{"id":"https://openalex.org/W4244580719","doi":"https://doi.org/10.1109/cgo.2015.7054196","title":"Locality aware concurrent start for stencil applications","display_name":"Locality aware concurrent start for stencil applications","publication_year":2015,"publication_date":"2015-02-01","ids":{"openalex":"https://openalex.org/W4244580719","doi":"https://doi.org/10.1109/cgo.2015.7054196"},"language":"en","primary_location":{"id":"doi:10.1109/cgo.2015.7054196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2015.7054196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"},"type":"article","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/A5031298418","display_name":"Sunil Shrestha","orcid":"https://orcid.org/0000-0002-9174-7120"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sunil Shrestha","raw_affiliation_strings":["University of Delaware"],"affiliations":[{"raw_affiliation_string":"University of Delaware","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046024163","display_name":"Guang R. Gao","orcid":"https://orcid.org/0000-0002-5265-7528"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guang R. Gao","raw_affiliation_strings":["University of Delaware"],"affiliations":[{"raw_affiliation_string":"University of Delaware","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010169378","display_name":"Joseph Manzano","orcid":"https://orcid.org/0000-0002-6616-0125"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Manzano","raw_affiliation_strings":["Pacific Nothwest National Laboratory"],"affiliations":[{"raw_affiliation_string":"Pacific Nothwest National Laboratory","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102811479","display_name":"Andr\u00e9s M\u00e1rquez","orcid":"https://orcid.org/0000-0002-4313-1882"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andres Marquez","raw_affiliation_strings":["Pacific Nothwest National Laboratory"],"affiliations":[{"raw_affiliation_string":"Pacific Nothwest National Laboratory","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057593011","display_name":"John Feo","orcid":"https://orcid.org/0000-0001-6546-8948"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Feo","raw_affiliation_strings":["Pacific Nothwest National Laboratory"],"affiliations":[{"raw_affiliation_string":"Pacific Nothwest National Laboratory","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5031298418"],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":1.2919,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82121294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"157","last_page":"166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8607658743858337},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.7845443487167358},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7447265386581421},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6707445383071899},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6629810333251953},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5727652311325073},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5195918083190918},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5194517970085144},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.517681360244751},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40171119570732117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8607658743858337},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.7845443487167358},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7447265386581421},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6707445383071899},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6629810333251953},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5727652311325073},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5195918083190918},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5194517970085144},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.517681360244751},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40171119570732117},{"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/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo.2015.7054196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2015.7054196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.6200000047683716}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1529356657","https://openalex.org/W1542156450","https://openalex.org/W1565751843","https://openalex.org/W1970141743","https://openalex.org/W1973122629","https://openalex.org/W1979457157","https://openalex.org/W2003798513","https://openalex.org/W2035701183","https://openalex.org/W2055253125","https://openalex.org/W2063249715","https://openalex.org/W2091074029","https://openalex.org/W2097909406","https://openalex.org/W2108315152","https://openalex.org/W2115140794","https://openalex.org/W2119609467","https://openalex.org/W2124343275","https://openalex.org/W2148038801","https://openalex.org/W2205893513","https://openalex.org/W2296218291","https://openalex.org/W3006533007","https://openalex.org/W4249968602","https://openalex.org/W4255560897","https://openalex.org/W6668295848","https://openalex.org/W6688061036","https://openalex.org/W6989454671"],"related_works":["https://openalex.org/W1555349535","https://openalex.org/W2583128298","https://openalex.org/W2053359564","https://openalex.org/W2161159383","https://openalex.org/W1495260638","https://openalex.org/W1511204342","https://openalex.org/W2369125128","https://openalex.org/W2010557350","https://openalex.org/W4384755779","https://openalex.org/W2078036665"],"abstract_inverted_index":{"Stencil":[0],"computations":[1],"are":[2],"at":[3],"the":[4,56,77,89,153,189,198,206],"heart":[5],"of":[6,19,25,76,98,114,152,156],"many":[7,52],"physical":[8],"simulations":[9],"used":[10],"in":[11,42,159,197],"scientific":[12],"codes.":[13],"Thus,":[14],"there":[15],"exists":[16],"a":[17,95],"plethora":[18],"optimization":[20,59],"efforts":[21],"for":[22,46,176],"this":[23,163],"family":[24],"computations.":[26],"Among":[27],"these":[28,47,58],"techniques,":[29],"tiling":[30,169],"techniques":[31,60],"that":[32,88,140,171],"allow":[33],"concurrent":[34,174],"start":[35,175],"have":[36],"proven":[37],"to":[38,65,149,223],"be":[39,63,92,150],"very":[40],"efficient":[41,168],"providing":[43],"better":[44],"performance":[45],"critical":[48],"kernels.":[49,216],"Nevertheless,":[50],"with":[51,100,211],"core":[53],"designs":[54,110,130],"being":[55],"norm,":[57],"might":[61],"not":[62],"able":[64],"fully":[66],"exploit":[67,188],"locality":[68,195],"(both":[69],"spatial":[70],"and":[71,104,119,138,185,194,213],"temporal)":[72],"on":[73,205],"multiple":[74],"levels":[75],"memory":[78,103,120,177],"hierarchy":[79,178],"without":[80],"compromising":[81],"parallelism.":[82],"It":[83],"is":[84],"no":[85],"longer":[86],"true":[87],"machine":[90],"can":[91],"seen":[93],"as":[94],"homogeneous":[96],"collection":[97],"nodes":[99],"caches,":[101],"main":[102],"an":[105,123,167],"interconnect":[106],"network.":[107],"New":[108],"architectural":[109],"exhibit":[111],"complex":[112],"grouping":[113],"nodes,":[115],"cores,":[116],"threads,":[117,145],"caches":[118],"connected":[121],"by":[122],"ever":[124],"evolving":[125],"network-on-chip":[126],"design.":[127],"These":[128],"new":[129],"may":[131],"benefit":[132],"greatly":[133],"from":[134,221],"carefully":[135],"crafted":[136],"schedules":[137],"groupings":[139],"encourage":[141],"parallel":[142],"actors":[143,158],"(i.e.":[144],"cores":[146],"or":[147],"nodes)":[148],"aware":[151,179],"computational":[154],"history":[155],"other":[157],"close":[160],"proximity.":[161],"In":[162],"paper,":[164],"we":[165],"provide":[166],"technique":[170,204],"allows":[172],"hierarchical":[173],"tile":[180,186],"groups.":[181],"Each":[182],"execution":[183],"schedule":[184],"shape":[187],"available":[190],"parallelism,":[191],"load":[192],"balance":[193],"present":[196],"given":[199],"applications.":[200],"We":[201,217],"demonstrate":[202],"our":[203],"Intel":[207],"Xeon":[208],"Phi":[209],"architecture":[210],"selected":[212],"representative":[214],"stencil":[215],"show":[218],"improvement":[219],"ranging":[220],"5.58%":[222],"31.17%":[224],"over":[225],"existing":[226],"state-of-the-art":[227],"techniques.":[228]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}