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 (C) 2010 PCSX4ALL Team *
* Copyright (C) 2010 Unai *
* *
* This program is free software; you can redistribute it and/or modify *
* it under the terms of the GNU General Public License as published by *
* the Free Software Foundation; either version 2 of the License, or *
* (at your option) any later version. *
* *
* This program 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 General Public License for more details. *
* *
* You should have received a copy of the GNU General Public License *
* along with this program; if not, write to the *
* Free Software Foundation, Inc., *
* 51 Franklin Street, Fifth Floor, Boston, MA 02111-1307 USA. *
***************************************************************************/
#ifndef FIXED_H
#define FIXED_H
typedef s32 fixed;
#ifdef GPU_TABLE_10_BITS
#define TABLE_BITS 10
#else
#define TABLE_BITS 16
#endif
#define FIXED_BITS 16
#define fixed_ZERO ((fixed)0)
#define fixed_ONE ((fixed)1<<FIXED_BITS)
#define fixed_TWO ((fixed)2<<FIXED_BITS)
#define fixed_HALF ((fixed)((1<<FIXED_BITS)>>1))
// big precision inverse table.
s32 s_invTable[(1<<TABLE_BITS)];
INLINE fixed i2x(const int _x) { return ((_x)<<FIXED_BITS); }
INLINE fixed x2i(const fixed _x) { return ((_x)>>FIXED_BITS); }
/*
INLINE u32 Log2(u32 _a)
{
u32 c = 0; // result of log2(v) will go here
if (_a & 0xFFFF0000) { _a >>= 16; c |= 16; }
if (_a & 0xFF00) { _a >>= 8; c |= 8; }
if (_a & 0xF0) { _a >>= 4; c |= 4; }
if (_a & 0xC) { _a >>= 2; c |= 2; }
if (_a & 0x2) { _a >>= 1; c |= 1; }
return c;
}
*/
#ifdef __arm__
INLINE u32 Log2(u32 x) { u32 res; asm("clz %0,%1" : "=r" (res) : "r" (x)); return 32-res; }
#else
INLINE u32 Log2(u32 x) { u32 i = 0; for ( ; x > 0; ++i, x >>= 1); return i - 1; }
#endif
#ifdef GPU_TABLE_10_BITS
INLINE void xInv (const fixed _b, s32& iFactor_, s32& iShift_)
{
u32 uD = (_b<0) ? -_b : _b ;
u32 uLog = Log2(uD);
uLog = uLog>(TABLE_BITS-1) ? uLog-(TABLE_BITS-1) : 0;
u32 uDen = uD>>uLog;
iFactor_ = s_invTable[uDen];
iFactor_ = (_b<0) ? -iFactor_ :iFactor_;
iShift_ = 15+uLog;
}
#else
INLINE void xInv (const fixed _b, s32& iFactor_, s32& iShift_)
{
u32 uD = (_b<0) ? -_b : _b;
if(uD>1)
{
u32 uLog = Log2(uD);
uLog = uLog>(TABLE_BITS-1) ? uLog-(TABLE_BITS-1) : 0;
u32 uDen = (uD>>uLog)-1;
iFactor_ = s_invTable[uDen];
iFactor_ = (_b<0) ? -iFactor_ :iFactor_;
iShift_ = 15+uLog;
}
else
{
iFactor_=_b;
iShift_ = 0;
}
}
#endif
INLINE fixed xInvMulx (const fixed _a, const s32 _iFact, const s32 _iShift)
{
#ifdef __arm__
s64 res;
asm ("smull %Q0, %R0, %1, %2" : "=&r" (res) : "r"(_a) , "r"(_iFact));
return fixed(res>>_iShift);
#else
return fixed( ((s64)(_a)*(s64)(_iFact))>>(_iShift) );
#endif
}
INLINE fixed xLoDivx (const fixed _a, const fixed _b)
{
s32 iFact, iShift;
xInv(_b, iFact, iShift);
return xInvMulx(_a, iFact, iShift);
}
///////////////////////////////////////////////////////////////////////////
template<typename T>
INLINE T Min2 (const T _a, const T _b) { return (_a<_b)?_a:_b; }
template<typename T>
INLINE T Min3 (const T _a, const T _b, const T _c) { return Min2(Min2(_a,_b),_c); }
///////////////////////////////////////////////////////////////////////////
template<typename T>
INLINE T Max2 (const T _a, const T _b) { return (_a>_b)?_a:_b; }
template<typename T>
INLINE T Max3 (const T _a, const T _b, const T _c) { return Max2(Max2(_a,_b),_c); }
///////////////////////////////////////////////////////////////////////////
#endif //FIXED_H
|
