Open Source BSD Clustering Software - Page 4

See http://www.cubrid.org/cluster. CUBRID Cluster is an open source clustered DBMS for high scalability including global schema, distributed partition and load balancing features. It is a spin-off project from CUBRID project and supported by NHN.

Cbench is intended as a relatively straightforward toolbox of tests, benchmarks, applications, utilities, and framework to hold them together with the goal to facilitate scalable testing, benchmarking, and analysis of a Linux parallel compute cluster.

Channel is a C++ framework for distributed message passing and event dispatching, configurable with its components (msg ids,routing algorithms...) as template parameters. As a namespace shared by peer threads, channel supports scope control and filtering

Cleo is written on perl5 and works on Linux and hopely on most UNIXes. This is the batch system for computational clusters, which supports possibly most parallel envinronments.

Clubmask is a resource and job manager that ties together the Bproc global process space system, SIS, the System Installation Suite for installing Linux clusters, the Maui HPC Scheduler, and Supermon resource managers. The goal of Clubmask is to provide

Removed

The Orchestrator server is responsible for distribution and launch of simple apply/rollback shell scripts in a particular order across multiple servers . If for any reason deployment is failing at a particular stage the process will stop and you can rollback any changes done until then. In case you want to deploy your code or just call your preferred DSC client to apply the configuration locally the Orchestrator can be a handy tool. The operation can be started manually or scheduled, depending on your needs. In terms of audit and trace capabilities, the system is collecting all console output of your shell scripts from all servers and saves the logs centrally for review.

Cluster101 allows you to run software on many hosts and perform a simple task scheduling. No need to install any software on the hosts (it just runs tasks via ssh). It is typically used for running scientific applications on University campuses.

ClusterNFS allows diskless clients to share a single root filesystem by matching "interpreted" file names of the form "/path/filename$$KEY=value$$" with fallback to the original filename. Keys include HOSTNAME, IP, UID, GID, and CLIENT (always matches

This is a software tool that automates the process of benchmarking high performance computer clusters by auto analyzing the hardware of the cluster and configuring and compiling specialized benchmarks (HPC Challenge, IOzone, Netperf)

Alternative implementation of Spring framework remoting subsystem that supports different schemes of remote communication between client and server (1-1, 1-many, dynamic services discovering).

Combined Utilities for Beowulf, or "cub," is based on work done at Compaq to integrate some of the best available tools to make it easy to build and install clusters of workstations for parallel computing applications.

Provide a common portal platform to join Internet Service Providers’ users into a community, both including personalization using "portlets" as the building blocks of .NET type applications and using a Parallel Portal Engine to overcome such demanding use

Condor GUI is a tool for managing and working with one or more HTCondor pools. It was developed at the Otto von Guericke University Magdeburg, Germany, to support the daily work using HTCondor. Version History: Version 0.9.3: - QDarkStyleSheet is an optional package now Version 0.9.2: - New layout of job file editor - Keyword arguments in job file editor - Linux compatibility

The BCR flavor of Cooperative Data Sharing (CDS) is a scalable, portable, flexible C-based API and daemon for initiating and communicating between processes/threads in uniprocessor and multiprocessor (e.g. distributed, SMP, and parallel) platforms.

Core Balance is a simple TCP Load Balancing proxy designed to balance connections based on node speed and number of cores. The design was intended to balance a distcc cluster. It features a status report in HTTP and an interactive mode.

Cos provides a high level interface to application developers wishing to manipulate objects stored in a corportate wide data source lightweight data entries are manipulated by services that are able to appear and dissapear across the network as needed.

DACCA == Database-Controlled Cluster Administration is a system for installation, configuration and maintenance of Linux and/or Windows NT hosts in a network environment.

Direct Access Programming Library (DAPL) is a high performance Remote Direct Memory Access API (see www.datcollaborative.org). Linux & Windows uDAPL maintenance/development is now discussed on general@lists.openfabrics.org & ofw@lists.openfabrics.org.

DeepCluster is a classic self-supervised clustering-based representation learning algorithm that iteratively groups image features and uses the cluster assignments as pseudo-labels to train the network. In each round, features produced by the network are clustered (e.g. k-means), and the cluster IDs become supervision targets in the next epoch, encouraging the model to refine its representation to better separate semantic groups. This alternating “cluster & train” scheme helps the model gradually discover meaningful structure without labels. DeepCluster was one of the early successes in unsupervised visual feature learning, demonstrating that clustering-based reformulation can rival supervised baselines for many downstream tasks. The repository includes code for feature extraction, clustering, training loops, and evaluation benchmarks like linear probes. Because of its simplicity and modular design, DeepCluster has inspired many later methods.

Allows creation and manipulation of diskless Linux (and Unix) clients, using templated system configuration files to increase the flexability and compatability of this application.

The project focuses on developing an environment where one can harness idle CPU cycles of numerous networked systems to work together on a particularly processing-intensive problem. (distributed computing you may call it)

Java package containing architecture to distribute CPU intensive processing tasks across the internet. A generic client will be capable of running any task the server provides it, automatically updating the code it runs.

DIPC stands for Distributed Inter-Process Communication. It enables you to build and program clusters of Linux computers very easily. It provides, among other things, Transparent Distributed Shared Memory (DSM). No special hardware required

Utilize Java to create an application capable of massivly parallel operations. Application will be targeted as a Napster Clone, with the additional capability of downloading projects which are seeking computer time.