{"id":"https://openalex.org/W1543710109","doi":null,"title":"Data Parallel Code Generation for Arbitrarily Tiled Loop Nests","display_name":"Data Parallel Code Generation for Arbitrarily Tiled Loop Nests","publication_year":2002,"publication_date":"2002-06-24","ids":{"openalex":"https://openalex.org/W1543710109","mag":"1543710109"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.146.5089","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.146.5089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cslab.ece.ntua.gr/~ndros/publications/pdpta2002.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/123456789/34341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023870696","display_name":"Georgios Goumas","orcid":"https://orcid.org/0000-0001-7811-4831","observed_orcids":["https://orcid.org/0000-0001-7811-4831"]},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Goumas","raw_affiliation_strings":["National Technical University Of Athens"],"raw_orcid":"https://orcid.org/0000-0001-7811-4831","affiliations":[{"raw_affiliation_string":"National Technical University Of Athens","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019410730","display_name":"Nikolaos Drosinos","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolaos Drosinos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061070844","display_name":"Maria Athanasaki","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maria Athanasaki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023526161","display_name":"Nectarios Koziris","orcid":"https://orcid.org/0000-0002-4890-8427","observed_orcids":["https://orcid.org/0000-0002-4890-8427"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nectarios Koziris","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4890-8427","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"610","last_page":"616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/loop-tiling","display_name":"loop tiling","score":0.8820000290870667},{"id":"https://openalex.org/keywords/loop-nests","display_name":"loop nests","score":0.8220000267028809},{"id":"https://openalex.org/keywords/distributed-memory-systems","display_name":"distributed memory systems","score":0.8650000095367432},{"id":"https://openalex.org/keywords/communication-cost-minimization","display_name":"communication cost minimization","score":0.6690000295639038},{"id":"https://openalex.org/keywords/loop-scheduling","display_name":"loop scheduling","score":0.765999972820282},{"id":"https://openalex.org/keywords/parallelizing-compilers","display_name":"parallelizing compilers","score":0.453000009059906}],"concepts":[{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.9059618711471558},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8599194288253784},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.8427931666374207},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7453384399414062},{"id":"https://openalex.org/C134718785","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fission","level":3,"score":0.6920346021652222},{"id":"https://openalex.org/C82653869","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fusion","level":3,"score":0.5922357439994812},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5909850597381592},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5868438482284546},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.5806820392608643},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.5254620313644409},{"id":"https://openalex.org/C113391598","wikidata":"https://www.wikidata.org/wiki/Q1681391","display_name":"Polytope model","level":3,"score":0.4999251365661621},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4905650019645691},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44325703382492065},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3406617045402527},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3284474015235901},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17061281204223633},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.105510413646698},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09088939428329468},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0761762261390686},{"id":"https://openalex.org/C145691206","wikidata":"https://www.wikidata.org/wiki/Q747980","display_name":"Polytope","level":2,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.146.5089","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.146.5089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cslab.ece.ntua.gr/~ndros/publications/pdpta2002.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.2.1249","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.2.1249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cslab.ece.ntua.gr/~maria/papers/PDPTA02.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.7.3373","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.7.3373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://matrix.cslab.ece.ntua.gr/publications/pdpta2002.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.79.30","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.79.30","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cslab.ece.ntua.gr/~maria/papers/PDPTA02.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.117","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cslab.ece.ntua.gr/~goumas/Publications/downloads/pdpta2002.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/34341","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/123456789/34341","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Parallel and Distributed Processing Techniques and Applications","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:1543710109","doi":null,"is_oa":false,"landing_page_url":"http://www.cslab.ece.ntua.gr/~maria/papers/PDPTA02.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420677","display_name":"Parallel and Distributed Processing Techniques and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Parallel and Distributed Processing Techniques and Applications","raw_type":null}],"best_oa_location":{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/34341","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/123456789/34341","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Parallel and Distributed Processing Techniques and Applications","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W315496310","https://openalex.org/W1973923211","https://openalex.org/W1983416598","https://openalex.org/W1984784609","https://openalex.org/W1995270665","https://openalex.org/W2053895556","https://openalex.org/W2061360138","https://openalex.org/W2098688018","https://openalex.org/W2107896839","https://openalex.org/W2116896429","https://openalex.org/W2143329533"],"related_works":["https://openalex.org/W2107896839","https://openalex.org/W1503700136","https://openalex.org/W42513275","https://openalex.org/W2120419528","https://openalex.org/W2137152633","https://openalex.org/W2096337350","https://openalex.org/W2172028774","https://openalex.org/W2061360138","https://openalex.org/W7097675257","https://openalex.org/W2159360349"],"abstract_inverted_index":{"Tiling":[0],"or":[1],"supernode":[2],"transformation":[3,10],"is":[4],"extensively":[5],"discussed":[6],"as":[7,69],"a":[8,22,33,36,84],"loop":[9],"to":[11,87,104],"efficiently":[12,88],"execute":[13],"nested":[14],"loops":[15],"onto":[16],"distributed":[17],"memory":[18],"machines.":[19],"In":[20,79],"addition,":[21],"lot":[23],"of":[24,32,49,101],"work":[25],"has":[26,44],"been":[27,45],"done":[28],"concerning":[29],"the":[30,105],"selection":[31],"communication-minimal":[34],"and":[35,72],"scheduling-optimal":[37],"tiling":[38,113],"transformation.":[39],"However,":[40],"no":[41],"complete":[42,85],"approach":[43],"presented":[46],"in":[47,58],"terms":[48],"implementation":[50],"for":[51,93],"non-rectangularly":[52],"tiled":[53,95],"iteration":[54,96],"spaces.":[55,97],"Code":[56],"generation":[57],"this":[59,80],"case":[60],"can":[61],"be":[62],"extremely":[63],"complex,":[64],"while":[65],"parallelization":[66],"issues":[67],"such":[68],"data":[70,90],"distribution":[71],"communication":[73],"are":[74],"far":[75],"from":[76],"being":[77],"straightforward.":[78],"paper,":[81],"we":[82],"propose":[83],"method":[86],"generate":[89],"parallel":[91],"code":[92],"arbitrarily":[94],"We":[98],"assign":[99],"chains":[100],"neighboring":[102],"tiles":[103],"same":[106],"processor.":[107],"Experimental":[108],"results":[109],"show":[110],"that":[111],"nonrectangular":[112],"allows":[114],"better":[115],"scheduling":[116],"schemes,":[117],"thus":[118],"achieving":[119],"less":[120],"overall":[121],"execution":[122],"time.":[123]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}
