{"id":"https://openalex.org/W2160722282","doi":"https://doi.org/10.1145/1086228.1086271","title":"Optimizing inter-processor data locality on embedded chip multiprocessors","display_name":"Optimizing inter-processor data locality on embedded chip multiprocessors","alternate_titles":[],"publication_year":2005,"publication_date":"2005-09-18","ids":{"openalex":"https://openalex.org/W2160722282","doi":"https://doi.org/10.1145/1086228.1086271","mag":"2160722282"},"language":"en","primary_location":{"id":"doi:10.1145/1086228.1086271","doi":"https://doi.org/10.1145/1086228.1086271","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1086228.1086271","pdf_url":null,"source":{"id":"https://openalex.org/S7407088516","display_name":"ACM International Conference on Embedded Software (EMSOFT)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM international conference on Embedded software","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2160722282"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100654877","display_name":"Guangyu Chen","orcid":"https://orcid.org/0000-0001-9573-6579","observed_orcids":["https://orcid.org/0000-0001-9573-6579"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"G. Chen","raw_affiliation_strings":["Pennsylvania State University, University Park, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007116603","display_name":"Mahmut Kandemir","orcid":"https://orcid.org/0000-0002-9940-9951","observed_orcids":["https://orcid.org/0000-0002-9940-9951"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"M. Kandemir","raw_affiliation_strings":["Pennsylvania State University, University Park, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"227","last_page":"236"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0005000000237487257,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-core-processors","display_name":"multi-core processors","score":0.8690000176429749},{"id":"https://openalex.org/keywords/embedded-computing","display_name":"embedded computing","score":0.4339999854564667},{"id":"https://openalex.org/keywords/stencil-computations","display_name":"stencil computations","score":0.847000002861023},{"id":"https://openalex.org/keywords/compiler-optimization","display_name":"compiler optimization","score":0.6819999814033508},{"id":"https://openalex.org/keywords/off-chip-memory-access","display_name":"off-chip memory access","score":0.875},{"id":"https://openalex.org/keywords/on-chip-memory","display_name":"on-chip memory","score":0.8450000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.850212812423706},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6294056177139282},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6106566190719604},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.5803894400596619},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5546016693115234},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.46213001012802124},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.44342461228370667},{"id":"https://openalex.org/C118021083","wikidata":"https://www.wikidata.org/wiki/Q610398","display_name":"System on a chip","level":2,"score":0.42193835973739624},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.4187626242637634},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4138895869255066},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4134473204612732},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3218805491924286},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11874356865882874},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.09523221850395203},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1086228.1086271","doi":"https://doi.org/10.1145/1086228.1086271","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1086228.1086271","pdf_url":null,"source":{"id":"https://openalex.org/S7407088516","display_name":"ACM International Conference on Embedded Software (EMSOFT)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM international conference on Embedded software","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W79098930","https://openalex.org/W114331401","https://openalex.org/W1489943243","https://openalex.org/W1536051636","https://openalex.org/W1595858234","https://openalex.org/W1850405760","https://openalex.org/W1971851724","https://openalex.org/W1987692736","https://openalex.org/W2032951732","https://openalex.org/W2033236937","https://openalex.org/W2064712511","https://openalex.org/W2064916516","https://openalex.org/W2102863623","https://openalex.org/W2119609467","https://openalex.org/W2135736783","https://openalex.org/W2138166974","https://openalex.org/W2152506070","https://openalex.org/W2161767397","https://openalex.org/W4205295188","https://openalex.org/W4233678979","https://openalex.org/W6631783819"],"related_works":["https://openalex.org/W7099064384","https://openalex.org/W85661918","https://openalex.org/W2165570292","https://openalex.org/W2054732504","https://openalex.org/W7098907792","https://openalex.org/W3140431386","https://openalex.org/W2114214456","https://openalex.org/W2118442104","https://openalex.org/W2153544658","https://openalex.org/W2094066970"],"abstract_inverted_index":{"Recent":[0],"research":[1],"in":[2,61,223,258],"embedded":[3,111,274],"computing":[4,275],"indicates":[5],"that":[6,37,56,113,124,144,162,202,217,251,278],"packing":[7],"multiple":[8,30],"processor":[9,54,187,257],"cores":[10,31,55],"on":[11,70,82,289],"the":[12,21,53,71,86,92,110,128,141,151,155,159,166,182,203,207,218,224,229,232,241,273,283],"same":[13,152],"die":[14,35],"is":[15,36,123,199],"an":[16,78,238,248],"effective":[17],"way":[18],"of":[19,24,28,45,94,120,138,185,214,231,240],"utilizing":[20],"ever-increasing":[22],"number":[23,93],"transistors.":[25],"The":[26,136,173,197,260],"advantage":[27],"placing":[29],"into":[32],"a":[33,97,103,211],"single":[34],"it":[38,125,246],"reduces":[39],"on-chip":[40,225],"communication":[41],"costs":[42],"(in":[43],"terms":[44],"both":[46],"execution":[47],"cycles":[48],"and":[49,132,244],"power":[50],"consumption)":[51],"between":[52,127],"are":[57,193],"traditionally":[58],"very":[59],"high":[60],"conventional":[62],"high-performance":[63],"parallel":[64],"architectures":[65],"(such":[66],"as":[67],"SMPs).":[68],"However,":[69],"negative":[72],"side,":[73],"this":[74,107,121],"tighter":[75],"integration":[76],"exerts":[77],"even":[79],"higher":[80],"pressure":[81],"off-chip":[83,95],"accesses":[84,96],"to":[85,106,150,170,200,247,267],"memory":[87,226],"system.":[88],"This":[89,234],"makes":[90],"minimizing":[91],"critical":[98],"optimization":[99,243],"goal.This":[100],"paper":[101,235],"discusses":[102],"compiler-based":[104],"solution":[105,122],"problem":[108],"for":[109,255],"applications":[112],"perform":[114],"stencil":[115],"computations.":[116],"An":[117],"important":[118],"characteristic":[119],"distinguishes":[126],"intra-processor":[129],"data":[130,134,142,160,191,209,219,253],"reuse":[131,143,161,179],"inter-processor":[133,178],"reuse.":[135,233],"first":[137],"these":[139],"captures":[140],"occurs":[145],"across":[146,165,195],"loop":[147,167,183],"iterations":[148,168,184],"assigned":[149,169],"processor,":[153],"whereas":[154],"second":[156],"one":[157],"represents":[158],"takes":[163],"place":[164],"different":[171,204],"processors.":[172,196],"proposed":[174,242],"approach":[175,280],"then":[176],"optimizes":[177,252],"by":[180,263,287],"re-organizing":[181],"each":[186,256],"carefully,":[188],"considering":[189],"how":[190],"elements":[192],"shared":[194,208],"goal":[198],"ensure":[201],"processors":[205],"access":[206],"within":[210],"short":[212],"period":[213],"time,":[215],"so":[216],"can":[220],"be":[221],"captured":[222],"space":[227],"at":[228],"time":[230],"also":[236],"presents":[237],"evaluation":[239],"compares":[245],"alternate":[249,285],"scheme":[250,286],"locality":[254],"isolation.":[259],"results":[261],"obtained":[262],"applying":[264],"our":[265,279],"implementation":[266],"eight":[268],"loop-intensive":[269],"benchmark":[270],"codes":[271],"from":[272],"domain":[276],"show":[277],"improves":[281],"over":[282],"mentioned":[284],"15.6%":[288],"average.":[290]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2160722282","counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2016-06-24T00:00:00"}
