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
|
/**************************************************************************
*
* Copyright 2008 Tungsten Graphics, Inc., Cedar Park, Texas.
* 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, sub license, 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 (including the
* next paragraph) 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 NON-INFRINGEMENT.
* IN NO EVENT SHALL TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS 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.
*
**************************************************************************/
#include "util/u_math.h"
#include "util/u_cpu_detect.h"
/** 2^x, for x in [-1.0, 1.0) */
float pow2_table[POW2_TABLE_SIZE];
static void
init_pow2_table(void)
{
int i;
for (i = 0; i < POW2_TABLE_SIZE; i++)
pow2_table[i] = (float) pow(2.0, (i - POW2_TABLE_OFFSET) / POW2_TABLE_SCALE);
}
/** log2(x), for x in [1.0, 2.0) */
float log2_table[LOG2_TABLE_SIZE];
static void
init_log2_table(void)
{
unsigned i;
for (i = 0; i < LOG2_TABLE_SIZE; i++)
log2_table[i] = (float) log2(1.0 + i * (1.0 / LOG2_TABLE_SCALE));
}
/**
* One time init for math utilities.
*/
void
util_init_math(void)
{
static boolean initialized = FALSE;
if (!initialized) {
init_pow2_table();
init_log2_table();
initialized = TRUE;
}
}
/**
* Fetches the contents of the fpstate (mxcsr on x86) register.
*
* On platforms without support for it just returns 0.
*/
unsigned
util_fpstate_get(void)
{
unsigned mxcsr = 0;
#if defined(PIPE_ARCH_X86) || defined(PIPE_ARCH_X86_64)
if (util_cpu_caps.has_sse) {
mxcsr = __builtin_ia32_stmxcsr();
}
#endif
return mxcsr;
}
/**
* Make sure that the fp treats the denormalized floating
* point numbers as zero.
*
* This is the behavior required by D3D10. OpenGL doesn't care.
*/
unsigned
util_fpstate_set_denorms_to_zero(unsigned current_mxcsr)
{
#if defined(PIPE_ARCH_X86) || defined(PIPE_ARCH_X86_64)
#define MXCSR_DAZ (1 << 6) /* Enable denormals are zero mode */
#define MXCSR_FTZ (1 << 15) /* Enable flush to zero mode */
if (util_cpu_caps.has_sse) {
current_mxcsr |= MXCSR_FTZ;
if (util_cpu_caps.has_sse3) {
current_mxcsr |= MXCSR_DAZ;
}
util_fpstate_set(current_mxcsr);
}
#endif
return current_mxcsr;
}
/**
* Set the state of the fpstate (mxcsr on x86) register.
*
* On platforms without support for it's a noop.
*/
void
util_fpstate_set(unsigned mxcsr)
{
#if defined(PIPE_ARCH_X86) || defined(PIPE_ARCH_X86_64)
if (util_cpu_caps.has_sse) {
__builtin_ia32_ldmxcsr(mxcsr);
}
#endif
}
|
