Parallel Operating Systems

• Angel (City University of London)
  Angel is designed as a generic parallel and distributed operating system, although it is currently targeted towards a high-speed network of PCs. This model of computing has the dual advantage of both a cheap initial cost and also a low incremental cost. By treating a network of nodes as a single shared memory machine, using distributed virtual shared memory (DVSM) techniques, we have addressed both the needs for improved performance and provided a more portable and useful platform for our applications.
• Chimera (Carnegie Mellon University)
  The Advanced Manipulators Laboratory, at Carnegie Mellon University, has developed the Chimera Real-Time Operating System, a next generation multiprocessor real-time operating system (RTOS) designed especially to support the development of dynamically reconfigurable software for robotic and automation systems. Version 3.0 and later of the software is already being used by several institutions outside of Carnegie Mellon, including university, government, and industrial research labs.
• COSY (University of Karlsruhe, University of Paderborn)
  Group Members: Wolfgang Burke, Roger Butenuth, Sven Gilles
  Cosy is an operating system for highly parallel computers, with hundreds or thousands of processors. All parts of the system are designed to scale up with the number of processors, without any one becoming a bottleneck.
• Helios (Perihelion Distributed Software)
  Helios is a micro kernel operating system for embedded and multiprocessor systems. The operating system is modular in design and can scale from an embedded runtime executive up to a fully distributed operating system.
• Hive (Stanford University Flash Project) Group Members
  The Hive OS Team is designing an operating system that is able to operate effectively in a traditional supercomputer environment as well as in a general-purpose, multiprogrammed environment. The latter environment poses significant challenges since general-purpose environments typically contain large numbers of processes making many system calls and many small I/O requests.
• Paramecium
  This kernel uses an object-based software architecture which together with instance naming, late binding and explicit overrides enables easy reconfiguration. Determining which components are allowed to reside in the kernel address space is up to a certification authority or one of its delegates. These delegates may include validation programs, correctness provers, and system administrators. The main advantage of certifications is that it can handle trust and sharing in a non-cooperative environment.
• PEACE (Process Execution And Communication Environment) (GMD FIRST)
  PEACE is a family of operating systems with a truly object-oriented design developed at GMD FIRST. Emphasis is laid on subjects as performance, configurability and portability. It is the native operating system for the MANNA computer, a massively parallel computer facilitating a high-performance interconnection network. Ports to SunOS, FreeBSD and Parix were made and expand the scope of this system to other parallel computers as well as to workstation networks.
• Puma and relatives (Sandia National Laboratory)
  The Puma operating system targets high-performance applications on tightly coupled distributed memory architectures. It is a descendant of SUNMOS.
• Sting
  Sting is an experimental operating system designed to serve as an efficient customizable substrate for modern programming languages. The base language used in our current implementation is Scheme, but Sting's core ideas could be incorporated into any reasonably high-level language. The ultimate goal in this project is to build a unified programming environment for parallel and distributed computing.
• Tornado (University of Toronto)
  Tornado is a new operating system being developed for the NUMAchine that addresses NUMA programming issues using novel approaches, some of which were developed for our previous operating system Hurricane. Tornado uses an object-oriented, building block approach that allows applications to customize policies and adapt them to their performance needs. For research purposes, we intend to tune Tornado for applications with very large data sets that typically do not fit in memory and hence have high I/O demands. We also intend to provide applications with an operating environment that provides predictable performance behavior to allow performance tuning and to allow the application to appropriately parameterize its algorithms at run-time.