xref: /third_party/mesa3d/src/util/rounding.h (revision bf215546)
1/*
2 * Copyright © 2015 Intel Corporation
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8 * and/or sell copies of the Software, and to permit persons to whom the
9 * Software is furnished to do so, subject to the following conditions:
10 *
11 * The above copyright notice and this permission notice (including the next
12 * paragraph) shall be included in all copies or substantial portions of the
13 * Software.
14 *
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
18 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
20 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
21 * IN THE SOFTWARE.
22 */
23
24#ifndef _ROUNDING_H
25#define _ROUNDING_H
26
27#include <limits.h>
28#include <stdint.h>
29#include <math.h>
30
31#if defined(__SSE__) || (defined(_M_IX86_FP) && (_M_IX86_FP >= 1)) || (defined(_M_X64) && !defined(_M_ARM64EC))
32#include <xmmintrin.h>
33#include <emmintrin.h>
34#endif
35
36#ifdef __SSE4_1__
37#include <smmintrin.h>
38#endif
39
40/* The C standard library has functions round()/rint()/nearbyint() that round
41 * their arguments according to the rounding mode set in the floating-point
42 * control register. While there are trunc()/ceil()/floor() functions that do
43 * a specific operation without modifying the rounding mode, there is no
44 * roundeven() in any version of C.
45 *
46 * Technical Specification 18661 (ISO/IEC TS 18661-1:2014) adds roundeven(),
47 * but it's unfortunately not implemented by glibc.
48 *
49 * This implementation differs in that it does not raise the inexact exception.
50 *
51 * We use rint() to implement these functions, with the assumption that the
52 * floating-point rounding mode has not been changed from the default Round
53 * to Nearest.
54 */
55
56/**
57 * \brief Rounds \c x to the nearest integer, with ties to the even integer.
58 */
59static inline float
60_mesa_roundevenf(float x)
61{
62#ifdef __SSE4_1__
63   float ret;
64   __m128 m = _mm_load_ss(&x);
65   m = _mm_round_ss(m, m, _MM_FROUND_CUR_DIRECTION | _MM_FROUND_NO_EXC);
66   _mm_store_ss(&ret, m);
67   return ret;
68#else
69   return rintf(x);
70#endif
71}
72
73/**
74 * \brief Rounds \c x to the nearest integer, with ties to the even integer.
75 */
76static inline double
77_mesa_roundeven(double x)
78{
79#ifdef __SSE4_1__
80   double ret;
81   __m128d m = _mm_load_sd(&x);
82   m = _mm_round_sd(m, m, _MM_FROUND_CUR_DIRECTION | _MM_FROUND_NO_EXC);
83   _mm_store_sd(&ret, m);
84   return ret;
85#else
86   return rint(x);
87#endif
88}
89
90/**
91 * \brief Rounds \c x to the nearest integer, with ties to the even integer,
92 * and returns the value as a long int.
93 */
94static inline long
95_mesa_lroundevenf(float x)
96{
97#if defined(__SSE__) || (defined(_M_IX86_FP) && (_M_IX86_FP >= 1)) || (defined(_M_X64) && !defined(_M_ARM64EC))
98#if LONG_MAX == INT64_MAX
99   return _mm_cvtss_si64(_mm_load_ss(&x));
100#elif LONG_MAX == INT32_MAX
101   return _mm_cvtss_si32(_mm_load_ss(&x));
102#else
103#error "Unsupported long size"
104#endif
105#else
106   return lrintf(x);
107#endif
108}
109
110/**
111 * \brief Rounds \c x to the nearest integer, with ties to the even integer,
112 * and returns the value as a long int.
113 */
114static inline long
115_mesa_lroundeven(double x)
116{
117#if defined(__SSE2__) || (defined(_M_IX86_FP) && (_M_IX86_FP >= 2)) || (defined(_M_X64) && !defined(_M_ARM64EC))
118#if LONG_MAX == INT64_MAX
119   return _mm_cvtsd_si64(_mm_load_sd(&x));
120#elif LONG_MAX == INT32_MAX
121   return _mm_cvtsd_si32(_mm_load_sd(&x));
122#else
123#error "Unsupported long size"
124#endif
125#else
126   return lrint(x);
127#endif
128}
129
130/**
131 * \brief Rounds \c x to the nearest integer, with ties to the even integer,
132 * and returns the value as an int64_t.
133 */
134static inline int64_t
135_mesa_i64roundevenf(float x)
136{
137#if LONG_MAX == INT64_MAX
138   return _mesa_lroundevenf(x);
139#elif LONG_MAX == INT32_MAX
140   return llrintf(x);
141#else
142#error "Unsupported long size"
143#endif
144}
145
146#endif
147