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
|
/*
===============================================================================
This C header file is part of the SoftFloat IEC/IEEE Floating-point
Arithmetic Package, Release 2.
Written by John R. Hauser. This work was made possible in part by the
International Computer Science Institute, located at Suite 600, 1947 Center
Street, Berkeley, California 94704. Funding was partially provided by the
National Science Foundation under grant MIP-9311980. The original version
of this code was written as part of a project to build a fixed-point vector
processor in collaboration with the University of California at Berkeley,
overseen by Profs. Nelson Morgan and John Wawrzynek. More information
is available through the Web page `http://HTTP.CS.Berkeley.EDU/~jhauser/
arithmetic/softfloat.html'.
THIS SOFTWARE IS DISTRIBUTED AS IS, FOR FREE. Although reasonable effort
has been made to avoid it, THIS SOFTWARE MAY CONTAIN FAULTS THAT WILL AT
TIMES RESULT IN INCORRECT BEHAVIOR. USE OF THIS SOFTWARE IS RESTRICTED TO
PERSONS AND ORGANIZATIONS WHO CAN AND WILL TAKE FULL RESPONSIBILITY FOR ANY
AND ALL LOSSES, COSTS, OR OTHER PROBLEMS ARISING FROM ITS USE.
Derivative works are acceptable, even for commercial purposes, so long as
(1) they include prominent notice that the work is derivative, and (2) they
include prominent notice akin to these three paragraphs for those parts of
this code that are retained.
===============================================================================
*/
/*
-------------------------------------------------------------------------------
Software IEC/IEEE floating-point types.
-------------------------------------------------------------------------------
*/
typedef unsigned int float32;
typedef struct {
unsigned int high, low;
} float64;
/*
-------------------------------------------------------------------------------
Software IEC/IEEE floating-point underflow tininess-detection mode.
-------------------------------------------------------------------------------
*/
extern int float_detect_tininess;
enum {
float_tininess_after_rounding = 0,
float_tininess_before_rounding = 1
};
/*
-------------------------------------------------------------------------------
Software IEC/IEEE floating-point rounding mode.
-------------------------------------------------------------------------------
*/
extern int float_rounding_mode;
enum {
float_round_nearest_even = 0,
float_round_to_zero = 1,
float_round_up = 2,
float_round_down = 3
};
/*
-------------------------------------------------------------------------------
Software IEC/IEEE floating-point exception flags.
-------------------------------------------------------------------------------
*/
extern int float_exception_flags;
enum {
float_flag_inexact = 1,
float_flag_divbyzero = 2,
float_flag_underflow = 4,
float_flag_overflow = 8,
float_flag_invalid = 16
};
/*
-------------------------------------------------------------------------------
Routine to raise any or all of the software IEC/IEEE floating-point
exception flags.
-------------------------------------------------------------------------------
*/
void float_raise( int );
/*
-------------------------------------------------------------------------------
Software IEC/IEEE integer-to-floating-point conversion routines.
-------------------------------------------------------------------------------
*/
float32 int32_to_float32( int );
float64 int32_to_float64( int );
/*
-------------------------------------------------------------------------------
Software IEC/IEEE single-precision conversion routines.
-------------------------------------------------------------------------------
*/
int float32_to_int32( float32 );
int float32_to_int32_round_to_zero( float32 );
float64 float32_to_float64( float32 );
/*
-------------------------------------------------------------------------------
Software IEC/IEEE single-precision operations.
-------------------------------------------------------------------------------
*/
float32 float32_round_to_int( float32 );
float32 float32_add( float32, float32 );
float32 float32_sub( float32, float32 );
float32 float32_mul( float32, float32 );
float32 float32_div( float32, float32 );
float32 float32_rem( float32, float32 );
float32 float32_sqrt( float32 );
int float32_eq( float32, float32 );
int float32_le( float32, float32 );
int float32_lt( float32, float32 );
int float32_eq_signaling( float32, float32 );
int float32_le_quiet( float32, float32 );
int float32_lt_quiet( float32, float32 );
int float32_is_signaling_nan( float32 );
/*
-------------------------------------------------------------------------------
Software IEC/IEEE double-precision conversion routines.
-------------------------------------------------------------------------------
*/
int float64_to_int32( float64 );
int float64_to_int32_round_to_zero( float64 );
float32 float64_to_float32( float64 );
/*
-------------------------------------------------------------------------------
Software IEC/IEEE double-precision operations.
-------------------------------------------------------------------------------
*/
float64 float64_round_to_int( float64 );
float64 float64_add( float64, float64 );
float64 float64_sub( float64, float64 );
float64 float64_mul( float64, float64 );
float64 float64_div( float64, float64 );
float64 float64_rem( float64, float64 );
float64 float64_sqrt( float64 );
int float64_eq( float64, float64 );
int float64_le( float64, float64 );
int float64_lt( float64, float64 );
int float64_eq_signaling( float64, float64 );
int float64_le_quiet( float64, float64 );
int float64_lt_quiet( float64, float64 );
int float64_is_signaling_nan( float64 );
|
