A hybird hierarchical architecture for 3D multi-cluster NoC

The pursuit of higher performance has driven the bus based architecture toward network-on-chip (NoC). Meanwhile the three dimensional (3D) IC technology was suggested as a promising approach to reduce the wire length since the chip size became larger and larger. Because of the trend of hundreds or e...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang Jiawen, Li Li, Zhang Yuang, Pan Hongbing, He Shuzhuan, Zhang Rong
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 516
container_issue
container_start_page 512
container_title
container_volume
creator Wang Jiawen
Li Li
Zhang Yuang
Pan Hongbing
He Shuzhuan
Zhang Rong
description The pursuit of higher performance has driven the bus based architecture toward network-on-chip (NoC). Meanwhile the three dimensional (3D) IC technology was suggested as a promising approach to reduce the wire length since the chip size became larger and larger. Because of the trend of hundreds or even thousands of processor cores integrated on one chip, it trigged a quest for the amalgamation of these two technologies above. As a result, 3D NoC emerged as a potent solution. In this paper, a hybrid hierarchical architecture for 3D multi-cluster NoC is proposed with the goal of optimizing the whole system performance. Each cluster is built based on hierarchical buses while global connections among clusters are formed with mesh topologies. The memory system is also divided into several layers and managed hierarchically. Both architectures and memory systems are discussed in detail and an analytical comparison of the average distance decreasing in the proposed architecture versus a standard NoC is presented. Experimental results indicate that the proposed architecture can improve the performance sharply. For writing operations, it can save 54.7% execution time in the best condition. While for reading operations, this value can reach 63.6%. And in a real communication-intensive application, 42.7% time savings have been observed compared to the conventional NoC.
doi_str_mv 10.1109/ICCSE.2011.6028691
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6028691</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6028691</ieee_id><sourcerecordid>6028691</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-833b75e109c370ed74ab298c49f6d3833f0cf77671d3e09163b8cea3ca24df243</originalsourceid><addsrcrecordid>eNpFT81KAzEYjIigtn0BveQFds2XpPnBU4lVC0UP7b1ks1_YyJZKNnvo27towbnMDAPDDCEPwGoAZp82zu3WNWcAtWLcKAtX5B4kl9JqUPr63-jlLVkMwxeboJSxXN2R5xXtzk3KLe0SZp9Dl4Lv6a8oGMqYkcZTpuKFHse-pCr041Aw04-Tm5Ob6PsBFxeekf3reu_eq-3n28attlWyrFRGiEYvcZoahGbYaukbbk2QNqpWTGlkIWqtNLQCmQUlGhPQi-C5bCOXYkYe_2oTIh6-czr6fD5cvoof-hVHKw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A hybird hierarchical architecture for 3D multi-cluster NoC</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Wang Jiawen ; Li Li ; Zhang Yuang ; Pan Hongbing ; He Shuzhuan ; Zhang Rong</creator><creatorcontrib>Wang Jiawen ; Li Li ; Zhang Yuang ; Pan Hongbing ; He Shuzhuan ; Zhang Rong</creatorcontrib><description>The pursuit of higher performance has driven the bus based architecture toward network-on-chip (NoC). Meanwhile the three dimensional (3D) IC technology was suggested as a promising approach to reduce the wire length since the chip size became larger and larger. Because of the trend of hundreds or even thousands of processor cores integrated on one chip, it trigged a quest for the amalgamation of these two technologies above. As a result, 3D NoC emerged as a potent solution. In this paper, a hybrid hierarchical architecture for 3D multi-cluster NoC is proposed with the goal of optimizing the whole system performance. Each cluster is built based on hierarchical buses while global connections among clusters are formed with mesh topologies. The memory system is also divided into several layers and managed hierarchically. Both architectures and memory systems are discussed in detail and an analytical comparison of the average distance decreasing in the proposed architecture versus a standard NoC is presented. Experimental results indicate that the proposed architecture can improve the performance sharply. For writing operations, it can save 54.7% execution time in the best condition. While for reading operations, this value can reach 63.6%. And in a real communication-intensive application, 42.7% time savings have been observed compared to the conventional NoC.</description><identifier>ISBN: 1424497175</identifier><identifier>ISBN: 9781424497171</identifier><identifier>EISBN: 1424497167</identifier><identifier>EISBN: 1424497183</identifier><identifier>EISBN: 9781424497188</identifier><identifier>EISBN: 9781424497164</identifier><identifier>DOI: 10.1109/ICCSE.2011.6028691</identifier><language>eng</language><publisher>IEEE</publisher><subject>3D NoC ; architecture ; hierarchical ; hybird ; Memory architecture ; multi-cluster ; Nickel ; System-on-a-chip ; Three dimensional displays ; Topology ; Writing</subject><ispartof>2011 6th International Conference on Computer Science &amp; Education (ICCSE), 2011, p.512-516</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6028691$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,777,781,786,787,2052,27906,54901</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6028691$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Wang Jiawen</creatorcontrib><creatorcontrib>Li Li</creatorcontrib><creatorcontrib>Zhang Yuang</creatorcontrib><creatorcontrib>Pan Hongbing</creatorcontrib><creatorcontrib>He Shuzhuan</creatorcontrib><creatorcontrib>Zhang Rong</creatorcontrib><title>A hybird hierarchical architecture for 3D multi-cluster NoC</title><title>2011 6th International Conference on Computer Science &amp; Education (ICCSE)</title><addtitle>ICCSE</addtitle><description>The pursuit of higher performance has driven the bus based architecture toward network-on-chip (NoC). Meanwhile the three dimensional (3D) IC technology was suggested as a promising approach to reduce the wire length since the chip size became larger and larger. Because of the trend of hundreds or even thousands of processor cores integrated on one chip, it trigged a quest for the amalgamation of these two technologies above. As a result, 3D NoC emerged as a potent solution. In this paper, a hybrid hierarchical architecture for 3D multi-cluster NoC is proposed with the goal of optimizing the whole system performance. Each cluster is built based on hierarchical buses while global connections among clusters are formed with mesh topologies. The memory system is also divided into several layers and managed hierarchically. Both architectures and memory systems are discussed in detail and an analytical comparison of the average distance decreasing in the proposed architecture versus a standard NoC is presented. Experimental results indicate that the proposed architecture can improve the performance sharply. For writing operations, it can save 54.7% execution time in the best condition. While for reading operations, this value can reach 63.6%. And in a real communication-intensive application, 42.7% time savings have been observed compared to the conventional NoC.</description><subject>3D NoC</subject><subject>architecture</subject><subject>hierarchical</subject><subject>hybird</subject><subject>Memory architecture</subject><subject>multi-cluster</subject><subject>Nickel</subject><subject>System-on-a-chip</subject><subject>Three dimensional displays</subject><subject>Topology</subject><subject>Writing</subject><isbn>1424497175</isbn><isbn>9781424497171</isbn><isbn>1424497167</isbn><isbn>1424497183</isbn><isbn>9781424497188</isbn><isbn>9781424497164</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpFT81KAzEYjIigtn0BveQFds2XpPnBU4lVC0UP7b1ks1_YyJZKNnvo27towbnMDAPDDCEPwGoAZp82zu3WNWcAtWLcKAtX5B4kl9JqUPr63-jlLVkMwxeboJSxXN2R5xXtzk3KLe0SZp9Dl4Lv6a8oGMqYkcZTpuKFHse-pCr041Aw04-Tm5Ob6PsBFxeekf3reu_eq-3n28attlWyrFRGiEYvcZoahGbYaukbbk2QNqpWTGlkIWqtNLQCmQUlGhPQi-C5bCOXYkYe_2oTIh6-czr6fD5cvoof-hVHKw</recordid><startdate>201108</startdate><enddate>201108</enddate><creator>Wang Jiawen</creator><creator>Li Li</creator><creator>Zhang Yuang</creator><creator>Pan Hongbing</creator><creator>He Shuzhuan</creator><creator>Zhang Rong</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201108</creationdate><title>A hybird hierarchical architecture for 3D multi-cluster NoC</title><author>Wang Jiawen ; Li Li ; Zhang Yuang ; Pan Hongbing ; He Shuzhuan ; Zhang Rong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-833b75e109c370ed74ab298c49f6d3833f0cf77671d3e09163b8cea3ca24df243</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>3D NoC</topic><topic>architecture</topic><topic>hierarchical</topic><topic>hybird</topic><topic>Memory architecture</topic><topic>multi-cluster</topic><topic>Nickel</topic><topic>System-on-a-chip</topic><topic>Three dimensional displays</topic><topic>Topology</topic><topic>Writing</topic><toplevel>online_resources</toplevel><creatorcontrib>Wang Jiawen</creatorcontrib><creatorcontrib>Li Li</creatorcontrib><creatorcontrib>Zhang Yuang</creatorcontrib><creatorcontrib>Pan Hongbing</creatorcontrib><creatorcontrib>He Shuzhuan</creatorcontrib><creatorcontrib>Zhang Rong</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Wang Jiawen</au><au>Li Li</au><au>Zhang Yuang</au><au>Pan Hongbing</au><au>He Shuzhuan</au><au>Zhang Rong</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A hybird hierarchical architecture for 3D multi-cluster NoC</atitle><btitle>2011 6th International Conference on Computer Science &amp; Education (ICCSE)</btitle><stitle>ICCSE</stitle><date>2011-08</date><risdate>2011</risdate><spage>512</spage><epage>516</epage><pages>512-516</pages><isbn>1424497175</isbn><isbn>9781424497171</isbn><eisbn>1424497167</eisbn><eisbn>1424497183</eisbn><eisbn>9781424497188</eisbn><eisbn>9781424497164</eisbn><abstract>The pursuit of higher performance has driven the bus based architecture toward network-on-chip (NoC). Meanwhile the three dimensional (3D) IC technology was suggested as a promising approach to reduce the wire length since the chip size became larger and larger. Because of the trend of hundreds or even thousands of processor cores integrated on one chip, it trigged a quest for the amalgamation of these two technologies above. As a result, 3D NoC emerged as a potent solution. In this paper, a hybrid hierarchical architecture for 3D multi-cluster NoC is proposed with the goal of optimizing the whole system performance. Each cluster is built based on hierarchical buses while global connections among clusters are formed with mesh topologies. The memory system is also divided into several layers and managed hierarchically. Both architectures and memory systems are discussed in detail and an analytical comparison of the average distance decreasing in the proposed architecture versus a standard NoC is presented. Experimental results indicate that the proposed architecture can improve the performance sharply. For writing operations, it can save 54.7% execution time in the best condition. While for reading operations, this value can reach 63.6%. And in a real communication-intensive application, 42.7% time savings have been observed compared to the conventional NoC.</abstract><pub>IEEE</pub><doi>10.1109/ICCSE.2011.6028691</doi><tpages>5</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 1424497175
ispartof 2011 6th International Conference on Computer Science & Education (ICCSE), 2011, p.512-516
issn
language eng
recordid cdi_ieee_primary_6028691
source IEEE Electronic Library (IEL) Conference Proceedings
subjects 3D NoC
architecture
hierarchical
hybird
Memory architecture
multi-cluster
Nickel
System-on-a-chip
Three dimensional displays
Topology
Writing
title A hybird hierarchical architecture for 3D multi-cluster NoC
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T01%3A18%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=A%20hybird%20hierarchical%20architecture%20for%203D%20multi-cluster%20NoC&rft.btitle=2011%206th%20International%20Conference%20on%20Computer%20Science%20&%20Education%20(ICCSE)&rft.au=Wang%20Jiawen&rft.date=2011-08&rft.spage=512&rft.epage=516&rft.pages=512-516&rft.isbn=1424497175&rft.isbn_list=9781424497171&rft_id=info:doi/10.1109/ICCSE.2011.6028691&rft_dat=%3Cieee_6IE%3E6028691%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1424497167&rft.eisbn_list=1424497183&rft.eisbn_list=9781424497188&rft.eisbn_list=9781424497164&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6028691&rfr_iscdi=true