{"id":"https://openalex.org/W2103838950","doi":"https://doi.org/10.1109/ipdps.2010.5470413","title":"Dynamic load balancing on single- and multi-GPU systems","display_name":"Dynamic load balancing on single- and multi-GPU systems","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2103838950","doi":"https://doi.org/10.1109/ipdps.2010.5470413","mag":"2103838950"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2010.5470413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","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/A5072305172","display_name":"Long Chen","orcid":"https://orcid.org/0000-0002-5807-7268"},"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":"Long Chen","raw_affiliation_strings":["Department of Electrical & Computer Engineering, University of Delaware, Newark, DE, USA","Department of Electrical and Computer Engineering, University of Delaware, Newark, DE, 19716"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Delaware, Newark, DE, 19716","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111373927","display_name":"Oreste Villa","orcid":null},"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":"Oreste Villa","raw_affiliation_strings":["High Performance Computing, Pacific Northwest National Laboratory, Richland, WA, USA","High Performance Computing, Pacific Northwest National Laboratory, Richland, WA 99352"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"High Performance Computing, Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"High Performance Computing, Pacific Northwest National Laboratory, Richland, WA 99352","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006650430","display_name":"Sriram Krishnamoorthy","orcid":"https://orcid.org/0000-0002-4682-1002"},"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":"Sriram Krishnamoorthy","raw_affiliation_strings":["High Performance Computing, Pacific Northwest National Laboratory, Richland, WA, USA","High Performance Computing, Pacific Northwest National Laboratory, Richland, WA 99352"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"High Performance Computing, Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"High Performance Computing, Pacific Northwest National Laboratory, Richland, WA 99352","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","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":["Department of Electrical & Computer Engineering, University of Delaware, Newark, DE, USA","Department of Electrical and Computer Engineering, University of Delaware, Newark, DE, 19716"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Delaware, Newark, DE, 19716","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":139,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9988999962806702,"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/cuda","display_name":"CUDA","score":0.903127133846283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8696994781494141},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.8041701912879944},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7416014671325684},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6632189750671387},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5900790095329285},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.5743889212608337},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5549376010894775},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4868397116661072},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4793308973312378},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4558486044406891},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10571059584617615}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.903127133846283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8696994781494141},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.8041701912879944},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7416014671325684},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6632189750671387},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5900790095329285},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.5743889212608337},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5549376010894775},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4868397116661072},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4793308973312378},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4558486044406891},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10571059584617615},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ipdps.2010.5470413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.470.7210","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.470.7210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cacs.usc.edu/education/cs653/Chen-LoadBalanceGPU-IPDPS10.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.653.2968","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.653.2968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.capsl.udel.edu/pub/doc/papers/LongChen-IPDPS2010.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1504291959","https://openalex.org/W1929766428","https://openalex.org/W1972090741","https://openalex.org/W1975353473","https://openalex.org/W1992851788","https://openalex.org/W2003488560","https://openalex.org/W2013979082","https://openalex.org/W2028499920","https://openalex.org/W2029953934","https://openalex.org/W2034441788","https://openalex.org/W2058730918","https://openalex.org/W2063186542","https://openalex.org/W2085407655","https://openalex.org/W2093481053","https://openalex.org/W2103185791","https://openalex.org/W2109426995","https://openalex.org/W2113079303","https://openalex.org/W2121893797","https://openalex.org/W2128022558","https://openalex.org/W2132600716","https://openalex.org/W3138798301","https://openalex.org/W3141650078","https://openalex.org/W3145128584","https://openalex.org/W3187688612","https://openalex.org/W3208444120","https://openalex.org/W4246219036","https://openalex.org/W4256084543","https://openalex.org/W6630135218","https://openalex.org/W6640339985","https://openalex.org/W6643353845","https://openalex.org/W6648639734","https://openalex.org/W6678379141"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"The":[0,16,35,69],"computational":[1],"power":[2],"provided":[3],"by":[4],"many-core":[5],"graphics":[6],"processing":[7],"units":[8],"(GPUs)":[9],"has":[10],"been":[11],"exploited":[12],"in":[13,51,82],"many":[14,52],"applications.":[15],"programming":[17,85],"techniques":[18,148],"currently":[19],"employed":[20],"on":[21,150],"these":[22],"GPUs":[23,45],"are":[24,48],"not":[25],"sufficient":[26],"to":[27,41],"address":[28],"problems":[29],"exhibiting":[30],"irregular,":[31],"and":[32,98,143],"unbalanced":[33,131],"workload.":[34,132],"problem":[36],"is":[37,80],"exacerbated":[38],"when":[39],"trying":[40],"effectively":[42],"exploit":[43],"multiple":[44],"concurrently,":[46],"which":[47],"commonly":[49],"available":[50],"modern":[53],"systems.":[54,68],"In":[55],"this":[56],"paper,":[57],"we":[58],"propose":[59],"a":[60,75,99,111],"task-based":[61],"dynamic":[62],"load-balancing":[63],"solution":[64,70,119,137],"for":[65,130],"single-and":[66],"multi-GPU":[67,134],"allows":[71],"load":[72,106,141],"balancing":[73],"at":[74],"finer":[76],"granularity":[77],"than":[78,126],"what":[79],"supported":[81],"current":[83],"GPU":[84],"APIs,":[86],"such":[87],"as":[88],"NVIDIA's":[89],"CUDA.":[90],"We":[91],"evaluate":[92],"our":[93,116,136],"approach":[94],"using":[95],"both":[96],"micro-benchmarks":[97],"molecular":[100],"dynamics":[101],"application":[102],"that":[103,115],"exhibits":[104],"significant":[105,144],"imbalance.":[107],"Experimental":[108],"results":[109],"with":[110],"single-GPU":[112],"configuration":[113],"show":[114],"fine-grained":[117],"task":[118],"can":[120],"utilize":[121],"the":[122,127],"hardware":[123],"more":[124],"efficiently":[125],"CUDA":[128,152],"scheduler":[129],"On":[133],"systems,":[135],"achieves":[138],"near-linear":[139],"speedup,":[140],"balance,":[142],"performance":[145],"improvement":[146],"over":[147],"based":[149],"standard":[151],"APIs.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":18},{"year":2012,"cited_by_count":16}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}