Sequoia provides high availability and performance scalability for databases. It is is the continuation of the C-JDBC project. It provides transparent database clustering (partitioning, replication, etc.). It works with any Java application without code modification and with any database engine. It has been successfully tested with Tomcat, JBoss, JOnAS, WebSphere, MySQL, PostgreSQL, Apache Derby, HSQLDB, SAP DB, Oracle, DB2, Sybase, MS SQL Server, Firebird, and more.
Son of Grid Engine is a highly-scalable and versatile distributed resource manager for scheduling batch or interactive jobs on clusters or desktop farms. It is a community project to continue Sun's Grid Engine. It is competitive against proprietary systems and provides better scheduling features and scalability than other free DRMs like Torque, SLURM, Condor, and Lava.
The Kent Retargettable Occam Compiler is a multi-platform Occam 2.1 compiler that is designed to allow the Occam programming language to be used on non-Transputer platforms. Extensions from a subset of the Occam 3 specification and from pi calculus have been added over time. As a result, the version of the language supported by the compiler is also sometimes referred to as Occam 2.5 or Occam-pi.
Makeflow is a workflow engine for executing large complex applications on clusters, clouds, and grids. It can be used to drive several different distributed computing systems, including Condor, SGE, and the included Work Queue system. It does not require a distributed filesystem, so you can use it to harness whatever collection of machines you have available. It is typically used for scaling up data-intensive scientific applications to hundreds or thousands of cores.
Warewulf is an operating system management toolkit designed to facilitate large scale deployments of homogeneous and heterogeneous systems on physical, virtual and cloud based infrastructures. Originally, the Warewulf project pioneered the concept of stateless computing in HPC, setting the standard for large-scale cluster provisioning. It provided two functions, provisioning and monitoring but the two functions did not communicate within Warewulf itself, nor was it possible to hook other functions directly into Warewulf itself. Today, Warewulf is more than just a basic provisioning and monitoring solution as it now implements an abstract, object-oriented data store and a modular interface that facilitates a highly extensible, customizable feature set. Current and planned modules include monitoring (operating system, services, filesystems, etc.), provisioning, power management, user management, configuration management, event/trigger handling and notification, scheduler integration, cloud services (both local and remote), etc.
Equalizer is middleware for creating and deploying parallel OpenGL-based applications. It enables applications to benefit from multiple graphics cards, processors, and computers to scale rendering performance, visual quality, and display size. An Equalizer-based application runs unmodified on any visualization system, from a simple workstation to large scale graphics clusters, multi-GPU workstations, and Virtual Reality installations.
LAM/MPI is an implementation of the Message Passing Interface (MPI) parallel standard that is especially friendly to clusters. It includes a persistent runtime environment for parallel programs, support for all of MPI-1, and a good chunk of MPI-2, such as all of the dynamic functions, one-way communication, C++ bindings, and MPI-IO.
MQ4CPP, or "Message Queuing for C++", is an implementation of an enterprise messaging system, also referred to as message-oriented middleware (MOM). It enables C++ application threads to communicate with other threads locally or remotely through the exchange of messages. A message is a request, report, and/or event that contains information needed to coordinate communication between different applications. MQ4CPP implements direct/indirect messaging, unsolicited messaging, request/reply, conversation, publish/subscribe, store & forward, and broadcast. It supports multithreading, application clustering (failover and session replication), and encryption. MQ4CPP also includes a distributed lock manager, a file transfer manager, and a distributed memory channel.
LAPACK is a linear algebra library, based on LINPACK and EISPACK, designed to provide routines for handling simultaneous equations and matrix algebra efficiently, particularly on shared memory vector processors, parallel processors, and clusters. The code is written in Fortran, and requires the BLAS (Basic Linear Algebra Subprograms) library.