NASP/cuda-samples
85
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2026-10-23 21:28:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

add and update samples for CUDA 11.5

Browse Source
This commit is contained in:
Rutwik Choughule
2021-10-21 16:34:49 +05:30
parent 3342d604fe
commit 1f76a2d110
2796 changed files with 1511725 additions and 827 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
Samples/VFlockingD3D10/README.md Normal file
View File

@@ -0,0 +1,49 @@
# VFlockingD3D10 - VFlockingD3D10
## Description
The sample models formation of V-shaped flocks by big birds, such as geese and cranes. The algorithms of such flocking are borrowed from the paper "V-like formations in flocks of artificial birds" from Artificial Life, Vol. 14, No. 2, 2008. The sample has CPU- and GPU-based implementations. Press 'g' to toggle between them. The GPU-based simulation works many times faster than the CPU-based one. The printout in the console window reports the simulation time per step. Press 'r' to reset the initial distribution of birds.
## Key Concepts
Graphics Interop, Data Parallel Algorithms, Physically-Based Simulation, Performance Strategies
## Supported SM Architectures
[SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
Windows
## Supported CPU Architecture
x86_64
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaD3D10SetGLDevice, cudaGraphicsMapResources, cudaGraphicsUnmapResources, cudaGraphicsResourceGetMappedPointer, cudaGraphicsRegisterResource, cudaGraphicsGLRegisterBuffer, cudaGraphicsUnregisterResource
## Dependencies needed to build/run
[DirectX](../../README.md#directx)
## Prerequisites
Download and install the [CUDA Toolkit 11.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run
### Windows
The Windows samples are built using the Visual Studio IDE. Solution files (.sln) are provided for each supported version of Visual Studio, using the format:
```
*_vs<version>.sln - for Visual Studio <version>
```
Each individual sample has its own set of solution files in its directory:
To build/examine all the samples at once, the complete solution files should be used. To build/examine a single sample, the individual sample solution files should be used.
> **Note:** Some samples require that the Microsoft DirectX SDK (June 2010 or newer) be installed and that the VC++ directory paths are properly set up (**Tools > Options...**). Check DirectX Dependencies section for details."
## References (for more details)

1260
Samples/VFlockingD3D10/VFlockingD3D10.cpp Normal file
View File

File diff suppressed because it is too large Load Diff

45
Samples/VFlockingD3D10/VFlockingD3D10.h Normal file
View File

@@ -0,0 +1,45 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
*
* 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.
*/
#ifndef VFLOCKING_D3D10_H
#define VFLOCKING_D3D10_H
#pragma once
// simulation parameters
struct Params {
float alpha;
float upwashX;
float upwashY;
float wingspan;
float dX;
float dY;
float epsilon;
float lambda; // -0.1073f * wingspan ;
};
#endif

20
Samples/VFlockingD3D10/VFlockingD3D10_vs2017.sln Normal file
View File

@@ -0,0 +1,20 @@

Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 2017
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "VFlockingD3D10", "VFlockingD3D10_vs2017.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

116
Samples/VFlockingD3D10/VFlockingD3D10_vs2017.vcxproj Normal file
View File

@@ -0,0 +1,116 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>VFlockingD3D10_vs2017</RootNamespace>
<ProjectName>VFlockingD3D10</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<PropertyGroup Condition="'$(WindowsTargetPlatformVersion)'==''">
<LatestTargetPlatformVersion>$([Microsoft.Build.Utilities.ToolLocationHelper]::GetLatestSDKTargetPlatformVersion('Windows', '10.0'))</LatestTargetPlatformVersion>
<WindowsTargetPlatformVersion Condition="'$(WindowsTargetPlatformVersion)' == ''">$(LatestTargetPlatformVersion)</WindowsTargetPlatformVersion>
<TargetPlatformVersion>$(WindowsTargetPlatformVersion)</TargetPlatformVersion>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v141</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;d3d10.lib;d3dcompiler.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/VFlockingD3D10.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="VFlockingD3D10.cpp" />
<CudaCompile Include="VFlocking_kernel.cu" />
<ClCompile Include="..\..\Common\rendercheck_d3d10.cpp" />
<ClInclude Include="VFlockingD3D10.h" />
<ClInclude Include="..\..\Common\rendercheck_d3d10.h" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.targets" />
</ImportGroup>
</Project>

20
Samples/VFlockingD3D10/VFlockingD3D10_vs2019.sln Normal file
View File

@@ -0,0 +1,20 @@

Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 2019
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "VFlockingD3D10", "VFlockingD3D10_vs2019.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

112
Samples/VFlockingD3D10/VFlockingD3D10_vs2019.vcxproj Normal file
View File

@@ -0,0 +1,112 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>VFlockingD3D10_vs2019</RootNamespace>
<ProjectName>VFlockingD3D10</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v142</PlatformToolset>
<WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;d3d10.lib;d3dcompiler.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/VFlockingD3D10.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="VFlockingD3D10.cpp" />
<CudaCompile Include="VFlocking_kernel.cu" />
<ClCompile Include="..\..\Common\rendercheck_d3d10.cpp" />
<ClInclude Include="VFlockingD3D10.h" />
<ClInclude Include="..\..\Common\rendercheck_d3d10.h" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.targets" />
</ImportGroup>
</Project>

288
Samples/VFlockingD3D10/VFlocking_kernel.cu Normal file
View File

@@ -0,0 +1,288 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
*
* 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.
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <helper_cuda.h>
#include <helper_math.h>
#include <VFlockingD3D10.h>
#define PI 3.1415926536f
typedef unsigned int uint;
__device__ bool isInsideQuad_D(float2 pos0, float2 pos1, float width,
float height) {
if (fabs(pos0.x - pos1.x) < 0.5f * width &&
fabs(pos0.y - pos1.y) < 0.5f * height) {
return true;
} else {
return false;
}
}
__device__ bool isInsideBird(float2 pixel, float2 pos, float width,
float height, float radius) {
if (abs(pixel.x - pos.x) < 0.5f * width &&
abs(pixel.y - pos.y) < 0.5f * height ||
(pixel.x - pos.x) * (pixel.x - pos.x) +
(pixel.y - pos.y) * (pixel.y - pos.y) <
radius * radius) {
return true;
} else {
return false;
}
}
__global__ void cuda_kernel_update(float2 *newPos, float2 *curPos,
uint numBirds, bool *hasproxy,
bool *neighbors, bool *rightgoals,
bool *leftgoals, Params *params) {
uint i = blockIdx.x * blockDim.x + threadIdx.x;
if (i >= numBirds) {
return;
}
float minDist = 50000.f;
float2 dij = make_float2(0.f);
if (!hasproxy[i]) {
for (uint j = 0; j < numBirds; j++) {
if (j == i) {
continue;
}
if (leftgoals[i * numBirds + j]) {
dij = params->dX * normalize(curPos[j] - curPos[i]);
break;
}
}
} else {
bool collision = false;
for (uint j = 0; j < numBirds; j++) {
float d;
if (leftgoals[i * numBirds + j]) {
d = curPos[j].x - (params->wingspan + params->lambda) - curPos[i].x;
if (fabs(d) < fabs(minDist)) {
minDist = d;
}
}
if (rightgoals[i * numBirds + j]) {
d = curPos[j].x + (params->wingspan + params->lambda) - curPos[i].x;
if (fabs(d) < fabs(minDist)) {
minDist = d;
}
}
if (neighbors[i * numBirds + j] && !collision) {
if (curPos[j].y >= curPos[i].y &&
curPos[j].y < curPos[i].y + params->epsilon) {
dij.y = -params->dY;
collision = true;
}
}
}
if (fabs(minDist) <= params->dX) {
return;
}
dij.x = minDist > 0 ? params->dX : -params->dX;
}
newPos[i].x = curPos[i].x + dij.x;
newPos[i].y = curPos[i].y + dij.y;
}
__global__ void cuda_kernel_checktriples(float2 *pos, uint numBirds,
bool *hasproxy, bool *neighbors,
bool *rightgoals, bool *leftgoals,
uint3 *triples, Params *params) {
uint ith = blockIdx.x * blockDim.x + threadIdx.x;
if (ith >= numBirds * (numBirds - 1) * (numBirds - 2) / 6) {
return;
}
uint a[3];
a[0] = triples[ith].x;
a[1] = triples[ith].y;
a[2] = triples[ith].z;
uint i, j, x;
for (i = 0; i < 3; i++) {
for (j = 2; j > i; j--) {
if (pos[a[j - 1]].y > pos[a[j]].y) {
x = a[j - 1];
a[j - 1] = a[j];
a[j] = x;
}
}
}
if (hasproxy[a[0]]) {
float a2a1 = pos[a[2]].x - pos[a[1]].x;
if (fabs(a2a1) < 2.f * (params->wingspan + params->lambda))
if (a2a1 >= 0) {
if (leftgoals[a[0] * numBirds + a[2]]) {
leftgoals[a[0] * numBirds + a[2]] = false;
}
if (rightgoals[a[0] * numBirds + a[1]]) {
rightgoals[a[0] * numBirds + a[1]] = false;
}
} else {
if (leftgoals[a[0] * numBirds + a[1]]) {
leftgoals[a[0] * numBirds + a[1]] = false;
}
if (rightgoals[a[0] * numBirds + a[2]]) {
rightgoals[a[0] * numBirds + a[2]] = false;
}
}
} else {
if ((leftgoals[a[0] * numBirds + a[2]]) &&
(leftgoals[a[0] * numBirds + a[1]]))
if ((length(pos[a[1]] - pos[a[0]]) < length(pos[a[2]] - pos[a[0]]))) {
leftgoals[a[0] * numBirds + a[2]] = false;
} else {
leftgoals[a[0] * numBirds + a[1]] = false;
}
}
}
__global__ void cuda_kernel_checkpairs(float2 *pos, uint numBirds,
bool *hasproxy, bool *neighbors,
bool *rightgoals, bool *leftgoals,
uint2 *pairs, Params *params) {
uint i = blockIdx.x * blockDim.x + threadIdx.x;
if (i >= numBirds * (numBirds - 1) / 2) {
return;
}
uint front, back;
if (pos[pairs[i].y].y > pos[pairs[i].x].y) {
front = pairs[i].y;
back = pairs[i].x;
} else {
front = pairs[i].x;
back = pairs[i].y;
}
leftgoals[back * numBirds + front] = true;
rightgoals[back * numBirds + front] = true;
float2 stepback;
stepback.x = pos[front].x;
stepback.y = pos[front].y - 0.5f * params->upwashY;
if (isInsideQuad_D(
pos[back], stepback,
2.f * (params->wingspan + params->lambda + params->upwashX),
params->upwashY)) {
neighbors[back * numBirds + front] = true;
if (!hasproxy[back]) {
hasproxy[back] = true;
}
}
}
extern "C" void cuda_simulate(float2 *newPos, float2 *curPos, uint numBirds,
bool *d_hasproxy, bool *d_neighbors,
bool *d_leftgoals, bool *d_rightgoals,
uint2 *d_pairs, uint3 *d_triples,
Params *d_params) {
cudaError_t error = cudaSuccess;
float tempms;
static float ms = 0.f;
static uint step = 0;
int smallblockSize = 32, midblockSize = 128, bigblockSize = 32;
cudaEvent_t e_start, e_stop;
cudaEventCreate(&e_start);
cudaEventCreate(&e_stop);
cudaEventRecord(e_start, 0);
cudaMemset(d_leftgoals, 0, numBirds * numBirds * sizeof(bool));
cudaMemset(d_rightgoals, 0, numBirds * numBirds * sizeof(bool));
cudaMemset(d_hasproxy, 0, numBirds * sizeof(bool));
cudaMemset(d_neighbors, 0, numBirds * numBirds * sizeof(bool));
dim3 Db = dim3(bigblockSize);
dim3 Dg =
dim3((numBirds * (numBirds - 1) / 2 + bigblockSize - 1) / bigblockSize);
cuda_kernel_checkpairs<<<Dg, Db>>>(curPos, numBirds, d_hasproxy, d_neighbors,
d_rightgoals, d_leftgoals, d_pairs,
d_params);
Db = dim3(midblockSize);
Dg =
dim3((numBirds * (numBirds - 1) * (numBirds - 2) / 6 + bigblockSize - 1) /
bigblockSize);
cuda_kernel_checktriples<<<Dg, Db>>>(curPos, numBirds, d_hasproxy,
d_neighbors, d_rightgoals, d_leftgoals,
d_triples, d_params);
Db = dim3(smallblockSize);
Dg = dim3((numBirds + smallblockSize - 1) / smallblockSize);
cuda_kernel_update<<<Dg, Db>>>(newPos, curPos, numBirds, d_hasproxy,
d_neighbors, d_rightgoals, d_leftgoals,
d_params /*, d_pWingTips */);
cudaDeviceSynchronize();
cudaEventRecord(e_stop, 0);
cudaEventSynchronize(e_stop);
cudaEventElapsedTime(&tempms, e_start, e_stop);
ms += tempms;
if (!(step % 100) && step) {
printf("GPU, step %d \ntime per step %6.3f ms \n", step, ms / 100.f);
ms = 0.f;
}
step++;
error = cudaGetLastError();
if (error != cudaSuccess) {
printf("one of the cuda kernels failed to launch, error = %d\n", error);
}
}

5
Samples/VFlockingD3D10/data/ref_VFlockingD3D10.ppm Normal file
View File

File diff suppressed because one or more lines are too long