)
    * NOTE: 1.442695 = 1/log(2).
    */
   return (GLfloat) (log(x) * 1.442695F);
#endif
}



/***
 *** IS_INF_OR_NAN: test if float is infinite or NaN
 ***/
#ifdef USE_IEEE
static inline int IS_INF_OR_NAN( float x )
{
   fi_type tmp;
   tmp.f = x;
   return !(int)((unsigned int)((tmp.i & 0x7fffffff)-0x7f800000) >> 31);
}
#elif defined(isfinite)
#define IS_INF_OR_NAN(x)        (!isfinite(x))
#elif defined(finite)
#define IS_INF_OR_NAN(x)        (!finite(x))
#elif defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
#define IS_INF_OR_NAN(x)        (!isfinite(x))
#else
#define IS_INF_OR_NAN(x)        (!finite(x))
#endif


/***
 *** CEILF: ceiling of float
 *** FLOORF: floor of float
 *** FABSF: absolute value of float
 *** LOGF: the natural logarithm (base e) of the value
 *** EXPF: raise e to the value
 *** LDEXPF: multiply value by an integral power of two
 *** FREXPF: extract mantissa and exponent from value
 ***/
#if defined(__gnu_linux__)
/* C99 functions */
#define CEILF(x)   ceilf(x)
#define FLOORF(x)  floorf(x)
#define FABSF(x)   fabsf(x)
#define LOGF(x)    logf(x)
#define EXPF(x)    expf(x)
#define LDEXPF(x,y)  ldexpf(x,y)
#define FREXPF(x,y)  frexpf(x,y)
#else
#define CEILF(x)   ((GLfloat) ceil(x))
#define FLOORF(x)  ((GLfloat) floor(x))
#define FABSF(x)   ((GLfloat) fabs(x))
#define LOGF(x)    ((GLfloat) log(x))
#define EXPF(x)    ((GLfloat) exp(x))
#define LDEXPF(x,y)  ((GLfloat) ldexp(x,y))
#define FREXPF(x,y)  ((GLfloat) frexp(x,y))
#endif


/**
 * Convert float to int by rounding to nearest integer, away from zero.
 */
static inline int IROUND(float f)
{
   return (int) ((f >= 0.0F) ? (f + 0.5F) : (f - 0.5F));
}


/**
 * Convert float to int64 by rounding to nearest integer.
 */
static inline GLint64 IROUND64(float f)
{
   return (GLint64) ((f >= 0.0F) ? (f + 0.5F) : (f - 0.5F));
}


/**
 * Convert positive float to int by rounding to nearest integer.
 */
static inline int IROUND_POS(float f)
{
   assert(f >= 0.0F);
   return (int) (f + 0.5F);
}


/**
 * Convert float to int using a fast method.  The rounding mode may vary.
 * XXX We could use an x86-64/SSE2 version here.
 */
static inline int F_TO_I(float f)
{
#if defined(USE_X86_ASM) && defined(__GNUC__) && defined(__i386__)
   int r;
   __asm__ ("fistpl %0" : "=m" (r) : "t" (f) : "st");
   return r;
#elif defined(USE_X86_ASM) && defined(_MSC_VER)
   int r;
   _asm {
	 fld f
	 fistp r
	}
   return r;
#else
   return IROUND(f);
#endif
}


/** Return (as an integer) floor of float */
static inline int IFLOOR(float f)
{
#if defined(USE_X86_ASM) && defined(__GNUC__) && defined(__i386__)
   /*
    * IEEE floor for computers that round to nearest or even.
    * 'f' must be between -4194304 and 4194303.
    * This floor operation is done by "(iround(f + .5) + iround(f - .5)) >> 1",
    * but uses some IEEE specific tricks for better speed.
    * Contributed by Josh Vanderhoof
    */
   int ai, bi;
   double af, bf;
   af = (3 << 22) + 0.5 + (double)f;
   bf = (3 << 22) + 0.5 - (double)f;
   /* GCC generates an extra fstp/fld without this. */
   __asm__ ("fstps %0" : "=m" (ai) : "t" (af) : "st");
   __asm__ ("fstps %0" : "=m" (bi) : "t" (bf) : "st");
   return (ai - bi) >> 1;
#elif defined(USE_IEEE)
   int ai, bi;
   double af, bf;
   fi_type u;
   af = (3 << 22) + 0.5 + (double)f;
   bf = (3 << 22) + 0.5 - (double)f;
   u.f = (float) af;  ai = u.i;
   u.f = (float) bf;  bi = u.i;
   return (ai - bi) >> 1;
#else
   int i = IROUND(f);
   return (i > f) ? i - 1 : i;
#endif
}


/** Return (as an integer) ceiling of float */
static inline int ICEIL(float f)
{
#if defined(USE_X86_ASM) && defined(__GNUC__) && defined(__i386__)
   /*
    * IEEE ceil for computers that round to nearest or even.
    * 'f' must be between -4194304 and 4194303.
    * This ceil operation is done by "(iround(f + .5) + iround(f - .5) + 1) >> 1",
    * but uses some IEEE specific tricks for better speed.
    * Contributed by Josh Vanderhoof
    */
   int ai, bi;
   double af, bf;
   af = (3 << 22) + 0.5 + (double)f;
   bf = (3 << 22) + 0.5 - (double)f;
   /* GCC generates an extra fstp/fld without this. */
   __asm__ ("fstps %0" : "=m" (ai) : "t" (af) : "st");
   __asm__ ("fstps %0" : "=m" (bi) : "t" (bf) : "st");
   return (ai - bi + 1) >> 1;
#elif defined(USE_IEEE)
   int ai, bi;
   double af, bf;
   fi_type u;
   af = (3 << 22) + 0.5 + (double)f;
   bf = (3 << 22) + 0.5 - (double)f;
   u.f = (float) af; ai = u.i;
   u.f = (float) bf; bi = u.i;
   return (ai - bi + 1) >> 1;
#else
   int i = IROUND(f);
   return (i < f) ? i + 1 : i;
#endif
}


/**
 * Is x a power of two?
 */
static inline int
_mesa_is_pow_two(int x)
{
   return !(x & (x - 1));
}

/**
 * Round given integer to next higer power of two
 * If X is zero result is undefined.
 *
 * Source for the fallback implementation is
 * Sean Eron Anderson's webpage "Bit Twiddling Hacks"
 * http://graphics.stanford.edu/~seander/bithacks.html
 *
 * When using builtin function have to do some work
 * for case when passed values 1 to prevent hiting
 * undefined result from __builtin_clz. Undefined
 * results would be different depending on optimization
 * level used for build.
 */
static inline int32_t
_mesa_next_pow_two_32(uint32_t x)
{
#if defined(__GNUC__) && \
	((__GNUC__ * 100 + __GNUC_MINOR__) >= 304) /* gcc 3.4 or later */
	uint32_t y = (x != 1);
	return (1 + y) << ((__builtin_clz(x - y) ^ 31) );
#else
	x--;
	x |= x >> 1;
	x |= x >> 2;
	x |= x >> 4;
	x |= x >> 8;
	x |= x >> 16;
	x++;
	return x;
#endif
}

static inline int64_t
_mesa_next_pow_two_64(uint64_t x)
{
#if defined(__GNUC__) && \
	((__GNUC__ * 100 + __GNUC_MINOR__) >= 304) /* gcc 3.4 or later */
	uint64_t y = (x != 1);
	if (sizeof(x) == sizeof(long))
		return (1 + y) << ((__builtin_clzl(x - y) ^ 63));
	else
		return (1 + y) << ((__builtin_clzll(x - y) ^ 63));
#else
	x--;
	x |= x >> 1;
	x |= x >> 2;
	x |= x >> 4;
	x |= x >> 8;
	x |= x >> 16;
	x |= x >> 32;
	x++;
	return x;
#endif
}


/*
 * Returns the floor form of binary logarithm for a 32-bit integer.
 */
static inline GLuint
_mesa_logbase2(GLuint n)
{
#if defined(__GNUC__) && \
   ((__GNUC__ * 100 + __GNUC_MINOR__) >= 304) /* gcc 3.4 or later */
   return (31 - __builtin_clz(n | 1));
#else
   GLuint pos = 0;
   if (n >= 1<<16) { n >>= 16; pos += 16; }
   if (n >= 1<< 8) { n >>=  8; pos +=  8; }
   if (n >= 1<< 4) { n >>=  4; pos +=  4; }
   if (n >= 1<< 2) { n >>=  2; pos +=  2; }
   if (n >= 1<< 1) {           pos +=  1; }
   return pos;
#endif
}


/**
 * Return 1 if this is a little endian machine, 0 if big endian.
 */
static inline GLboolean
_mesa_little_endian(void)
{
   const GLuint ui = 1; /* intentionally not static */
   return *((const GLubyte *) &ui);
}



/**********************************************************************
 * Functions
 */

extern void *
_mesa_align_malloc( size_t bytes, unsigned long alignment );

extern void *
_mesa_align_calloc( size_t bytes, unsigned long alignment );

extern void
_mesa_align_free( void *ptr );

extern void *
_mesa_align_realloc(void *oldBuffer, size_t oldSize, size_t newSize,
                    unsigned long alignment);

extern void *
_mesa_exec_malloc( GLuint size );

extern void 
_mesa_exec_free( void *addr );

extern void *
_mesa_realloc( void *oldBuffer, size_t oldSize, size_t newSize );


#ifndef FFS_DEFINED
#define FFS_DEFINED 1
#ifdef __GNUC__
#define ffs __builtin_ffs
#define ffsll __builtin_ffsll
#else
extern int ffs(int i);
extern int ffsll(long long int i);
#endif /*__ GNUC__ */
#endif /* FFS_DEFINED */


#if defined(__GNUC__) && ((__GNUC__ * 100 + __GNUC_MINOR__) >= 304) /* gcc 3.4 or later */
#define _mesa_bitcount(i) __builtin_popcount(i)
#define _mesa_bitcount_64(i) __builtin_popcountll(i)
#else
extern unsigned int
_mesa_bitcount(unsigned int n);
extern unsigned int
_mesa_bitcount_64(uint64_t n);
#endif

/**
 * Find the last (most significant) bit set in a word.
 *
 * Essentially ffs() in the reverse direction.
 */
static inline unsigned int
_mesa_fls(unsigned int n)
{
#if defined(__GNUC__) && ((__GNUC__ * 100 + __GNUC_MINOR__) >= 304)
   return n == 0 ? 0 : 32 - __builtin_clz(n);
#else
   unsigned int v = 1;

   if (n == 0)
      return 0;

   while (n >>= 1)
       v++;

   return v;
#endif
}

extern int
_mesa_round_to_even(float val);

extern GLhalfARB
_mesa_float_to_half(float f);

extern float
_mesa_half_to_float(GLhalfARB h);


extern void *
_mesa_bsearch( const void *key, const void *base, size_t nmemb, size_t size, 
               int (*compar)(const void *, const void *) );

extern char *
_mesa_getenv( const char *var );

extern char *
_mesa_strdup( const char *s );

extern float
_mesa_strtof( const char *s, char **end );

extern unsigned int
_mesa_str_checksum(const char *str);

extern int
_mesa_snprintf( char *str, size_t size, const char *fmt, ... ) PRINTFLIKE(3, 4);

extern int
_mesa_vsnprintf(char *str, size_t size, const char *fmt, va_list arg);


#if defined(_MSC_VER) && !defined(snprintf)
#define snprintf _snprintf
#endif


#ifdef __cplusplus
}
#endif


#endif /* IMPORTS_H */