Dpsyco is a automated system to distribute system configurations to several computers. It is written mainly for the Debian distribution but should be portable (without too much difficulties) to other distributions or Unixes as well. It consists of a number of shell scripts to perform the desired actions. With it you can handle users, add ssh-public-keys, patch the system, update things using cfengine, install files (overriding other package files), and more.
Moab Grid Suite is a professional grid workload management solution that integrates scheduling, management, monitoring, and reporting of workloads across independent clusters. Moab makes moving to a grid easy by adding grid-optimized job submission and management in a matter of minutes. Moab optimizes data staging and seamlessly integrates with existing security mechanisms or with grid security tool kits such as Globus. It gives sites extensive control over ownership-based access, priority, and service levels. It provides fine-tuned control over the workload and resources to make the grid usable.
TORQUE is a resource manager that provides control over batch jobs and distributed compute nodes. It is a community effort based on the original *PBS project and, with more than 1,200 patches, it has incorporated significant advances in the areas of scalability, fault tolerance, and feature extensions.
Tsung is a distributed load testing tool. It is protocol-independent and can currently be used to stress HTTP, WebDAV, PostgreSQL, MySQL, LDAP, AMQP, and XMPP/Jabber servers. It simulates user behavior using an XML description file, reports many measurements in real time (statistics can be customized with transactions, and graphics generated using gnuplot). For HTTP, it supports 1.0 and 1.1, has a proxy mode to record sessions, supports GET, POST, PUT, and DELETE methods, cookies, and basic/digest authentication. It also has support for SSL, WebSocket, and BOSH.
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.
distcc is a parallel build system that distributes compilation of C/C++/ObjC code across machines on a network. It can be set up in just a few minutes and makes builds up to ten times faster. It does not require machines to share a filesystem or have the same libraries or header files, and installation does not need superuser privileges.
Unified Parallel C (UPC) is an extension of the C programming language designed for high performance computing on large-scale parallel machines. The language provides a uniform programming model for both shared and distributed memory hardware. The programmer is presented with a single shared, partitioned address space, where variables may be directly read and written by any processor, but each variable is physically associated with a single processor. UPC uses a Single Program Multiple Data (SPMD) model of computation in which the amount of parallelism is fixed at program startup time, typically with a single thread of execution per processor. Berkeley UPC provides a portable, high-performance compiler for developing UPC software on systems ranging from clusters to custom supercomputers and even laptop-grade systems.