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
|
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions
// are met:
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above copyright
// notice, this list of conditions and the following disclaimer in the
// documentation and/or other materials provided with the distribution.
// * Neither the name of NVIDIA CORPORATION nor the names of its
// contributors may be used to endorse or promote products derived
// from this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
// PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
// OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Copyright (c) 2008-2018 NVIDIA Corporation. All rights reserved.
// Copyright (c) 2004-2008 AGEIA Technologies, Inc. All rights reserved.
// Copyright (c) 2001-2004 NovodeX AG. All rights reserved.
#ifndef PSFOUNDATION_PSUNIXNEONAOS_H
#define PSFOUNDATION_PSUNIXNEONAOS_H
// no includes here! this file should be included from PxcVecMath.h only!!!
#if !COMPILE_VECTOR_INTRINSICS
#error Vector intrinsics should not be included when using scalar implementation.
#endif
// only ARM NEON compatible platforms should reach this
#include <arm_neon.h>
namespace physx
{
namespace shdfnd
{
namespace aos
{
typedef float32x2_t FloatV;
typedef float32x4_t Vec3V;
typedef float32x4_t Vec4V;
typedef uint32x4_t BoolV;
typedef float32x4_t QuatV;
typedef uint32x4_t VecU32V;
typedef int32x4_t VecI32V;
typedef uint16x8_t VecU16V;
typedef int16x8_t VecI16V;
typedef uint8x16_t VecU8V;
#define FloatVArg FloatV &
#define Vec3VArg Vec3V &
#define Vec4VArg Vec4V &
#define BoolVArg BoolV &
#define VecU32VArg VecU32V &
#define VecI32VArg VecI32V &
#define VecU16VArg VecU16V &
#define VecI16VArg VecI16V &
#define VecU8VArg VecU8V &
#define QuatVArg QuatV &
// KS - TODO - make an actual VecCrossV type for NEON
#define VecCrossV Vec3V
typedef VecI32V VecShiftV;
#define VecShiftVArg VecShiftV &
PX_ALIGN_PREFIX(16)
struct Mat33V
{
Mat33V()
{
}
Mat33V(const Vec3V& c0, const Vec3V& c1, const Vec3V& c2) : col0(c0), col1(c1), col2(c2)
{
}
Vec3V PX_ALIGN(16, col0);
Vec3V PX_ALIGN(16, col1);
Vec3V PX_ALIGN(16, col2);
} PX_ALIGN_SUFFIX(16);
PX_ALIGN_PREFIX(16)
struct Mat34V
{
Mat34V()
{
}
Mat34V(const Vec3V& c0, const Vec3V& c1, const Vec3V& c2, const Vec3V& c3) : col0(c0), col1(c1), col2(c2), col3(c3)
{
}
Vec3V PX_ALIGN(16, col0);
Vec3V PX_ALIGN(16, col1);
Vec3V PX_ALIGN(16, col2);
Vec3V PX_ALIGN(16, col3);
} PX_ALIGN_SUFFIX(16);
PX_ALIGN_PREFIX(16)
struct Mat43V
{
Mat43V()
{
}
Mat43V(const Vec4V& c0, const Vec4V& c1, const Vec4V& c2) : col0(c0), col1(c1), col2(c2)
{
}
Vec4V PX_ALIGN(16, col0);
Vec4V PX_ALIGN(16, col1);
Vec4V PX_ALIGN(16, col2);
} PX_ALIGN_SUFFIX(16);
PX_ALIGN_PREFIX(16)
struct Mat44V
{
Mat44V()
{
}
Mat44V(const Vec4V& c0, const Vec4V& c1, const Vec4V& c2, const Vec4V& c3) : col0(c0), col1(c1), col2(c2), col3(c3)
{
}
Vec4V PX_ALIGN(16, col0);
Vec4V PX_ALIGN(16, col1);
Vec4V PX_ALIGN(16, col2);
Vec4V PX_ALIGN(16, col3);
} PX_ALIGN_SUFFIX(16);
} // namespace aos
} // namespace shdfnd
} // namespace physx
#endif // PSFOUNDATION_PSUNIXNEONAOS_H
|