Enhancing throughput for streaming applications running on cluster systems

dc.contributor.authorGuirado Fernández, Fernando
dc.contributor.authorRoig Mateu, Concepció
dc.contributor.authorRipoll, A.
dc.date.accessioned2016-06-20T11:47:28Z
dc.date.embargoEndDate2025-01-01
dc.date.issued2013
dc.description.abstractThe exploitation of throughput in a parallel application that processes an input data stream is a difficult challenge. For typical coarse-grain applications, where the computation time of tasks is greater than their communication time, the maximum achievable throughput is determined by the maximum task computation time. Thus, the improvement in throughput above this maximum would eventually require the modification of the source code of the tasks. In this work, we address the improvement of throughput by proposing two task replication methodologies that have the target throughput to be achieved as an input parameter. They proceed by generating a new task graph structure that permits the target throughput to be achieved. The first replication mechanism, named DPRM (Data Parallel Replication Mechanism), exploits the inner task data parallelism. The second mechanism, named TCRM (Task Copy Replication Mechanism), creates new execution paths inside the application task graph structure that allows more than one instance of data to be processed concurrently. We evaluate the effectiveness of these mechanisms with three real applications executed in a cluster system: the MPEG2 video compressor, the IVUS (Intra-Vascular Ultra-Sound) medical image application and the BASIZ (Bright and SAtured Images Zone) video processing application. In all these cases, the obtained throughput was greater after applying the proposed replication mechanism than what the application could provide with the original implementation.ca_ES
dc.description.sponsorshipThis work was supported by the Ministry of Education and Science (Spain) under contract TIN2011-28689-C02-02.ca_ES
dc.identifier.doihttps://doi.org/10.1016/j.jpdc.2013.04.006
dc.identifier.idgrec020334
dc.identifier.issn0743-7315
dc.identifier.urihttp://hdl.handle.net/10459.1/57226
dc.language.isoengca_ES
dc.publisherElsevierca_ES
dc.relationMICINN/PN2008-2011/TIN2011-28689-C02-02ca_ES
dc.relation.isformatofReproducció del document publicat a https://doi.org/10.1016/j.jpdc.2013.04.006ca_ES
dc.relation.ispartofJournal of Parallel and Distributed Computing, 2013, vol. 73, núm. 8, p. 1092-1105ca_ES
dc.rights(c) Elsevier, 2013ca_ES
dc.rights.accessRightsinfo:eu-repo/semantics/restrictedAccessca_ES
dc.subjectStreaming applicationsca_ES
dc.subjectPipeline executionca_ES
dc.subjectData parallelismca_ES
dc.subjectTask parallelismca_ES
dc.titleEnhancing throughput for streaming applications running on cluster systemsca_ES
dc.typearticleca_ES
dc.type.versionpublishedVersionca_ES
Files
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: