source: mainline/softfloat/generic/conversion.c@ d9f51ccc

lfn serial ticket/834-toolchain-update topic/msim-upgrade topic/simplify-dev-export
Last change on this file since d9f51ccc was 1266543, checked in by Josef Cejka <malyzelenyhnus@…>, 19 years ago

32 bit float division added.
Some small bugs fixed.
Code cleanup.

  • Property mode set to 100644
File size: 3.6 KB
Line 
1/*
2 * Copyright (C) 2005 Josef Cejka
3 * All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
8 *
9 * - Redistributions of source code must retain the above copyright
10 * notice, this list of conditions and the following disclaimer.
11 * - Redistributions in binary form must reproduce the above copyright
12 * notice, this list of conditions and the following disclaimer in the
13 * documentation and/or other materials provided with the distribution.
14 * - The name of the author may not be used to endorse or promote products
15 * derived from this software without specific prior written permission.
16 *
17 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
18 * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
19 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
20 * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
21 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
22 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
23 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
24 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
25 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
26 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
27 */
28
29#include "sftypes.h"
30#include "conversion.h"
31
32float64 convertFloat32ToFloat64(float32 a)
33{
34 float64 result;
35 __u64 frac;
36
37 result.parts.sign = a.parts.sign;
38 result.parts.fraction = a.parts.fraction;
39 result.parts.fraction <<= (FLOAT64_FRACTION_SIZE - FLOAT32_FRACTION_SIZE );
40
41 if ((isFloat32Infinity(a))||(isFloat32NaN(a))) {
42 result.parts.exp = 0x7FF;
43 /* TODO; check if its correct for SigNaNs*/
44 return result;
45 };
46
47 result.parts.exp = a.parts.exp + ( (int)FLOAT64_BIAS - FLOAT32_BIAS );
48 if (a.parts.exp == 0) {
49 /* normalize denormalized numbers */
50
51 if (result.parts.fraction == 0ll) { /* fix zero */
52 result.parts.exp = 0ll;
53 return result;
54 }
55
56 frac = result.parts.fraction;
57
58 while (!(frac & (0x10000000000000ll))) {
59 frac <<= 1;
60 --result.parts.exp;
61 };
62
63 ++result.parts.exp;
64 result.parts.fraction = frac;
65 };
66
67 return result;
68
69};
70
71float32 convertFloat64ToFloat32(float64 a)
72{
73 float32 result;
74 __s32 exp;
75 __u64 frac;
76
77 result.parts.sign = a.parts.sign;
78
79 if (isFloat64NaN(a)) {
80
81 result.parts.exp = 0xFF;
82
83 if (isFloat64SigNaN(a)) {
84 result.parts.fraction = 0x800000; /* set first bit of fraction nonzero */
85 return result;
86 }
87
88 result.parts.fraction = 0x1; /* fraction nonzero but its first bit is zero */
89 return result;
90 };
91
92 if (isFloat64Infinity(a)) {
93 result.parts.fraction = 0;
94 result.parts.exp = 0xFF;
95 return result;
96 };
97
98 exp = (int)a.parts.exp - FLOAT64_BIAS + FLOAT32_BIAS;
99
100 if (exp >= 0xFF) {
101 /*FIXME: overflow*/
102 result.parts.fraction = 0;
103 result.parts.exp = 0xFF;
104 return result;
105
106 } else if (exp <= 0 ) {
107
108 /* underflow or denormalized */
109
110 result.parts.exp = 0;
111
112 exp *= -1;
113 if (exp > FLOAT32_FRACTION_SIZE ) {
114 /* FIXME: underflow */
115 result.parts.fraction = 0;
116 return result;
117 };
118
119 /* denormalized */
120
121 frac = a.parts.fraction;
122 frac |= 0x10000000000000ll; /* denormalize and set hidden bit */
123
124 frac >>= (FLOAT64_FRACTION_SIZE - FLOAT32_FRACTION_SIZE + 1);
125
126 while (exp > 0) {
127 --exp;
128 frac >>= 1;
129 };
130 result.parts.fraction = frac;
131
132 return result;
133 };
134
135 result.parts.exp = exp;
136 result.parts.fraction = a.parts.fraction >> (FLOAT64_FRACTION_SIZE - FLOAT32_FRACTION_SIZE);
137 return result;
138};
139
Note: See TracBrowser for help on using the repository browser.