summaryrefslogtreecommitdiffstats
path: root/src/mesa/pipe/p_util.h
blob: 69b69a3c67d6c290d325664f907d67d7d5e4e7c2 (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

/*
 * Mesa 3-D graphics library
 * Version:  6.5.2
 *
 * Copyright (C) 1999-2006  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
 * BRIAN PAUL 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.
 */


#ifndef P_UTIL_H
#define P_UTIL_H

#include "p_compiler.h"
#include <math.h>

#define CALLOC_STRUCT(T)   (struct T *) calloc(1, sizeof(struct T))

#define CLAMP( X, MIN, MAX )  ( (X)<(MIN) ? (MIN) : ((X)>(MAX) ? (MAX) : (X)) )
#define MIN2( A, B )   ( (A)<(B) ? (A) : (B) )
#define MAX2( A, B )   ( (A)>(B) ? (A) : (B) )

#define Elements(x) sizeof(x)/sizeof(*(x))

#if defined(__MSC__) && defined(__WIN32__)
static INLINE unsigned ffs( unsigned u )
{
   unsigned i;

   __asm bsf eax, [u]
   __asm mov [i], eax

   return i;
}
#endif

union fi {
   float f;
   int i;
   unsigned ui;
};

#define UBYTE_TO_FLOAT( ub ) ((float)(ub) / 255.0F)

#define IEEE_0996 0x3f7f0000	/* 0.996 or so */

/* This function/macro is sensitive to precision.  Test very carefully
 * if you change it!
 */
#define UNCLAMPED_FLOAT_TO_UBYTE(UB, F)					\
        do {								\
           union fi __tmp;						\
           __tmp.f = (F);						\
           if (__tmp.i < 0)						\
              UB = (ubyte) 0;						\
           else if (__tmp.i >= IEEE_0996)				\
              UB = (ubyte) 255;					\
           else {							\
              __tmp.f = __tmp.f * (255.0f/256.0f) + 32768.0f;		\
              UB = (ubyte) __tmp.i;					\
           }								\
        } while (0)



static INLINE unsigned pack_ub4( unsigned char b0,
				 unsigned char b1,
				 unsigned char b2,
				 unsigned char b3 )
{
   return ((((unsigned int)b0) << 0) |
	   (((unsigned int)b1) << 8) |
	   (((unsigned int)b2) << 16) |
	   (((unsigned int)b3) << 24));
}

static INLINE unsigned fui( float f )
{
   union fi fi;
   fi.f = f;
   return fi.ui;
}

static INLINE unsigned char float_to_ubyte( float f )
{
   unsigned char ub;
   UNCLAMPED_FLOAT_TO_UBYTE(ub, f);
   return ub;
}

static INLINE unsigned pack_ui32_float4( float a,
					 float b, 
					 float d, 
					 float c )
{
   return pack_ub4( float_to_ubyte(a),
		    float_to_ubyte(b),
		    float_to_ubyte(c),
		    float_to_ubyte(d) );
}

#define COPY_4V( DST, SRC )         \
do {                                \
   (DST)[0] = (SRC)[0];             \
   (DST)[1] = (SRC)[1];             \
   (DST)[2] = (SRC)[2];             \
   (DST)[3] = (SRC)[3];             \
} while (0)


#define COPY_4FV( DST, SRC )  COPY_4V(DST, SRC)


#define ASSIGN_4V( DST, V0, V1, V2, V3 ) \
do {                                     \
   (DST)[0] = (V0);                      \
   (DST)[1] = (V1);                      \
   (DST)[2] = (V2);                      \
   (DST)[3] = (V3);                      \
} while (0)


static INLINE int ifloor(float f)
{
   int ai, bi;
   double af, bf;
   union fi 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;
}


#if defined(__GNUC__) && defined(__i386__) 
static INLINE int iround(float f)
{
   int r;
   __asm__ ("fistpl %0" : "=m" (r) : "t" (f) : "st");
   return r;
}
#elif defined(__MSC__) && defined(__WIN32__)
static INLINE int iround(float f)
{
   int r;
   _asm {
	 fld f
	 fistp r
	}
   return r;
}
#else
#define IROUND(f)  ((int) (((f) >= 0.0F) ? ((f) + 0.5F) : ((f) - 0.5F)))
#endif


/* Could maybe have an inline version of this?
 */
#if defined(__GNUC__)
#define FABSF(x)   fabsf(x)
#else
#define FABSF(x)   ((float) fabs(x))
#endif

/* Pretty fast, and accurate.
 * Based on code from http://www.flipcode.com/totd/
 */
static INLINE float LOG2(float val)
{
   union fi num;
   int log_2;

   num.f = val;
   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;
}


#endif