Precedence-constrained task allocation onto point-to-point networks for pipelined execution

The problem of scheduling directed acyclic task flow graphs to multiprocessor systems using point-to-point networks is examined. An environment where the application has a strict throughput requirement is assumed. Pipelined parallelism is used to meet the throughput requirement. Communication and co...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on parallel and distributed systems 1999-08, Vol.10 (8), p.838-851
Hauptverfasser: Hary, S.L., Ozguner, F.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 851
container_issue 8
container_start_page 838
container_title IEEE transactions on parallel and distributed systems
container_volume 10
creator Hary, S.L.
Ozguner, F.
description The problem of scheduling directed acyclic task flow graphs to multiprocessor systems using point-to-point networks is examined. An environment where the application has a strict throughput requirement is assumed. Pipelined parallelism is used to meet the throughput requirement. Communication and computation are completely overlapped. Each task and message has a periodic rate and deadline equal to the throughput requirement. A heuristic procedure based on preclustering, recursive mincut bipartitioning, and iterative improvement is proposed to reduce the maximum contention due to communication in the network, increasing the likelihood that messages meet their deadlines. The task assignment procedure takes into account the topology of the multiprocessor system and the distance between communicating tasks.
doi_str_mv 10.1109/71.790601
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_790601</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>790601</ieee_id><sourcerecordid>919913244</sourcerecordid><originalsourceid>FETCH-LOGICAL-c340t-4a5b03aecd0998034e2a6bf6caab3d7820f4cfcdba38131428df8eeabf0e357c3</originalsourceid><addsrcrecordid>eNqF0T1PwzAQBmALgUQpDKxMmUAMLufYaewRIb6kSjDAxBA5zlkKTe1guwL-PWlTMcJ0J91zN9xLyCmDGWOgrko2KxXMge2RCSsKSXMm-f7Qgyioypk6JEcxvgMwUYCYkLfngAYbdAap8S6moFuHTZZ0XGa667zRqfUu8y75rPetSzR5um0yh-nTh2XMrA9Z3_bYbVfxC816s3RMDqzuIp7s6pS83t2-3DzQxdP94831ghouIFGhixq4RtOAUhK4wFzPazs3Wte8KWUOVhhrmlpzyTgTuWysRNS1BeRFafiUXIx3--A_1hhTtWqjwa7TDv06VoopxXguxCDP_5S5LIQa3vg_LEGCYuUAL0dogo8xoK360K50-K4YVJtEqpJVYyKDPRtti4i_bjf8Ad1WiBY</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>27080917</pqid></control><display><type>article</type><title>Precedence-constrained task allocation onto point-to-point networks for pipelined execution</title><source>IEEE Electronic Library (IEL)</source><creator>Hary, S.L. ; Ozguner, F.</creator><creatorcontrib>Hary, S.L. ; Ozguner, F.</creatorcontrib><description>The problem of scheduling directed acyclic task flow graphs to multiprocessor systems using point-to-point networks is examined. An environment where the application has a strict throughput requirement is assumed. Pipelined parallelism is used to meet the throughput requirement. Communication and computation are completely overlapped. Each task and message has a periodic rate and deadline equal to the throughput requirement. A heuristic procedure based on preclustering, recursive mincut bipartitioning, and iterative improvement is proposed to reduce the maximum contention due to communication in the network, increasing the likelihood that messages meet their deadlines. The task assignment procedure takes into account the topology of the multiprocessor system and the distance between communicating tasks.</description><identifier>ISSN: 1045-9219</identifier><identifier>EISSN: 1558-2183</identifier><identifier>DOI: 10.1109/71.790601</identifier><identifier>CODEN: ITDSEO</identifier><language>eng</language><publisher>IEEE</publisher><subject>Allocations ; Communicating ; Flow graphs ; Messages ; Multiprocessing systems ; Multiprocessor ; Network topology ; Networks ; Parallel processing ; Pipelines ; Processor scheduling ; Radar signal processing ; Real time systems ; Recursive ; Scheduling ; Sun ; Tasks ; Throughput</subject><ispartof>IEEE transactions on parallel and distributed systems, 1999-08, Vol.10 (8), p.838-851</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c340t-4a5b03aecd0998034e2a6bf6caab3d7820f4cfcdba38131428df8eeabf0e357c3</citedby><cites>FETCH-LOGICAL-c340t-4a5b03aecd0998034e2a6bf6caab3d7820f4cfcdba38131428df8eeabf0e357c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/790601$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/790601$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Hary, S.L.</creatorcontrib><creatorcontrib>Ozguner, F.</creatorcontrib><title>Precedence-constrained task allocation onto point-to-point networks for pipelined execution</title><title>IEEE transactions on parallel and distributed systems</title><addtitle>TPDS</addtitle><description>The problem of scheduling directed acyclic task flow graphs to multiprocessor systems using point-to-point networks is examined. An environment where the application has a strict throughput requirement is assumed. Pipelined parallelism is used to meet the throughput requirement. Communication and computation are completely overlapped. Each task and message has a periodic rate and deadline equal to the throughput requirement. A heuristic procedure based on preclustering, recursive mincut bipartitioning, and iterative improvement is proposed to reduce the maximum contention due to communication in the network, increasing the likelihood that messages meet their deadlines. The task assignment procedure takes into account the topology of the multiprocessor system and the distance between communicating tasks.</description><subject>Allocations</subject><subject>Communicating</subject><subject>Flow graphs</subject><subject>Messages</subject><subject>Multiprocessing systems</subject><subject>Multiprocessor</subject><subject>Network topology</subject><subject>Networks</subject><subject>Parallel processing</subject><subject>Pipelines</subject><subject>Processor scheduling</subject><subject>Radar signal processing</subject><subject>Real time systems</subject><subject>Recursive</subject><subject>Scheduling</subject><subject>Sun</subject><subject>Tasks</subject><subject>Throughput</subject><issn>1045-9219</issn><issn>1558-2183</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1999</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNqF0T1PwzAQBmALgUQpDKxMmUAMLufYaewRIb6kSjDAxBA5zlkKTe1guwL-PWlTMcJ0J91zN9xLyCmDGWOgrko2KxXMge2RCSsKSXMm-f7Qgyioypk6JEcxvgMwUYCYkLfngAYbdAap8S6moFuHTZZ0XGa667zRqfUu8y75rPetSzR5um0yh-nTh2XMrA9Z3_bYbVfxC816s3RMDqzuIp7s6pS83t2-3DzQxdP94831ghouIFGhixq4RtOAUhK4wFzPazs3Wte8KWUOVhhrmlpzyTgTuWysRNS1BeRFafiUXIx3--A_1hhTtWqjwa7TDv06VoopxXguxCDP_5S5LIQa3vg_LEGCYuUAL0dogo8xoK360K50-K4YVJtEqpJVYyKDPRtti4i_bjf8Ad1WiBY</recordid><startdate>19990801</startdate><enddate>19990801</enddate><creator>Hary, S.L.</creator><creator>Ozguner, F.</creator><general>IEEE</general><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7SP</scope><scope>F28</scope><scope>FR3</scope></search><sort><creationdate>19990801</creationdate><title>Precedence-constrained task allocation onto point-to-point networks for pipelined execution</title><author>Hary, S.L. ; Ozguner, F.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c340t-4a5b03aecd0998034e2a6bf6caab3d7820f4cfcdba38131428df8eeabf0e357c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1999</creationdate><topic>Allocations</topic><topic>Communicating</topic><topic>Flow graphs</topic><topic>Messages</topic><topic>Multiprocessing systems</topic><topic>Multiprocessor</topic><topic>Network topology</topic><topic>Networks</topic><topic>Parallel processing</topic><topic>Pipelines</topic><topic>Processor scheduling</topic><topic>Radar signal processing</topic><topic>Real time systems</topic><topic>Recursive</topic><topic>Scheduling</topic><topic>Sun</topic><topic>Tasks</topic><topic>Throughput</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hary, S.L.</creatorcontrib><creatorcontrib>Ozguner, F.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>ANTE: Abstracts in New Technology &amp; Engineering</collection><collection>Engineering Research Database</collection><jtitle>IEEE transactions on parallel and distributed systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hary, S.L.</au><au>Ozguner, F.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Precedence-constrained task allocation onto point-to-point networks for pipelined execution</atitle><jtitle>IEEE transactions on parallel and distributed systems</jtitle><stitle>TPDS</stitle><date>1999-08-01</date><risdate>1999</risdate><volume>10</volume><issue>8</issue><spage>838</spage><epage>851</epage><pages>838-851</pages><issn>1045-9219</issn><eissn>1558-2183</eissn><coden>ITDSEO</coden><abstract>The problem of scheduling directed acyclic task flow graphs to multiprocessor systems using point-to-point networks is examined. An environment where the application has a strict throughput requirement is assumed. Pipelined parallelism is used to meet the throughput requirement. Communication and computation are completely overlapped. Each task and message has a periodic rate and deadline equal to the throughput requirement. A heuristic procedure based on preclustering, recursive mincut bipartitioning, and iterative improvement is proposed to reduce the maximum contention due to communication in the network, increasing the likelihood that messages meet their deadlines. The task assignment procedure takes into account the topology of the multiprocessor system and the distance between communicating tasks.</abstract><pub>IEEE</pub><doi>10.1109/71.790601</doi><tpages>14</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1045-9219
ispartof IEEE transactions on parallel and distributed systems, 1999-08, Vol.10 (8), p.838-851
issn 1045-9219
1558-2183
language eng
recordid cdi_ieee_primary_790601
source IEEE Electronic Library (IEL)
subjects Allocations
Communicating
Flow graphs
Messages
Multiprocessing systems
Multiprocessor
Network topology
Networks
Parallel processing
Pipelines
Processor scheduling
Radar signal processing
Real time systems
Recursive
Scheduling
Sun
Tasks
Throughput
title Precedence-constrained task allocation onto point-to-point networks for pipelined execution
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T07%3A18%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Precedence-constrained%20task%20allocation%20onto%20point-to-point%20networks%20for%20pipelined%20execution&rft.jtitle=IEEE%20transactions%20on%20parallel%20and%20distributed%20systems&rft.au=Hary,%20S.L.&rft.date=1999-08-01&rft.volume=10&rft.issue=8&rft.spage=838&rft.epage=851&rft.pages=838-851&rft.issn=1045-9219&rft.eissn=1558-2183&rft.coden=ITDSEO&rft_id=info:doi/10.1109/71.790601&rft_dat=%3Cproquest_RIE%3E919913244%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=27080917&rft_id=info:pmid/&rft_ieee_id=790601&rfr_iscdi=true