{"id":"https://openalex.org/W2054284140","doi":"https://doi.org/10.1109/padsw.2014.7097863","title":"WorkQ: A many-core producer/consumer execution model applied to PGAS computations","display_name":"WorkQ: A many-core producer/consumer execution model applied to PGAS computations","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2054284140","doi":"https://doi.org/10.1109/padsw.2014.7097863","mag":"2054284140"},"language":"en","primary_location":{"id":"doi:10.1109/padsw.2014.7097863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/padsw.2014.7097863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103263285","display_name":"David Ozog","orcid":"https://orcid.org/0000-0001-6158-145X"},"institutions":[{"id":"https://openalex.org/I181233156","display_name":"University of Oregon","ror":"https://ror.org/0293rh119","country_code":"US","type":"education","lineage":["https://openalex.org/I181233156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Ozog","raw_affiliation_strings":["Dept. of Computer and Information Science, University of Oregon, Eugene, Oregon","Dept. of Computer and Information Science, University of Oregon, Eugene, 97403, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer and Information Science, University of Oregon, Eugene, Oregon","institution_ids":["https://openalex.org/I181233156"]},{"raw_affiliation_string":"Dept. of Computer and Information Science, University of Oregon, Eugene, 97403, USA","institution_ids":["https://openalex.org/I181233156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107829029","display_name":"Allen Malony","orcid":null},"institutions":[{"id":"https://openalex.org/I181233156","display_name":"University of Oregon","ror":"https://ror.org/0293rh119","country_code":"US","type":"education","lineage":["https://openalex.org/I181233156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allen Malony","raw_affiliation_strings":["Dept. of Computer and Information Science, University of Oregon, Eugene, Oregon","Dept. of Computer and Information Science, University of Oregon, Eugene, 97403, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer and Information Science, University of Oregon, Eugene, Oregon","institution_ids":["https://openalex.org/I181233156"]},{"raw_affiliation_string":"Dept. of Computer and Information Science, University of Oregon, Eugene, 97403, USA","institution_ids":["https://openalex.org/I181233156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081388506","display_name":"Jeff R. Hammond","orcid":"https://orcid.org/0000-0003-3181-8190"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff R. Hammond","raw_affiliation_strings":["Parallel Computing Lab, Intel Corporation, Hillsboro, Oregon","Parallel Computing Lab, Intel Corporation, Hillsboro, Oregon 97124, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel Computing Lab, Intel Corporation, Hillsboro, Oregon","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Parallel Computing Lab, Intel Corporation, Hillsboro, Oregon 97124, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050531633","display_name":"Pavan Balaji","orcid":"https://orcid.org/0000-0002-9785-4461"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavan Balaji","raw_affiliation_strings":["Math. and Computer Science Div., Argonne National Laboratory, Lemont, Illinois","Math. and Computer Science Div., Argonne National Laboratory, Lemont, Illinois 60439, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Math. and Computer Science Div., Argonne National Laboratory, Lemont, Illinois","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Math. and Computer Science Div., Argonne National Laboratory, Lemont, Illinois 60439, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.14037861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"632","last_page":"639"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9524000287055969,"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"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9524000287055969,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9483000040054321,"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":0.9442999958992004,"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/computer-science","display_name":"Computer science","score":0.7426866292953491},{"id":"https://openalex.org/keywords/partitioned-global-address-space","display_name":"Partitioned global address space","score":0.684659481048584},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6649373173713684},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.6428768634796143},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6206263303756714},{"id":"https://openalex.org/keywords/many-core","display_name":"Many core","score":0.5218621492385864},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.41587963700294495},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.26152223348617554},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.1515132486820221},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13884365558624268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426866292953491},{"id":"https://openalex.org/C60832428","wikidata":"https://www.wikidata.org/wiki/Q945818","display_name":"Partitioned global address space","level":3,"score":0.684659481048584},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6649373173713684},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.6428768634796143},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6206263303756714},{"id":"https://openalex.org/C3020431745","wikidata":"https://www.wikidata.org/wiki/Q25325220","display_name":"Many core","level":2,"score":0.5218621492385864},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.41587963700294495},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26152223348617554},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.1515132486820221},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13884365558624268}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/padsw.2014.7097863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/padsw.2014.7097863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.723.52","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.723.52","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mcs.anl.gov/%7Ebalaji/pubs/2014/icpads/icpads14.workq.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1551272572","https://openalex.org/W1573434297","https://openalex.org/W1603470798","https://openalex.org/W1861151562","https://openalex.org/W1897240848","https://openalex.org/W1965092590","https://openalex.org/W2034669281","https://openalex.org/W2047547750","https://openalex.org/W2057262256","https://openalex.org/W2061306165","https://openalex.org/W2064332668","https://openalex.org/W2093135480","https://openalex.org/W2103104694","https://openalex.org/W2106546807","https://openalex.org/W2108369438","https://openalex.org/W2109982223","https://openalex.org/W2110256578","https://openalex.org/W2113366658","https://openalex.org/W2136434791","https://openalex.org/W2146381930","https://openalex.org/W2159303840","https://openalex.org/W2166834428","https://openalex.org/W6632937919","https://openalex.org/W6639223761","https://openalex.org/W6666216864"],"related_works":["https://openalex.org/W1993191611","https://openalex.org/W2023938924","https://openalex.org/W2918840249","https://openalex.org/W1991859582","https://openalex.org/W2110053126","https://openalex.org/W2079303253","https://openalex.org/W2104702637","https://openalex.org/W4248099758","https://openalex.org/W2979015021","https://openalex.org/W2108125751"],"abstract_inverted_index":{"Partitioned":[0],"global":[1],"address":[2],"space":[3],"(PGAS)":[4],"applications,":[5],"such":[6],"as":[7],"the":[8,26,48,65,81,151,167,201,208,226,230,239,243,258],"Tensor":[9],"Contraction":[10],"Engine":[11],"(TCE)":[12],"in":[13,20,124,257],"NWChem,":[14],"often":[15],"apply":[16],"a":[17,32,101,111,183,220,248],"one-process-per-core":[18],"mapping":[19],"which":[21],"each":[22],"process":[23],"iterates":[24],"through":[25],"following":[27],"work-processing":[28],"cycle:":[29],"(1)":[30],"determine":[31],"work-item":[33],"dynamically,":[34],"(2)":[35],"get":[36],"data":[37,49,56],"via":[38],"one-sided":[39],"operations":[40],"on":[41,47],"remote":[42,60],"blocks,":[43],"(3)":[44],"perform":[45],"computation":[46,157,179],"locally,":[50],"(4)":[51],"put":[52],"(or":[53],"accumulate)":[54],"resultant":[55],"into":[57],"an":[58,195],"appropriate":[59],"location,":[61],"and":[62,115,148,150,174,178,207,214,235],"(5)":[63],"repeat":[64],"cycle.":[66],"However,":[67],"this":[68],"simple":[69],"flow":[70],"of":[71,104,136,169,176,211,229,250,263],"execution":[72,129],"does":[73],"not":[74,92],"effectively":[75],"hide":[76],"communication":[77,89,106,143,177],"latency":[78],"costs":[79],"despite":[80],"opportunities":[82],"for":[83,119,166],"making":[84],"asynchronous":[85],"progress.":[86],"Utilizing":[87],"nonblocking":[88],"calls":[90],"is":[91,96],"sufficient":[93],"unless":[94],"care":[95],"taken":[97],"to":[98,140,155],"efficiently":[99],"manage":[100],"responsive":[102],"queue":[103,188],"outstanding":[105],"requests.":[107],"This":[108],"paper":[109],"presents":[110],"new":[112],"runtime":[113,128],"model":[114,199,245],"its":[116],"library":[117,192],"implementation":[118,193],"managing":[120],"tunable":[121,184],"\u201cwork":[122],"queues\u201d":[123],"PGAS":[125],"applications.":[126],"Our":[127,190],"model,":[130],"called":[131],"WorkQ,":[132],"assigns":[133],"some":[134],"number":[135],"on-node":[137],"\u201cproducer\u201d":[138],"processes":[139,154,161],"primarily":[141],"do":[142,156],"(steps":[144],"1,":[145],"2,":[146],"4,":[147],"5)":[149],"other":[152],"\u201cconsumer\u201d":[153],"(step":[158],"3);":[159],"but":[160],"can":[162],"switch":[163],"roles":[164],"dynamically":[165],"sake":[168],"performance.":[170],"Load":[171],"balance,":[172],"synchronization,":[173],"overlap":[175],"are":[180],"facilitated":[181],"by":[182,246],"nodewise":[185],"FIFO":[186],"message":[187,205],"protocol.":[189],"WorkQ":[191,240],"enables":[194],"MPI+X":[196],"hybrid":[197],"programming":[198],"where":[200],"X":[202],"comprises":[203],"SysV":[204],"queues":[206],"user's":[209],"choice":[210],"SysV,":[212],"POSIX,":[213],"MPI":[215],"shared":[216],"memory.":[217],"We":[218,252],"develop":[219],"simplified":[221],"software":[222],"mini-application":[223],"that":[224,238],"mimics":[225],"performance":[227,255],"behavior":[228],"TCE":[231,259],"at":[232],"arbitrary":[233],"scale,":[234],"we":[236],"show":[237,254],"engine":[241],"outperforms":[242],"original":[244],"about":[247],"factor":[249],"2.":[251],"also":[253],"improvement":[256],"coupled":[260],"cluster":[261],"module":[262],"NWChem.":[264]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}