Submission: SANCHIT GARG

Project1-Part1/CMakeLists.txt

@@ -40,8 +40,6 @@ set(CORELIBS
 # Enable C++11 for host code
 set(CMAKE_CXX_STANDARD 11)
 
-list(APPEND CUDA_NVCC_FLAGS -G -g)
-
 # OSX-specific hacks/fixes
 if(${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
     list(APPEND CORELIBS "-framework IOKit")

Project1-Part1/src/kernel.cu

@@ -169,6 +169,17 @@ void Nbody::copyPlanetsToVBO(float *vbodptr) {
  * stepSimulation *
  ******************/
 
+__device__ glm::vec3 computeNeighbourForce(glm::vec3 this_planet_position, glm::vec3 that_planet_position, float mass)
+{
+	//TODO: check distance is not very small
+	float dis = (glm::distance(this_planet_position, that_planet_position));
+
+	if(dis < 1.f)
+		return glm::vec3(0.0f);
+
+	return ( ( (that_planet_position - this_planet_position) / dis) * (float) ( (G * mass) / (dis * dis)) ) ;
+}
+
 /**
  * Compute the acceleration on a body at `my_pos` due to the `N` bodies in the array `other_planets`.
  */
@@ -189,8 +200,18 @@ __device__  glm::vec3 accelerate(int N, int iSelf, glm::vec3 this_planet, const
     //    * G is the universal gravitational constant (already defined for you)
     //    * M is the mass of the other object
     //    * r is the distance between this object and the other object
-
-    return glm::vec3(0.0f);
+
+	glm::vec3 neighbourForce(0.0f);
+
+	neighbourForce = computeNeighbourForce(this_planet, glm::vec3(0.0f), starMass);
+
+	for(int i=0; i<N; i++)
+	{
+		if(i != iSelf)
+			neighbourForce += computeNeighbourForce(this_planet, other_planets[i], planetMass);
+	}
+
+    return neighbourForce;
 }
 
 /**
@@ -201,6 +222,13 @@ __global__ void kernUpdateAcc(int N, float dt, const glm::vec3 *pos, glm::vec3 *
     // TODO: implement updateAccArray.
     // This function body runs once on each CUDA thread.
     // To avoid race conditions, each instance should only write ONE value to `acc`!
+
+	int index = threadIdx.x + (blockIdx.x * blockDim.x);
+
+	if(index < N)
+	{
+		acc[index] = accelerate(N, index, pos[index], pos);
+	}
 }
 
 /**
@@ -209,6 +237,14 @@ __global__ void kernUpdateAcc(int N, float dt, const glm::vec3 *pos, glm::vec3 *
  */
 __global__ void kernUpdateVelPos(int N, float dt, glm::vec3 *pos, glm::vec3 *vel, const glm::vec3 *acc) {
     // TODO: implement updateVelocityPosition
+
+	int index = threadIdx.x + (blockIdx.x * blockDim.x);
+
+	if(index < N)
+	{
+		vel[index] += acc[index] * dt;
+		pos[index] += vel[index] * dt;
+	}
 }
 
 /**
@@ -217,4 +253,24 @@ __global__ void kernUpdateVelPos(int N, float dt, glm::vec3 *pos, glm::vec3 *vel
 void Nbody::stepSimulation(float dt) {
     // TODO: Using the CUDA kernels you wrote above, write a function that
     // calls the kernels to perform a full simulation step.
+
+//	//For actual simulation
+//	dim3 fullBlocksPerGrid((numObjects + blockSize - 1) / blockSize);
+//
+//	kernUpdateAcc<<<fullBlocksPerGrid, blockSize>>>(numObjects, dt, dev_pos, dev_acc);
+//	kernUpdateVelPos<<<fullBlocksPerGrid, blockSize>>>(numObjects, dt, dev_pos, dev_vel, dev_acc);
+
+	//For performance analysis
+	int analysisGridSize = 32;
+	int analysisBlockSize = 128;
+
+	kernUpdateAcc<<<analysisGridSize, analysisBlockSize>>>(numObjects, dt, dev_pos, dev_acc);
+	kernUpdateVelPos<<<analysisGridSize, analysisBlockSize>>>(numObjects, dt, dev_pos, dev_vel, dev_acc);
 }
+
+//void Nbody::endSimulation()
+//{
+//    cudaFree(dev_acc);
+//    cudaFree(dev_vel);
+//    cudaFree(dev_pos);
+//}

Project1-Part1/src/main.cpp

@@ -12,9 +12,9 @@
 // Configuration
 // ================
 
-#define VISUALIZE 1
+#define VISUALIZE 0
 
-const int N_FOR_VIS = 5000;
+const int N_FOR_VIS = 4096;
 const float DT = 0.2f;
 
 /**
@@ -237,9 +237,9 @@ void mainLoop() {
 
         glUseProgram(0);
         glBindVertexArray(0);
-#endif
-
         glfwSwapBuffers(window);
+
+#endif
     }
     glfwDestroyWindow(window);
     glfwTerminate();

Project1-Part2/CMakeLists.txt

@@ -0,0 +1,86 @@
+cmake_minimum_required(VERSION 3.0)
+
+project(cis565_matMath)
+
+set(CMAKE_MODULE_PATH "${CMAKE_SOURCE_DIR}/cmake" ${CMAKE_MODULE_PATH})
+
+# Set up include and lib paths
+set(EXTERNAL "external")
+include_directories("${EXTERNAL}/include")
+include_directories("${EXTERNAL}/src")
+if(${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
+    set(EXTERNAL_LIB_PATH "${EXTERNAL}/lib/osx")
+elseif(${CMAKE_SYSTEM_NAME} MATCHES "Linux")
+    set(EXTERNAL_LIB_PATH "${EXTERNAL}/lib/linux" "/usr/lib64")
+elseif(WIN32)
+    set(EXTERNAL_LIB_PATH "${EXTERNAL}/lib/win")
+endif()
+link_directories(${EXTERNAL_LIB_PATH})
+list(APPEND CMAKE_LIBRARY_PATH "${EXTERNAL_LIB_PATH}")
+
+# Find up and set up core dependency libs
+
+set(GLFW_INCLUDE_DIR "${EXTERNAL}/include")
+set(GLFW_LIBRARY_DIR "${CMAKE_LIBRARY_PATH}")
+find_library(GLFW_LIBRARY "glfw3" HINTS "${GLFW_LIBRARY_DIR}")
+
+set(GLEW_INCLUDE_DIR "${EXTERNAL}/include")
+set(GLEW_LIBRARY_DIR "${CMAKE_LIBRARY_PATH}")
+add_definitions(-DGLEW_STATIC)
+find_package(GLEW)
+
+find_package(OpenGL)
+
+set(CORELIBS
+    "${GLFW_LIBRARY}"
+    "${OPENGL_LIBRARY}"
+    "${GLEW_LIBRARY}"
+    )
+
+# Enable C++11 for host code
+set(CMAKE_CXX_STANDARD 11)
+
+list(APPEND CUDA_NVCC_FLAGS -G -g)
+
+# OSX-specific hacks/fixes
+if(${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
+    list(APPEND CORELIBS "-framework IOKit")
+    list(APPEND CORELIBS "-framework Cocoa")
+    list(APPEND CORELIBS "-framework CoreVideo")
+endif()
+
+# Linux-specific hacks/fixes
+if(${CMAKE_SYSTEM_NAME} MATCHES "Linux")
+    list(APPEND CMAKE_EXE_LINKER_FLAGS "-lX11 -lXxf86vm -lXrandr -lpthread -lXi")
+endif()
+
+# Crucial magic for CUDA linking
+find_package(Threads REQUIRED)
+find_package(CUDA REQUIRED)
+
+set(CUDA_ATTACH_VS_BUILD_RULE_TO_CUDA_FILE ON)
+set(CUDA_SEPARABLE_COMPILATION ON)
+
+if(${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
+    set(CUDA_PROPAGATE_HOST_FLAGS OFF)
+endif()
+
+add_subdirectory(src)
+
+cuda_add_executable(${CMAKE_PROJECT_NAME}
+	"src/main.hpp"
+    "src/main.cpp"
+    )
+
+target_link_libraries(${CMAKE_PROJECT_NAME}
+    src
+    ${CORELIBS}
+    )
+
+add_custom_command(
+    TARGET ${CMAKE_PROJECT_NAME}
+    POST_BUILD
+    COMMAND ${CMAKE_COMMAND} -E copy_directory
+        ${CMAKE_SOURCE_DIR}/shaders
+        ${CMAKE_BINARY_DIR}/shaders
+    )

Project1-Part2/GNUmakefile

@@ -0,0 +1,31 @@
+CMAKE_ALT1 := /usr/local/bin/cmake
+CMAKE_ALT2 := /Applications/CMake.app/Contents/bin/cmake
+CMAKE := $(shell \
+	which cmake 2>/dev/null || \
+	([ -e ${CMAKE_ALT1} ] && echo "${CMAKE_ALT1}") || \
+	([ -e ${CMAKE_ALT2} ] && echo "${CMAKE_ALT2}") \
+	)
+
+all: RelWithDebugInfo
+
+
+Debug: build
+	(cd build && ${CMAKE} -DCMAKE_BUILD_TYPE=$@ .. && make)
+
+MinSizeRel: build
+	(cd build && ${CMAKE} -DCMAKE_BUILD_TYPE=$@ .. && make)
+
+Release: build
+	(cd build && ${CMAKE} -DCMAKE_BUILD_TYPE=$@ .. && make)
+
+RelWithDebugInfo: build
+	(cd build && ${CMAKE} -DCMAKE_BUILD_TYPE=$@ .. && make)
+
+
+build:
+	(mkdir -p build && cd build)
+
+clean:
+	((cd build && make clean) 2>&- || true)
+
+.PHONY: all Debug MinSizeRel Release RelWithDebugInfo clean