CIS565-Fall-2014 · RTCassidy1 · Sep 21, 2014 · Sep 21, 2014
diff --git a/Part1/PROJ_NIX/makefile b/Part1/PROJ_NIX/makefile
@@ -4,7 +4,7 @@ NVCC     = nvcc -m64
 CC       = gcc -m64
 CPPC     = g++ -m64
 
-CUDA_FLAGS = -I/usr/local/cuda/samples/common/inc -I/usr/local/cuda/include
+CUDA_FLAGS = -I/Developer/NVIDIA/CUDA-6.5/extras/CUPTI/include/GL -I/usr/local/cuda/samples/common/inc -I/usr/local/cuda/include 
 
 LFLAGS = -lglut -lGL -lGLEW 
 
@@ -19,7 +19,7 @@ glslUtility.o: ../src/glslUtility.cpp
 utilities.o: ../src/utilities.cpp
 	$(CPPC) $(CUDA_FLAGS) ../src/utilities.cpp -c
 
-main.o: ../src/main.cpp ../src/glslUtility.h ../src/kernel.h ../src/utilities.h ../src/main.h
+main.o: ../src/main.cpp ../src/glslUtility.h ../src/kernel.h ../src/utilities.h ../src/main.h /Developer/NVIDIA/CUDA-6.5/extras/CUPTI/include/GL/gl.h
 	$(CPPC) $(CUDA_FLAGS) ../src/main.cpp -c
 
 565simulator: main.o kernel.o glslUtility.o utilities.o

diff --git a/Part1/PROJ_WIN/CIS565_PROJ_1/CIS565_PROJ_1.vcxproj b/Part1/PROJ_WIN/CIS565_PROJ_1/CIS565_PROJ_1.vcxproj
@@ -30,7 +30,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
   <ImportGroup Label="ExtensionSettings">
-    <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 5.5.props" />
+    <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 6.5.props" />
   </ImportGroup>
   <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
     <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
@@ -46,12 +46,12 @@
     <ClCompile>
       <WarningLevel>Level3</WarningLevel>
       <Optimization>Disabled</Optimization>
-      <AdditionalIncludeDirectories>$(SolutionDir)/shared/glew/include/;$(SolutionDir)/shared/freeglut/include/;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+      <AdditionalIncludeDirectories>C:\Users\Robert Cassidy\Documents\Visual Studio 2010\Projects\Project-1\Part1\PROJ_WIN\shared\freeglut\include\GL;C:\Users\Robert Cassidy\Documents\Visual Studio 2010\Projects\Project-1\Part1\PROJ_WIN\shared\glew\include\GL;$(SolutionDir)/shared/glew/include/;$(SolutionDir)/shared/freeglut/include/;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
       <PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
     </ClCompile>
     <Link>
       <GenerateDebugInformation>true</GenerateDebugInformation>
-      <AdditionalLibraryDirectories>$(SolutionDir)/shared/glew/lib;$(SolutionDir)/shared/freeglut/lib;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
+      <AdditionalLibraryDirectories>C:\Users\Robert Cassidy\Documents\Visual Studio 2010\Projects\Project-1\Part1\PROJ_WIN\shared\freeglut\lib;C:\Users\Robert Cassidy\Documents\Visual Studio 2010\Projects\Project-1\Part1\PROJ_WIN\shared\glew\lib;$(SolutionDir)/shared/glew/lib;$(SolutionDir)/shared/freeglut/lib;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
       <AdditionalDependencies>opengl32.lib;glut32.lib;glew32.lib;freeglut.lib;cudart.lib;%(AdditionalDependencies)</AdditionalDependencies>
       <SubSystem>Console</SubSystem>
       <EntryPointSymbol>mainCRTStartup</EntryPointSymbol>
@@ -62,7 +62,7 @@
       <GPUDebugInfo>true</GPUDebugInfo>
       <GenerateLineInfo>true</GenerateLineInfo>
       <HostDebugInfo>true</HostDebugInfo>
-      <CodeGeneration>compute_10,sm_10;compute_20,sm_20;compute_30,sm_30</CodeGeneration>
+      <CodeGeneration>compute_20,sm_20;compute_30,sm_30</CodeGeneration>
     </CudaCompile>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
@@ -95,7 +95,7 @@
   <ItemGroup>
     <CudaCompile Include="..\..\src\kernel.cu">
       <FileType>Document</FileType>
-      <CodeGeneration Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">compute_10,sm_10;compute_20,sm_20</CodeGeneration>
+      <CodeGeneration Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">compute_20,sm_20</CodeGeneration>
     </CudaCompile>
   </ItemGroup>
   <ItemGroup>
@@ -114,6 +114,6 @@
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">
-    <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 5.5.targets" />
+    <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 6.5.targets" />
   </ImportGroup>
 </Project>
diff --git a/Part1/PROJ_WIN/src/kernel.cu.deps b/Part1/PROJ_WIN/src/kernel.cu.deps
diff --git a/Part1/src/kernel.cu b/Part1/src/kernel.cu
@@ -9,7 +9,7 @@
 dim3 threadsPerBlock(blockSize);
 
 int numObjects;
-const float planetMass = 3e8;
+const __device__ float planetMass = 3e8;
 const __device__ float starMass = 5e10;
 
 const float scene_scale = 2e2; //size of the height map in simulation space
@@ -87,21 +87,64 @@ __global__ void generateCircularVelArray(int time, int N, glm::vec3 * arr, glm::
 //		 HINT : You may want to write a helper function that will help you 
 //              calculate the acceleration contribution of a single body.
 //		 REMEMBER : F = (G * m_a * m_b) / (r_ab ^ 2)
+
 __device__  glm::vec3 accelerate(int N, glm::vec4 my_pos, glm::vec4 * their_pos)
 {
-    return glm::vec3(0.0f);
+	glm::vec3 results(0.0f);
+	glm::vec4 r(0.0f);
+	float distR;
+	float denom;
+	for(int i = 0; i < N ; i++){
+		r.x = their_pos[i].x - my_pos.x;
+		r.y = their_pos[i].y - my_pos.y;
+		r.z = their_pos[i].z - my_pos.z;
+		distR = r.x * r.x + r.y * r.y + r.z * r.z; 
+		//denominator = 1 / (dist^2)^2/3
+		if(distR < .25){ //to avoid planets shooting off into oblivion when they get near each other.
+			continue;
+		}
+		denom = 1.0f / sqrt(distR * distR * distR);
+		results.x += G * planetMass * denom * r.x;
+		results.y += G * planetMass * denom * r.y;
+		results.z += G * planetMass * denom * r.z;
+	}
+	//Planet Mass too
+	r.x = 0 - my_pos.x;
+	r.y = 0 - my_pos.y;
+	r.z = 0 - my_pos.z;
+	distR = r.x * r.x + r.y * r.y + r.z * r.z;
+	//denominator = 1 / (dist^2 + EPSILON)^3/2
+	if(distR > .25){ //to avoid planets shooting off into oblivion when they get near each other.
+		denom = 1.0f / sqrt(distR * distR * distR);
+		results.x += G * starMass * denom * r.x;
+		results.y += G * starMass * denom * r.y;
+		results.z += G * starMass * denom * r.z;
+	}
+	return results;
 }
 
 // TODO : update the acceleration of each body
 __global__ void updateF(int N, float dt, glm::vec4 * pos, glm::vec3 * vel, glm::vec3 * acc)
 {
-	// FILL IN HERE
+	int index = threadIdx.x + (blockIdx.x * blockDim.x);
+	acc[index] = accelerate(N,pos[index],pos);
+	//acc[index] = glm::vec3(1.0f);
+	return;
 }
 
 // TODO : update velocity and position using a simple Euler integration scheme
 __global__ void updateS(int N, float dt, glm::vec4 * pos, glm::vec3 * vel, glm::vec3 * acc)
 {
-	// FILL IN HERE
+	int index = threadIdx.x + (blockIdx.x * blockDim.x);
+	vel[index].x = vel[index].x + dt * acc[index].x;
+	vel[index].y = vel[index].y + dt * acc[index].y;
+	vel[index].z = vel[index].z + dt * acc[index].z;
+
+	pos[index].x = pos[index].x + dt * vel[index].x;
+	pos[index].y = pos[index].y + dt * vel[index].y;
+	pos[index].z = pos[index].z + dt * vel[index].z;
+	return;
+
 }
 
 // Update the vertex buffer object
@@ -137,7 +180,8 @@ __global__ void sendToPBO(int N, glm::vec4 * pos, float4 * pbo, int width, int h
     float c_scale_h = height / s_scale;
 
     glm::vec3 color(0.05, 0.15, 0.3);
-    glm::vec3 acc = accelerate(N, glm::vec4((x-w2)/c_scale_w,(y-h2)/c_scale_h,0,1), pos);
+    //glm::vec3 acc = accelerate(N, glm::vec4((x-w2)/c_scale_w,(y-h2)/c_scale_h,0,1), pos);
+	glm::vec3 acc(1.0f); //Changed this to speed it up since not being used in homework
 
     if(x<width && y<height)
     {
@@ -179,7 +223,12 @@ void initCuda(int N)
 // TODO : Using the functions you wrote above, write a function that calls the CUDA kernels to update a single sim step
 void cudaNBodyUpdateWrapper(float dt)
 {
-	// FILL IN HERE
+	int threads = 128;
+	int blocks = numObjects / threads + 1;
+	updateF<<<blocks, threads>>>(numObjects, dt, dev_pos, dev_vel, dev_acc);
+	updateS<<<blocks, threads>>>(numObjects, dt, dev_pos, dev_vel, dev_acc);
+
+	return;
 }
 
 void cudaUpdateVBO(float * vbodptr, int width, int height)

diff --git a/Part1/src/main.cpp b/Part1/src/main.cpp
@@ -4,7 +4,7 @@
 
 #include "main.h"
 
-#define N_FOR_VIS 5000
+#define N_FOR_VIS 6000
 #define DT 0.2
 #define VISUALIZE 1
 //-------------------------------

diff --git a/Part3/cusamatrixmath.sln b/Part3/cusamatrixmath.sln
@@ -0,0 +1,20 @@
+
+Microsoft Visual Studio Solution File, Format Version 11.00
+# Visual Studio 2010
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "cusamatrixmath", "cusamatrixmath\cusamatrixmath.vcxproj", "{2A8A854C-1E6A-44C5-B4B6-E66CCCC6E99D}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Win32 = Debug|Win32
+		Release|Win32 = Release|Win32
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{2A8A854C-1E6A-44C5-B4B6-E66CCCC6E99D}.Debug|Win32.ActiveCfg = Debug|Win32
+		{2A8A854C-1E6A-44C5-B4B6-E66CCCC6E99D}.Debug|Win32.Build.0 = Debug|Win32
+		{2A8A854C-1E6A-44C5-B4B6-E66CCCC6E99D}.Release|Win32.ActiveCfg = Release|Win32
+		{2A8A854C-1E6A-44C5-B4B6-E66CCCC6E99D}.Release|Win32.Build.0 = Release|Win32
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+EndGlobal
diff --git a/Part3/cusamatrixmath/cudaMat4.h b/Part3/cusamatrixmath/cudaMat4.h
@@ -0,0 +1,25 @@
+// CIS565 CUDA Raytracer: A parallel raytracer for Patrick Cozzi's CIS565: GPU Computing at the University of Pennsylvania
+// Written by Yining Karl Li, Copyright (c) 2012 University of Pennsylvania
+// This file includes code from:
+//       Yining Karl Li's TAKUA Render, a massively parallel pathtracing renderer: http://www.yiningkarlli.com
+
+#ifndef CUDAMAT4_H
+#define CUDAMAT4_H
+
+#include "glm/glm.hpp"
+#include <cuda_runtime.h>
+
+struct cudaMat3{
+	glm::vec3 x;
+	glm::vec3 y;
+	glm::vec3 z;
+};
+
+struct cudaMat4{
+	glm::vec4 x;
+	glm::vec4 y;
+	glm::vec4 z;
+	glm::vec4 w;
+};
+
+#endif
diff --git a/Part3/cusamatrixmath/cusamatrixmath.vcxproj b/Part3/cusamatrixmath/cusamatrixmath.vcxproj
@@ -0,0 +1,74 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <ItemGroup Label="ProjectConfigurations">
+    <ProjectConfiguration Include="Debug|Win32">
+      <Configuration>Debug</Configuration>
+      <Platform>Win32</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Release|Win32">
+      <Configuration>Release</Configuration>
+      <Platform>Win32</Platform>
+    </ProjectConfiguration>
+  </ItemGroup>
+  <ItemGroup>
+    <CudaCompile Include="matrix_math.cu" />
+  </ItemGroup>
+  <ItemGroup>
+    <ClInclude Include="matrix_math.h" />
+  </ItemGroup>
+  <PropertyGroup Label="Globals">
+    <ProjectGuid>{2A8A854C-1E6A-44C5-B4B6-E66CCCC6E99D}</ProjectGuid>
+    <RootNamespace>cusamatrixmath</RootNamespace>
+  </PropertyGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+    <ConfigurationType>Application</ConfigurationType>
+    <UseDebugLibraries>true</UseDebugLibraries>
+    <CharacterSet>MultiByte</CharacterSet>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+    <ConfigurationType>Application</ConfigurationType>
+    <UseDebugLibraries>false</UseDebugLibraries>
+    <WholeProgramOptimization>true</WholeProgramOptimization>
+    <CharacterSet>MultiByte</CharacterSet>
+  </PropertyGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+  <ImportGroup Label="ExtensionSettings">
+    <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 6.5.props" />
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <PropertyGroup Label="UserMacros" />
+  <PropertyGroup />
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+    <ClCompile>
+      <WarningLevel>Level3</WarningLevel>
+      <Optimization>Disabled</Optimization>
+    </ClCompile>
+    <Link>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+      <AdditionalDependencies>cudart.lib;%(AdditionalDependencies)</AdditionalDependencies>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+    <ClCompile>
+      <WarningLevel>Level3</WarningLevel>
+      <Optimization>MaxSpeed</Optimization>
+      <FunctionLevelLinking>true</FunctionLevelLinking>
+      <IntrinsicFunctions>true</IntrinsicFunctions>
+    </ClCompile>
+    <Link>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+      <EnableCOMDATFolding>true</EnableCOMDATFolding>
+      <OptimizeReferences>true</OptimizeReferences>
+    </Link>
+  </ItemDefinitionGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+  <ImportGroup Label="ExtensionTargets">
+    <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 6.5.targets" />
+  </ImportGroup>
+</Project>
diff --git a/Part3/cusamatrixmath/cusamatrixmath.vcxproj.filters b/Part3/cusamatrixmath/cusamatrixmath.vcxproj.filters
@@ -0,0 +1,27 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <ItemGroup>
+    <Filter Include="Source Files">
+      <UniqueIdentifier>{4FC737F1-C7A5-4376-A066-2A32D752A2FF}</UniqueIdentifier>
+      <Extensions>cpp;c;cc;cxx;def;odl;idl;hpj;bat;asm;asmx</Extensions>
+    </Filter>
+    <Filter Include="Header Files">
+      <UniqueIdentifier>{93995380-89BD-4b04-88EB-625FBE52EBFB}</UniqueIdentifier>
+      <Extensions>h;hpp;hxx;hm;inl;inc;xsd</Extensions>
+    </Filter>
+    <Filter Include="Resource Files">
+      <UniqueIdentifier>{67DA6AB6-F800-4c08-8B7A-83BB121AAD01}</UniqueIdentifier>
+      <Extensions>rc;ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe;resx;tiff;tif;png;wav;mfcribbon-ms</Extensions>
+    </Filter>
+  </ItemGroup>
+  <ItemGroup>
+    <CudaCompile Include="matrix_math.cu">
+      <Filter>Source Files</Filter>
+    </CudaCompile>
+  </ItemGroup>
+  <ItemGroup>
+    <ClInclude Include="matrix_math.h">
+      <Filter>Source Files</Filter>
+    </ClInclude>
+  </ItemGroup>
+</Project>
diff --git a/Part3/cusamatrixmath/glslUtility.h b/Part3/cusamatrixmath/glslUtility.h
@@ -0,0 +1,21 @@
+// GLSL Utility: A utility class for loading GLSL shaders, for Patrick Cozzi's CIS565: GPU Computing at the University of Pennsylvania
+// Written by Varun Sampath and Patrick Cozzi, Copyright (c) 2012 University of Pennsylvania
+
+#ifndef GLSLUTILITY_H_
+#define GLSLUTILITY_H_
+
+#ifdef __APPLE__
+	#include <GL/glfw.h>
+#else
+	#include <GL/glew.h>
+#endif
+
+namespace glslUtility
+{
+
+GLuint createProgram(const char *vertexShaderPath, const char *fragmentShaderPath, const char *attributeLocations[], GLuint numberOfLocations);
+GLuint createProgram(const char *vertexShaderPath, const char *geometryShaderPath, const char *fragmentShaderPath, const char *attributeLocations[], GLuint numberOfLocations);
+
+}
+
+#endif
diff --git a/Part3/cusamatrixmath/kernel.h b/Part3/cusamatrixmath/kernel.h
@@ -0,0 +1,18 @@
+#ifndef KERNEL_H
+#define KERNEL_H
+
+#include <stdio.h>
+#include <thrust/random.h>
+#include <cuda.h>
+#include <cmath>
+
+#define blockSize 128
+#define checkCUDAErrorWithLine(msg) checkCUDAError(msg, __LINE__)
+#define SHARED 0
+
+void checkCUDAError(const char *msg, int line);
+void cudaNBodyUpdateWrapper(float dt);
+void initCuda(int N);
+void cudaUpdatePBO(float4 * pbodptr, int width, int height);
+void cudaUpdateVBO(float * vbodptr, int width, int height);
+#endif