blob: 4b25c842b9f9fa106d3501fb090e3c08c2644681 (
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
|
#ifndef _DEFLOAT16_H
#define _DEFLOAT16_H
/*-------------------------------------------------------------------------
* drawElements Base Portability Library
* -------------------------------------
*
* Copyright 2014 The Android Open Source Project
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*
*//*!
* \file
* \brief 16-bit floating-point math.
*//*--------------------------------------------------------------------*/
#include "deDefs.h"
#include "deMath.h"
DE_BEGIN_EXTERN_C
typedef deUint16 deFloat16;
#if defined(DE_DEPRECATED_TYPES)
typedef deFloat16 DEfloat16;
#endif
/*--------------------------------------------------------------------*//*!
* \brief Convert 32-bit floating point number to 16 bit.
* \param val32 Input value.
* \return Converted 16-bit floating-point value.
*//*--------------------------------------------------------------------*/
deFloat16 deFloat32To16 (float val32);
deFloat16 deFloat32To16Round (float val32, deRoundingMode mode);
void deFloat16_selfTest (void);
deFloat16 deFloat64To16 (double val64);
deFloat16 deFloat64To16Round (double val64, deRoundingMode mode);
/*--------------------------------------------------------------------*//*!
* \brief Convert 16-bit floating point number to 32 bit.
* \param val16 Input value.
* \return Converted 32-bit floating-point value.
*//*--------------------------------------------------------------------*/
float deFloat16To32 (deFloat16 val16);
/*--------------------------------------------------------------------*//*!
* \brief Convert 16-bit floating point number to 64 bit.
* \param val16 Input value.
* \return Converted 64-bit floating-point value.
*//*--------------------------------------------------------------------*/
double deFloat16To64 (deFloat16 val16);
DE_INLINE deBool deHalfIsPositiveZero(deFloat16 x)
{
return deFloat16To32(x) == 0 && (x >> 15) == 0;
}
DE_INLINE deBool deHalfIsNegativeZero(deFloat16 x)
{
return deFloat16To32(x) == 0 && (x >> 15) != 0;
}
static const deFloat16 deFloat16SignalingNaN = 0x7c01;
static const deFloat16 deFloat16QuietNaN = 0x7e01;
DE_INLINE deBool deHalfIsIEEENaN(deFloat16 x)
{
deUint16 e = (deUint16)((x & 0x7c00u) >> 10);
deUint16 m = (x & 0x03ffu);
return e == 0x1f && m != 0;
}
DE_INLINE deBool deHalfIsSignalingNaN(deFloat16 x)
{
return deHalfIsIEEENaN(x) && (x & (1u << 9)) == 0;
}
DE_INLINE deBool deHalfIsQuietNaN(deFloat16 x)
{
return deHalfIsIEEENaN(x) && (x & (1u << 9)) != 0;
}
DE_END_EXTERN_C
#endif /* _DEFLOAT16_H */
|
