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
|
/**
* @file llv4math.h
* @brief LLV4* class header file - vector processor enabled math
*
* $LicenseInfo:firstyear=2007&license=viewerlgpl$
* Second Life Viewer Source Code
* Copyright (C) 2010, Linden Research, Inc.
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation;
* version 2.1 of the License only.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*
* Linden Research, Inc., 945 Battery Street, San Francisco, CA 94111 USA
* $/LicenseInfo$
*/
#ifndef LL_LLV4MATH_H
#define LL_LLV4MATH_H
// *NOTE: We do not support SSE acceleration on Windows builds.
// Our minimum specification for the viewer includes 1 GHz Athlon processors,
// which covers the Athlon Thunderbird series that does not support SSE.
//
// Our header files include statements like this
// const F32 HAVOK_TIMESTEP = 1.f / 45.f;
// This creates "globals" that are included in each .obj file. If a single
// .cpp file has SSE code generation turned on (eg, llviewerjointmesh_sse.cpp)
// these globals will be initialized using SSE instructions. This causes SL
// to crash before main() on processors without SSE. Untangling all these
// headers/variables is too much work for the small performance gains of
// vectorization.
//
// Therefore we only support vectorization on builds where the everything is
// built with SSE or Altivec. See https://jira.secondlife.com/browse/VWR-1610
// and https://jira.lindenlab.com/browse/SL-47720 for details.
//
// Sorry the code is such a mess. JC
//-----------------------------------------------------------------------------
//-----------------------------------------------------------------------------
// LLV4MATH - GNUC
//-----------------------------------------------------------------------------
//-----------------------------------------------------------------------------
#if LL_GNUC && __GNUC__ >= 4 && __SSE__
#define LL_VECTORIZE 1
#if LL_DARWIN
#include <Accelerate/Accelerate.h>
#include <xmmintrin.h>
typedef vFloat V4F32;
#else
#include <xmmintrin.h>
typedef float V4F32 __attribute__((vector_size(16)));
#endif
#endif
#if LL_GNUC
#define LL_LLV4MATH_ALIGN_PREFIX
#define LL_LLV4MATH_ALIGN_POSTFIX __attribute__((aligned(16)))
#endif
//-----------------------------------------------------------------------------
//-----------------------------------------------------------------------------
// LLV4MATH - MSVC
//-----------------------------------------------------------------------------
//-----------------------------------------------------------------------------
// Only vectorize if the entire Windows build uses SSE.
// _M_IX86_FP is set when SSE code generation is turned on, and I have
// confirmed this in VS2003, VS2003 SP1, and VS2005. JC
#if LL_MSVC && _M_IX86_FP
#define LL_VECTORIZE 1
#include <xmmintrin.h>
typedef __m128 V4F32;
#endif
#if LL_MSVC
#define LL_LLV4MATH_ALIGN_PREFIX __declspec(align(16))
#define LL_LLV4MATH_ALIGN_POSTFIX
#endif
//-----------------------------------------------------------------------------
//-----------------------------------------------------------------------------
// LLV4MATH - default - no vectorization
//-----------------------------------------------------------------------------
//-----------------------------------------------------------------------------
#if !LL_VECTORIZE
#define LL_VECTORIZE 0
struct V4F32 { F32 __pad__[4]; };
inline F32 llv4lerp(F32 a, F32 b, F32 w) { return ( b - a ) * w + a; }
#endif
#ifndef LL_LLV4MATH_ALIGN_PREFIX
# define LL_LLV4MATH_ALIGN_PREFIX
#endif
#ifndef LL_LLV4MATH_ALIGN_POSTFIX
# define LL_LLV4MATH_ALIGN_POSTFIX
#endif
//-----------------------------------------------------------------------------
//-----------------------------------------------------------------------------
// LLV4MATH
//-----------------------------------------------------------------------------
//-----------------------------------------------------------------------------
#define LLV4_NUM_AXIS 4
class LLV4Vector3;
class LLV4Matrix3;
class LLV4Matrix4;
#endif
|
