{"id":"https://openalex.org/W2323693848","doi":"https://doi.org/10.1109/hpca.2016.7446078","title":"Simultaneous Multikernel GPU: Multi-tasking throughput processors via fine-grained sharing","display_name":"Simultaneous Multikernel GPU: Multi-tasking throughput processors via fine-grained sharing","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2323693848","doi":"https://doi.org/10.1109/hpca.2016.7446078","mag":"2323693848"},"language":"en","primary_location":{"id":"doi:10.1109/hpca.2016.7446078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2016.7446078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on High Performance Computer Architecture (HPCA)","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/A5101634974","display_name":"Zhenning Wang","orcid":"https://orcid.org/0000-0003-3831-987X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenning Wang","raw_affiliation_strings":["Department of Coumuter Science, Shanghai Jiao Tong University, P.R. China","Department of Coumuter Science, University of Pittsburgh, U.S.A"],"affiliations":[{"raw_affiliation_string":"Department of Coumuter Science, Shanghai Jiao Tong University, P.R. China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Coumuter Science, University of Pittsburgh, U.S.A","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101605460","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0001-8372-6541"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["Electrical and Computer Engineering Department, Department of Coumuter Science"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Department of Coumuter Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038997010","display_name":"Rami Melhem","orcid":"https://orcid.org/0000-0001-6403-5446"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rami Melhem","raw_affiliation_strings":["Department of Coumuter Science, Shanghai Jiao Tong University, P.R. China","Department of Coumuter Science, University of Pittsburgh, U.S.A"],"affiliations":[{"raw_affiliation_string":"Department of Coumuter Science, Shanghai Jiao Tong University, P.R. China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Coumuter Science, University of Pittsburgh, U.S.A","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113485085","display_name":"Bruce R. Childers","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bruce Childers","raw_affiliation_strings":["Department of Coumuter Science, Shanghai Jiao Tong University, P.R. China","Department of Coumuter Science, University of Pittsburgh, U.S.A"],"affiliations":[{"raw_affiliation_string":"Department of Coumuter Science, Shanghai Jiao Tong University, P.R. China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Coumuter Science, University of Pittsburgh, U.S.A","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026996875","display_name":"Youtao Zhang","orcid":"https://orcid.org/0000-0001-8425-8743"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youtao Zhang","raw_affiliation_strings":["Department of Coumuter Science, University of Pittsburgh, U.S.A","Department of Computer Science, University of Pittsburgh, U.S.A"],"affiliations":[{"raw_affiliation_string":"Department of Coumuter Science, University of Pittsburgh, U.S.A","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, University of Pittsburgh, U.S.A","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["Electrical and Computer Engineering Department, Department of Coumuter Science"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Department of Coumuter Science","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101634974"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":23.1355,"has_fulltext":false,"cited_by_count":157,"citation_normalized_percentile":{"value":0.99797496,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"358","last_page":"369"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987999796867371,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9983999729156494,"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":0.8733063340187073},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.669349193572998},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.5651044249534607},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.543618381023407},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.520248293876648},{"id":"https://openalex.org/keywords/shared-resource","display_name":"Shared resource","score":0.5102877616882324},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4464089274406433},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.431209921836853},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.4287392497062683},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.42747700214385986},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4228576719760895},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4162253439426422},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4057600498199463},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20596057176589966},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12165522575378418}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8733063340187073},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.669349193572998},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.5651044249534607},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.543618381023407},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.520248293876648},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.5102877616882324},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4464089274406433},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.431209921836853},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.4287392497062683},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.42747700214385986},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4228576719760895},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4162253439426422},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4057600498199463},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20596057176589966},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12165522575378418},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca.2016.7446078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2016.7446078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W115476871","https://openalex.org/W1890643295","https://openalex.org/W1968047430","https://openalex.org/W1968391520","https://openalex.org/W1979527452","https://openalex.org/W2047060659","https://openalex.org/W2079038734","https://openalex.org/W2090584832","https://openalex.org/W2097643185","https://openalex.org/W2098274770","https://openalex.org/W2111678563","https://openalex.org/W2117093250","https://openalex.org/W2125551452","https://openalex.org/W2129381159","https://openalex.org/W2129817042","https://openalex.org/W2141579716","https://openalex.org/W2150851481","https://openalex.org/W2153190325","https://openalex.org/W2153375074","https://openalex.org/W2154118576","https://openalex.org/W2160428323","https://openalex.org/W2166746673","https://openalex.org/W2169880332","https://openalex.org/W2273440736","https://openalex.org/W3112784795","https://openalex.org/W4212782655","https://openalex.org/W4236786453","https://openalex.org/W6639249596","https://openalex.org/W6641984271","https://openalex.org/W6680965528","https://openalex.org/W6684554443","https://openalex.org/W6694513646"],"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":{"Studies":[0],"show":[1],"that":[2,90,120],"non-graphics":[3],"programs":[4,23],"can":[5,24],"be":[6],"less":[7],"optimized":[8],"for":[9,121],"the":[10,19,40],"GPU":[11,20,41,77,130],"hardware,":[12],"leading":[13],"to":[14,32,39,52,110],"significant":[15],"resource":[16,78,107,126],"under-utilization.":[17],"Sharing":[18],"among":[21],"multiple":[22],"effectively":[25,75],"improve":[26,76,111],"utilization,":[27],"which":[28,65],"is":[29],"particularly":[30],"attractive":[31],"systems":[33],"where":[34],"many":[35],"applications":[36],"require":[37],"access":[38],"(e.g.,":[42],"cloud":[43],"computing).":[44],"However,":[45],"current":[46],"GPUs":[47],"lack":[48],"proper":[49],"architecture":[50],"features":[51],"support":[53],"sharing.":[54],"Initial":[55],"attempts":[56],"are":[57],"preliminary:":[58],"They":[59],"either":[60],"provide":[61],"only":[62],"static":[63],"sharing,":[64],"requires":[66],"recompilation":[67],"or":[68,71],"code":[69],"transformation,":[70],"they":[72],"do":[73],"not":[74],"utilization.":[79],"We":[80,104],"propose":[81,105],"Simultaneous":[82],"Multikernel":[83],"(SMK),":[84],"a":[85,95,140],"fine-grain":[86],"dynamic":[87],"sharing":[88],"mechanism,":[89],"fully":[91],"utilizes":[92],"resources":[93],"within":[94],"streaming":[96],"multiprocessor":[97],"by":[98,132],"exploiting":[99],"heterogeneity":[100],"of":[101],"different":[102],"kernels.":[103],"several":[106],"allocation":[108],"strategies":[109],"system":[112],"throughput":[113,131],"while":[114],"maintaining":[115],"fairness.":[116],"Our":[117],"evaluation":[118],"shows":[119],"shared":[122],"workloads":[123],"with":[124],"complementary":[125],"occupancy,":[127],"SMK":[128],"improves":[129],"52%":[133],"over":[134,139],"non-shared":[135],"execution":[136],"and":[137],"17%":[138],"state-of-the-art":[141],"design.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":27},{"year":2016,"cited_by_count":3}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}