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
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
|
//
// 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.
#include "PxPhysics.h"
#include "PxVec4.h"
#include "PxVec3.h"
#include "PxVec2.h"
#include "PxMat33.h"
#include "PxStrideIterator.h"
namespace physx
{
template <typename T>
__device__ T* ptrOffset(T* p, PxU32 byteOffset)
{
return (T*)((unsigned char*)(p) + byteOffset);
}
#if __CUDA_ARCH__ < 200
__device__ PxU32 gOffset;
#else
__device__ __shared__ PxU32 gOffset;
#endif
// copies orientations and positions to the destination vertex
// buffer based on the validityBitmap state
extern "C" __global__ void updateInstancedVB(
PxVec3* destPositions,
PxVec3* destRotation0,
PxVec3* destRotation1,
PxVec3* destRotation2,
PxU32 destStride,
const PxVec4* srcPositions,
const PxMat33* srcRotations,
const PxU32* validParticleBitmap,
PxU32 validParticleRange)
{
if (!threadIdx.x)
gOffset = 0;
__syncthreads();
if (validParticleRange)
{
for (PxU32 w=threadIdx.x; w <= (validParticleRange) >> 5; w+=blockDim.x)
{
const PxU32 srcBaseIndex = w << 5;
// reserve space in the output vertex buffer based on
// population count of validity bitmap (avoids excess atomic ops)
PxU32 destIndex = atomicAdd(&gOffset, __popc(validParticleBitmap[w]));
for (PxU32 b=validParticleBitmap[w]; b; b &= b-1)
{
const PxU32 index = srcBaseIndex | __ffs(b)-1;
const PxU32 offset = destIndex*destStride;
*ptrOffset(destRotation0, offset) = srcRotations[index].column0;
*ptrOffset(destRotation1, offset) = srcRotations[index].column1;
*ptrOffset(destRotation2, offset) = srcRotations[index].column2;
PxVec3* p = ptrOffset(destPositions, offset);
p->x = srcPositions[index].x;
p->y = srcPositions[index].y;
p->z = srcPositions[index].z;
++destIndex;
}
}
}
}
// copies positions and alpha to the destination vertex buffer based on
// validity bitmap and particle life times
extern "C" __global__ void updateBillboardVB(
PxVec3* destPositions,
PxU8* destAlphas,
PxU32 destStride,
PxF32 fadingPeriod,
const PxVec4* srcPositions,
const PxReal* srcLifetimes,
const PxU32* validParticleBitmap,
PxU32 validParticleRange)
{
if (!threadIdx.x)
gOffset = 0;
__syncthreads();
if (validParticleRange)
{
for (PxU32 w=threadIdx.x; w <= (validParticleRange) >> 5; w+=blockDim.x)
{
const PxU32 srcBaseIndex = w << 5;
// reserve space in the output vertex buffer based on
// population count of validity bitmap (avoids excess atomic ops)
PxU32 destIndex = atomicAdd(&gOffset, __popc(validParticleBitmap[w]));
for (PxU32 b=validParticleBitmap[w]; b; b &= b-1)
{
PxU32 index = srcBaseIndex | __ffs(b)-1;
const PxU32 offset = destIndex*destStride;
// copy position
PxVec3* p = ptrOffset(destPositions, offset);
p->x = srcPositions[index].x;
p->y = srcPositions[index].y;
p->z = srcPositions[index].z;
// update alpha
if (srcLifetimes)
{
PxU8 lifetime = 0;
if(srcLifetimes[index] >= fadingPeriod)
lifetime = 255;
else
{
if(srcLifetimes[index] <= 0.0f)
lifetime = 0;
else
lifetime = static_cast<PxU8>(srcLifetimes[index] * 255 / fadingPeriod);
}
destAlphas[destIndex*4] = lifetime;
}
++destIndex;
}
}
}
}
}
|