Efficient distributed execution of computationally intensive tasks

Meliones, AN; Barosan, I; Varvarigou, TT

dc.contributor.author	Meliones, AN	en
dc.contributor.author	Barosan, I	en
dc.contributor.author	Varvarigou, TT	en
dc.date.accessioned	2014-03-01T01:13:43Z
dc.date.available	2014-03-01T01:13:43Z
dc.date.issued	1998	en
dc.identifier.issn	0302-9743	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/12677
dc.subject	Distributed Architecture	en
dc.subject	Distributed System	en
dc.subject	Network Computing	en
dc.subject	Network Delay	en
dc.subject	Physical Layer	en
dc.subject.classification	Computer Science, Theory & Methods	en
dc.title	Efficient distributed execution of computationally intensive tasks	en
heal.type	journalArticle	en
heal.identifier.primary	10.1007/BFb0037153	en
heal.identifier.secondary	http://dx.doi.org/10.1007/BFb0037153	en
heal.language	English	en
heal.publicationDate	1998	en
heal.abstract	Recent advances in computer and network technology have made distributed systems appropriate for the provision of high quality services in many application areas, especially when execution time is the critical factor. Many modern problems are extremely computationally intensive, leading to an unavoidable compromise to the quality of the generated results in order to best fit time and budgetary restrictions. This paper reports on the implementation of a distributed architecture, suitable for the efficient execution of computationally intensive parallel jobs that may require/generate large volume of data. A cluster of networked computing nodes as a physical layer to the distributed architecture is considered. We present a job model for the submitted tasks that is derived from real-life application areas. Overlapping techniques are proposed as a method of reducing network delays. We prove that the proposed distribution of work over the nodes of the execution network is optimal, in terms of minimizing the execution time, with respect to the availability of resources. Certain configuration and implementation details are discussed, mainly in the job management and submission and delivery manager layers. We conclude by presenting our experience of testing the environment for computing-intensive 3D rendering jobs derived from the ESPRIT project EROPPA.	en
heal.publisher	SPRINGER-VERLAG BERLIN	en
heal.journalName	HIGH-PERFORMANCE COMPUTING AND NETWORKING	en
heal.bookName	LECTURE NOTES IN COMPUTER SCIENCE	en
dc.identifier.doi	10.1007/BFb0037153	en
dc.identifier.isi	ISI:000077581300028	en
dc.identifier.volume	1401	en
dc.identifier.spage	262	en
dc.identifier.epage	273	en