Overlapped loop support in the Cydra 5

The CydraTM 5 architecture adds unique support for overlapping successive iterations of a loop to a very long instruction word (VLIW) base. This architecture allows highly parallel loop execution for a much larger class of loops than can be vectorized, without requiring the unrolling of loops usuall...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Dehnert, James C., Hsu, Peter Y.-T., Bratt, Joseph P.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Computer systems organization > Architectures Computer systems organization > Architectures > Parallel architectures > Very long instruction word Computer systems organization > Architectures > Serial architectures > Complex instruction set computing Computer systems organization > Architectures > Serial architectures > Reduced instruction set computing Theory of computation > Design and analysis of algorithms > Approximation algorithms analysis > Scheduling algorithms Theory of computation > Design and analysis of algorithms > Online algorithms > Online learning algorithms > Scheduling algorithms Theory of computation > Theory and algorithms for application domains > Machine learning theory > Reinforcement learning > Sequential decision making
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page	38
container_issue
container_start_page	26
container_title
container_volume
creator	Dehnert, James C. Hsu, Peter Y.-T. Bratt, Joseph P.
description	The CydraTM 5 architecture adds unique support for overlapping successive iterations of a loop to a very long instruction word (VLIW) base. This architecture allows highly parallel loop execution for a much larger class of loops than can be vectorized, without requiring the unrolling of loops usually used by compilers for VLIW machines. This paper discusses the Cydra 5 loop scheduling model, the special architectural features which support it, and the loop compilation techniques used to take full advantage of the architecture.
doi_str_mv	10.1145/70082.68185
format	Conference Proceeding
fullrecord	<record><control><sourceid>proquest_acm_b</sourceid><recordid>TN_cdi_proquest_miscellaneous_31693716</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>31693716</sourcerecordid><originalsourceid>FETCH-LOGICAL-a163t-c4d2ee3530f1d1c0fb6541ef2c1c1dafcedd88b8b224780a8bac16ae60af31de3</originalsourceid><addsrcrecordid>eNqNkM1KxDAUhQMqONZZ-QJZyCyEjvc2bZoupfgHA7PRdUiTG6x2JrVpBd_eOuMDuDpw-DgHPsauENaIeXFbAqhsLRWq4oRdgKrKCgUAnLIFoBRpUcn8nC1jfJ9LKAsBKl-w1faLhs70PTnehdDzOPV9GEbe7vn4Rrz-doPhxSU786aLtPzLhL0-3L_UT-lm-_hc321SM1-Mqc1dRiTmbY8OLfhGFjmSzyxadMZbck6pRjVZlpcKjGqMRWlIgvECHYmErY67_RA-J4qj3rXRUteZPYUpaoGyEuX8lbCbI2jsTjchfESNoH9F6IMIfRChm6ElP8PX_4DFDxMGWsA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype><pqid>31693716</pqid></control><display><type>conference_proceeding</type><title>Overlapped loop support in the Cydra 5</title><source>ACM Digital Library Complete</source><creator>Dehnert, James C. ; Hsu, Peter Y.-T. ; Bratt, Joseph P.</creator><creatorcontrib>Dehnert, James C. ; Hsu, Peter Y.-T. ; Bratt, Joseph P.</creatorcontrib><description>The CydraTM 5 architecture adds unique support for overlapping successive iterations of a loop to a very long instruction word (VLIW) base. This architecture allows highly parallel loop execution for a much larger class of loops than can be vectorized, without requiring the unrolling of loops usually used by compilers for VLIW machines. This paper discusses the Cydra 5 loop scheduling model, the special architectural features which support it, and the loop compilation techniques used to take full advantage of the architecture.</description><identifier>ISSN: 0163-5964</identifier><identifier>ISBN: 0897913000</identifier><identifier>ISBN: 9780897913003</identifier><identifier>DOI: 10.1145/70082.68185</identifier><language>eng</language><publisher>New York, NY, USA: ACM</publisher><subject>Computer systems organization -- Architectures ; Computer systems organization -- Architectures -- Parallel architectures -- Very long instruction word ; Computer systems organization -- Architectures -- Serial architectures -- Complex instruction set computing ; Computer systems organization -- Architectures -- Serial architectures -- Reduced instruction set computing ; Theory of computation -- Design and analysis of algorithms -- Approximation algorithms analysis -- Scheduling algorithms ; Theory of computation -- Design and analysis of algorithms -- Online algorithms -- Online learning algorithms -- Scheduling algorithms ; Theory of computation -- Theory and algorithms for application domains -- Machine learning theory -- Reinforcement learning -- Sequential decision making</subject><ispartof>Computer architecture news, 1989, p.26-38</ispartof><rights>1989 ACM</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>309,310,780,784,789,790,23930,23931,25140,27925</link.rule.ids></links><search><creatorcontrib>Dehnert, James C.</creatorcontrib><creatorcontrib>Hsu, Peter Y.-T.</creatorcontrib><creatorcontrib>Bratt, Joseph P.</creatorcontrib><title>Overlapped loop support in the Cydra 5</title><title>Computer architecture news</title><description>The CydraTM 5 architecture adds unique support for overlapping successive iterations of a loop to a very long instruction word (VLIW) base. This architecture allows highly parallel loop execution for a much larger class of loops than can be vectorized, without requiring the unrolling of loops usually used by compilers for VLIW machines. This paper discusses the Cydra 5 loop scheduling model, the special architectural features which support it, and the loop compilation techniques used to take full advantage of the architecture.</description><subject>Computer systems organization -- Architectures</subject><subject>Computer systems organization -- Architectures -- Parallel architectures -- Very long instruction word</subject><subject>Computer systems organization -- Architectures -- Serial architectures -- Complex instruction set computing</subject><subject>Computer systems organization -- Architectures -- Serial architectures -- Reduced instruction set computing</subject><subject>Theory of computation -- Design and analysis of algorithms -- Approximation algorithms analysis -- Scheduling algorithms</subject><subject>Theory of computation -- Design and analysis of algorithms -- Online algorithms -- Online learning algorithms -- Scheduling algorithms</subject><subject>Theory of computation -- Theory and algorithms for application domains -- Machine learning theory -- Reinforcement learning -- Sequential decision making</subject><issn>0163-5964</issn><isbn>0897913000</isbn><isbn>9780897913003</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1989</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNqNkM1KxDAUhQMqONZZ-QJZyCyEjvc2bZoupfgHA7PRdUiTG6x2JrVpBd_eOuMDuDpw-DgHPsauENaIeXFbAqhsLRWq4oRdgKrKCgUAnLIFoBRpUcn8nC1jfJ9LKAsBKl-w1faLhs70PTnehdDzOPV9GEbe7vn4Rrz-doPhxSU786aLtPzLhL0-3L_UT-lm-_hc321SM1-Mqc1dRiTmbY8OLfhGFjmSzyxadMZbck6pRjVZlpcKjGqMRWlIgvECHYmErY67_RA-J4qj3rXRUteZPYUpaoGyEuX8lbCbI2jsTjchfESNoH9F6IMIfRChm6ElP8PX_4DFDxMGWsA</recordid><startdate>19890401</startdate><enddate>19890401</enddate><creator>Dehnert, James C.</creator><creator>Hsu, Peter Y.-T.</creator><creator>Bratt, Joseph P.</creator><general>ACM</general><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>19890401</creationdate><title>Overlapped loop support in the Cydra 5</title><author>Dehnert, James C. ; Hsu, Peter Y.-T. ; Bratt, Joseph P.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a163t-c4d2ee3530f1d1c0fb6541ef2c1c1dafcedd88b8b224780a8bac16ae60af31de3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1989</creationdate><topic>Computer systems organization -- Architectures</topic><topic>Computer systems organization -- Architectures -- Parallel architectures -- Very long instruction word</topic><topic>Computer systems organization -- Architectures -- Serial architectures -- Complex instruction set computing</topic><topic>Computer systems organization -- Architectures -- Serial architectures -- Reduced instruction set computing</topic><topic>Theory of computation -- Design and analysis of algorithms -- Approximation algorithms analysis -- Scheduling algorithms</topic><topic>Theory of computation -- Design and analysis of algorithms -- Online algorithms -- Online learning algorithms -- Scheduling algorithms</topic><topic>Theory of computation -- Theory and algorithms for application domains -- Machine learning theory -- Reinforcement learning -- Sequential decision making</topic><toplevel>online_resources</toplevel><creatorcontrib>Dehnert, James C.</creatorcontrib><creatorcontrib>Hsu, Peter Y.-T.</creatorcontrib><creatorcontrib>Bratt, Joseph P.</creatorcontrib><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></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Dehnert, James C.</au><au>Hsu, Peter Y.-T.</au><au>Bratt, Joseph P.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Overlapped loop support in the Cydra 5</atitle><btitle>Computer architecture news</btitle><date>1989-04-01</date><risdate>1989</risdate><spage>26</spage><epage>38</epage><pages>26-38</pages><issn>0163-5964</issn><isbn>0897913000</isbn><isbn>9780897913003</isbn><abstract>The CydraTM 5 architecture adds unique support for overlapping successive iterations of a loop to a very long instruction word (VLIW) base. This architecture allows highly parallel loop execution for a much larger class of loops than can be vectorized, without requiring the unrolling of loops usually used by compilers for VLIW machines. This paper discusses the Cydra 5 loop scheduling model, the special architectural features which support it, and the loop compilation techniques used to take full advantage of the architecture.</abstract><cop>New York, NY, USA</cop><pub>ACM</pub><doi>10.1145/70082.68185</doi><tpages>13</tpages></addata></record>
fulltext	fulltext
identifier	ISSN: 0163-5964
ispartof	Computer architecture news, 1989, p.26-38
issn	0163-5964
language	eng
recordid	cdi_proquest_miscellaneous_31693716
source	ACM Digital Library Complete
subjects	Computer systems organization -- Architectures Computer systems organization -- Architectures -- Parallel architectures -- Very long instruction word Computer systems organization -- Architectures -- Serial architectures -- Complex instruction set computing Computer systems organization -- Architectures -- Serial architectures -- Reduced instruction set computing Theory of computation -- Design and analysis of algorithms -- Approximation algorithms analysis -- Scheduling algorithms Theory of computation -- Design and analysis of algorithms -- Online algorithms -- Online learning algorithms -- Scheduling algorithms Theory of computation -- Theory and algorithms for application domains -- Machine learning theory -- Reinforcement learning -- Sequential decision making
title	Overlapped loop support in the Cydra 5
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-18T20%3A05%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_acm_b&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Overlapped%20loop%20support%20in%20the%20Cydra%205&rft.btitle=Computer%20architecture%20news&rft.au=Dehnert,%20James%20C.&rft.date=1989-04-01&rft.spage=26&rft.epage=38&rft.pages=26-38&rft.issn=0163-5964&rft.isbn=0897913000&rft.isbn_list=9780897913003&rft_id=info:doi/10.1145/70082.68185&rft_dat=%3Cproquest_acm_b%3E31693716%3C/proquest_acm_b%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=31693716&rft_id=info:pmid/&rfr_iscdi=true