G. A. Geist and V. S. Sunderam, "Experiences with network-based concurrent computing on the PVM system", Concurrency: Practice and Experience, Vol. 4, No. 4, 1992, pp. 293-311.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....and memory of current applications. The absence of a general reference language for programming with this kind of architecture, has been the cause of the overabundance of distributed language proposals in the last fifteen years. Many of these proposals have had a wide distribution, such as PVM [5], but they don t allow the verification of the total correctness of programs. Others, even though carried out by important scientists, e.g. Joyce [6] haven t achieved the necessary diffusion to be implemented in concrete architectures. And classical languages, like Ada [3] are not adequate to be ....

Geist, G.A., Sunderam, V.S. "Experiences with Network-Based Concurrent Computing on the PVM System". Concurrency: Practice and Experience, v.4, n.4., pp.293-311, 1992.

....resource allocation should allow resources to be fairly shared between the processes, whilst also allowing them to maximise their resource consumption and thus performance within this share. Traditionally the task of distributed resource management is broadly divided into two categories. The first [1, 2] considers the task to be managed blindly by the applications themselves. This performs well on dedicated systems, but is inappropriate for 1 Email: fadm2,timg sarc.city.ac.uk Phone: 0171 477 8551 Fax: 0171 477 8587 multi user situations where load distribution is dynamic since data placement ....

G. A. Geist and V. S. Sunderam, "Experiences with network based concurrent computing on the PVM system," tech. rep., Oak Ridge National Laboratory, 1991.

....their potential. Much of this work has centred around distributing work amongst machines, either for load balancing a group of applications, or for parallelising a single application in order to increase performance. General solutions to this problem rely either on explicit program placement [1, 2] or on relatively simple dynamic placement managed by the operating system [3] We believe that with the increasing complexity of resource management necessary for realtime and multimedia applications, a system is required which leaves the application in control while limiting its overall ....

....model operates in a simplified environment. 2 Resource management Research into the management of resources in distributed systems can be broadly divided into two categories. The first considers the task to be managed blindly by the applications themselves. This works well for dedicated systems [1, 2], but badly for multi user situations where load distribution is dynamic. The second approach regards management to be part of the operating or a third party system s duties. This alternative works well for small systems [6, 7, 3, 8, 9, 10] since the allocator can spread the load at application ....

G.A.Geist and V.S.Sunderam, "Experiences with network based concurrent computing on the PVM system," Tech. Rep., Oak Ridge National Laboratory, 1991.

.... Computing Environment, HeNCE, provides a graphical interface for creating, configuring, executing and debugging parallel programs [1] The HeNCE interface supports PVM programming for a collection of serial, parallel and vector computers in a network which behaves as a large distributed computer [4]. ParaGraph relies on the input trace files produced by a communication library, PICL [5] to provide a post mortem replay with 25 different perspectives [6] Supporting an iconic representation of the parallel programming library, MMK [2] VISTOP uses software, hardware and hybrid monitoring ....

Geist, G.A. and Sunderam, V.S., Experiences with Network-Based Concurrent Computing on the PVM System. Concurrency: Practice and Experience, Vol.4, No.4, June 1992, 293-311.

....Machine) is a parallel programming environment. It provides a generic parallel programming interface, and a runtime system. The system runs on a heterogeneous collection of machines, connected by a local network. These machines can include different kinds of workstations and or parallel machines [4, 2, 10, 9, 20]. PVM is not restricted to a single parallel programming paradigm, because of the flexible implementation of the runtime system; hybrid schemes can be used. This makes it possible to implement (parts of) a problem using the optimal model. The heterogeneity and support for multiple parallel ....

G. A. Geist and V.S. Sunderam. Experiences with network based concurrent computing on the PVM system. Technical Report ORNL/TM11760, Oak Ridge National Laboratory, Tenessee, January 1991.

....resource on the network remained a separate unit, but now over 100 institutions worldwide are writing and running truly heterogeneous programs utilizing multiple computer systems to solve applications through the use of a software package called PVM. PVM stands for Parallel Virtual Machine [13, 11, 3]. PVM is designed from the ground up with heterogeneity and portability as primary goals. As such it is one of the first software systems that allows machines with wildly different architectures and floating point representations to work together on a single computational task. The Heterogeneous ....

G. A. Geist and V. S. Sunderam. Experiences with network based concurrent computing on the pvm system. Technical Report ORNL/TM-11760, Oak Ridge National Laboratory, January 1991.

....data formats automatically; it will, however, support a Linda tuple space over a network of machines which conform to the same data formats. Express [9] like Linda, is also a commercial product. Express provides libraries and tools for writing programs for distributed memory multicomputers. PVM [10] is used as the infrastructure for HeNCE because it provides the right combination of attributes important to HeNCE: support for heterogeneity, ease of installation, minimal system resource requirements, portability, lack of commercial restrictions, and a straightforward programming interface. 2 ....

G. A. Geist and V. S. Sunderam. Experiences with network based concurrent computing on the pvm system. Technical Report ORNL/TM11760, Oak Ridge National Laboratory, January 1991.

No context found.

G. A. Geist and V. S. Sunderam, "Experiences with network-based concurrent computing on the PVM system", Concurrency: Practice and Experience, Vol. 4, No. 4, 1992, pp. 293-311.

No context found.

G.A. Geist and V.S. Sunderam. Experiences with Network Based Concurrent Computing on the PVM System, 1991, Report Number TM-11760, Oak Ridge National Laboratory.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC