{"id":"https://openalex.org/W3017087102","doi":"https://doi.org/10.1145/3377138","title":"A Model-Based Software Solution for Simultaneous Multiple Kernels on GPUs","display_name":"A Model-Based Software Solution for Simultaneous Multiple Kernels on GPUs","publication_year":2020,"publication_date":"2020-03-04","ids":{"openalex":"https://openalex.org/W3017087102","doi":"https://doi.org/10.1145/3377138","mag":"3017087102"},"language":"en","primary_location":{"id":"doi:10.1145/3377138","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3377138","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3377138","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3377138","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101874776","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0002-0372-5504"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Hao Wu","raw_affiliation_strings":["The University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-0372-5504","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101697632","display_name":"Weizhi Liu","orcid":"https://orcid.org/0000-0002-0566-1604"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Weizhi Liu","raw_affiliation_strings":["The University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066328999","display_name":"Huanxin Lin","orcid":"https://orcid.org/0000-0003-1795-9309"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Huanxin Lin","raw_affiliation_strings":["The University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113952625","display_name":"Cho\u2010Li Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Cho-Li Wang","raw_affiliation_strings":["The University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101874776"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.7072,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66488087,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"17","issue":"1","first_page":"1","last_page":"26"},"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":0.9998000264167786,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8652676343917847},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7255810499191284},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6338173747062683},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6196749210357666},{"id":"https://openalex.org/keywords/human-multitasking","display_name":"Human multitasking","score":0.6119663715362549},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5794578194618225},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5589040517807007},{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.5091487765312195},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4922155439853668},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.45422011613845825},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3627502918243408},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.26624757051467896},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2315160036087036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8652676343917847},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7255810499191284},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6338173747062683},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6196749210357666},{"id":"https://openalex.org/C107418235","wikidata":"https://www.wikidata.org/wiki/Q1520565","display_name":"Human multitasking","level":2,"score":0.6119663715362549},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5794578194618225},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5589040517807007},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.5091487765312195},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4922155439853668},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.45422011613845825},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3627502918243408},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.26624757051467896},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2315160036087036},{"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3377138","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3377138","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3377138","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3377138","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3377138","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3377138","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.4300000071525574,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3017087102.pdf","grobid_xml":"https://content.openalex.org/works/W3017087102.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1985747326","https://openalex.org/W2020145470","https://openalex.org/W2053744175","https://openalex.org/W2078391824","https://openalex.org/W2080592089","https://openalex.org/W2099891946","https://openalex.org/W2106329447","https://openalex.org/W2128120785","https://openalex.org/W2140348470","https://openalex.org/W2142769604","https://openalex.org/W2146207215","https://openalex.org/W2152517358","https://openalex.org/W2163687928","https://openalex.org/W2323693848","https://openalex.org/W2470243357","https://openalex.org/W2522707445","https://openalex.org/W2605178034","https://openalex.org/W2791833900","https://openalex.org/W2794729807","https://openalex.org/W2795326697","https://openalex.org/W2952562588","https://openalex.org/W2997701623","https://openalex.org/W4243035950","https://openalex.org/W7047442821"],"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/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"As":[0],"a":[1,16,73,147,173,184,205],"critical":[2],"computing":[3],"resource":[4,81,96,200],"in":[5,31],"multiuser":[6],"systems":[7],"such":[8],"as":[9],"supercomputers,":[10],"data":[11],"centers,":[12],"and":[13,62,124,149,177,212,217,221,264,273,288,297],"cloud":[14],"services,":[15],"GPU":[17,23,107,118],"contains":[18,178],"multiple":[19,69],"compute":[20,59],"units":[21,60],"(CUs).":[22],"Multitasking":[24],"is":[25,100,131,170],"an":[26,127,192],"intuitive":[27],"solution":[28],"to":[29,76,86,102,134,153,224,240,280],"underutilization":[30],"GPGPU":[32],"computing.":[33],"Recently":[34],"proposed":[35],"solutions":[36],"of":[37,58,89,117,138,158,164,214,230,257],"multitasking":[38],"GPUs":[39,228],"can":[40,79,190,202],"be":[41],"classified":[42],"into":[43],"two":[44],"categories:":[45],"(1)":[46,110],"spatially":[47],"partitioned":[48],"sharing":[49],"(SPS),":[50],"which":[51,67,189],"coexecutes":[52],"different":[53],"kernels":[54,70,92,197],"on":[55,105,115,161,227,236,267,277,291,301],"disjointed":[56],"sets":[57],"(CU),":[61],"(2)":[63,125],"simultaneous":[64],"multikernel":[65],"(SMK),":[66],"runs":[68],"simultaneously":[71],"within":[72,204],"CU.":[74,206],"Compared":[75,239,279],"SPS,":[77],"SMK":[78,104,114,129,193,226],"improve":[80],"utilization":[82,201],"even":[83],"further":[84],"due":[85,133],"the":[87,135,155,162,210,241,255,281,283],"interleaving":[88],"instructions":[90],"from":[91,172],"with":[93,198],"low":[94],"dynamic":[95],"contentions.":[97],"However,":[98],"it":[99],"hard":[101],"implement":[103],"current":[106],"architecture,":[108],"because":[109],"techniques":[111,220],"for":[112],"applying":[113],"top":[116],"hardware":[119],"scheduling":[120],"policy":[121],"are":[122],"scarce":[123],"finding":[126],"efficient":[128],"scheme":[130,194],"difficult":[132],"complex":[136,156],"interferences":[137,157],"concurrently":[139],"executed":[140],"kernels.":[141],"In":[142],"this":[143],"article,":[144],"we":[145,182,208],"propose":[146,183],"lightweight":[148],"effective":[150],"performance":[151,168],"model":[152,169,235],"evaluate":[154,191],"SMK.":[159],"Based":[160],"probability":[163],"independent":[165],"events,":[166],"our":[167,234],"built":[171],"totally":[174],"new":[175],"angle":[176],"limited":[179],"parameters.":[180],"Then,":[181],"metric,":[185],"symbiotic":[186],"factor":[187],",":[188],"so":[195],"that":[196],"complementary":[199],"corun":[203],"Also,":[207],"analyze":[209],"advantages":[211],"disadvantages":[213],"kernel":[215,218,245,248,259],"slicing":[216],"stretching":[219],"integrate":[222],"them":[223],"apply":[225],"instead":[229],"simulators.":[231],"We":[232],"validate":[233],"18":[237],"benchmarks.":[238],"optimized":[242],"hardware-based":[243],"concurrent":[244],"execution":[246,253],"whose":[247],"launching":[249],"order":[250],"brings":[251],"fast":[252],"time,":[254],"results":[256,284],"corunning":[258],"pairs":[260],"show":[261,285],"11%,":[262],"18%,":[263,287],"12%":[265],"speedup":[266,290],"AMD":[268,292],"R9":[269,293],"290X,":[270,294],"RX":[271,295],"480,":[272,296],"Vega":[274,298],"64,":[275,299],"respectively,":[276,300],"average.":[278,302],"Warped-Slicer,":[282],"29%,":[286],"51%":[289]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}