{"id":"https://openalex.org/W2152517358","doi":"https://doi.org/10.1109/tpds.2014.2313342","title":"Efficient GPU Spatial-Temporal Multitasking","display_name":"Efficient GPU Spatial-Temporal Multitasking","publication_year":2014,"publication_date":"2014-03-25","ids":{"openalex":"https://openalex.org/W2152517358","doi":"https://doi.org/10.1109/tpds.2014.2313342","mag":"2152517358"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2014.2313342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2313342","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yun Liang","raw_affiliation_strings":["Center for Energy-Efficient Computing and Applications, Peking University, Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"Center for Energy-Efficient Computing and Applications, Peking University, Beijing, P.R. China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077959628","display_name":"Huynh Phung Huynh","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huynh Phung Huynh","raw_affiliation_strings":["Computing Science Department, A*STAR Institute of High Performance Computing, Singapore"],"affiliations":[{"raw_affiliation_string":"Computing Science Department, A*STAR Institute of High Performance Computing, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090843153","display_name":"Kyle Rupnow","orcid":"https://orcid.org/0000-0003-2908-2225"},"institutions":[{"id":"https://openalex.org/I4210108443","display_name":"Advanced Digital Sciences Center","ror":"https://ror.org/01xaqx887","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4210108443"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kyle Rupnow","raw_affiliation_strings":["Advanced Digital Science Center, Singapore"],"affiliations":[{"raw_affiliation_string":"Advanced Digital Science Center, Singapore","institution_ids":["https://openalex.org/I4210108443"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001599295","display_name":"Rick Siow Mong Goh","orcid":"https://orcid.org/0000-0001-9116-1595"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rick Siow Mong Goh","raw_affiliation_strings":["Computing Science Department, A*STAR Institute of High Performance Computing, Singapore"],"affiliations":[{"raw_affiliation_string":"Computing Science Department, A*STAR Institute of High Performance Computing, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056321228","display_name":"Deming Chen","orcid":"https://orcid.org/0000-0002-3016-0270"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deming Chen","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100604860"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":11.6308,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.98824231,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"26","issue":"3","first_page":"748","last_page":"760"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9988999962806702,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9984999895095825,"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":0.8789743185043335},{"id":"https://openalex.org/keywords/human-multitasking","display_name":"Human multitasking","score":0.8661649227142334},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5943158268928528},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5940451622009277},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4956713914871216},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4520331919193268},{"id":"https://openalex.org/keywords/emulation","display_name":"Emulation","score":0.44428667426109314},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.42536816000938416},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.4131876230239868},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.24916577339172363},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18774652481079102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8789743185043335},{"id":"https://openalex.org/C107418235","wikidata":"https://www.wikidata.org/wiki/Q1520565","display_name":"Human multitasking","level":2,"score":0.8661649227142334},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5943158268928528},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5940451622009277},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4956713914871216},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4520331919193268},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.44428667426109314},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.42536816000938416},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.4131876230239868},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.24916577339172363},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18774652481079102},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2014.2313342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2313342","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309434","display_name":"University of Wisconsin-Madison","ror":"https://ror.org/01y2jtd41"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1969617278","https://openalex.org/W1972090741","https://openalex.org/W1992851788","https://openalex.org/W2012110315","https://openalex.org/W2013247896","https://openalex.org/W2026782279","https://openalex.org/W2084309410","https://openalex.org/W2106018915","https://openalex.org/W2113282196","https://openalex.org/W2129232868","https://openalex.org/W2150851481","https://openalex.org/W2160428323","https://openalex.org/W2165707017","https://openalex.org/W2167266655","https://openalex.org/W2167334577","https://openalex.org/W2169880332","https://openalex.org/W2231791608","https://openalex.org/W2242479605","https://openalex.org/W2295862081","https://openalex.org/W4237024478","https://openalex.org/W4250981202","https://openalex.org/W4251590233","https://openalex.org/W6643353845"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W3145240193","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2147073383","https://openalex.org/W2129306603"],"abstract_inverted_index":{"Heterogeneous":[0],"computing":[1,15,23],"nodes":[2],"are":[3,51],"now":[4],"pervasive":[5],"throughout":[6],"computing,":[7],"and":[8,28,58,138,198],"GPUs":[9,20,32],"have":[10,21],"emerged":[11],"as":[12,81],"a":[13,131,139],"leading":[14],"device":[16],"for":[17,25,53,101,134,144],"application":[18],"acceleration.":[19],"tremendous":[22],"potential":[24],"data-parallel":[26],"applications,":[27],"the":[29,62,92,124,208],"emergence":[30],"of":[31,37,61,72,91],"has":[33,42],"led":[34,44],"to":[35,45,55,67,116,160,189,219],"proliferation":[36,41],"GPU-accelerated":[38],"applications.":[39],"This":[40],"also":[43],"systems":[46],"in":[47,104,152],"which":[48],"many":[49],"applications":[50],"competing":[52],"access":[54],"GPU":[56,63,79,86,93,170,195],"resources,":[57],"efficient":[59,135,150],"utilization":[60],"resources":[64,80],"is":[65],"critical":[66],"system":[68],"performance.":[69],"Prior":[70],"techniques":[71,167],"temporal":[73],"multitasking":[74,103,137],"can":[75,112,120],"be":[76,113],"employed":[77],"with":[78,154,207],"well,":[82],"but":[83],"not":[84],"all":[85],"kernels":[87],"make":[88],"full":[89],"use":[90,123],"resources.":[94,125],"There":[95],"is,":[96],"therefore,":[97],"an":[98,149],"unmet":[99],"need":[100],"spatial":[102],"GPUs.":[105],"Resources":[106],"used":[107],"inefficiently":[108],"by":[109,187],"one":[110],"kernel":[111,118],"instead":[114],"assigned":[115],"another":[117],"that":[119],"more":[121],"effectively":[122],"In":[126],"this":[127],"paper":[128],"we":[129],"propose":[130],"software-hardware":[132],"solution":[133],"spatial-temporal":[136,162],"software":[140,153],"based":[141,157],"emulation":[142],"framework":[143],"our":[145,166,215],"system.":[146],"We":[147,164],"pair":[148],"heuristic":[151],"hardware":[155],"leaky-bucket":[156],"thread-block":[158],"interleaving":[159],"implement":[161],"multitasking.":[163,205,228],"demonstrate":[165,184],"on":[168,181],"various":[169],"architecture":[171],"using":[172,212],"nine":[173],"representative":[174],"benchmarks":[175],"from":[176],"CUDA":[177],"SDK.":[178],"Our":[179],"experiments":[180],"Fermi":[182],"GTX480":[183],"performance":[185,223],"improvement":[186,224],"up":[188,218],"46%":[190],"(average":[191,200,221],"26%)":[192],"over":[193,202,225],"sequential":[194],"task":[196],"execution":[197],"37%":[199],"18%)":[201],"default":[203,226],"concurrent":[204,227],"Compared":[206],"state-of-the-art":[209],"Kepler":[210],"K20":[211],"Hyper-Q":[213],"technology,":[214],"technique":[216],"achieves":[217],"40%":[220],"17%)":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}