Projects tagged ‘computing’ and ‘parallel’

Open MPI is a project that originated as the merging of technologies and resources from several other projects (FT- MPI, LA-MPI, LAM/MPI, and PACX-MPI) in order to build the best MPI library ... [More] available. A completely new MPI-2 compliant implementation, Open MPI offers advantages for system and software vendors, application developers, and computer science researchers. It is easy to use, and runs natively on a wide variety of operating systems, network interconnects, and batch/scheduling systems. [Less]

openMosix is a a set of extensions to the standard Linux kernel allowing you to build a cluster of out of off-the-shelf PC hardware. openMosix scales perfectly up to thousands of nodes. You do not ... [More] need to modify your applications to benefit from your cluster (unlike PVM, MPI, Linda, etc.). Processes in openMosix migrate transparently between nodes and the cluster will always auto-balance. [Less]

XMDS is a code generator that integrates equations. You write them down in human readable form in a XML file, and it goes away and writes and compiles a C++ program that integrates those equations as ... [More] fast as it can possibly be done in your architecture. [Less]

NGrid is an open source (LGPL) grid computing framework written in C#. NGrid aims to be platform independent via the Mono project. NGrid aims to provide * a transparent multithread programming ... [More] model for grid programming. * a physical grid framework & some grid implementations. * common utilities both for grid programming or grid implementations. [Less]

Project Description Message Passing Interface (MPI) is the standard of message passing in a distributed computing environment. Its benefit for researchers is invaluable. The idea is to have many ... [More] machines on a high-speed network, clusters of computers running the same program. Recently, with the invention and adoption of multi-core CPU systems for desktops, it has become even more important. MPI makes even easier for people to build supercomputers by the usage of powerful computers, high speed networks and powerful libraries. The goal of MPI Tools is to make easy to write programs that runs on a cluster of machines. Also make the transition easy of existing programs in cluster. Using MPITools, it is possible to create distributed functional applications with F#. [Less]

Sector is a system infrastructure software that provides functionality for distributed data storage, access, and analysis/processing. It automatically manages large volumetric data across servers or ... [More] clusters, even those over distributed wide area high speed networks. Sector provides simple tools and APIs to access and/or process the data. Data and server locations are transparent to users, as the whole Sector network is a single networked super computer to the users. [Less]

DescriptionThis is a Java implementation of the MapReduce concept. The main goal is to provide robust implementation in terms of usage and simplicify of used technologies and design patterns. ... [More] Implementation doesn't relay on Java features like RMI or Reflection so it can be easily rewritten to other languages, like C++ or python. It doesn't use any other third party libraries so it is very light. The API is very simple and looks like this one used in reference documentation about MapReduce by Google. I would like to clean-up code and make some refectoring before code publishing. So stay ready. UPDATE: Here is a development log. Example job configurationNotation used in this configuration was designed for jruce. It resambles JSON or JavaFx syntax. node-config { reporting-frequency : 2000 reporting-timeout : 8000 mtp-port : 52000 mtp-slave-address : 224.0.1.184 mtp-master-address : 224.0.1.185 udp-port : 0 tcp-port : 0 data-timeout : 500 working-dir : "c:\mapred_workdir" } map-reduce-config { attempts-num : 2 map-max-pairs-in-memory : 500000 reduce-max-pairs-in-memory : 500000 reducers-num : 1 user-library { "userlib/mymapreduce-lib.jar" "userlib/xercesImpl.jar" "userlib/jena.jar" "userlib/commons-logging-1.1.jar" } input-config { splitter-class : "alna.mapred.TextSplitter" { files-location : "C:\mapred_text\one" pattern : "*.txt" split-bytes : 60000000 } input-class : "alna.mapred.mapper.io.TextMapInput" { encoding : "cp1250" } mapper-class : "alna.mapred.mapper.WordCounter" partitioner-class : "alna.mapred.HashPartitioner" ordering-class : "alna.mapred.pair.cmp.KeyStrAscCmp" combiner-class : "alna.mapred.reducer.Adder" } output-config { filename-base : "c:\mapred_text\output" ordering-class : "alna.mapred.pair.cmp.KeyStrAscCmp" reducer-class : "alna.mapred.reducer.Adder" output-class : "alna.mapred.reducer.io.TextReduceOutput" } } Example codeBelow as a reference I present the word count example. Mapper code public class WordCounter extends Mapper { @Override public void map(MapInput input) { for (String word : input.getValue().split("\\s*[\\d\\p{Punct}\\s]+\\s*")) { emit(word.toLowerCase(), "1"); } } @Override public void end() { } @Override public void begin(ConfigValue config) { } }Reducer code public class Adder extends Reducer { @Override public void reduce(ReduceInput input) { int value = 0; while (!input.done()) { value += Integer.parseInt(input.getValue()); input.next(); } emit(input.getKey()); emit(String.valueOf(value)); } @Override public void end() { } @Override public void begin(ConfigValue config) { } } [Less]

Attempt of development universal end-user tool of parallel distributed computing. It should have it's own scripting language to describe problem in user-friendly form.

Comming soon ;-) If you use the cnnplus library for your research, please cite it with the following reference: @misc{cnnplus, author = {Daniel Strigl and Klaus Kofler}, title = {cnnplus: A ... [More] library for fast convolutional neural network training and classification.}, howpublished = {http://code.google.com/p/cnnplus} } [Less]

This project is an attempt at rewriting the Financial Algorithm Recipes algorithms to take advantage of GPGPU technologies. Also, for the author, this project represent a good and simple way to gain ... [More] more experience with Parallel Computing and learning more about computational finance and finance in general. [Less]