Rewrote the entire thing using my new OpenCL template. Makes small one offs like these reallly simple
MitchellHansen
7 years ago
parent
08fd8b2398
commit
7743321465
@ -1,63 +0,0 @@
|
||||
###############################################################################
|
||||
# Set default behavior to automatically normalize line endings.
|
||||
###############################################################################
|
||||
* text=auto
|
||||
|
||||
###############################################################################
|
||||
# Set default behavior for command prompt diff.
|
||||
#
|
||||
# This is need for earlier builds of msysgit that does not have it on by
|
||||
# default for csharp files.
|
||||
# Note: This is only used by command line
|
||||
###############################################################################
|
||||
#*.cs diff=csharp
|
||||
|
||||
###############################################################################
|
||||
# Set the merge driver for project and solution files
|
||||
#
|
||||
# Merging from the command prompt will add diff markers to the files if there
|
||||
# are conflicts (Merging from VS is not affected by the settings below, in VS
|
||||
# the diff markers are never inserted). Diff markers may cause the following
|
||||
# file extensions to fail to load in VS. An alternative would be to treat
|
||||
# these files as binary and thus will always conflict and require user
|
||||
# intervention with every merge. To do so, just uncomment the entries below
|
||||
###############################################################################
|
||||
#*.sln merge=binary
|
||||
#*.csproj merge=binary
|
||||
#*.vbproj merge=binary
|
||||
#*.vcxproj merge=binary
|
||||
#*.vcproj merge=binary
|
||||
#*.dbproj merge=binary
|
||||
#*.fsproj merge=binary
|
||||
#*.lsproj merge=binary
|
||||
#*.wixproj merge=binary
|
||||
#*.modelproj merge=binary
|
||||
#*.sqlproj merge=binary
|
||||
#*.wwaproj merge=binary
|
||||
|
||||
###############################################################################
|
||||
# behavior for image files
|
||||
#
|
||||
# image files are treated as binary by default.
|
||||
###############################################################################
|
||||
#*.jpg binary
|
||||
#*.png binary
|
||||
#*.gif binary
|
||||
|
||||
###############################################################################
|
||||
# diff behavior for common document formats
|
||||
#
|
||||
# Convert binary document formats to text before diffing them. This feature
|
||||
# is only available from the command line. Turn it on by uncommenting the
|
||||
# entries below.
|
||||
###############################################################################
|
||||
#*.doc diff=astextplain
|
||||
#*.DOC diff=astextplain
|
||||
#*.docx diff=astextplain
|
||||
#*.DOCX diff=astextplain
|
||||
#*.dot diff=astextplain
|
||||
#*.DOT diff=astextplain
|
||||
#*.pdf diff=astextplain
|
||||
#*.PDF diff=astextplain
|
||||
#*.rtf diff=astextplain
|
||||
#*.RTF diff=astextplain
|
||||
@ -1,212 +1,47 @@
|
||||
## Ignore Visual Studio temporary files, build results, and
|
||||
## files generated by popular Visual Studio add-ons.
|
||||
|
||||
# User-specific files
|
||||
*.suo
|
||||
*.user
|
||||
*.userosscache
|
||||
*.sln.docstates
|
||||
|
||||
# User-specific files (MonoDevelop/Xamarin Studio)
|
||||
*.userprefs
|
||||
|
||||
# Build results
|
||||
[Dd]ebug/
|
||||
[Dd]ebugPublic/
|
||||
[Rr]elease/
|
||||
[Rr]eleases/
|
||||
x64/
|
||||
x86/
|
||||
build/
|
||||
bld/
|
||||
[Bb]in/
|
||||
[Oo]bj/
|
||||
|
||||
# Visual Studio 2015 cache/options directory
|
||||
.vs/
|
||||
|
||||
# MSTest test Results
|
||||
[Tt]est[Rr]esult*/
|
||||
[Bb]uild[Ll]og.*
|
||||
|
||||
# NUNIT
|
||||
*.VisualState.xml
|
||||
TestResult.xml
|
||||
|
||||
# Build Results of an ATL Project
|
||||
[Dd]ebugPS/
|
||||
[Rr]eleasePS/
|
||||
dlldata.c
|
||||
|
||||
# DNX
|
||||
project.lock.json
|
||||
artifacts/
|
||||
|
||||
*_i.c
|
||||
*_p.c
|
||||
*_i.h
|
||||
*.ilk
|
||||
*.meta
|
||||
*.obj
|
||||
*.pch
|
||||
*.pdb
|
||||
*.pgc
|
||||
*.pgd
|
||||
*.rsp
|
||||
*.sbr
|
||||
*.tlb
|
||||
*.tli
|
||||
*.tlh
|
||||
*.tmp
|
||||
*.tmp_proj
|
||||
# Compiled source #
|
||||
###################
|
||||
*.com
|
||||
*.class
|
||||
*.dll
|
||||
*.exe
|
||||
*.o
|
||||
*.so
|
||||
|
||||
# Packages #
|
||||
############
|
||||
# it's better to unpack these files and commit the raw source
|
||||
# git has its own built in compression methods
|
||||
*.7z
|
||||
*.dmg
|
||||
*.gz
|
||||
*.iso
|
||||
*.jar
|
||||
*.rar
|
||||
*.tar
|
||||
*.zip
|
||||
|
||||
# Logs and databases #
|
||||
######################
|
||||
*.log
|
||||
*.vspscc
|
||||
*.vssscc
|
||||
.builds
|
||||
*.pidb
|
||||
*.svclog
|
||||
*.scc
|
||||
|
||||
# Chutzpah Test files
|
||||
_Chutzpah*
|
||||
|
||||
# Visual C++ cache files
|
||||
ipch/
|
||||
*.aps
|
||||
*.ncb
|
||||
*.opensdf
|
||||
*.sdf
|
||||
*.cachefile
|
||||
|
||||
# Visual Studio profiler
|
||||
*.psess
|
||||
*.vsp
|
||||
*.vspx
|
||||
|
||||
# TFS 2012 Local Workspace
|
||||
$tf/
|
||||
|
||||
# Guidance Automation Toolkit
|
||||
*.gpState
|
||||
|
||||
# ReSharper is a .NET coding add-in
|
||||
_ReSharper*/
|
||||
*.[Rr]e[Ss]harper
|
||||
*.DotSettings.user
|
||||
|
||||
# JustCode is a .NET coding add-in
|
||||
.JustCode
|
||||
|
||||
# TeamCity is a build add-in
|
||||
_TeamCity*
|
||||
|
||||
# DotCover is a Code Coverage Tool
|
||||
*.dotCover
|
||||
|
||||
# NCrunch
|
||||
_NCrunch_*
|
||||
.*crunch*.local.xml
|
||||
|
||||
# MightyMoose
|
||||
*.mm.*
|
||||
AutoTest.Net/
|
||||
|
||||
# Web workbench (sass)
|
||||
.sass-cache/
|
||||
|
||||
# Installshield output folder
|
||||
[Ee]xpress/
|
||||
|
||||
# DocProject is a documentation generator add-in
|
||||
DocProject/buildhelp/
|
||||
DocProject/Help/*.HxT
|
||||
DocProject/Help/*.HxC
|
||||
DocProject/Help/*.hhc
|
||||
DocProject/Help/*.hhk
|
||||
DocProject/Help/*.hhp
|
||||
DocProject/Help/Html2
|
||||
DocProject/Help/html
|
||||
|
||||
# Click-Once directory
|
||||
publish/
|
||||
|
||||
# Publish Web Output
|
||||
*.[Pp]ublish.xml
|
||||
*.azurePubxml
|
||||
## TODO: Comment the next line if you want to checkin your
|
||||
## web deploy settings but do note that will include unencrypted
|
||||
## passwords
|
||||
#*.pubxml
|
||||
|
||||
*.publishproj
|
||||
|
||||
# NuGet Packages
|
||||
*.nupkg
|
||||
# The packages folder can be ignored because of Package Restore
|
||||
**/packages/*
|
||||
# except build/, which is used as an MSBuild target.
|
||||
!**/packages/build/
|
||||
# Uncomment if necessary however generally it will be regenerated when needed
|
||||
#!**/packages/repositories.config
|
||||
|
||||
# Windows Azure Build Output
|
||||
csx/
|
||||
*.build.csdef
|
||||
|
||||
# Windows Store app package directory
|
||||
AppPackages/
|
||||
|
||||
# Visual Studio cache files
|
||||
# files ending in .cache can be ignored
|
||||
*.[Cc]ache
|
||||
# but keep track of directories ending in .cache
|
||||
!*.[Cc]ache/
|
||||
|
||||
# Others
|
||||
ClientBin/
|
||||
[Ss]tyle[Cc]op.*
|
||||
~$*
|
||||
*~
|
||||
*.dbmdl
|
||||
*.dbproj.schemaview
|
||||
*.pfx
|
||||
*.publishsettings
|
||||
node_modules/
|
||||
orleans.codegen.cs
|
||||
|
||||
# RIA/Silverlight projects
|
||||
Generated_Code/
|
||||
|
||||
# Backup & report files from converting an old project file
|
||||
# to a newer Visual Studio version. Backup files are not needed,
|
||||
# because we have git ;-)
|
||||
_UpgradeReport_Files/
|
||||
Backup*/
|
||||
UpgradeLog*.XML
|
||||
UpgradeLog*.htm
|
||||
|
||||
# SQL Server files
|
||||
*.mdf
|
||||
*.ldf
|
||||
|
||||
# Business Intelligence projects
|
||||
*.rdl.data
|
||||
*.bim.layout
|
||||
*.bim_*.settings
|
||||
|
||||
# Microsoft Fakes
|
||||
FakesAssemblies/
|
||||
|
||||
# Node.js Tools for Visual Studio
|
||||
.ntvs_analysis.dat
|
||||
|
||||
# Visual Studio 6 build log
|
||||
*.plg
|
||||
|
||||
# Visual Studio 6 workspace options file
|
||||
*.opt
|
||||
|
||||
# LightSwitch generated files
|
||||
GeneratedArtifacts/
|
||||
_Pvt_Extensions/
|
||||
ModelManifest.xml
|
||||
*.sql
|
||||
*.sqlite
|
||||
|
||||
# OS generated files #
|
||||
######################
|
||||
.DS_Store
|
||||
.DS_Store?
|
||||
._*
|
||||
.Spotlight-V100
|
||||
.Trashes
|
||||
ehthumbs.db
|
||||
Thumbs.db
|
||||
|
||||
# CMake Generated Files #
|
||||
#########################
|
||||
CMakeCache.txt
|
||||
CMakeFiles
|
||||
CMakeScripts
|
||||
Makefile
|
||||
cmake_install.cmake
|
||||
install_manifest.txt
|
||||
CTestTestfile.cmake
|
||||
|
||||
@ -0,0 +1,101 @@
|
||||
# Check versions
|
||||
message(STATUS "CMake version: ${CMAKE_VERSION}")
|
||||
cmake_minimum_required(VERSION 3.1)
|
||||
|
||||
set_property(GLOBAL PROPERTY USE_FOLDERS ON)
|
||||
|
||||
# Set the project name
|
||||
set(PNAME Conways)
|
||||
project(${PNAME})
|
||||
|
||||
# Set up variables, and find SFML
|
||||
if (WIN32)
|
||||
set(SFML_ROOT root CACHE STRING "User specified path")
|
||||
set(SFML_INCLUDE_DIR ${SFML_ROOT}/include)
|
||||
endif()
|
||||
|
||||
set(SFML_COMPONENTS graphics window system network audio)
|
||||
set(CMAKE_MODULE_PATH ${CMAKE_CURRENT_SOURCE_DIR})
|
||||
find_package(SFML 2.1 COMPONENTS ${SFML_COMPONENTS} REQUIRED)
|
||||
message(STATUS "SFML found: ${SFML_FOUND}")
|
||||
|
||||
# Find OpenCL
|
||||
find_package( OpenCL REQUIRED )
|
||||
message(STATUS "OpenCL found: ${OPENCL_FOUND}")
|
||||
|
||||
# Find OpenGL
|
||||
find_package( OpenGL REQUIRED)
|
||||
message(STATUS "OpenGL found: ${OPENGL_FOUND}")
|
||||
|
||||
# Include the directories for the main program, GL, CL and SFML's headers
|
||||
include_directories(${SFML_INCLUDE_DIR})
|
||||
include_directories(${OpenCL_INCLUDE_DIRS})
|
||||
include_directories(include)
|
||||
|
||||
# Glob all thr sources into their values
|
||||
file(GLOB_RECURSE SOURCES "src/*.cpp")
|
||||
file(GLOB_RECURSE HEADERS "include/*.h" "include/*.hpp")
|
||||
file(GLOB_RECURSE KERNELS "kernels/*.cl")
|
||||
|
||||
add_executable(${PNAME} ${SOURCES} ${HEADERS} ${KERNELS})
|
||||
|
||||
# Follow the sub directory structure to add sub-filters in VS
|
||||
# Gotta do it one by one unfortunately
|
||||
|
||||
foreach (source IN ITEMS ${SOURCES})
|
||||
if (IS_ABSOLUTE "${source}")
|
||||
|
||||
get_filename_component(filename ${source} DIRECTORY)
|
||||
|
||||
STRING(REGEX REPLACE "/" "\\\\" filename ${filename})
|
||||
|
||||
string(REGEX MATCHALL "src(.*)" substrings ${filename})
|
||||
list(GET substrings 0 substring)
|
||||
|
||||
SOURCE_GROUP(${substring} FILES ${source})
|
||||
|
||||
endif()
|
||||
endforeach()
|
||||
|
||||
foreach (source IN ITEMS ${HEADERS})
|
||||
if (IS_ABSOLUTE "${source}")
|
||||
|
||||
get_filename_component(filename ${source} DIRECTORY)
|
||||
|
||||
STRING(REGEX REPLACE "/" "\\\\" filename ${filename})
|
||||
|
||||
string(REGEX MATCHALL "include(.*)" substrings ${filename})
|
||||
list(GET substrings 0 substring)
|
||||
|
||||
SOURCE_GROUP(${substring} FILES ${source})
|
||||
|
||||
endif()
|
||||
endforeach()
|
||||
|
||||
foreach (source IN ITEMS ${KERNELS})
|
||||
if (IS_ABSOLUTE "${source}")
|
||||
|
||||
get_filename_component(filename ${source} DIRECTORY)
|
||||
|
||||
STRING(REGEX REPLACE "/" "\\\\" filename ${filename})
|
||||
|
||||
string(REGEX MATCHALL "kernels(.*)" substrings ${filename})
|
||||
list(GET substrings 0 substring)
|
||||
|
||||
SOURCE_GROUP(${substring} FILES ${source})
|
||||
|
||||
endif()
|
||||
endforeach()
|
||||
|
||||
# Link CL, GL, and SFML
|
||||
target_link_libraries (${PNAME} ${SFML_LIBRARIES} ${SFML_DEPENDENCIES})
|
||||
target_link_libraries (${PNAME} ${OpenCL_LIBRARY})
|
||||
target_link_libraries (${PNAME} ${OPENGL_LIBRARIES})
|
||||
|
||||
if (NOT WIN32)
|
||||
target_link_libraries (${PNAME} -lpthread)
|
||||
endif()
|
||||
|
||||
# Setup to use C++14
|
||||
set_property(TARGET ${PNAME} PROPERTY CXX_STANDARD 14)
|
||||
|
||||
@ -1,395 +0,0 @@
|
||||
#include <CL/cl.h>
|
||||
#include <CL/opencl.h>
|
||||
#include <string.h>
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <iostream>
|
||||
#include <string>
|
||||
#include <fstream>
|
||||
#include <random>
|
||||
#include <ctime>
|
||||
#include <SFML/Graphics.hpp>
|
||||
#include <windows.h>
|
||||
#include <GL/glew.h>
|
||||
#include <GLFW/glfw3.h>
|
||||
#include "Shader.hpp"
|
||||
|
||||
#define SUCCESS 0
|
||||
#define FAILURE 1
|
||||
|
||||
float elap_time() {
|
||||
static __int64 start = 0;
|
||||
static __int64 frequency = 0;
|
||||
|
||||
if (start == 0) {
|
||||
QueryPerformanceCounter((LARGE_INTEGER*)&start);
|
||||
QueryPerformanceFrequency((LARGE_INTEGER*)&frequency);
|
||||
return 0.0f;
|
||||
}
|
||||
|
||||
__int64 counter = 0;
|
||||
QueryPerformanceCounter((LARGE_INTEGER*)&counter);
|
||||
return (float)((counter - start) / double(frequency));
|
||||
}
|
||||
|
||||
// convert the kernel file into a string
|
||||
int convertToString(const char *filename, std::string& s)
|
||||
{
|
||||
size_t size;
|
||||
char* str;
|
||||
std::fstream f(filename, (std::fstream::in | std::fstream::binary));
|
||||
|
||||
if(f.is_open())
|
||||
{
|
||||
size_t fileSize;
|
||||
f.seekg(0, std::fstream::end);
|
||||
size = fileSize = (size_t)f.tellg();
|
||||
f.seekg(0, std::fstream::beg);
|
||||
str = new char[size+1];
|
||||
if(!str)
|
||||
{
|
||||
f.close();
|
||||
return 0;
|
||||
}
|
||||
|
||||
f.read(str, fileSize);
|
||||
f.close();
|
||||
str[size] = '\0';
|
||||
s = str;
|
||||
delete[] str;
|
||||
return 0;
|
||||
}
|
||||
std::cout << "Error: failed to open file\n:" << filename << std::endl;
|
||||
return FAILURE;
|
||||
}
|
||||
|
||||
void key_callback(GLFWwindow* window, int key, int scancode, int action, int mode) {
|
||||
if (key == GLFW_KEY_ESCAPE && action == GLFW_PRESS)
|
||||
glfwSetWindowShouldClose(window, GL_TRUE);
|
||||
}
|
||||
|
||||
int main(int argc, char* argv[])
|
||||
{
|
||||
int WINDOW_X = 1000;
|
||||
int WINDOW_Y = 1000;
|
||||
int GRID_WIDTH = WINDOW_X;
|
||||
int GRID_HEIGHT = WINDOW_Y;
|
||||
int WORKER_SIZE = 1000;
|
||||
|
||||
// ======================================= Setup OpenGL =======================================================
|
||||
|
||||
glfwInit();
|
||||
|
||||
glfwWindowHint(GLFW_CONTEXT_VERSION_MAJOR, 3);
|
||||
glfwWindowHint(GLFW_CONTEXT_VERSION_MINOR, 3);
|
||||
glfwWindowHint(GLFW_OPENGL_PROFILE, GLFW_OPENGL_CORE_PROFILE);
|
||||
glfwWindowHint(GLFW_RESIZABLE, GL_FALSE);
|
||||
|
||||
GLFWwindow* gl_window = glfwCreateWindow(GRID_WIDTH, GRID_HEIGHT, "GPU accelerated life", nullptr, nullptr);
|
||||
glfwMakeContextCurrent(gl_window);
|
||||
|
||||
glfwSetKeyCallback(gl_window, key_callback);
|
||||
|
||||
glewExperimental = GL_TRUE;
|
||||
glewInit();
|
||||
|
||||
glViewport(0, 0, GRID_WIDTH, GRID_HEIGHT);
|
||||
|
||||
glClearColor(0.2f, 0.3f, 0.3f, 1.0f);
|
||||
|
||||
// Stolen from LearnOpenGL, aint got no time for that
|
||||
Shader vert_frag_shaders("Z:\\VS_Projects\\Conway_OpenCL\\Conway_OpenCL\\vertex_shader.sh", "Z:\\VS_Projects\\Conway_OpenCL\\Conway_OpenCL\\fragment_shader.sh");
|
||||
|
||||
GLfloat vertices[] = {
|
||||
// Positions // Colors // Texture Coords
|
||||
1.0f, 1.0f, 0.0f, 1.0f, 0.0f, 0.0f, 1.0f, 1.0f, // Top Right
|
||||
1.0f, -1.0f, 0.0f, 0.0f, 1.0f, 0.0f, 1.0f, 0.0f, // Bottom Right
|
||||
-1.0f, -1.0f, 0.0f, 0.0f, 0.0f, 1.0f, 0.0f, 0.0f, // Bottom Left
|
||||
-1.0f, 1.0f, 0.0f, 1.0f, 1.0f, 0.0f, 0.0f, 1.0f // Top Left
|
||||
};
|
||||
GLuint indices[] = {
|
||||
0, 1, 3, // First Triangle
|
||||
1, 2, 3 // Second Triangle
|
||||
};
|
||||
|
||||
GLuint VBO, VAO, EBO;
|
||||
glGenVertexArrays(1, &VAO);
|
||||
glGenBuffers(1, &VBO);
|
||||
glGenBuffers(1, &EBO);
|
||||
|
||||
// Bind the Vertex Array Object first, then bind and set vertex buffer(s) and attribute pointer(s).
|
||||
glBindVertexArray(VAO);
|
||||
|
||||
glBindBuffer(GL_ARRAY_BUFFER, VBO);
|
||||
glBufferData(GL_ARRAY_BUFFER, sizeof(vertices), vertices, GL_STATIC_DRAW);
|
||||
|
||||
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, EBO);
|
||||
glBufferData(GL_ELEMENT_ARRAY_BUFFER, sizeof(indices), indices, GL_STATIC_DRAW);
|
||||
|
||||
|
||||
// Position attribute
|
||||
glVertexAttribPointer(0, 3, GL_FLOAT, GL_FALSE, 8 * sizeof(GLfloat), (GLvoid*)0);
|
||||
glEnableVertexAttribArray(0);
|
||||
// Color attribute
|
||||
glVertexAttribPointer(1, 3, GL_FLOAT, GL_FALSE, 8 * sizeof(GLfloat), (GLvoid*)(3 * sizeof(GLfloat)));
|
||||
glEnableVertexAttribArray(1);
|
||||
// TexCoord attribute
|
||||
glVertexAttribPointer(2, 2, GL_FLOAT, GL_FALSE, 8 * sizeof(GLfloat), (GLvoid*)(6 * sizeof(GLfloat)));
|
||||
glEnableVertexAttribArray(2);
|
||||
|
||||
glBindVertexArray(0); // Unbind VAO
|
||||
|
||||
// ============================== OpenCL Setup ==================================================================
|
||||
|
||||
// Get the platforms
|
||||
cl_uint numPlatforms;
|
||||
cl_platform_id platform = NULL;
|
||||
cl_int status = clGetPlatformIDs(0, NULL, &numPlatforms); // Retrieve the number of platforms
|
||||
if (status != CL_SUCCESS) {
|
||||
std::cout << "Error: Getting platforms!" << std::endl;
|
||||
return FAILURE;
|
||||
}
|
||||
|
||||
// Choose the first available platform
|
||||
if(numPlatforms > 0) {
|
||||
cl_platform_id* platforms = new cl_platform_id[numPlatforms];
|
||||
status = clGetPlatformIDs(numPlatforms, platforms, NULL); // Now populate the array with the platforms
|
||||
platform = platforms[0];
|
||||
delete platforms;
|
||||
}
|
||||
|
||||
cl_uint numDevices = 0;
|
||||
cl_device_id *devices;
|
||||
status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_GPU, 0, NULL, &numDevices);
|
||||
if (numDevices == 0) { //no GPU available.
|
||||
std::cout << "No GPU device available." << std::endl;
|
||||
std::cout << "Choose CPU as default device." << std::endl;
|
||||
status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_CPU, 0, NULL, &numDevices);
|
||||
devices = new cl_device_id[numDevices];
|
||||
status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_CPU, numDevices, devices, NULL);
|
||||
}
|
||||
else {
|
||||
devices = new cl_device_id[numDevices];
|
||||
status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_GPU, numDevices, devices, NULL);
|
||||
}
|
||||
|
||||
HGLRC hGLRC = wglGetCurrentContext();
|
||||
HDC hDC = wglGetCurrentDC();
|
||||
cl_context_properties cps[] ={CL_CONTEXT_PLATFORM, (cl_context_properties)platform, CL_GL_CONTEXT_KHR, (cl_context_properties)hGLRC, CL_WGL_HDC_KHR, (cl_context_properties)hDC, 0 };
|
||||
|
||||
|
||||
cl_context context = clCreateContext(cps, 1, devices,NULL,NULL,NULL);
|
||||
cl_command_queue commandQueue = clCreateCommandQueue(context, devices[0], 0, NULL);
|
||||
|
||||
|
||||
// ============================== Kernel Compilation, Setup ====================================================
|
||||
|
||||
// Read the kernel from the file to a string
|
||||
const char *compute_kernel_filename = "Z:\\VS_Projects\\Conway_OpenCL\\Conway_OpenCL\\conway_compute.cl";
|
||||
const char *align_kernel_filename = "Z:\\VS_Projects\\Conway_OpenCL\\Conway_OpenCL\\conway_align.cl";
|
||||
|
||||
std::string compute_kernel_string;
|
||||
std::string align_kernel_string;
|
||||
|
||||
convertToString(compute_kernel_filename, compute_kernel_string);
|
||||
convertToString(align_kernel_filename, align_kernel_string);
|
||||
|
||||
// Create a program with the source
|
||||
const char *compute_source = compute_kernel_string.c_str();
|
||||
const char *align_source = align_kernel_string.c_str();
|
||||
|
||||
size_t compute_source_size[] = {strlen(compute_source)};
|
||||
size_t align_source_size[] = { strlen(align_source) };
|
||||
|
||||
cl_program compute_program = clCreateProgramWithSource(context, 1, &compute_source, compute_source_size, NULL);
|
||||
cl_program align_program = clCreateProgramWithSource(context, 1, &align_source, align_source_size, NULL);
|
||||
|
||||
// Build the compute program
|
||||
status = clBuildProgram(compute_program, 1, devices, NULL, NULL, NULL);
|
||||
|
||||
if (status == CL_BUILD_PROGRAM_FAILURE) {
|
||||
|
||||
size_t log_size;
|
||||
clGetProgramBuildInfo(compute_program, devices[0], CL_PROGRAM_BUILD_LOG, 0, NULL, &log_size);
|
||||
char *log = new char[log_size];
|
||||
|
||||
clGetProgramBuildInfo(compute_program, devices[0], CL_PROGRAM_BUILD_LOG, log_size, log, NULL);
|
||||
|
||||
std::cout << log << std::endl;
|
||||
}
|
||||
|
||||
// Build the align program
|
||||
status = clBuildProgram(align_program, 1, devices, NULL, NULL, NULL);
|
||||
|
||||
if (status == CL_BUILD_PROGRAM_FAILURE) {
|
||||
|
||||
size_t log_size;
|
||||
clGetProgramBuildInfo(align_program, devices[0], CL_PROGRAM_BUILD_LOG, 0, NULL, &log_size);
|
||||
char *log = new char[log_size];
|
||||
|
||||
clGetProgramBuildInfo(align_program, devices[0], CL_PROGRAM_BUILD_LOG, log_size, log, NULL);
|
||||
|
||||
std::cout << log << std::endl;
|
||||
}
|
||||
|
||||
// Now create the kernels
|
||||
cl_kernel compute_kernel = clCreateKernel(compute_program, "conway_compute", NULL);
|
||||
cl_kernel align_kernel = clCreateKernel(align_program, "conway_align", NULL);
|
||||
|
||||
|
||||
|
||||
// ======================================= Setup grid =========================================================
|
||||
|
||||
// Setup the rng
|
||||
std::mt19937 rng(time(NULL));
|
||||
std::uniform_int_distribution<int> rgen(0, 4); // 25% chance
|
||||
|
||||
// Init the grids
|
||||
unsigned char* node_grid = new unsigned char[GRID_WIDTH * GRID_HEIGHT];
|
||||
|
||||
for (int i = 0; i < GRID_WIDTH * GRID_HEIGHT; i++) {
|
||||
if (rgen(rng) == 1) {
|
||||
node_grid[i] = 1;
|
||||
}
|
||||
else {
|
||||
node_grid[i] = 0;
|
||||
}
|
||||
}
|
||||
|
||||
// ====================================== Setup Rendering ==========================================================
|
||||
|
||||
unsigned char* pixel_array = new sf::Uint8[WINDOW_X * WINDOW_Y * 4];
|
||||
|
||||
for (int i = 0; i < GRID_WIDTH * GRID_HEIGHT * 4; i += 4) {
|
||||
|
||||
pixel_array[i] = i % 255; // R?
|
||||
pixel_array[i + 1] = 70; // G?
|
||||
pixel_array[i + 2] = 100; // B?
|
||||
pixel_array[i + 3] = 100; // A?
|
||||
}
|
||||
|
||||
GLuint texture;
|
||||
|
||||
glGenTextures(1, &texture);
|
||||
glBindTexture(GL_TEXTURE_2D, texture);
|
||||
|
||||
//////////////////////////
|
||||
|
||||
glTexEnvf(GL_TEXTURE_ENV, GL_TEXTURE_ENV_MODE, GL_REPLACE);
|
||||
|
||||
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_DECAL);
|
||||
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_DECAL);
|
||||
|
||||
// when texture area is small, bilinear filter the closest mipmap
|
||||
glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR_MIPMAP_NEAREST);
|
||||
// when texture area is large, bilinear filter the first mipmap
|
||||
glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR);
|
||||
|
||||
// texture should tile
|
||||
glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_REPEAT);
|
||||
glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_REPEAT);
|
||||
|
||||
glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA, GRID_WIDTH, GRID_HEIGHT, 0, GL_RGBA, GL_UNSIGNED_BYTE, pixel_array);
|
||||
|
||||
glGenerateMipmap(GL_TEXTURE_2D);
|
||||
|
||||
|
||||
delete pixel_array;
|
||||
|
||||
|
||||
|
||||
// ========================================= Setup the buffers ==================================================
|
||||
|
||||
int err = 0;
|
||||
|
||||
cl_mem frontWriteBuffer = clCreateFromGLTexture(context , CL_MEM_WRITE_ONLY, GL_TEXTURE_2D, 0, texture, &err);
|
||||
cl_mem frontReadBuffer = clCreateFromGLTexture(context, CL_MEM_READ_ONLY, GL_TEXTURE_2D, 0, texture, &err);
|
||||
cl_mem backBuffer = clCreateBuffer(context, CL_MEM_READ_WRITE | CL_MEM_COPY_HOST_PTR, sizeof(int), (void*)node_grid, &err);
|
||||
|
||||
cl_mem workerCountBuffer = clCreateBuffer(context, CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR, sizeof(int), &WORKER_SIZE, &err);
|
||||
cl_mem gridWidthBuffer = clCreateBuffer(context, CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR, sizeof(int), &GRID_WIDTH, &err);
|
||||
cl_mem gridHeightBuffer = clCreateBuffer(context, CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR, sizeof(int), &GRID_HEIGHT, &err);
|
||||
|
||||
// Compute kernel args
|
||||
status = clSetKernelArg(compute_kernel, 0, sizeof(cl_mem), (void *)&frontWriteBuffer);
|
||||
status = clSetKernelArg(compute_kernel, 1, sizeof(cl_mem), (void *)&backBuffer);
|
||||
status = clSetKernelArg(compute_kernel, 2, sizeof(cl_mem), (void *)&workerCountBuffer);
|
||||
status = clSetKernelArg(compute_kernel, 3, sizeof(cl_mem), (void *)&gridWidthBuffer);
|
||||
status = clSetKernelArg(compute_kernel, 4, sizeof(cl_mem), (void *)&gridHeightBuffer);
|
||||
|
||||
status = clSetKernelArg(align_kernel, 0, sizeof(cl_mem), (void *)&frontReadBuffer);
|
||||
status = clSetKernelArg(align_kernel, 1, sizeof(cl_mem), (void *)&backBuffer);
|
||||
status = clSetKernelArg(align_kernel, 2, sizeof(cl_mem), (void *)&workerCountBuffer);
|
||||
status = clSetKernelArg(align_kernel, 3, sizeof(cl_mem), (void *)&gridWidthBuffer);
|
||||
status = clSetKernelArg(align_kernel, 4, sizeof(cl_mem), (void *)&gridHeightBuffer);
|
||||
|
||||
|
||||
// ===================================== Loop ==================================================================
|
||||
|
||||
while (!glfwWindowShouldClose(gl_window)) {
|
||||
|
||||
glClearColor(0.2f, 0.3f, 0.3f, 1.0f);
|
||||
glClear(GL_COLOR_BUFFER_BIT);
|
||||
|
||||
// ======================================= OpenCL Shtuff ===================================================
|
||||
|
||||
// Work size, for each y line
|
||||
size_t global_work_size[1] = { WORKER_SIZE };
|
||||
|
||||
status = clEnqueueAcquireGLObjects(commandQueue, 1, &frontReadBuffer, 0, 0, 0);
|
||||
status = clEnqueueAcquireGLObjects(commandQueue, 1, &frontWriteBuffer, 0, 0, 0);
|
||||
|
||||
status = clEnqueueNDRangeKernel(commandQueue, compute_kernel, 1, NULL, global_work_size, NULL, 0, NULL, NULL);
|
||||
status = clEnqueueNDRangeKernel(commandQueue, align_kernel, 1, NULL, global_work_size, NULL, 0, NULL, NULL);
|
||||
|
||||
status = clEnqueueReleaseGLObjects(commandQueue, 1, &frontReadBuffer, 0, NULL, NULL);
|
||||
status = clEnqueueReleaseGLObjects(commandQueue, 1, &frontWriteBuffer, 0, NULL, NULL);
|
||||
|
||||
clFinish(commandQueue);
|
||||
|
||||
// ======================================= Rendering Shtuff =================================================
|
||||
|
||||
glfwPollEvents();
|
||||
|
||||
glActiveTexture(GL_TEXTURE0);
|
||||
glBindTexture(GL_TEXTURE_2D, texture);
|
||||
glUniform1i(glGetUniformLocation(vert_frag_shaders.Program, "pixel_texture"), 0);
|
||||
|
||||
// Draw the triangle
|
||||
vert_frag_shaders.Use();
|
||||
glBindVertexArray(VAO);
|
||||
glDrawElements(GL_TRIANGLES, 6, GL_UNSIGNED_INT, 0);
|
||||
glBindVertexArray(0);
|
||||
|
||||
glFinish();
|
||||
|
||||
// Render
|
||||
glfwSwapBuffers(gl_window);
|
||||
|
||||
|
||||
|
||||
}
|
||||
|
||||
glfwTerminate();
|
||||
|
||||
// Release the buffers
|
||||
status = clReleaseMemObject(frontReadBuffer);
|
||||
status = clReleaseMemObject(workerCountBuffer);
|
||||
status = clReleaseMemObject(gridWidthBuffer);
|
||||
status = clReleaseMemObject(gridHeightBuffer);
|
||||
|
||||
// And the program stuff
|
||||
status = clReleaseKernel(compute_kernel);
|
||||
status = clReleaseProgram(compute_program);
|
||||
status = clReleaseProgram(align_program);
|
||||
status = clReleaseCommandQueue(commandQueue);
|
||||
status = clReleaseContext(context);
|
||||
|
||||
if (devices != NULL)
|
||||
{
|
||||
delete devices;
|
||||
devices = NULL;
|
||||
}
|
||||
|
||||
return SUCCESS;
|
||||
}
|
||||
@ -1,90 +0,0 @@
|
||||
#ifndef SHADER_H
|
||||
#define SHADER_H
|
||||
|
||||
#include <string>
|
||||
#include <fstream>
|
||||
#include <sstream>
|
||||
#include <iostream>
|
||||
|
||||
#include <GL/glew.h>
|
||||
|
||||
class Shader {
|
||||
public:
|
||||
GLuint Program;
|
||||
// Constructor generates the shader on the fly
|
||||
Shader(const GLchar* vertexPath, const GLchar* fragmentPath) {
|
||||
// 1. Retrieve the vertex/fragment source code from filePath
|
||||
std::string vertexCode;
|
||||
std::string fragmentCode;
|
||||
std::ifstream vShaderFile;
|
||||
std::ifstream fShaderFile;
|
||||
// ensures ifstream objects can throw exceptions:
|
||||
vShaderFile.exceptions(std::ifstream::badbit);
|
||||
fShaderFile.exceptions(std::ifstream::badbit);
|
||||
try {
|
||||
// Open files
|
||||
vShaderFile.open(vertexPath);
|
||||
fShaderFile.open(fragmentPath);
|
||||
std::stringstream vShaderStream, fShaderStream;
|
||||
// Read file's buffer contents into streams
|
||||
vShaderStream << vShaderFile.rdbuf();
|
||||
fShaderStream << fShaderFile.rdbuf();
|
||||
// close file handlers
|
||||
vShaderFile.close();
|
||||
fShaderFile.close();
|
||||
// Convert stream into string
|
||||
vertexCode = vShaderStream.str();
|
||||
fragmentCode = fShaderStream.str();
|
||||
}
|
||||
catch (std::ifstream::failure e) {
|
||||
std::cout << "ERROR::SHADER::FILE_NOT_SUCCESFULLY_READ" << std::endl;
|
||||
}
|
||||
const GLchar* vShaderCode = vertexCode.c_str();
|
||||
const GLchar * fShaderCode = fragmentCode.c_str();
|
||||
|
||||
GLint success = 0;
|
||||
GLchar infoLog[512];
|
||||
|
||||
// Vertex Shader
|
||||
GLuint vertex = glCreateShader(GL_VERTEX_SHADER);
|
||||
glShaderSource(vertex, 1, &vShaderCode, NULL);
|
||||
glCompileShader(vertex);
|
||||
// Print compile errors if any
|
||||
glGetShaderiv(vertex, GL_COMPILE_STATUS, &success);
|
||||
if (!success) {
|
||||
glGetShaderInfoLog(vertex, 512, NULL, infoLog);
|
||||
std::cout << "ERROR::SHADER::VERTEX::COMPILATION_FAILED\n" << infoLog << std::endl;
|
||||
}
|
||||
// Fragment Shader
|
||||
GLuint fragment = glCreateShader(GL_FRAGMENT_SHADER);
|
||||
glShaderSource(fragment, 1, &fShaderCode, NULL);
|
||||
glCompileShader(fragment);
|
||||
// Print compile errors if any
|
||||
glGetShaderiv(fragment, GL_COMPILE_STATUS, &success);
|
||||
if (!success) {
|
||||
glGetShaderInfoLog(fragment, 512, NULL, infoLog);
|
||||
std::cout << "ERROR::SHADER::FRAGMENT::COMPILATION_FAILED\n" << infoLog << std::endl;
|
||||
}
|
||||
// Shader Program
|
||||
this->Program = glCreateProgram();
|
||||
glAttachShader(this->Program, vertex);
|
||||
glAttachShader(this->Program, fragment);
|
||||
glLinkProgram(this->Program);
|
||||
// Print linking errors if any
|
||||
glGetProgramiv(this->Program, GL_LINK_STATUS, &success);
|
||||
if (!success) {
|
||||
glGetProgramInfoLog(this->Program, 512, NULL, infoLog);
|
||||
std::cout << "ERROR::SHADER::PROGRAM::LINKING_FAILED\n" << infoLog << std::endl;
|
||||
}
|
||||
// Delete the shaders as they're linked into our program now and no longer necessery
|
||||
glDeleteShader(vertex);
|
||||
glDeleteShader(fragment);
|
||||
|
||||
}
|
||||
// Uses the current shader
|
||||
void Use() {
|
||||
glUseProgram(this->Program);
|
||||
}
|
||||
};
|
||||
|
||||
#endif
|
||||
@ -1,20 +0,0 @@
|
||||
__kernel void conway_align(__read_only image2d_t front_image, __global char* back_image, __global int* num_workers, __global int* grid_width, __global int *grid_height)
|
||||
{
|
||||
const sampler_t sampler=CLK_NORMALIZED_COORDS_FALSE | CLK_ADDRESS_CLAMP | CLK_FILTER_NEAREST;
|
||||
|
||||
// Caclulate the start and end range that this worker will be calculating
|
||||
int data_length = *grid_width * *grid_height;
|
||||
|
||||
int start_range = (data_length / *num_workers) * get_global_id(0);
|
||||
int end_range = (data_length / *num_workers) * (get_global_id(0) + 1);
|
||||
|
||||
|
||||
for (int i = start_range; i < end_range; i++){
|
||||
|
||||
uint4 pixel;
|
||||
pixel = read_imageui(front_image, sampler, (int2)(i,get_global_id(0)));
|
||||
|
||||
back_image[i] = pixel.w / 255;
|
||||
}
|
||||
|
||||
}
|
||||
@ -1,59 +0,0 @@
|
||||
__kernel void conway_compute(__write_only image2d_t front_image, __global char* back_image, __global int* num_workers, __global int* grid_width, __global int *grid_height)
|
||||
{
|
||||
|
||||
float4 black = (float4)(.49, .68, .81, 1);
|
||||
float4 white = (float4)(.49, .68, .71, .3);
|
||||
|
||||
// Caclulate the start and end range that this worker will be calculating
|
||||
int data_length = *grid_width * *grid_height;
|
||||
|
||||
int start_range = (data_length / *num_workers) * get_global_id(0);
|
||||
int end_range = (data_length / *num_workers) * (get_global_id(0) + 1);
|
||||
|
||||
// x, y + 1
|
||||
|
||||
int neighbors = 0;
|
||||
|
||||
for (int i = start_range; i < end_range; i++){
|
||||
|
||||
int2 pixelcoord = (int2) (i % *grid_width, i / *grid_height);
|
||||
|
||||
// add all 8 blocks to neghbors
|
||||
neighbors = 0;
|
||||
// Top
|
||||
neighbors += back_image[i - *grid_width];
|
||||
|
||||
// Top right
|
||||
neighbors += back_image[i - *grid_width + 1];
|
||||
|
||||
// Right
|
||||
neighbors += back_image[i + 1];
|
||||
|
||||
// Bottom Right
|
||||
neighbors += back_image[i + *grid_width + 1];
|
||||
|
||||
// Bottom
|
||||
neighbors += back_image[i + *grid_width];
|
||||
|
||||
// Bottom Left
|
||||
neighbors += back_image[i + *grid_width - 1];
|
||||
|
||||
// Left
|
||||
neighbors += back_image[i - 1];
|
||||
|
||||
// Top left
|
||||
neighbors += back_image[i - *grid_width - 1];
|
||||
|
||||
// push living status to the padded second char
|
||||
|
||||
|
||||
write_imagef(front_image, pixelcoord, black);
|
||||
|
||||
if (neighbors == 3 || (neighbors == 2 && back_image[i])){
|
||||
write_imagef(front_image, pixelcoord, white);
|
||||
}
|
||||
|
||||
//else
|
||||
//write_imagei(front_image, pixelcoord, white);
|
||||
}
|
||||
}
|
||||
@ -1,15 +0,0 @@
|
||||
#version 330 core
|
||||
in vec3 ourColor;
|
||||
in vec2 TexCoord;
|
||||
|
||||
out vec4 color;
|
||||
|
||||
// Texture samplers
|
||||
uniform sampler2D pixel_texture;
|
||||
|
||||
void main()
|
||||
{
|
||||
// Linearly interpolate between both textures (second texture is only slightly combined)
|
||||
//color = vec4(1.0f, 0.5f, 0.2f, 1.0f);
|
||||
color = texture(pixel_texture, TexCoord);
|
||||
}
|
||||
@ -1,16 +0,0 @@
|
||||
#version 330 core
|
||||
layout (location = 0) in vec3 position;
|
||||
layout (location = 1) in vec3 color;
|
||||
layout (location = 2) in vec2 texCoord;
|
||||
|
||||
out vec3 ourColor;
|
||||
out vec2 TexCoord;
|
||||
|
||||
void main()
|
||||
{
|
||||
gl_Position = vec4(position, 1.0f);
|
||||
ourColor = color;
|
||||
// We swap the y-axis by substracing our coordinates from 1. This is done because most images have the top y-axis inversed with OpenGL's top y-axis.
|
||||
// TexCoord = texCoord;
|
||||
TexCoord = vec2(texCoord.x, 1.0 - texCoord.y);
|
||||
}
|
||||
@ -0,0 +1,369 @@
|
||||
# This script locates the SFML library
|
||||
# ------------------------------------
|
||||
#
|
||||
# Usage
|
||||
# -----
|
||||
#
|
||||
# When you try to locate the SFML libraries, you must specify which modules you want to use (system, window, graphics, network, audio, main).
|
||||
# If none is given, the SFML_LIBRARIES variable will be empty and you'll end up linking to nothing.
|
||||
# example:
|
||||
# find_package(SFML COMPONENTS graphics window system) # find the graphics, window and system modules
|
||||
#
|
||||
# You can enforce a specific version, either MAJOR.MINOR or only MAJOR.
|
||||
# If nothing is specified, the version won't be checked (i.e. any version will be accepted).
|
||||
# example:
|
||||
# find_package(SFML COMPONENTS ...) # no specific version required
|
||||
# find_package(SFML 2 COMPONENTS ...) # any 2.x version
|
||||
# find_package(SFML 2.4 COMPONENTS ...) # version 2.4 or greater
|
||||
#
|
||||
# By default, the dynamic libraries of SFML will be found. To find the static ones instead,
|
||||
# you must set the SFML_STATIC_LIBRARIES variable to TRUE before calling find_package(SFML ...).
|
||||
# Since you have to link yourself all the SFML dependencies when you link it statically, the following
|
||||
# additional variables are defined: SFML_XXX_DEPENDENCIES and SFML_DEPENDENCIES (see their detailed
|
||||
# description below).
|
||||
# In case of static linking, the SFML_STATIC macro will also be defined by this script.
|
||||
# example:
|
||||
# set(SFML_STATIC_LIBRARIES TRUE)
|
||||
# find_package(SFML 2 COMPONENTS network system)
|
||||
#
|
||||
# On Mac OS X if SFML_STATIC_LIBRARIES is not set to TRUE then by default CMake will search for frameworks unless
|
||||
# CMAKE_FIND_FRAMEWORK is set to "NEVER" for example. Please refer to CMake documentation for more details.
|
||||
# Moreover, keep in mind that SFML frameworks are only available as release libraries unlike dylibs which
|
||||
# are available for both release and debug modes.
|
||||
#
|
||||
# If SFML is not installed in a standard path, you can use the SFML_ROOT CMake (or environment) variable
|
||||
# to tell CMake where SFML is.
|
||||
#
|
||||
# Output
|
||||
# ------
|
||||
#
|
||||
# This script defines the following variables:
|
||||
# - For each specified module XXX (system, window, graphics, network, audio, main):
|
||||
# - SFML_XXX_LIBRARY_DEBUG: the name of the debug library of the xxx module (set to SFML_XXX_LIBRARY_RELEASE is no debug version is found)
|
||||
# - SFML_XXX_LIBRARY_RELEASE: the name of the release library of the xxx module (set to SFML_XXX_LIBRARY_DEBUG is no release version is found)
|
||||
# - SFML_XXX_LIBRARY: the name of the library to link to for the xxx module (includes both debug and optimized names if necessary)
|
||||
# - SFML_XXX_FOUND: true if either the debug or release library of the xxx module is found
|
||||
# - SFML_XXX_DEPENDENCIES: the list of libraries the module depends on, in case of static linking
|
||||
# - SFML_LIBRARIES: the list of all libraries corresponding to the required modules
|
||||
# - SFML_FOUND: true if all the required modules are found
|
||||
# - SFML_INCLUDE_DIR: the path where SFML headers are located (the directory containing the SFML/Config.hpp file)
|
||||
# - SFML_DEPENDENCIES: the list of libraries SFML depends on, in case of static linking
|
||||
#
|
||||
# example:
|
||||
# find_package(SFML 2 COMPONENTS system window graphics audio REQUIRED)
|
||||
# include_directories(${SFML_INCLUDE_DIR})
|
||||
# add_executable(myapp ...)
|
||||
# target_link_libraries(myapp ${SFML_LIBRARIES})
|
||||
|
||||
# define the SFML_STATIC macro if static build was chosen
|
||||
if(SFML_STATIC_LIBRARIES)
|
||||
add_definitions(-DSFML_STATIC)
|
||||
endif()
|
||||
|
||||
# define the list of search paths for headers and libraries
|
||||
set(FIND_SFML_PATHS
|
||||
${SFML_ROOT}
|
||||
$ENV{SFML_ROOT}
|
||||
~/Library/Frameworks
|
||||
/Library/Frameworks
|
||||
/usr/local
|
||||
/usr
|
||||
/sw
|
||||
/opt/local
|
||||
/opt/csw
|
||||
/opt)
|
||||
|
||||
# find the SFML include directory
|
||||
find_path(SFML_INCLUDE_DIR SFML/Config.hpp
|
||||
PATH_SUFFIXES include
|
||||
PATHS ${FIND_SFML_PATHS})
|
||||
|
||||
# check the version number
|
||||
set(SFML_VERSION_OK TRUE)
|
||||
if(SFML_FIND_VERSION AND SFML_INCLUDE_DIR)
|
||||
# extract the major and minor version numbers from SFML/Config.hpp
|
||||
# we have to handle framework a little bit differently:
|
||||
if("${SFML_INCLUDE_DIR}" MATCHES "SFML.framework")
|
||||
set(SFML_CONFIG_HPP_INPUT "${SFML_INCLUDE_DIR}/Headers/Config.hpp")
|
||||
else()
|
||||
set(SFML_CONFIG_HPP_INPUT "${SFML_INCLUDE_DIR}/SFML/Config.hpp")
|
||||
endif()
|
||||
FILE(READ "${SFML_CONFIG_HPP_INPUT}" SFML_CONFIG_HPP_CONTENTS)
|
||||
STRING(REGEX REPLACE ".*#define SFML_VERSION_MAJOR ([0-9]+).*" "\\1" SFML_VERSION_MAJOR "${SFML_CONFIG_HPP_CONTENTS}")
|
||||
STRING(REGEX REPLACE ".*#define SFML_VERSION_MINOR ([0-9]+).*" "\\1" SFML_VERSION_MINOR "${SFML_CONFIG_HPP_CONTENTS}")
|
||||
STRING(REGEX REPLACE ".*#define SFML_VERSION_PATCH ([0-9]+).*" "\\1" SFML_VERSION_PATCH "${SFML_CONFIG_HPP_CONTENTS}")
|
||||
if (NOT "${SFML_VERSION_PATCH}" MATCHES "^[0-9]+$")
|
||||
set(SFML_VERSION_PATCH 0)
|
||||
endif()
|
||||
math(EXPR SFML_REQUESTED_VERSION "${SFML_FIND_VERSION_MAJOR} * 10000 + ${SFML_FIND_VERSION_MINOR} * 100 + ${SFML_FIND_VERSION_PATCH}")
|
||||
|
||||
# if we could extract them, compare with the requested version number
|
||||
if (SFML_VERSION_MAJOR)
|
||||
# transform version numbers to an integer
|
||||
math(EXPR SFML_VERSION "${SFML_VERSION_MAJOR} * 10000 + ${SFML_VERSION_MINOR} * 100 + ${SFML_VERSION_PATCH}")
|
||||
|
||||
# compare them
|
||||
if(SFML_VERSION LESS SFML_REQUESTED_VERSION)
|
||||
set(SFML_VERSION_OK FALSE)
|
||||
endif()
|
||||
else()
|
||||
# SFML version is < 2.0
|
||||
if (SFML_REQUESTED_VERSION GREATER 10900)
|
||||
set(SFML_VERSION_OK FALSE)
|
||||
set(SFML_VERSION_MAJOR 1)
|
||||
set(SFML_VERSION_MINOR x)
|
||||
set(SFML_VERSION_PATCH x)
|
||||
endif()
|
||||
endif()
|
||||
endif()
|
||||
|
||||
# find the requested modules
|
||||
set(SFML_FOUND TRUE) # will be set to false if one of the required modules is not found
|
||||
foreach(FIND_SFML_COMPONENT ${SFML_FIND_COMPONENTS})
|
||||
string(TOLOWER ${FIND_SFML_COMPONENT} FIND_SFML_COMPONENT_LOWER)
|
||||
string(TOUPPER ${FIND_SFML_COMPONENT} FIND_SFML_COMPONENT_UPPER)
|
||||
set(FIND_SFML_COMPONENT_NAME sfml-${FIND_SFML_COMPONENT_LOWER})
|
||||
|
||||
# no suffix for sfml-main, it is always a static library
|
||||
if(FIND_SFML_COMPONENT_LOWER STREQUAL "main")
|
||||
# release library
|
||||
find_library(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_RELEASE
|
||||
NAMES ${FIND_SFML_COMPONENT_NAME}
|
||||
PATH_SUFFIXES lib64 lib
|
||||
PATHS ${FIND_SFML_PATHS})
|
||||
|
||||
# debug library
|
||||
find_library(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DEBUG
|
||||
NAMES ${FIND_SFML_COMPONENT_NAME}-d
|
||||
PATH_SUFFIXES lib64 lib
|
||||
PATHS ${FIND_SFML_PATHS})
|
||||
else()
|
||||
# static release library
|
||||
find_library(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_STATIC_RELEASE
|
||||
NAMES ${FIND_SFML_COMPONENT_NAME}-s
|
||||
PATH_SUFFIXES lib64 lib
|
||||
PATHS ${FIND_SFML_PATHS})
|
||||
|
||||
# static debug library
|
||||
find_library(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_STATIC_DEBUG
|
||||
NAMES ${FIND_SFML_COMPONENT_NAME}-s-d
|
||||
PATH_SUFFIXES lib64 lib
|
||||
PATHS ${FIND_SFML_PATHS})
|
||||
|
||||
# dynamic release library
|
||||
find_library(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DYNAMIC_RELEASE
|
||||
NAMES ${FIND_SFML_COMPONENT_NAME}
|
||||
PATH_SUFFIXES lib64 lib
|
||||
PATHS ${FIND_SFML_PATHS})
|
||||
|
||||
# dynamic debug library
|
||||
find_library(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DYNAMIC_DEBUG
|
||||
NAMES ${FIND_SFML_COMPONENT_NAME}-d
|
||||
PATH_SUFFIXES lib64 lib
|
||||
PATHS ${FIND_SFML_PATHS})
|
||||
|
||||
# choose the entries that fit the requested link type
|
||||
if(SFML_STATIC_LIBRARIES)
|
||||
if(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_STATIC_RELEASE)
|
||||
set(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_RELEASE ${SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_STATIC_RELEASE})
|
||||
endif()
|
||||
if(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_STATIC_DEBUG)
|
||||
set(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DEBUG ${SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_STATIC_DEBUG})
|
||||
endif()
|
||||
else()
|
||||
if(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DYNAMIC_RELEASE)
|
||||
set(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_RELEASE ${SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DYNAMIC_RELEASE})
|
||||
endif()
|
||||
if(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DYNAMIC_DEBUG)
|
||||
set(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DEBUG ${SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DYNAMIC_DEBUG})
|
||||
endif()
|
||||
endif()
|
||||
endif()
|
||||
|
||||
if (SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DEBUG OR SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_RELEASE)
|
||||
# library found
|
||||
set(SFML_${FIND_SFML_COMPONENT_UPPER}_FOUND TRUE)
|
||||
|
||||
# if both are found, set SFML_XXX_LIBRARY to contain both
|
||||
if (SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DEBUG AND SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_RELEASE)
|
||||
set(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY debug ${SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DEBUG}
|
||||
optimized ${SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_RELEASE})
|
||||
endif()
|
||||
|
||||
# if only one debug/release variant is found, set the other to be equal to the found one
|
||||
if (SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DEBUG AND NOT SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_RELEASE)
|
||||
# debug and not release
|
||||
set(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_RELEASE ${SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DEBUG})
|
||||
set(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY ${SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DEBUG})
|
||||
endif()
|
||||
if (SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_RELEASE AND NOT SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DEBUG)
|
||||
# release and not debug
|
||||
set(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DEBUG ${SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_RELEASE})
|
||||
set(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY ${SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_RELEASE})
|
||||
endif()
|
||||
else()
|
||||
# library not found
|
||||
set(SFML_FOUND FALSE)
|
||||
set(SFML_${FIND_SFML_COMPONENT_UPPER}_FOUND FALSE)
|
||||
set(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY "")
|
||||
set(FIND_SFML_MISSING "${FIND_SFML_MISSING} SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY")
|
||||
endif()
|
||||
|
||||
# mark as advanced
|
||||
MARK_AS_ADVANCED(SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY
|
||||
SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_RELEASE
|
||||
SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DEBUG
|
||||
SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_STATIC_RELEASE
|
||||
SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_STATIC_DEBUG
|
||||
SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DYNAMIC_RELEASE
|
||||
SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY_DYNAMIC_DEBUG)
|
||||
|
||||
# add to the global list of libraries
|
||||
set(SFML_LIBRARIES ${SFML_LIBRARIES} "${SFML_${FIND_SFML_COMPONENT_UPPER}_LIBRARY}")
|
||||
endforeach()
|
||||
|
||||
# in case of static linking, we must also define the list of all the dependencies of SFML libraries
|
||||
if(SFML_STATIC_LIBRARIES)
|
||||
|
||||
# detect the OS
|
||||
if(${CMAKE_SYSTEM_NAME} MATCHES "Windows")
|
||||
set(FIND_SFML_OS_WINDOWS 1)
|
||||
elseif(${CMAKE_SYSTEM_NAME} MATCHES "Linux")
|
||||
set(FIND_SFML_OS_LINUX 1)
|
||||
elseif(${CMAKE_SYSTEM_NAME} MATCHES "FreeBSD")
|
||||
set(FIND_SFML_OS_FREEBSD 1)
|
||||
elseif(${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
|
||||
set(FIND_SFML_OS_MACOSX 1)
|
||||
endif()
|
||||
|
||||
# start with an empty list
|
||||
set(SFML_DEPENDENCIES)
|
||||
set(FIND_SFML_DEPENDENCIES_NOTFOUND)
|
||||
|
||||
# macro that searches for a 3rd-party library
|
||||
macro(find_sfml_dependency output friendlyname)
|
||||
# No lookup in environment variables (PATH on Windows), as they may contain wrong library versions
|
||||
find_library(${output} NAMES ${ARGN} PATHS ${FIND_SFML_PATHS} PATH_SUFFIXES lib NO_SYSTEM_ENVIRONMENT_PATH)
|
||||
if(${${output}} STREQUAL "${output}-NOTFOUND")
|
||||
unset(output)
|
||||
set(FIND_SFML_DEPENDENCIES_NOTFOUND "${FIND_SFML_DEPENDENCIES_NOTFOUND} ${friendlyname}")
|
||||
endif()
|
||||
endmacro()
|
||||
|
||||
# sfml-system
|
||||
list(FIND SFML_FIND_COMPONENTS "system" FIND_SFML_SYSTEM_COMPONENT)
|
||||
if(NOT ${FIND_SFML_SYSTEM_COMPONENT} EQUAL -1)
|
||||
|
||||
# update the list -- these are only system libraries, no need to find them
|
||||
if(FIND_SFML_OS_LINUX OR FIND_SFML_OS_FREEBSD OR FIND_SFML_OS_MACOSX)
|
||||
set(SFML_SYSTEM_DEPENDENCIES "pthread")
|
||||
endif()
|
||||
if(FIND_SFML_OS_LINUX)
|
||||
set(SFML_SYSTEM_DEPENDENCIES ${SFML_SYSTEM_DEPENDENCIES} "rt")
|
||||
endif()
|
||||
if(FIND_SFML_OS_WINDOWS)
|
||||
set(SFML_SYSTEM_DEPENDENCIES "winmm")
|
||||
endif()
|
||||
set(SFML_DEPENDENCIES ${SFML_SYSTEM_DEPENDENCIES} ${SFML_DEPENDENCIES})
|
||||
endif()
|
||||
|
||||
# sfml-network
|
||||
list(FIND SFML_FIND_COMPONENTS "network" FIND_SFML_NETWORK_COMPONENT)
|
||||
if(NOT ${FIND_SFML_NETWORK_COMPONENT} EQUAL -1)
|
||||
|
||||
# update the list -- these are only system libraries, no need to find them
|
||||
if(FIND_SFML_OS_WINDOWS)
|
||||
set(SFML_NETWORK_DEPENDENCIES "ws2_32")
|
||||
endif()
|
||||
set(SFML_DEPENDENCIES ${SFML_NETWORK_DEPENDENCIES} ${SFML_DEPENDENCIES})
|
||||
endif()
|
||||
|
||||
# sfml-window
|
||||
list(FIND SFML_FIND_COMPONENTS "window" FIND_SFML_WINDOW_COMPONENT)
|
||||
if(NOT ${FIND_SFML_WINDOW_COMPONENT} EQUAL -1)
|
||||
|
||||
# find libraries
|
||||
if(FIND_SFML_OS_LINUX OR FIND_SFML_OS_FREEBSD)
|
||||
find_sfml_dependency(X11_LIBRARY "X11" X11)
|
||||
find_sfml_dependency(LIBXCB_LIBRARIES "XCB" xcb libxcb)
|
||||
find_sfml_dependency(X11_XCB_LIBRARY "X11-xcb" X11-xcb libX11-xcb)
|
||||
find_sfml_dependency(XCB_RANDR_LIBRARY "xcb-randr" xcb-randr libxcb-randr)
|
||||
find_sfml_dependency(XCB_IMAGE_LIBRARY "xcb-image" xcb-image libxcb-image)
|
||||
endif()
|
||||
|
||||
if(FIND_SFML_OS_LINUX)
|
||||
find_sfml_dependency(UDEV_LIBRARIES "UDev" udev libudev)
|
||||
endif()
|
||||
|
||||
# update the list
|
||||
if(FIND_SFML_OS_WINDOWS)
|
||||
set(SFML_WINDOW_DEPENDENCIES ${SFML_WINDOW_DEPENDENCIES} "opengl32" "winmm" "gdi32")
|
||||
elseif(FIND_SFML_OS_LINUX)
|
||||
set(SFML_WINDOW_DEPENDENCIES ${SFML_WINDOW_DEPENDENCIES} "GL" ${X11_LIBRARY} ${LIBXCB_LIBRARIES} ${X11_XCB_LIBRARY} ${XCB_RANDR_LIBRARY} ${XCB_IMAGE_LIBRARY} ${UDEV_LIBRARIES})
|
||||
elseif(FIND_SFML_OS_FREEBSD)
|
||||
set(SFML_WINDOW_DEPENDENCIES ${SFML_WINDOW_DEPENDENCIES} "GL" ${X11_LIBRARY} ${LIBXCB_LIBRARIES} ${X11_XCB_LIBRARY} ${XCB_RANDR_LIBRARY} ${XCB_IMAGE_LIBRARY} "usbhid")
|
||||
elseif(FIND_SFML_OS_MACOSX)
|
||||
set(SFML_WINDOW_DEPENDENCIES ${SFML_WINDOW_DEPENDENCIES} "-framework OpenGL -framework Foundation -framework AppKit -framework IOKit -framework Carbon")
|
||||
endif()
|
||||
set(SFML_DEPENDENCIES ${SFML_WINDOW_DEPENDENCIES} ${SFML_DEPENDENCIES})
|
||||
endif()
|
||||
|
||||
# sfml-graphics
|
||||
list(FIND SFML_FIND_COMPONENTS "graphics" FIND_SFML_GRAPHICS_COMPONENT)
|
||||
if(NOT ${FIND_SFML_GRAPHICS_COMPONENT} EQUAL -1)
|
||||
|
||||
# find libraries
|
||||
find_sfml_dependency(FREETYPE_LIBRARY "FreeType" freetype)
|
||||
find_sfml_dependency(JPEG_LIBRARY "libjpeg" jpeg)
|
||||
|
||||
# update the list
|
||||
set(SFML_GRAPHICS_DEPENDENCIES ${FREETYPE_LIBRARY} ${JPEG_LIBRARY})
|
||||
set(SFML_DEPENDENCIES ${SFML_GRAPHICS_DEPENDENCIES} ${SFML_DEPENDENCIES})
|
||||
endif()
|
||||
|
||||
# sfml-audio
|
||||
list(FIND SFML_FIND_COMPONENTS "audio" FIND_SFML_AUDIO_COMPONENT)
|
||||
if(NOT ${FIND_SFML_AUDIO_COMPONENT} EQUAL -1)
|
||||
|
||||
# find libraries
|
||||
find_sfml_dependency(OPENAL_LIBRARY "OpenAL" openal openal32)
|
||||
find_sfml_dependency(OGG_LIBRARY "Ogg" ogg)
|
||||
find_sfml_dependency(VORBIS_LIBRARY "Vorbis" vorbis)
|
||||
find_sfml_dependency(VORBISFILE_LIBRARY "VorbisFile" vorbisfile)
|
||||
find_sfml_dependency(VORBISENC_LIBRARY "VorbisEnc" vorbisenc)
|
||||
find_sfml_dependency(FLAC_LIBRARY "FLAC" FLAC)
|
||||
|
||||
# update the list
|
||||
set(SFML_AUDIO_DEPENDENCIES ${OPENAL_LIBRARY} ${FLAC_LIBRARY} ${VORBISENC_LIBRARY} ${VORBISFILE_LIBRARY} ${VORBIS_LIBRARY} ${OGG_LIBRARY})
|
||||
set(SFML_DEPENDENCIES ${SFML_DEPENDENCIES} ${SFML_AUDIO_DEPENDENCIES})
|
||||
endif()
|
||||
|
||||
endif()
|
||||
|
||||
# handle errors
|
||||
if(NOT SFML_VERSION_OK)
|
||||
# SFML version not ok
|
||||
set(FIND_SFML_ERROR "SFML found but version too low (requested: ${SFML_FIND_VERSION}, found: ${SFML_VERSION_MAJOR}.${SFML_VERSION_MINOR}.${SFML_VERSION_PATCH})")
|
||||
set(SFML_FOUND FALSE)
|
||||
elseif(SFML_STATIC_LIBRARIES AND FIND_SFML_DEPENDENCIES_NOTFOUND)
|
||||
set(FIND_SFML_ERROR "SFML found but some of its dependencies are missing (${FIND_SFML_DEPENDENCIES_NOTFOUND})")
|
||||
set(SFML_FOUND FALSE)
|
||||
elseif(NOT SFML_FOUND)
|
||||
# include directory or library not found
|
||||
set(FIND_SFML_ERROR "Could NOT find SFML (missing: ${FIND_SFML_MISSING})")
|
||||
endif()
|
||||
if (NOT SFML_FOUND)
|
||||
if(SFML_FIND_REQUIRED)
|
||||
# fatal error
|
||||
message(FATAL_ERROR ${FIND_SFML_ERROR})
|
||||
elseif(NOT SFML_FIND_QUIETLY)
|
||||
# error but continue
|
||||
message("${FIND_SFML_ERROR}")
|
||||
endif()
|
||||
endif()
|
||||
|
||||
# handle success
|
||||
if(SFML_FOUND AND NOT SFML_FIND_QUIETLY)
|
||||
message(STATUS "Found SFML ${SFML_VERSION_MAJOR}.${SFML_VERSION_MINOR}.${SFML_VERSION_PATCH} in ${SFML_INCLUDE_DIR}")
|
||||
endif()
|
||||
|
||||
@ -0,0 +1,4 @@
|
||||
|
||||
##About
|
||||
|
||||
A simple rework of the CPU based Conway's game of life simulation on the GPU
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
After Width: | Height: | Size: 322 KiB |
|
After Width: | Height: | Size: 21 KiB |
@ -0,0 +1,149 @@
|
||||
#pragma once
|
||||
|
||||
#include <string>
|
||||
#include <SFML/Graphics.hpp>
|
||||
#include <unordered_map>
|
||||
#include <iostream>
|
||||
#include "Vector4.hpp"
|
||||
#include <string.h>
|
||||
#include <memory>
|
||||
|
||||
#ifdef linux
|
||||
#include <CL/cl.h>
|
||||
#include <CL/opencl.h>
|
||||
#include <GL/glx.h>
|
||||
|
||||
#elif defined _WIN32
|
||||
#define CL_USE_DEPRECATED_OPENCL_1_2_APIS
|
||||
#include <CL/cl_gl.h>
|
||||
#include <CL/cl.h>
|
||||
#include <CL/opencl.h>
|
||||
|
||||
// Note: windows.h must be included before Gl/GL.h
|
||||
#include <windows.h>
|
||||
#include <GL/GL.h>
|
||||
|
||||
#elif defined TARGET_OS_MAC
|
||||
#include <OpenCL/opencl.h>
|
||||
|
||||
#endif
|
||||
|
||||
|
||||
class OpenCL {
|
||||
|
||||
public:
|
||||
|
||||
OpenCL();
|
||||
~OpenCL();
|
||||
|
||||
// command queues are associated with a device and context, so for multi-gpu applications you would need
|
||||
// multiple command queues
|
||||
|
||||
|
||||
// CONTEXTS
|
||||
// - An OpenCL context is created with one or more devices. Contexts are used by the OpenCL runtime
|
||||
// for managing objects such as command - queues, memory, program and kernel objects and for executing
|
||||
// kernels on one or more devices specified in the context.
|
||||
// - Contexts cannot be created using more than one platform!
|
||||
|
||||
bool init();
|
||||
|
||||
bool compile_kernel(std::string kernel_path, std::string kernel_name);
|
||||
|
||||
// Create an image buffer from an SF texture. Access Type is the read/write specifier required by OpenCL
|
||||
bool create_image_buffer_from_texture(std::string buffer_name, sf::Texture* texture, cl_int access_type);
|
||||
|
||||
// Have CL create and manage the texture for the image buffer. Access Type is the read/write specifier required by OpenCL
|
||||
bool create_image_buffer(std::string buffer_name, sf::Vector2i size, sf::Vector2f position, cl_int access_type);
|
||||
|
||||
// Create a buffer with CL_MEM_READ_ONLY and CL_MEM_COPY_HOST_PTR
|
||||
int create_buffer(std::string buffer_name, cl_uint size, void* data);
|
||||
|
||||
// Create a buffer with user defined data access flags
|
||||
int create_buffer(std::string buffer_name, cl_uint size, void* data, cl_mem_flags flags);
|
||||
|
||||
int set_kernel_arg(std::string kernel_name, int index, std::string buffer_name);
|
||||
|
||||
void run_kernel(std::string kernel_name, sf::Vector2i work_size);
|
||||
|
||||
void draw(sf::RenderWindow *window);
|
||||
|
||||
class device {
|
||||
|
||||
public:
|
||||
|
||||
#pragma pack(push, 1)
|
||||
struct packed_data {
|
||||
|
||||
cl_device_type device_type;
|
||||
cl_uint clock_frequency;
|
||||
char opencl_version[64];
|
||||
cl_uint compute_units;
|
||||
char device_extensions[1024];
|
||||
char device_name[256];
|
||||
char platform_name[128];
|
||||
};
|
||||
#pragma pack(pop)
|
||||
|
||||
device(cl_device_id device_id, cl_platform_id platform_id);
|
||||
device(const device& d);
|
||||
void print(std::ostream& stream) const;
|
||||
void print_packed_data(std::ostream& stream);
|
||||
|
||||
cl_device_id getDeviceId() const { return device_id; };
|
||||
cl_platform_id getPlatformId() const { return platform_id; };
|
||||
|
||||
private:
|
||||
|
||||
packed_data data;
|
||||
|
||||
cl_device_id device_id;
|
||||
cl_platform_id platform_id;
|
||||
|
||||
cl_bool is_little_endian = false;
|
||||
bool cl_gl_sharing = false;
|
||||
|
||||
};
|
||||
|
||||
private:
|
||||
|
||||
|
||||
int error = 0;
|
||||
|
||||
|
||||
// The device which we have selected according to certain criteria
|
||||
cl_platform_id platform_id;
|
||||
cl_device_id device_id;
|
||||
|
||||
// The GL shared context and its subsiquently generated command queue
|
||||
cl_context context;
|
||||
cl_command_queue command_queue;
|
||||
|
||||
// Maps which contain a mapping from "name" to the host side CL memory object
|
||||
std::unordered_map<std::string, cl_kernel> kernel_map;
|
||||
std::unordered_map<std::string, cl_mem> buffer_map;
|
||||
std::unordered_map<std::string, std::pair<sf::Sprite, std::unique_ptr<sf::Texture>>> image_map;
|
||||
std::vector<device> device_list;
|
||||
|
||||
// Query the hardware on this machine and store the devices
|
||||
bool aquire_hardware();
|
||||
|
||||
// After aquiring hardware, create a shared context using platform specific CL commands
|
||||
bool create_shared_context();
|
||||
|
||||
// Command queues must be created with a valid context
|
||||
bool create_command_queue();
|
||||
|
||||
|
||||
// Store a cl_mem object in the buffer map <string:name, cl_mem:buffer>
|
||||
bool store_buffer(cl_mem buffer, std::string buffer_name);
|
||||
|
||||
// Using CL release the memory object and remove the KVP associated with the buffer name
|
||||
bool release_buffer(std::string buffer_name);
|
||||
|
||||
bool load_config();
|
||||
void save_config();
|
||||
|
||||
static bool vr_assert(int error_code, std::string function_name);
|
||||
|
||||
};
|
||||
@ -0,0 +1,479 @@
|
||||
////////////////////////////////////////////////////////////
|
||||
//
|
||||
// This is a small addition to the SFML sf::Vector templates which
|
||||
// adds a sf::Vector4(f, i, u)
|
||||
//
|
||||
////////////////////////////////////////////////////////////
|
||||
//
|
||||
// SFML - Simple and Fast Multimedia Library
|
||||
// Copyright (C) 2007-2016 Laurent Gomila (laurent@sfml-dev.org)
|
||||
//
|
||||
// This software is provided 'as-is', without any express or implied warranty.
|
||||
// In no event will the authors be held liable for any damages arising from the use of this software.
|
||||
//
|
||||
// Permission is granted to anyone to use this software for any purpose,
|
||||
// including commercial applications, and to alter it and redistribute it freely,
|
||||
// subject to the following restrictions:
|
||||
//
|
||||
// 1. The origin of this software must not be misrepresented;
|
||||
// you must not claim that you wrote the original software.
|
||||
// If you use this software in a product, an acknowledgment
|
||||
// in the product documentation would be appreciated but is not required.
|
||||
//
|
||||
// 2. Altered source versions must be plainly marked as such,
|
||||
// and must not be misrepresented as being the original software.
|
||||
//
|
||||
// 3. This notice may not be removed or altered from any source distribution.
|
||||
//
|
||||
////////////////////////////////////////////////////////////
|
||||
|
||||
#ifndef SFML_VECTOR4_H
|
||||
#define SFML_VECTOR4_H
|
||||
|
||||
namespace sf {
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \brief Utility template class for manipulating
|
||||
/// 2-dimensional vectors
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
class Vector4 {
|
||||
public:
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \brief Default constructor
|
||||
///
|
||||
/// Creates a Vector4(0, 0).
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
Vector4();
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \brief Construct the vector from its coordinates
|
||||
///
|
||||
/// \param X X coordinate
|
||||
/// \param Y Y coordinate
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
Vector4(T X, T Y, T Z, T W);
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \brief Construct the vector from another type of vector
|
||||
///
|
||||
/// This constructor doesn't replace the copy constructor,
|
||||
/// it's called only when U != T.
|
||||
/// A call to this constructor will fail to compile if U
|
||||
/// is not convertible to T.
|
||||
///
|
||||
/// \param vector Vector to convert
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename U>
|
||||
explicit Vector4(const Vector4<U>& vector);
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
// Member data
|
||||
////////////////////////////////////////////////////////////
|
||||
T x; ///< X coordinate of the vector
|
||||
T y; ///< Y coordinate of the vector
|
||||
T z; ///< Z coordinate of the vector
|
||||
T w; ///< W coordinate of the vector
|
||||
};
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \relates Vector4
|
||||
/// \brief Overload of unary operator -
|
||||
///
|
||||
/// \param right Vector to negate
|
||||
///
|
||||
/// \return Memberwise opposite of the vector
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
Vector4<T> operator -(const Vector4<T>& right);
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \relates Vector4
|
||||
/// \brief Overload of binary operator +=
|
||||
///
|
||||
/// This operator performs a memberwise addition of both vectors,
|
||||
/// and assigns the result to \a left.
|
||||
///
|
||||
/// \param left Left operand (a vector)
|
||||
/// \param right Right operand (a vector)
|
||||
///
|
||||
/// \return Reference to \a left
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
Vector4<T>& operator +=(Vector4<T>& left, const Vector4<T>& right);
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \relates Vector4
|
||||
/// \brief Overload of binary operator -=
|
||||
///
|
||||
/// This operator performs a memberwise subtraction of both vectors,
|
||||
/// and assigns the result to \a left.
|
||||
///
|
||||
/// \param left Left operand (a vector)
|
||||
/// \param right Right operand (a vector)
|
||||
///
|
||||
/// \return Reference to \a left
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
Vector4<T>& operator -=(Vector4<T>& left, const Vector4<T>& right);
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \relates Vector4
|
||||
/// \brief Overload of binary operator +
|
||||
///
|
||||
/// \param left Left operand (a vector)
|
||||
/// \param right Right operand (a vector)
|
||||
///
|
||||
/// \return Memberwise addition of both vectors
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
Vector4<T> operator +(const Vector4<T>& left, const Vector4<T>& right);
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \relates Vector4
|
||||
/// \brief Overload of binary operator -
|
||||
///
|
||||
/// \param left Left operand (a vector)
|
||||
/// \param right Right operand (a vector)
|
||||
///
|
||||
/// \return Memberwise subtraction of both vectors
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
Vector4<T> operator -(const Vector4<T>& left, const Vector4<T>& right);
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \relates Vector4
|
||||
/// \brief Overload of binary operator *
|
||||
///
|
||||
/// \param left Left operand (a vector)
|
||||
/// \param right Right operand (a scalar value)
|
||||
///
|
||||
/// \return Memberwise multiplication by \a right
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
Vector4<T> operator *(const Vector4<T>& left, T right);
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \relates Vector4
|
||||
/// \brief Overload of binary operator *
|
||||
///
|
||||
/// \param left Left operand (a scalar value)
|
||||
/// \param right Right operand (a vector)
|
||||
///
|
||||
/// \return Memberwise multiplication by \a left
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
Vector4<T> operator *(T left, const Vector4<T>& right);
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \relates Vector4
|
||||
/// \brief Overload of binary operator *=
|
||||
///
|
||||
/// This operator performs a memberwise multiplication by \a right,
|
||||
/// and assigns the result to \a left.
|
||||
///
|
||||
/// \param left Left operand (a vector)
|
||||
/// \param right Right operand (a scalar value)
|
||||
///
|
||||
/// \return Reference to \a left
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
Vector4<T>& operator *=(Vector4<T>& left, T right);
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \relates Vector4
|
||||
/// \brief Overload of binary operator /
|
||||
///
|
||||
/// \param left Left operand (a vector)
|
||||
/// \param right Right operand (a scalar value)
|
||||
///
|
||||
/// \return Memberwise division by \a right
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
Vector4<T> operator /(const Vector4<T>& left, T right);
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \relates Vector4
|
||||
/// \brief Overload of binary operator /=
|
||||
///
|
||||
/// This operator performs a memberwise division by \a right,
|
||||
/// and assigns the result to \a left.
|
||||
///
|
||||
/// \param left Left operand (a vector)
|
||||
/// \param right Right operand (a scalar value)
|
||||
///
|
||||
/// \return Reference to \a left
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
Vector4<T>& operator /=(Vector4<T>& left, T right);
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \relates Vector4
|
||||
/// \brief Overload of binary operator ==
|
||||
///
|
||||
/// This operator compares strict equality between two vectors.
|
||||
///
|
||||
/// \param left Left operand (a vector)
|
||||
/// \param right Right operand (a vector)
|
||||
///
|
||||
/// \return True if \a left is equal to \a right
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
bool operator ==(const Vector4<T>& left, const Vector4<T>& right);
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \relates Vector4
|
||||
/// \brief Overload of binary operator !=
|
||||
///
|
||||
/// This operator compares strict difference between two vectors.
|
||||
///
|
||||
/// \param left Left operand (a vector)
|
||||
/// \param right Right operand (a vector)
|
||||
///
|
||||
/// \return True if \a left is not equal to \a right
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
bool operator !=(const Vector4<T>& left, const Vector4<T>& right);
|
||||
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
inline Vector4<T>::Vector4() :
|
||||
x(0),
|
||||
y(0),
|
||||
z(0),
|
||||
w(0){
|
||||
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
inline Vector4<T>::Vector4(T X, T Y, T Z, T W) :
|
||||
x(X),
|
||||
y(Y),
|
||||
z(Z),
|
||||
w(W) {
|
||||
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
template <typename U>
|
||||
inline Vector4<T>::Vector4(const Vector4<U>& vector) :
|
||||
x(static_cast<T>(vector.x)),
|
||||
y(static_cast<T>(vector.y)),
|
||||
z(static_cast<T>(vector.z)),
|
||||
w(static_cast<T>(vector.w)) {
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
inline Vector4<T> operator -(const Vector4<T>& right) {
|
||||
return Vector4<T>(
|
||||
-right.x,
|
||||
-right.y,
|
||||
-right.z,
|
||||
-right.w
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
inline Vector4<T>& operator +=(Vector4<T>& left, const Vector4<T>& right) {
|
||||
left.x += right.x;
|
||||
left.y += right.y;
|
||||
left.z += right.z;
|
||||
left.w += right.w;
|
||||
|
||||
return left;
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
inline Vector4<T>& operator -=(Vector4<T>& left, const Vector4<T>& right) {
|
||||
left.x -= right.x;
|
||||
left.y -= right.y;
|
||||
left.z -= right.z;
|
||||
left.w -= right.w;
|
||||
|
||||
return left;
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
inline Vector4<T> operator +(const Vector4<T>& left, const Vector4<T>& right) {
|
||||
return Vector4<T>(
|
||||
left.x + right.x,
|
||||
left.y + right.y,
|
||||
left.z + right.z,
|
||||
left.w + right.w
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
inline Vector4<T> operator -(const Vector4<T>& left, const Vector4<T>& right) {
|
||||
return Vector4<T>(
|
||||
left.x - right.x,
|
||||
left.y - right.y,
|
||||
left.z - right.z,
|
||||
left.w - right.w
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
inline Vector4<T> operator *(const Vector4<T>& left, T right) {
|
||||
return Vector4<T>(
|
||||
left.x * right,
|
||||
left.y * right,
|
||||
left.z * right,
|
||||
left.w * right
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
inline Vector4<T> operator *(T left, const Vector4<T>& right) {
|
||||
return Vector4<T>(
|
||||
right.x * left,
|
||||
right.y * left,
|
||||
right.z * left,
|
||||
right.w * left
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
inline Vector4<T>& operator *=(Vector4<T>& left, T right) {
|
||||
left.x *= right;
|
||||
left.y *= right;
|
||||
left.z *= right;
|
||||
left.w *= right;
|
||||
|
||||
return left;
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
inline Vector4<T> operator /(const Vector4<T>& left, T right) {
|
||||
return Vector4<T>(
|
||||
left.x / right,
|
||||
left.y / right,
|
||||
left.z / right,
|
||||
left.w / right
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
inline Vector4<T>& operator /=(Vector4<T>& left, T right) {
|
||||
left.x /= right;
|
||||
left.y /= right;
|
||||
left.z /= right;
|
||||
left.w /= right;
|
||||
|
||||
return left;
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
inline bool operator ==(const Vector4<T>& left, const Vector4<T>& right) {
|
||||
return
|
||||
(left.x == right.x) &&
|
||||
(left.y == right.y) &&
|
||||
(left.z == right.z) &&
|
||||
(left.w == right.w);;
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
template <typename T>
|
||||
inline bool operator !=(const Vector4<T>& left, const Vector4<T>& right) {
|
||||
return
|
||||
(left.x != right.x) ||
|
||||
(left.y != right.y) ||
|
||||
(left.z != right.z) ||
|
||||
(left.w != right.w);
|
||||
}
|
||||
|
||||
// Define the most common types
|
||||
typedef Vector4<int> Vector4i;
|
||||
typedef Vector4<unsigned int> Vector4u;
|
||||
typedef Vector4<float> Vector4f;
|
||||
|
||||
} // namespace sf
|
||||
|
||||
|
||||
#endif // SFML_Vector4_HPP
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
/// \class sf::Vector4
|
||||
/// \ingroup system
|
||||
///
|
||||
/// sf::Vector4 is a simple class that defines a mathematical
|
||||
/// vector with two coordinates (x and y). It can be used to
|
||||
/// represent anything that has two dimensions: a size, a point,
|
||||
/// a velocity, etc.
|
||||
///
|
||||
/// The template parameter T is the type of the coordinates. It
|
||||
/// can be any type that supports arithmetic operations (+, -, /, *)
|
||||
/// and comparisons (==, !=), for example int or float.
|
||||
///
|
||||
/// You generally don't have to care about the templated form (sf::Vector4<T>),
|
||||
/// the most common specializations have special typedefs:
|
||||
/// \li sf::Vector4<float> is sf::Vector4f
|
||||
/// \li sf::Vector4<int> is sf::Vector4i
|
||||
/// \li sf::Vector4<unsigned int> is sf::Vector4u
|
||||
///
|
||||
/// The sf::Vector4 class has a small and simple interface, its x and y members
|
||||
/// can be accessed directly (there are no accessors like setX(), getX()) and it
|
||||
/// contains no mathematical function like dot product, cross product, length, etc.
|
||||
///
|
||||
/// Usage example:
|
||||
/// \code
|
||||
/// sf::Vector4f v1(16.5f, 24.f);
|
||||
/// v1.x = 18.2f;
|
||||
/// float y = v1.y;
|
||||
///
|
||||
/// sf::Vector4f v2 = v1 * 5.f;
|
||||
/// sf::Vector4
|
||||
/// v3 = v1 + v2;
|
||||
///
|
||||
/// bool different = (v2 != v3);
|
||||
/// \endcode
|
||||
///
|
||||
/// Note: for 3-dimensional vectors, see sf::Vector3.
|
||||
///
|
||||
////////////////////////////////////////////////////////////
|
||||
@ -0,0 +1,159 @@
|
||||
#pragma once
|
||||
#include <SFML/Graphics.hpp>
|
||||
#include <SFML/Graphics/VertexArray.hpp>
|
||||
#include "Vector4.hpp"
|
||||
#include <math.h>
|
||||
#include <bitset>
|
||||
#include <iostream>
|
||||
#include <fstream>
|
||||
#include <sstream>
|
||||
#include <string>
|
||||
#include <iterator>
|
||||
#include <list>
|
||||
#include <algorithm>
|
||||
|
||||
|
||||
const double PI = 3.141592653589793238463;
|
||||
const float PI_F = 3.14159265358979f;
|
||||
|
||||
inline sf::Vector3f SphereToCart(sf::Vector2f i) {
|
||||
|
||||
auto r = sf::Vector3f(
|
||||
(1 * sin(i.y) * cos(i.x)),
|
||||
(1 * sin(i.y) * sin(i.x)),
|
||||
(1 * cos(i.y))
|
||||
);
|
||||
return r;
|
||||
};
|
||||
|
||||
inline sf::Vector3f SphereToCart(sf::Vector3f i) {
|
||||
|
||||
auto r = sf::Vector3f(
|
||||
(i.x * sin(i.z) * cos(i.y)),
|
||||
(i.x * sin(i.z) * sin(i.y)),
|
||||
(i.x * cos(i.z))
|
||||
);
|
||||
return r;
|
||||
};
|
||||
|
||||
|
||||
inline sf::Vector3f CartToSphere(sf::Vector3f in) {
|
||||
|
||||
auto r = sf::Vector3f(
|
||||
sqrt(in.x * in.x + in.y * in.y + in.z * in.z),
|
||||
atan(in.y / in.x),
|
||||
atan(sqrt(in.x * in.x + in.y * in.y) / in.z)
|
||||
);
|
||||
return r;
|
||||
};
|
||||
|
||||
inline sf::Vector2f CartToNormalizedSphere(sf::Vector3f in) {
|
||||
|
||||
auto r = sf::Vector2f(
|
||||
atan2(sqrt(in.x * in.x + in.y * in.y), in.z),
|
||||
atan2(in.y, in.x)
|
||||
);
|
||||
|
||||
return r;
|
||||
}
|
||||
|
||||
inline sf::Vector3f FixOrigin(sf::Vector3f base, sf::Vector3f head) {
|
||||
return head - base;
|
||||
}
|
||||
|
||||
inline sf::Vector3f Normalize(sf::Vector3f in) {
|
||||
|
||||
float multiplier = sqrt(in.x * in.x + in.y * in.y + in.z * in.z);
|
||||
auto r = sf::Vector3f(
|
||||
in.x / multiplier,
|
||||
in.y / multiplier,
|
||||
in.z / multiplier
|
||||
);
|
||||
return r;
|
||||
|
||||
}
|
||||
|
||||
inline float DotProduct(sf::Vector3f a, sf::Vector3f b){
|
||||
return a.x * b.x + a.y * b.y + a.z * b.z;
|
||||
}
|
||||
|
||||
inline float Magnitude(sf::Vector3f in){
|
||||
return sqrt(in.x * in.x + in.y * in.y + in.z * in.z);
|
||||
}
|
||||
|
||||
inline float AngleBetweenVectors(sf::Vector3f a, sf::Vector3f b){
|
||||
return acos(DotProduct(a, b) / (Magnitude(a) * Magnitude(b)));
|
||||
}
|
||||
|
||||
inline float DistanceBetweenPoints(sf::Vector3f a, sf::Vector3f b) {
|
||||
return sqrt(DotProduct(a, b));
|
||||
}
|
||||
|
||||
inline float DegreesToRadians(float in) {
|
||||
return static_cast<float>(in * PI / 180.0f);
|
||||
}
|
||||
|
||||
inline float RadiansToDegrees(float in) {
|
||||
return static_cast<float>(in * 180.0f / PI);
|
||||
}
|
||||
|
||||
inline std::string read_file(std::string file_name){
|
||||
std::ifstream input_file(file_name);
|
||||
|
||||
if (!input_file.is_open()){
|
||||
std::cout << file_name << " could not be opened" << std::endl;
|
||||
return "";
|
||||
}
|
||||
|
||||
std::stringstream buf;
|
||||
buf << input_file.rdbuf();
|
||||
input_file.close();
|
||||
return buf.str();
|
||||
}
|
||||
|
||||
inline void PrettyPrintUINT64(uint64_t i, std::stringstream* ss) {
|
||||
|
||||
*ss << "[" << std::bitset<15>(i) << "]";
|
||||
*ss << "[" << std::bitset<1>(i >> 15) << "]";
|
||||
*ss << "[" << std::bitset<8>(i >> 16) << "]";
|
||||
*ss << "[" << std::bitset<8>(i >> 24) << "]";
|
||||
*ss << "[" << std::bitset<32>(i >> 32) << "]";
|
||||
|
||||
}
|
||||
|
||||
inline void PrettyPrintUINT64(uint64_t i) {
|
||||
|
||||
std::cout << "[" << std::bitset<15>(i) << "]";
|
||||
std::cout << "[" << std::bitset<1>(i >> 15) << "]";
|
||||
std::cout << "[" << std::bitset<8>(i >> 16) << "]";
|
||||
std::cout << "[" << std::bitset<8>(i >> 24) << "]";
|
||||
std::cout << "[" << std::bitset<32>(i >> 32) << "]" << std::endl;
|
||||
|
||||
}
|
||||
|
||||
inline void DumpLog(std::stringstream* ss, std::string file_name) {
|
||||
|
||||
std::ofstream log_file;
|
||||
log_file.open(file_name);
|
||||
|
||||
log_file << ss->str();
|
||||
|
||||
log_file.close();
|
||||
|
||||
}
|
||||
|
||||
#ifdef _MSC_VER
|
||||
# include <intrin.h>
|
||||
# define __builtin_popcount _mm_popcnt_u32
|
||||
# define __builtin_popcountll _mm_popcnt_u64
|
||||
#endif
|
||||
|
||||
inline int count_bits(int32_t v) {
|
||||
|
||||
return static_cast<int>(__builtin_popcount(v));
|
||||
}
|
||||
|
||||
inline int count_bits(int64_t v) {
|
||||
|
||||
return static_cast<int>(__builtin_popcountll(v));
|
||||
}
|
||||
@ -0,0 +1,141 @@
|
||||
int pixel_to_index(int2 dimensions, int2 pixel) {
|
||||
|
||||
if (pixel.x >= 0 && pixel.x <= dimensions.x &&
|
||||
pixel.y >= 0 && pixel.x <= dimensions.y ){
|
||||
|
||||
return pixel.y * dimensions.x + pixel.x;
|
||||
}
|
||||
|
||||
return -1;
|
||||
}
|
||||
|
||||
|
||||
__kernel void conways (
|
||||
global int2* image_res,
|
||||
__write_only image2d_t image,
|
||||
global char* first_node_buffer,
|
||||
global char* second_node_buffer,
|
||||
global char* buffer_flip
|
||||
){
|
||||
|
||||
size_t x_pixel = get_global_id(0);
|
||||
size_t y_pixel = get_global_id(1);
|
||||
|
||||
|
||||
//printf(": %i", y_pixel);
|
||||
|
||||
int2 pixel = (int2)(x_pixel, y_pixel);
|
||||
|
||||
//if (pixel.x > 1800)
|
||||
// printf("%i, %i", pixel.x, pixel.y);
|
||||
|
||||
float4 dead = (float4)(.49, .68, .81, 1);
|
||||
float4 alive = (float4)(.49, .68, .71, .3);
|
||||
|
||||
// add all 8 blocks to neghbors
|
||||
int neighbors = 0;
|
||||
int val = 0;
|
||||
|
||||
if (*buffer_flip == 0){
|
||||
|
||||
// Top
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x, pixel.y+1));
|
||||
if (val >= 0)
|
||||
neighbors += first_node_buffer[val];
|
||||
|
||||
// Top Right
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x+1, pixel.y+1));
|
||||
if (val >= 0)
|
||||
neighbors += first_node_buffer[val];
|
||||
|
||||
// Right
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x+1, pixel.y));
|
||||
if (val >= 0)
|
||||
neighbors += first_node_buffer[val];
|
||||
|
||||
// Bottom Right
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x+1, pixel.y-1));
|
||||
if (val >= 0)
|
||||
neighbors += first_node_buffer[val];
|
||||
|
||||
// Bottom
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x, pixel.y-1));
|
||||
if (val >= 0)
|
||||
neighbors += first_node_buffer[val];
|
||||
|
||||
// Bottom Left
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x-1, pixel.y-1));
|
||||
if (val >= 0)
|
||||
neighbors += first_node_buffer[val];
|
||||
|
||||
// Left
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x-1, pixel.y));
|
||||
if (val >= 0)
|
||||
neighbors += first_node_buffer[val];
|
||||
|
||||
// Top Left
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x-1, pixel.y+1));
|
||||
if (val >= 0)
|
||||
neighbors += first_node_buffer[val];
|
||||
|
||||
int base = pixel_to_index(*image_res, pixel);
|
||||
if (neighbors == 3 || (neighbors == 2 && first_node_buffer[base])){
|
||||
write_imagef(image, pixel, alive);
|
||||
second_node_buffer[base] = 1;
|
||||
} else {
|
||||
write_imagef(image, pixel, dead);
|
||||
second_node_buffer[base] = 0;
|
||||
}
|
||||
|
||||
} else {
|
||||
|
||||
// Top
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x, pixel.y+1));
|
||||
if (val >= 0)
|
||||
neighbors += second_node_buffer[val];
|
||||
|
||||
// Top Right
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x+1, pixel.y+1));
|
||||
if (val >= 0)
|
||||
neighbors += second_node_buffer[val];
|
||||
|
||||
// Right
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x+1, pixel.y));
|
||||
if (val >= 0)
|
||||
neighbors += second_node_buffer[val];
|
||||
|
||||
// Bottom Right
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x+1, pixel.y-1));
|
||||
if (val >= 0)
|
||||
neighbors += second_node_buffer[val];
|
||||
|
||||
// Bottom
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x, pixel.y-1));
|
||||
if (val >= 0)
|
||||
neighbors += second_node_buffer[val];
|
||||
|
||||
// Bottom Left
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x-1, pixel.y-1));
|
||||
if (val >= 0)
|
||||
neighbors += second_node_buffer[val];
|
||||
|
||||
// Left
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x-1, pixel.y));
|
||||
if (val >= 0)
|
||||
neighbors += second_node_buffer[val];
|
||||
|
||||
// Top Left
|
||||
val = pixel_to_index(*image_res, (int2)(pixel.x-1, pixel.y+1));
|
||||
if (val >= 0)
|
||||
neighbors += second_node_buffer[val];
|
||||
|
||||
int base = pixel_to_index(*image_res, pixel);
|
||||
if (neighbors == 3 || (neighbors == 2 && second_node_buffer[base])){
|
||||
write_imagef(image, pixel, alive);
|
||||
first_node_buffer[base] = 1;
|
||||
} else {
|
||||
write_imagef(image, pixel, dead);
|
||||
first_node_buffer[base] = 0;
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,737 @@
|
||||
#include <OpenCL.h>
|
||||
#include "util.hpp"
|
||||
|
||||
|
||||
OpenCL::OpenCL() {
|
||||
}
|
||||
|
||||
OpenCL::~OpenCL() {
|
||||
}
|
||||
|
||||
void OpenCL::run_kernel(std::string kernel_name, sf::Vector2i work_size) {
|
||||
|
||||
size_t global_work_size[2] = { static_cast<size_t>(work_size.x), static_cast<size_t>(work_size.y) };
|
||||
|
||||
cl_kernel kernel = kernel_map.at(kernel_name);
|
||||
|
||||
error = clEnqueueAcquireGLObjects(command_queue, 1, &buffer_map.at("viewport_image"), 0, 0, 0);
|
||||
if (vr_assert(error, "clEnqueueAcquireGLObjects"))
|
||||
return;
|
||||
|
||||
//error = clEnqueueTask(command_queue, kernel, 0, NULL, NULL);
|
||||
error = clEnqueueNDRangeKernel(
|
||||
command_queue, kernel,
|
||||
2, NULL, global_work_size,
|
||||
NULL, 0, NULL, NULL);
|
||||
|
||||
if (vr_assert(error, "clEnqueueNDRangeKernel"))
|
||||
return;
|
||||
|
||||
clFinish(command_queue);
|
||||
|
||||
// What if errors out and gl objects are never released?
|
||||
error = clEnqueueReleaseGLObjects(command_queue, 1, &buffer_map.at("viewport_image"), 0, NULL, NULL);
|
||||
if (vr_assert(error, "clEnqueueReleaseGLObjects"))
|
||||
return;
|
||||
|
||||
}
|
||||
|
||||
void OpenCL::draw(sf::RenderWindow *window) {
|
||||
|
||||
for (auto &&i: image_map) {
|
||||
window->draw(i.second.first);
|
||||
}
|
||||
}
|
||||
|
||||
bool OpenCL::aquire_hardware()
|
||||
{
|
||||
|
||||
// Get the number of platforms
|
||||
cl_uint platform_count = 0;
|
||||
clGetPlatformIDs(0, nullptr, &platform_count);
|
||||
|
||||
if (platform_count == 0) {
|
||||
std::cout << "There appears to be no OpenCL platforms on this machine" << std::endl;
|
||||
return false;
|
||||
}
|
||||
|
||||
// Get the ID's for those platforms
|
||||
std::vector<cl_platform_id> plt_buf(platform_count);
|
||||
|
||||
clGetPlatformIDs(platform_count, plt_buf.data(), nullptr);
|
||||
if (vr_assert(error, "clGetPlatformIDs"))
|
||||
return false;
|
||||
|
||||
// Cycle through the platform ID's
|
||||
for (unsigned int i = 0; i < platform_count; i++) {
|
||||
|
||||
// And get their device count
|
||||
cl_uint deviceIdCount = 0;
|
||||
error = clGetDeviceIDs(plt_buf[i], CL_DEVICE_TYPE_ALL, 0, nullptr, &deviceIdCount);
|
||||
if (vr_assert(error, "clGetDeviceIDs"))
|
||||
return false;
|
||||
|
||||
if (deviceIdCount == 0) {
|
||||
std::cout << "There appears to be no devices associated with this platform" << std::endl;
|
||||
|
||||
} else {
|
||||
|
||||
// Get the device ids and place them in the device list
|
||||
std::vector<cl_device_id> deviceIds(deviceIdCount);
|
||||
|
||||
error = clGetDeviceIDs(plt_buf[i], CL_DEVICE_TYPE_ALL, deviceIdCount, deviceIds.data(), NULL);
|
||||
if (vr_assert(error, "clGetDeviceIDs"))
|
||||
return false;
|
||||
|
||||
for (int d = 0; d < deviceIds.size(); d++) {
|
||||
device_list.emplace_back(device(deviceIds[d], plt_buf.at(i)));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
bool OpenCL::create_shared_context() {
|
||||
|
||||
// Hurray for standards!
|
||||
// Setup the context properties to grab the current GL context
|
||||
|
||||
#ifdef linux
|
||||
|
||||
cl_context_properties context_properties[] = {
|
||||
CL_GL_CONTEXT_KHR, (cl_context_properties)glXGetCurrentContext(),
|
||||
CL_GLX_DISPLAY_KHR, (cl_context_properties)glXGetCurrentDisplay(),
|
||||
CL_CONTEXT_PLATFORM, (cl_context_properties)platform_id,
|
||||
0
|
||||
};
|
||||
|
||||
#elif defined _WIN32
|
||||
|
||||
HGLRC hGLRC = wglGetCurrentContext();
|
||||
HDC hDC = wglGetCurrentDC();
|
||||
cl_context_properties context_properties[] = {
|
||||
CL_CONTEXT_PLATFORM, (cl_context_properties)platform_id,
|
||||
CL_GL_CONTEXT_KHR, (cl_context_properties)hGLRC,
|
||||
CL_WGL_HDC_KHR, (cl_context_properties)hDC,
|
||||
0
|
||||
};
|
||||
|
||||
|
||||
#elif defined TARGET_OS_MAC
|
||||
|
||||
CGLContextObj glContext = CGLGetCurrentContext();
|
||||
CGLShareGroupObj shareGroup = CGLGetShareGroup(glContext);
|
||||
cl_context_properties context_properties[] = {
|
||||
CL_CONTEXT_PROPERTY_USE_CGL_SHAREGROUP_APPLE,
|
||||
(cl_context_properties)shareGroup,
|
||||
0
|
||||
};
|
||||
|
||||
#elif
|
||||
|
||||
std::cout << "Target machine not supported for cl_khr_gl_sharing" << std::endl;
|
||||
return false;
|
||||
|
||||
#endif
|
||||
|
||||
// Create our shared context
|
||||
context = clCreateContext(
|
||||
context_properties,
|
||||
1,
|
||||
&device_id,
|
||||
nullptr, nullptr,
|
||||
&error
|
||||
);
|
||||
|
||||
if (vr_assert(error, "clCreateContext"))
|
||||
return false;
|
||||
|
||||
return true;
|
||||
|
||||
}
|
||||
|
||||
bool OpenCL::create_command_queue() {
|
||||
|
||||
// Command queue requires a context and device id. It can also be a device ID list
|
||||
// as long as the devices reside on the same platform
|
||||
if (context && device_id) {
|
||||
|
||||
command_queue = clCreateCommandQueue(context, device_id, 0, &error);
|
||||
if (vr_assert(error, "clCreateCommandQueue"))
|
||||
return false;
|
||||
|
||||
} else {
|
||||
|
||||
std::cout << "Failed creating the command queue. Context or device_id not initialized" << std::endl;
|
||||
return false;
|
||||
}
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
bool OpenCL::compile_kernel(std::string kernel_path, std::string kernel_name) {
|
||||
|
||||
const char* source;
|
||||
std::string tmp;
|
||||
|
||||
//Load in the kernel, and c stringify it
|
||||
tmp = read_file(kernel_path);
|
||||
source = tmp.c_str();
|
||||
|
||||
|
||||
size_t kernel_source_size = strlen(source);
|
||||
|
||||
// Load the source into CL's data structure
|
||||
|
||||
cl_program program = clCreateProgramWithSource(
|
||||
context, 1,
|
||||
&source,
|
||||
&kernel_source_size, &error
|
||||
);
|
||||
|
||||
// This is not for compilation, it only loads the source
|
||||
if (vr_assert(error, "clCreateProgramWithSource"))
|
||||
return false;
|
||||
|
||||
|
||||
// Try and build the program
|
||||
// "-cl-finite-math-only -cl-fast-relaxed-math -cl-unsafe-math-optimizations"
|
||||
error = clBuildProgram(program, 1, &device_id, "-cl-finite-math-only -cl-fast-relaxed-math -cl-unsafe-math-optimizations", NULL, NULL);
|
||||
|
||||
// Check to see if it errored out
|
||||
if (vr_assert(error, "clBuildProgram")) {
|
||||
|
||||
// Get the size of the queued log
|
||||
size_t log_size;
|
||||
clGetProgramBuildInfo(program, device_id, CL_PROGRAM_BUILD_LOG, 0, NULL, &log_size);
|
||||
char *log = new char[log_size];
|
||||
|
||||
// Grab the log
|
||||
clGetProgramBuildInfo(program, device_id, CL_PROGRAM_BUILD_LOG, log_size, log, NULL);
|
||||
|
||||
std::cout << log;
|
||||
return false;
|
||||
}
|
||||
|
||||
// Done initializing the kernel
|
||||
cl_kernel kernel = clCreateKernel(program, kernel_name.c_str(), &error);
|
||||
|
||||
if (vr_assert(error, "clCreateKernel"))
|
||||
return false;
|
||||
|
||||
// Do I want these to overlap when repeated??
|
||||
kernel_map[kernel_name] = kernel;
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
bool OpenCL::create_image_buffer_from_texture(std::string buffer_name, sf::Texture* texture, cl_int access_type) {
|
||||
|
||||
if (buffer_map.count(buffer_name) > 0) {
|
||||
release_buffer(buffer_name);
|
||||
|
||||
// Need to check to see if we are taking care of the texture as well
|
||||
if (image_map.count(buffer_name) > 0)
|
||||
image_map.erase(buffer_name);
|
||||
}
|
||||
|
||||
cl_mem buff = clCreateFromGLTexture(
|
||||
context, access_type, GL_TEXTURE_2D,
|
||||
0, texture->getNativeHandle(), &error);
|
||||
|
||||
if (vr_assert(error, "clCreateFromGLTexture"))
|
||||
return false;
|
||||
|
||||
store_buffer(buff, buffer_name);
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
|
||||
bool OpenCL::create_image_buffer(std::string buffer_name, sf::Vector2i size, sf::Vector2f position, cl_int access_type) {
|
||||
|
||||
if (buffer_map.count(buffer_name) > 0) {
|
||||
release_buffer(buffer_name);
|
||||
|
||||
// Need to check to see if we are taking care of the texture as well
|
||||
if (image_map.count(buffer_name) > 0)
|
||||
image_map.erase(buffer_name);
|
||||
}
|
||||
|
||||
std::unique_ptr<sf::Texture> texture(new sf::Texture);
|
||||
texture->create(size.x, size.y);
|
||||
|
||||
cl_mem buff = clCreateFromGLTexture(
|
||||
context, access_type, GL_TEXTURE_2D,
|
||||
0, texture->getNativeHandle(), &error);
|
||||
|
||||
if (vr_assert(error, "clCreateFromGLTexture"))
|
||||
return false;
|
||||
|
||||
sf::Sprite sprite(*texture);
|
||||
sprite.setPosition(position);
|
||||
|
||||
image_map[buffer_name] = std::pair<sf::Sprite, std::unique_ptr<sf::Texture>>(sprite, std::move(texture));
|
||||
|
||||
store_buffer(buff, buffer_name);
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
int OpenCL::create_buffer(std::string buffer_name, cl_uint size, void* data) {
|
||||
|
||||
if (buffer_map.count(buffer_name) > 0) {
|
||||
release_buffer(buffer_name);
|
||||
}
|
||||
|
||||
cl_mem buff = clCreateBuffer(
|
||||
context, CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR,
|
||||
size, data, &error
|
||||
);
|
||||
|
||||
if (vr_assert(error, "clCreateBuffer"))
|
||||
return -1;
|
||||
|
||||
store_buffer(buff, buffer_name);
|
||||
|
||||
return 1;
|
||||
}
|
||||
|
||||
int OpenCL::create_buffer(std::string buffer_name, cl_uint size, void* data, cl_mem_flags flags) {
|
||||
|
||||
if (buffer_map.count(buffer_name) > 0) {
|
||||
release_buffer(buffer_name);
|
||||
}
|
||||
|
||||
((char*)data)[10000];
|
||||
|
||||
cl_mem buff = clCreateBuffer(
|
||||
context, flags,
|
||||
size, data, &error
|
||||
);
|
||||
|
||||
if (vr_assert(error, "clCreateBuffer"))
|
||||
return -1;
|
||||
|
||||
store_buffer(buff, buffer_name);
|
||||
|
||||
return 1;
|
||||
|
||||
}
|
||||
|
||||
bool OpenCL::store_buffer(cl_mem buffer, std::string buffer_name) {
|
||||
|
||||
if (buffer_map.count(buffer_name) > 0) {
|
||||
|
||||
error = clReleaseMemObject(buffer_map.at(buffer_name));
|
||||
|
||||
if (vr_assert(error, "clReleaseMemObject")) {
|
||||
std::cout << "Error releasing overlapping buffer : " << buffer_name;
|
||||
std::cout << "Buffer not added";
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
buffer_map[buffer_name] = buffer;
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
bool OpenCL::release_buffer(std::string buffer_name) {
|
||||
|
||||
if (buffer_map.count(buffer_name) > 0) {
|
||||
|
||||
error = clReleaseMemObject(buffer_map.at(buffer_name));
|
||||
|
||||
if (vr_assert(error, "clReleaseMemObject")) {
|
||||
std::cout << "Error releasing buffer : " << buffer_name;
|
||||
std::cout << "Buffer not removed";
|
||||
return false;
|
||||
|
||||
}
|
||||
|
||||
buffer_map.erase(buffer_name);
|
||||
|
||||
} else {
|
||||
|
||||
std::cout << "Error releasing buffer : " << buffer_name;
|
||||
std::cout << "Buffer not found";
|
||||
return false;
|
||||
}
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
int OpenCL::set_kernel_arg(std::string kernel_name, int index, std::string buffer_name) {
|
||||
|
||||
error = clSetKernelArg(
|
||||
kernel_map.at(kernel_name),
|
||||
index,
|
||||
sizeof(cl_mem),
|
||||
(void *)&buffer_map.at(buffer_name));
|
||||
|
||||
if (vr_assert(error, "clSetKernelArg")) {
|
||||
std::cout << buffer_name << std::endl;
|
||||
std::cout << buffer_map.at(buffer_name) << std::endl;
|
||||
return -1;
|
||||
}
|
||||
return 1;
|
||||
}
|
||||
|
||||
bool OpenCL::load_config() {
|
||||
|
||||
std::ifstream input_file("device_config.bin", std::ios::binary | std::ios::in);
|
||||
|
||||
if (!input_file.is_open()) {
|
||||
std::cout << "No config file..." << std::endl;
|
||||
return false;
|
||||
}
|
||||
|
||||
device::packed_data data;
|
||||
input_file.read(reinterpret_cast<char*>(&data), sizeof(data));
|
||||
|
||||
std::cout << "config loaded, looking for device..." << std::endl;
|
||||
|
||||
for (auto d: device_list) {
|
||||
|
||||
if (memcmp(&d, &data, sizeof(device::packed_data)) == 0) {
|
||||
std::cout << "Found saved device" << std::endl;
|
||||
device_id = d.getDeviceId();
|
||||
platform_id = d.getPlatformId();
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
input_file.close();
|
||||
return true;
|
||||
}
|
||||
|
||||
|
||||
void OpenCL::save_config() {
|
||||
|
||||
std::ofstream output_file;
|
||||
output_file.open("device_config.bin", std::ofstream::binary | std::ofstream::out | std::ofstream::trunc);
|
||||
|
||||
device d(device_id, platform_id);
|
||||
d.print_packed_data(output_file);
|
||||
|
||||
output_file.close();
|
||||
}
|
||||
|
||||
bool OpenCL::init() {
|
||||
|
||||
if (!aquire_hardware())
|
||||
return false;
|
||||
|
||||
if (!load_config()) {
|
||||
|
||||
std::cout << "Select a device number which you wish to use" << std::endl;
|
||||
|
||||
for (int i = 0; i < device_list.size(); i++) {
|
||||
|
||||
std::cout << "\n-----------------------------------------------------------------" << std::endl;
|
||||
std::cout << "\tDevice Number : " << i << std::endl;
|
||||
std::cout << "-----------------------------------------------------------------" << std::endl;
|
||||
|
||||
device_list.at(i).print(std::cout);
|
||||
}
|
||||
|
||||
int selection = -1;
|
||||
|
||||
while (selection < 0 && selection >= device_list.size()) {
|
||||
|
||||
std::cout << "Device which you wish to use : ";
|
||||
std::cin >> selection;
|
||||
}
|
||||
|
||||
device_id = device_list.at(selection).getDeviceId();
|
||||
platform_id = device_list.at(selection).getPlatformId();
|
||||
|
||||
save_config();
|
||||
}
|
||||
|
||||
if (!create_shared_context())
|
||||
return false;
|
||||
|
||||
if (!create_command_queue())
|
||||
return false;
|
||||
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
|
||||
bool OpenCL::vr_assert(int error_code, std::string function_name) {
|
||||
|
||||
// Just gonna do a little jump table here, just error codes so who cares
|
||||
std::string err_msg = "Error : ";
|
||||
|
||||
switch (error_code) {
|
||||
|
||||
case CL_SUCCESS:
|
||||
return false;
|
||||
|
||||
case 1:
|
||||
return false;
|
||||
|
||||
case CL_DEVICE_NOT_FOUND:
|
||||
err_msg += "CL_DEVICE_NOT_FOUND";
|
||||
break;
|
||||
case CL_DEVICE_NOT_AVAILABLE:
|
||||
err_msg = "CL_DEVICE_NOT_AVAILABLE";
|
||||
break;
|
||||
case CL_COMPILER_NOT_AVAILABLE:
|
||||
err_msg = "CL_COMPILER_NOT_AVAILABLE";
|
||||
break;
|
||||
case CL_MEM_OBJECT_ALLOCATION_FAILURE:
|
||||
err_msg = "CL_MEM_OBJECT_ALLOCATION_FAILURE";
|
||||
break;
|
||||
case CL_OUT_OF_RESOURCES:
|
||||
err_msg = "CL_OUT_OF_RESOURCES";
|
||||
break;
|
||||
case CL_OUT_OF_HOST_MEMORY:
|
||||
err_msg = "CL_OUT_OF_HOST_MEMORY";
|
||||
break;
|
||||
case CL_PROFILING_INFO_NOT_AVAILABLE:
|
||||
err_msg = "CL_PROFILING_INFO_NOT_AVAILABLE";
|
||||
break;
|
||||
case CL_MEM_COPY_OVERLAP:
|
||||
err_msg = "CL_MEM_COPY_OVERLAP";
|
||||
break;
|
||||
case CL_IMAGE_FORMAT_MISMATCH:
|
||||
err_msg = "CL_IMAGE_FORMAT_MISMATCH";
|
||||
break;
|
||||
case CL_IMAGE_FORMAT_NOT_SUPPORTED:
|
||||
err_msg = "CL_IMAGE_FORMAT_NOT_SUPPORTED";
|
||||
break;
|
||||
case CL_BUILD_PROGRAM_FAILURE:
|
||||
err_msg = "CL_BUILD_PROGRAM_FAILURE";
|
||||
break;
|
||||
case CL_MAP_FAILURE:
|
||||
err_msg = "CL_MAP_FAILURE";
|
||||
break;
|
||||
case CL_MISALIGNED_SUB_BUFFER_OFFSET:
|
||||
err_msg = "CL_MISALIGNED_SUB_BUFFER_OFFSET";
|
||||
break;
|
||||
case CL_EXEC_STATUS_ERROR_FOR_EVENTS_IN_WAIT_LIST:
|
||||
err_msg = "CL_EXEC_STATUS_ERROR_FOR_EVENTS_IN_WAIT_LIST";
|
||||
break;
|
||||
case CL_COMPILE_PROGRAM_FAILURE:
|
||||
err_msg = "CL_COMPILE_PROGRAM_FAILURE";
|
||||
break;
|
||||
case CL_LINKER_NOT_AVAILABLE:
|
||||
err_msg = "CL_LINKER_NOT_AVAILABLE";
|
||||
break;
|
||||
case CL_LINK_PROGRAM_FAILURE:
|
||||
err_msg = "CL_LINK_PROGRAM_FAILURE";
|
||||
break;
|
||||
case CL_DEVICE_PARTITION_FAILED:
|
||||
err_msg = "CL_DEVICE_PARTITION_FAILED";
|
||||
break;
|
||||
case CL_KERNEL_ARG_INFO_NOT_AVAILABLE:
|
||||
err_msg = "CL_KERNEL_ARG_INFO_NOT_AVAILABLE";
|
||||
break;
|
||||
case CL_INVALID_VALUE:
|
||||
err_msg = "CL_INVALID_VALUE";
|
||||
break;
|
||||
case CL_INVALID_DEVICE_TYPE:
|
||||
err_msg = "CL_INVALID_DEVICE_TYPE";
|
||||
break;
|
||||
case CL_INVALID_PLATFORM:
|
||||
err_msg = "CL_INVALID_PLATFORM";
|
||||
break;
|
||||
case CL_INVALID_DEVICE:
|
||||
err_msg = "CL_INVALID_DEVICE";
|
||||
break;
|
||||
case CL_INVALID_CONTEXT:
|
||||
err_msg = "CL_INVALID_CONTEXT";
|
||||
break;
|
||||
case CL_INVALID_QUEUE_PROPERTIES:
|
||||
err_msg = "CL_INVALID_QUEUE_PROPERTIES";
|
||||
break;
|
||||
case CL_INVALID_COMMAND_QUEUE:
|
||||
err_msg = "CL_INVALID_COMMAND_QUEUE";
|
||||
break;
|
||||
case CL_INVALID_HOST_PTR:
|
||||
err_msg = "CL_INVALID_HOST_PTR";
|
||||
break;
|
||||
case CL_INVALID_MEM_OBJECT:
|
||||
err_msg = "CL_INVALID_MEM_OBJECT";
|
||||
break;
|
||||
case CL_INVALID_IMAGE_FORMAT_DESCRIPTOR:
|
||||
err_msg = "CL_INVALID_IMAGE_FORMAT_DESCRIPTOR";
|
||||
break;
|
||||
case CL_INVALID_IMAGE_SIZE:
|
||||
err_msg = "CL_INVALID_IMAGE_SIZE";
|
||||
break;
|
||||
case CL_INVALID_SAMPLER:
|
||||
err_msg = "CL_INVALID_SAMPLER";
|
||||
break;
|
||||
case CL_INVALID_BINARY:
|
||||
err_msg = "CL_INVALID_BINARY";
|
||||
break;
|
||||
case CL_INVALID_BUILD_OPTIONS:
|
||||
err_msg = "CL_INVALID_BUILD_OPTIONS";
|
||||
break;
|
||||
case CL_INVALID_PROGRAM:
|
||||
err_msg = "CL_INVALID_PROGRAM";
|
||||
break;
|
||||
case CL_INVALID_PROGRAM_EXECUTABLE:
|
||||
err_msg = "CL_INVALID_PROGRAM_EXECUTABLE";
|
||||
break;
|
||||
case CL_INVALID_KERNEL_NAME:
|
||||
err_msg = "CL_INVALID_KERNEL_NAME";
|
||||
break;
|
||||
case CL_INVALID_KERNEL_DEFINITION:
|
||||
err_msg = "CL_INVALID_KERNEL_DEFINITION";
|
||||
break;
|
||||
case CL_INVALID_KERNEL:
|
||||
err_msg = "CL_INVALID_KERNEL";
|
||||
break;
|
||||
case CL_INVALID_ARG_INDEX:
|
||||
err_msg = "CL_INVALID_ARG_INDEX";
|
||||
break;
|
||||
case CL_INVALID_ARG_VALUE:
|
||||
err_msg = "CL_INVALID_ARG_VALUE";
|
||||
break;
|
||||
case CL_INVALID_ARG_SIZE:
|
||||
err_msg = "CL_INVALID_ARG_SIZE";
|
||||
break;
|
||||
case CL_INVALID_KERNEL_ARGS:
|
||||
err_msg = "CL_INVALID_KERNEL_ARGS";
|
||||
break;
|
||||
case CL_INVALID_WORK_DIMENSION:
|
||||
err_msg = "CL_INVALID_WORK_DIMENSION";
|
||||
break;
|
||||
case CL_INVALID_WORK_GROUP_SIZE:
|
||||
err_msg = "CL_INVALID_WORK_GROUP_SIZE";
|
||||
break;
|
||||
case CL_INVALID_WORK_ITEM_SIZE:
|
||||
err_msg = "CL_INVALID_WORK_ITEM_SIZE";
|
||||
break;
|
||||
case CL_INVALID_GLOBAL_OFFSET:
|
||||
err_msg = "CL_INVALID_GLOBAL_OFFSET";
|
||||
break;
|
||||
case CL_INVALID_EVENT_WAIT_LIST:
|
||||
err_msg = "CL_INVALID_EVENT_WAIT_LIST";
|
||||
break;
|
||||
case CL_INVALID_EVENT:
|
||||
err_msg = "CL_INVALID_EVENT";
|
||||
break;
|
||||
case CL_INVALID_OPERATION:
|
||||
err_msg = "CL_INVALID_OPERATION";
|
||||
break;
|
||||
case CL_INVALID_GL_OBJECT:
|
||||
err_msg = "CL_INVALID_GL_OBJECT";
|
||||
break;
|
||||
case CL_INVALID_BUFFER_SIZE:
|
||||
err_msg = "CL_INVALID_BUFFER_SIZE";
|
||||
break;
|
||||
case CL_INVALID_MIP_LEVEL:
|
||||
err_msg = "CL_INVALID_MIP_LEVEL";
|
||||
break;
|
||||
case CL_INVALID_GLOBAL_WORK_SIZE:
|
||||
err_msg = "CL_INVALID_GLOBAL_WORK_SIZE";
|
||||
break;
|
||||
case CL_INVALID_PROPERTY:
|
||||
err_msg = "CL_INVALID_PROPERTY";
|
||||
break;
|
||||
case CL_INVALID_IMAGE_DESCRIPTOR:
|
||||
err_msg = "CL_INVALID_IMAGE_DESCRIPTOR";
|
||||
break;
|
||||
case CL_INVALID_COMPILER_OPTIONS:
|
||||
err_msg = "CL_INVALID_COMPILER_OPTIONS";
|
||||
break;
|
||||
case CL_INVALID_LINKER_OPTIONS:
|
||||
err_msg = "CL_INVALID_LINKER_OPTIONS";
|
||||
break;
|
||||
case CL_INVALID_DEVICE_PARTITION_COUNT:
|
||||
err_msg = "CL_INVALID_DEVICE_PARTITION_COUNT";
|
||||
break;
|
||||
case CL_INVALID_GL_SHAREGROUP_REFERENCE_KHR:
|
||||
err_msg = "CL_INVALID_GL_SHAREGROUP_REFERENCE_KHR";
|
||||
break;
|
||||
case CL_PLATFORM_NOT_FOUND_KHR:
|
||||
err_msg = "CL_PLATFORM_NOT_FOUND_KHR";
|
||||
break;
|
||||
}
|
||||
|
||||
std::cout << err_msg << " =at= " << function_name << std::endl;
|
||||
return true;
|
||||
}
|
||||
|
||||
OpenCL::device::device(cl_device_id device_id, cl_platform_id platform_id) {
|
||||
|
||||
this->device_id = device_id;
|
||||
this->platform_id = platform_id;
|
||||
|
||||
int error = 0;
|
||||
error = clGetPlatformInfo(platform_id, CL_PLATFORM_NAME, 128, (void*)&data.platform_name, nullptr);
|
||||
if (vr_assert(error, "clGetPlatformInfo"))
|
||||
return;
|
||||
|
||||
error = clGetDeviceInfo(device_id, CL_DEVICE_VERSION, sizeof(char) * 128, &data.opencl_version, NULL);
|
||||
error = clGetDeviceInfo(device_id, CL_DEVICE_TYPE, sizeof(cl_device_type), &data.device_type, NULL);
|
||||
error = clGetDeviceInfo(device_id, CL_DEVICE_MAX_CLOCK_FREQUENCY, sizeof(cl_uint), &data.clock_frequency, NULL);
|
||||
error = clGetDeviceInfo(device_id, CL_DEVICE_MAX_COMPUTE_UNITS, sizeof(cl_uint), &data.compute_units, NULL);
|
||||
error = clGetDeviceInfo(device_id, CL_DEVICE_EXTENSIONS, 1024, &data.device_extensions, NULL);
|
||||
error = clGetDeviceInfo(device_id, CL_DEVICE_NAME, 256, &data.device_name, NULL);
|
||||
error = clGetDeviceInfo(device_id, CL_DEVICE_ENDIAN_LITTLE, sizeof(cl_bool), &is_little_endian, NULL);
|
||||
|
||||
// Check for the sharing extension
|
||||
if (std::string(data.device_extensions).find("cl_khr_gl_sharing") != std::string::npos ||
|
||||
std::string(data.device_extensions).find("cl_APPLE_gl_sharing") != std::string::npos) {
|
||||
cl_gl_sharing = true;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
OpenCL::device::device(const device& d) {
|
||||
|
||||
// member values, copy individually
|
||||
device_id = d.device_id;
|
||||
platform_id = d.platform_id;
|
||||
is_little_endian = d.is_little_endian;
|
||||
cl_gl_sharing = d.cl_gl_sharing;
|
||||
|
||||
// struct so it copies by value
|
||||
data = d.data;
|
||||
|
||||
}
|
||||
|
||||
void OpenCL::device::print(std::ostream& stream) const {
|
||||
|
||||
stream << "\n\tDevice ID : " << device_id << std::endl;
|
||||
stream << "\tDevice Name : " << data.device_name << std::endl;
|
||||
|
||||
stream << "\tPlatform ID : " << platform_id << std::endl;
|
||||
stream << "\tPlatform Name : " << data.platform_name << std::endl;
|
||||
|
||||
stream << "\tOpenCL Version : " << data.opencl_version << std::endl;
|
||||
stream << "\tSupports sharing : " << std::boolalpha << cl_gl_sharing << std::endl;
|
||||
stream << "\tDevice Type : ";
|
||||
|
||||
if (data.device_type == CL_DEVICE_TYPE_CPU)
|
||||
stream << "CPU" << std::endl;
|
||||
|
||||
else if (data.device_type == CL_DEVICE_TYPE_GPU)
|
||||
stream << "GPU" << std::endl;
|
||||
|
||||
else if (data.device_type == CL_DEVICE_TYPE_ACCELERATOR)
|
||||
stream << "Accelerator" << std::endl;
|
||||
|
||||
stream << "\tIs Little Endian : " << std::boolalpha << is_little_endian << std::endl;
|
||||
|
||||
stream << "\tClock Frequency : " << data.clock_frequency << std::endl;
|
||||
stream << "\tCompute Units : " << data.compute_units << std::endl;
|
||||
|
||||
stream << "\n*Extensions*" << std::endl;
|
||||
stream << data.device_extensions << std::endl;
|
||||
stream << "\n";
|
||||
|
||||
}
|
||||
|
||||
void OpenCL::device::print_packed_data(std::ostream& stream) {
|
||||
stream.write(reinterpret_cast<char*>(&data), sizeof(data));
|
||||
}
|
||||
@ -0,0 +1,133 @@
|
||||
|
||||
#include <iostream>
|
||||
#include <SFML/Graphics.hpp>
|
||||
#include <random>
|
||||
#include <chrono>
|
||||
#include "util.hpp"
|
||||
#include <thread>
|
||||
#include "OpenCL.h"
|
||||
|
||||
float elap_time() {
|
||||
static std::chrono::time_point<std::chrono::system_clock> start;
|
||||
static bool started = false;
|
||||
|
||||
if (!started) {
|
||||
start = std::chrono::system_clock::now();
|
||||
started = true;
|
||||
}
|
||||
|
||||
std::chrono::time_point<std::chrono::system_clock> now = std::chrono::system_clock::now();
|
||||
std::chrono::duration<double> elapsed_time = now - start;
|
||||
return static_cast<float>(elapsed_time.count());
|
||||
}
|
||||
|
||||
const int WINDOW_X = 1080;
|
||||
const int WINDOW_Y = 1080;
|
||||
|
||||
void generate_nodes(sf::Uint8* nodes) {
|
||||
|
||||
for (int i = 0; i < WINDOW_X * WINDOW_Y; i += 1) {
|
||||
if (rand() % 10 > 8)
|
||||
nodes[i] = 1;
|
||||
else
|
||||
nodes[i] = 0;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
int main() {
|
||||
|
||||
sf::RenderWindow window(sf::VideoMode(WINDOW_X, WINDOW_Y), "conways-game-of-life-opencl");
|
||||
window.setFramerateLimit(60);
|
||||
|
||||
float physic_step = 0.166f;
|
||||
float physic_time = 0.0f;
|
||||
double frame_time = 0.0, elapsed_time = 0.0, delta_time = 0.0, accumulator_time = 0.0, current_time = 0.0;
|
||||
|
||||
OpenCL cl;
|
||||
|
||||
|
||||
if (!cl.init())
|
||||
return -1;
|
||||
|
||||
while (!cl.compile_kernel("../kernels/conways.cl", "conways")) {
|
||||
std::cin.get();
|
||||
}
|
||||
|
||||
sf::Vector2i image_resolution(WINDOW_X, WINDOW_Y);
|
||||
cl.create_image_buffer("viewport_image", image_resolution, sf::Vector2f(0, 0), CL_MEM_WRITE_ONLY);
|
||||
cl.create_buffer("image_res", sizeof(sf::Vector2i), &image_resolution);
|
||||
|
||||
sf::Uint8* nodes = new sf::Uint8[WINDOW_X * WINDOW_Y];
|
||||
generate_nodes(nodes);
|
||||
nodes[0] = 1;
|
||||
cl.create_buffer("first_node_buffer", WINDOW_X * WINDOW_Y, (void*)nodes, CL_MEM_READ_WRITE | CL_MEM_COPY_HOST_PTR);
|
||||
cl.create_buffer("second_node_buffer", WINDOW_X * WINDOW_Y, (void*)nodes, CL_MEM_READ_WRITE | CL_MEM_COPY_HOST_PTR);
|
||||
|
||||
char buffer_flip = 0;
|
||||
cl.create_buffer("buffer_flip", sizeof(char), (void*)&buffer_flip, CL_MEM_READ_ONLY | CL_MEM_USE_HOST_PTR);
|
||||
|
||||
cl.set_kernel_arg("conways", 0, "image_res");
|
||||
cl.set_kernel_arg("conways", 1, "viewport_image");
|
||||
cl.set_kernel_arg("conways", 2, "first_node_buffer");
|
||||
cl.set_kernel_arg("conways", 3, "second_node_buffer");
|
||||
cl.set_kernel_arg("conways", 4, "buffer_flip");
|
||||
|
||||
while (window.isOpen())
|
||||
{
|
||||
sf::Event event; // Handle input
|
||||
while (window.pollEvent(event)) {
|
||||
if (event.type == sf::Event::Closed) {
|
||||
window.close();
|
||||
}
|
||||
if (event.type == sf::Event::KeyPressed) {
|
||||
if (event.key.code == sf::Keyboard::Down) {
|
||||
|
||||
}
|
||||
if (event.key.code == sf::Keyboard::Up) {
|
||||
|
||||
}
|
||||
if (event.key.code == sf::Keyboard::Right) {
|
||||
|
||||
}
|
||||
if (event.key.code == sf::Keyboard::Left) {
|
||||
|
||||
}
|
||||
if (event.key.code == sf::Keyboard::Equal) {
|
||||
|
||||
}
|
||||
if (event.key.code == sf::Keyboard::Dash) {
|
||||
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
elapsed_time = elap_time(); // Handle time
|
||||
delta_time = elapsed_time - current_time;
|
||||
current_time = elapsed_time;
|
||||
if (delta_time > 0.02f)
|
||||
delta_time = 0.02f;
|
||||
accumulator_time += delta_time;
|
||||
|
||||
while (accumulator_time >= physic_step) { // While the frame has sim time, update
|
||||
accumulator_time -= physic_step;
|
||||
physic_time += physic_step;
|
||||
}
|
||||
|
||||
window.clear(sf::Color::White);
|
||||
|
||||
cl.run_kernel("conways", image_resolution);
|
||||
//cl.run_kernel("conways", sf::Vector2i(5, 5));
|
||||
cl.draw(&window);
|
||||
|
||||
if (buffer_flip == 1)
|
||||
buffer_flip = 0;
|
||||
else
|
||||
buffer_flip = 1;
|
||||
|
||||
window.display();
|
||||
|
||||
}
|
||||
return 0;
|
||||
|
||||
}
|
||||
Loading…
Reference in new issue