Project_1 finished

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.$(Platform).user.props')" Label="LocalAppDataPlatform" />
@@ -114,6 +114,6 @@
   </ItemGroup>
   <Import Project="$(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>

Part1/PROJ_WIN/CIS565_PROJ_1/CIS565_PROJ_1.vcxproj.user

@@ -1,3 +1,8 @@
 <?xml version="1.0" encoding="utf-8"?>
 <Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+    <LocalDebuggerEnvironment>
+    </LocalDebuggerEnvironment>
+    <DebuggerFlavor>WindowsLocalDebugger</DebuggerFlavor>
+  </PropertyGroup>
 </Project>

Part1/src/kernel.cu

@@ -89,19 +89,47 @@ __global__ void generateCircularVelArray(int time, int N, glm::vec3 * arr, glm::
 //		 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);
+	int index = (blockIdx.x * blockDim.x) + threadIdx.x;
+	glm::vec3 r;
+	//float mass = my_pos.z; 
+	glm::vec3 acc = glm::vec3(0.0f,0.0f,0.0f);
+	glm::vec3 pos(my_pos.x, my_pos.y, my_pos.z);
+	float l = glm::length(pos);
+	for(int i = 0;i < N; i++)
+	{
+		if(i != index)
+		{
+			r = glm::vec3(their_pos[i].x-my_pos.x, their_pos[i].y-my_pos.y, their_pos[i].z-my_pos.z);
+			float l = glm::length(r);
+			glm::vec3 mag = r / l;
+			acc +=  (float)( (float)their_pos[i].w / powf(l * l + ZERO_ABSORPTION_EPSILON * ZERO_ABSORPTION_EPSILON,3/2)) * mag;
+			//acc +=  r * (float) (their_pos[i].w / (l* l * l + EPSILON)) ;
+		}
+	}
+	acc += (float)(  (float)starMass / powf(l * l + ZERO_ABSORPTION_EPSILON * ZERO_ABSORPTION_EPSILON,3/2)) * (-pos)/glm::length(-pos); 
+	//acc +=  (-pos) * (float)(starMass / ( s * s * s + EPSILON )) ; 
+    return (float)G * acc;
 }
 
 // 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 = (blockIdx.x * blockDim.x) + threadIdx.x;
+    if(index < N)
+    {
+		acc[index] =  accelerate(N, pos[index], pos) ;
+    }
 }
 
 // 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 = (blockIdx.x * blockDim.x) + threadIdx.x;
+    if(index < N)
+    {	
+		pos[index] += glm::vec4(vel[index].x, vel[index].y, vel[index].z, 0.0f) * dt; 
+		vel[index] += acc[index] * dt;
+    }
 }
 
 // Update the vertex buffer object
@@ -179,7 +207,10 @@ 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
+	dim3 fullBlocksPerGrid((int)ceil(float(numObjects)/float(blockSize)));
+	updateF<<<fullBlocksPerGrid, blockSize>>>( numObjects, dt, dev_pos, dev_vel, dev_acc);
+	updateS<<<fullBlocksPerGrid, blockSize>>>( numObjects, dt, dev_pos, dev_vel, dev_acc);
+	cudaThreadSynchronize();
 }
 
 void cudaUpdateVBO(float * vbodptr, int width, int height)

Part1/src/main.cpp

@@ -4,8 +4,8 @@
 
 #include "main.h"
 
-#define N_FOR_VIS 5000
-#define DT 0.2
+#define N_FOR_VIS 2000
+#define DT 0.1
 #define VISUALIZE 1
 //-------------------------------
 //-------------MAIN--------------

Part2/matrix/matrix.sln

@@ -0,0 +1,20 @@
+
+Microsoft Visual Studio Solution File, Format Version 11.00
+# Visual Studio 2010
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "matrix", "matrix\matrix.vcxproj", "{6D40842A-A7DB-4254-9652-8C9A21F55B4F}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Win32 = Debug|Win32
+		Release|Win32 = Release|Win32
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{6D40842A-A7DB-4254-9652-8C9A21F55B4F}.Debug|Win32.ActiveCfg = Debug|Win32
+		{6D40842A-A7DB-4254-9652-8C9A21F55B4F}.Debug|Win32.Build.0 = Debug|Win32
+		{6D40842A-A7DB-4254-9652-8C9A21F55B4F}.Release|Win32.ActiveCfg = Release|Win32
+		{6D40842A-A7DB-4254-9652-8C9A21F55B4F}.Release|Win32.Build.0 = Release|Win32
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+EndGlobal

Part2/matrix/matrix/matrix.vcxproj

@@ -0,0 +1,76 @@
+<?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>
+  <PropertyGroup Label="Globals">
+    <ProjectGuid>{6D40842A-A7DB-4254-9652-8C9A21F55B4F}</ProjectGuid>
+    <RootNamespace>matrix</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)|$(Platform)'=='Debug|Win32'">
+    <ClCompile>
+      <WarningLevel>Level3</WarningLevel>
+      <Optimization>Disabled</Optimization>
+    </ClCompile>
+    <Link>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+    <ClCompile>
+      <WarningLevel>Level3</WarningLevel>
+      <Optimization>MaxSpeed</Optimization>
+      <FunctionLevelLinking>true</FunctionLevelLinking>
+      <IntrinsicFunctions>true</IntrinsicFunctions>
+    </ClCompile>
+    <Link>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+      <EnableCOMDATFolding>true</EnableCOMDATFolding>
+      <OptimizeReferences>true</OptimizeReferences>
+      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;cudart.lib;%(AdditionalDependencies)</AdditionalDependencies>
+    </Link>
+    <CudaCompile>
+      <Include>$(CudaToolkitIncludeDir)</Include>
+    </CudaCompile>
+  </ItemDefinitionGroup>
+  <ItemGroup>
+    <CudaCompile Include="matrix_math.cu">
+      <FileType>Document</FileType>
+    </CudaCompile>
+  </ItemGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+  <ImportGroup Label="ExtensionTargets">
+    <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 6.5.targets" />
+  </ImportGroup>
+</Project>

Part2/matrix/matrix/matrix.vcxproj.filters

@@ -0,0 +1,22 @@
+<?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>
+</Project>

Part2/matrix/matrix/matrix_math.cu

@@ -0,0 +1,134 @@
+#include <cuda.h>
+#include <cuda_runtime.h>
+#include <iostream>
+#include <math.h>
+
+using namespace std;
+const int N = 5;
+
+//data on device
+float * dev_matA;
+float * dev_matB;
+float * dev_res;
+
+//data on host
+float * matA = (float *)malloc(N*N*sizeof(float));
+float * matB = (float *)malloc(N*N*sizeof(float));
+float * res = (float *)malloc(N*N*sizeof(float));
+
+void initMat(float * mat)
+{
+	for(int i = 0; i < N; i++)
+		for(int j = 0; j < N; j++)
+			mat[i + j*N] = i + j * N;
+}
+
+void printRes()
+{
+	for(int j =0; j <N; j++)
+	{
+		cout << endl;
+		for(int i=0;i<N;i++)
+			cout << res[j*N + i] << " ";
+	}
+}
+
+__global__ void mat_add(float * A, float * B, float * res)
+{
+	int x = threadIdx.x + blockIdx.x *blockDim.x;
+	int y = threadIdx.y + blockIdx.y *blockDim.y;
+	res[x + y*N] = A[x + y*N] + B[x + y*N];
+}
+
+__global__ void mat_sub(float * A, float * B, float * res)
+{
+	int x = threadIdx.x + blockIdx.x *blockDim.x;
+	int y = threadIdx.y + blockIdx.y *blockDim.y;
+	res[x + y*N] = A[x + y*N] - B[x + y*N];
+}
+
+__global__ void mat_mult(float * A, float * B, float * res)
+{
+	int x = threadIdx.x + blockIdx.x *blockDim.x;
+	int y = threadIdx.y + blockIdx.y *blockDim.y;
+
+	float result = 0;
+	for(int i = 0; i < N; i++)
+	{
+		result += A[y * N + i] * B[x + i * N];
+	}
+	res[x + y*N] = result;
+}
+
+void mat_add_serial(float * A, float * B, float * res)
+{
+	for(int i = 0; i < N * N; i++)
+	{
+		res[i] = A[i] + B[i];
+	}
+}
+void mat_sub_serial(float * A, float * B, float * res)
+{
+	for(int i = 0; i < N * N; i++)
+	{
+		res[i] = A[i] - B[i];
+	}
+}
+void mat_mult_serial(float * A, float * B, float * res)
+{
+	for(int i = 0; i < N; i++)
+		for(int j = 0; j < N; j++)
+		{
+			float result = 0;
+			for(int k = 0; k < N; k++)
+			{
+				result += A[i*N + k] * B[k*N + j];
+			}
+			res[i*N + j] = result;
+		}
+}
+
+int main(int argc, char** argv)
+{
+	dim3 threadsPerBlock(16,16);
+	dim3 numBlocks((int)ceil((float)N / threadsPerBlock.x), (int)ceil((float)N/threadsPerBlock.y));
+
+	cudaMalloc((void**)&dev_matA, N*N*sizeof(float));
+	cudaMalloc((void**)&dev_matB, N*N*sizeof(float));
+	cudaMalloc((void**)&dev_res, N*N*sizeof(float));
+
+	initMat(matA);
+	initMat(matB);
+	cudaMemcpy(dev_matA, matA, N*N*sizeof(float), cudaMemcpyHostToDevice);
+	cudaMemcpy(dev_matB, matB, N*N*sizeof(float), cudaMemcpyHostToDevice);
+
+	mat_add<<<numBlocks, threadsPerBlock>>>(dev_matA, dev_matB, dev_res);
+	cudaMemcpy(res, dev_res, N*N*sizeof(float), cudaMemcpyDeviceToHost);
+	cout<< endl << "###########parallel mat_add test######## ";
+	printRes();
+
+	mat_sub<<<numBlocks, threadsPerBlock>>>(dev_matA, dev_matB, dev_res);
+	cudaMemcpy(res, dev_res, N*N*sizeof(float), cudaMemcpyDeviceToHost);
+	cout<< endl << "###########parallel mat_add test######## ";
+	printRes();
+
+	mat_mult<<<numBlocks, threadsPerBlock>>>(dev_matA, dev_matB, dev_res);
+	cudaMemcpy(res, dev_res, N*N*sizeof(float), cudaMemcpyDeviceToHost);
+	cout<< endl << "###########parallel mat_mul test######## ";
+	printRes();
+
+	mat_add_serial(matA, matB, res);
+	cout<< endl << "###########serial mat_add test######## ";
+	printRes();
+
+	mat_sub_serial(matA, matB, res);
+	cout<< endl << "###########serial mat_add test######## ";
+	printRes();
+
+	mat_mult_serial(matA, matB, res);
+	cout<< endl << "###########serial mat_mul test######## ";
+	printRes();
+
+	int in;
+	cin >> in;
+}