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 © 2015 Intel Corporation
*
* 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, sublicense,
* 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 NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS 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.
*/
#ifndef _ROUNDING_H
#define _ROUNDING_H
#include <math.h>
#include <limits.h>
#ifdef __x86_64__
#include <xmmintrin.h>
#include <emmintrin.h>
#endif
#ifdef __SSE4_1__
#include <smmintrin.h>
#endif
/* The C standard library has functions round()/rint()/nearbyint() that round
* their arguments according to the rounding mode set in the floating-point
* control register. While there are trunc()/ceil()/floor() functions that do
* a specific operation without modifying the rounding mode, there is no
* roundeven() in any version of C.
*
* Technical Specification 18661 (ISO/IEC TS 18661-1:2014) adds roundeven(),
* but it's unfortunately not implemented by glibc.
*
* This implementation differs in that it does not raise the inexact exception.
*
* We use rint() to implement these functions, with the assumption that the
* floating-point rounding mode has not been changed from the default Round
* to Nearest.
*/
/**
* \brief Rounds \c x to the nearest integer, with ties to the even integer.
*/
static inline float
_mesa_roundevenf(float x)
{
#ifdef __SSE4_1__
float ret;
__m128 m = _mm_load_ss(&x);
m = _mm_round_ss(m, m, _MM_FROUND_CUR_DIRECTION | _MM_FROUND_NO_EXC);
_mm_store_ss(&ret, m);
return ret;
#else
return rintf(x);
#endif
}
/**
* \brief Rounds \c x to the nearest integer, with ties to the even integer.
*/
static inline double
_mesa_roundeven(double x)
{
#ifdef __SSE4_1__
double ret;
__m128d m = _mm_load_sd(&x);
m = _mm_round_sd(m, m, _MM_FROUND_CUR_DIRECTION | _MM_FROUND_NO_EXC);
_mm_store_sd(&ret, m);
return ret;
#else
return rint(x);
#endif
}
/**
* \brief Rounds \c x to the nearest integer, with ties to the even integer,
* and returns the value as a long int.
*/
static inline long
_mesa_lroundevenf(float x)
{
#ifdef __x86_64__
#if LONG_BIT == 64
return _mm_cvtss_si64(_mm_load_ss(&x));
#elif LONG_BIT == 32 || defined(_WIN32)
return _mm_cvtss_si32(_mm_load_ss(&x));
#else
#error "Unsupported or undefined LONG_BIT"
#endif
#else
return lrintf(x);
#endif
}
/**
* \brief Rounds \c x to the nearest integer, with ties to the even integer,
* and returns the value as a long int.
*/
static inline long
_mesa_lroundeven(double x)
{
#ifdef __x86_64__
#if LONG_BIT == 64
return _mm_cvtsd_si64(_mm_load_sd(&x));
#elif LONG_BIT == 32 || defined(_WIN32)
return _mm_cvtsd_si32(_mm_load_sd(&x));
#else
#error "Unsupported or undefined LONG_BIT"
#endif
#else
return lrint(x);
#endif
}
#endif
|
