{"id":"https://openalex.org/W2461316586","doi":"https://doi.org/10.1109/tpds.2016.2586074","title":"Understanding Co-Running Behaviors on Integrated CPU/GPU Architectures","display_name":"Understanding Co-Running Behaviors on Integrated CPU/GPU Architectures","publication_year":2016,"publication_date":"2016-06-29","ids":{"openalex":"https://openalex.org/W2461316586","doi":"https://doi.org/10.1109/tpds.2016.2586074","mag":"2461316586"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2016.2586074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2586074","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/A5091139467","display_name":"Feng Zhang","orcid":"https://orcid.org/0000-0003-1983-7321"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071200777","display_name":"Jidong Zhai","orcid":"https://orcid.org/0000-0002-7656-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jidong Zhai","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039946576","display_name":"Bingsheng He","orcid":"https://orcid.org/0000-0001-8618-4581"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bingsheng He","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696504","display_name":"Shuhao Zhang","orcid":"https://orcid.org/0000-0002-9927-6925"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shuhao Zhang","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103141832","display_name":"Wenguang Chen","orcid":"https://orcid.org/0000-0002-4281-1018"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenguang Chen","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.4347,"has_fulltext":false,"cited_by_count":87,"citation_normalized_percentile":{"value":0.98272625,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"28","issue":"3","first_page":"905","last_page":"918"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9977999925613403,"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":0.8598991632461548},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5869125127792358},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5661098957061768},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5592688918113708},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5038334727287292},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.47958555817604065},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.46561765670776367},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.45236510038375854},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3662089407444},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31721121072769165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8598991632461548},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5869125127792358},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5661098957061768},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5592688918113708},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5038334727287292},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.47958555817604065},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.46561765670776367},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.45236510038375854},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3662089407444},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31721121072769165},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2016.2586074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2586074","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":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8799999952316284}],"awards":[{"id":"https://openalex.org/G3680111643","display_name":null,"funder_award_id":"MOE2012-T2-2-067","funder_id":"https://openalex.org/F4320320390","funder_display_name":"Australian Cancer Research Foundation"},{"id":"https://openalex.org/G5782689143","display_name":"\u9762\u5411\u9ad8\u6027\u80fd\u4e91\u5e73\u53f0\u7684\u5e76\u884c\u7a0b\u5e8f\u4f18\u5316\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61472201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320390","display_name":"Australian Cancer Research Foundation","ror":"https://ror.org/0459phn12"},{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W780656674","https://openalex.org/W782017735","https://openalex.org/W813884746","https://openalex.org/W1504694836","https://openalex.org/W1512360629","https://openalex.org/W1805440014","https://openalex.org/W1963958818","https://openalex.org/W1964836692","https://openalex.org/W1976534780","https://openalex.org/W1982020565","https://openalex.org/W1984222112","https://openalex.org/W1991126176","https://openalex.org/W1994999558","https://openalex.org/W2002555321","https://openalex.org/W2012591111","https://openalex.org/W2036850008","https://openalex.org/W2039467384","https://openalex.org/W2059226577","https://openalex.org/W2066860750","https://openalex.org/W2080592089","https://openalex.org/W2091589449","https://openalex.org/W2125055259","https://openalex.org/W2128120785","https://openalex.org/W2137269004","https://openalex.org/W2155203732","https://openalex.org/W2165039583","https://openalex.org/W2167826244","https://openalex.org/W2169049902","https://openalex.org/W2273440736","https://openalex.org/W2276395270","https://openalex.org/W2289989444","https://openalex.org/W2464859674","https://openalex.org/W2468944713","https://openalex.org/W2622515782","https://openalex.org/W4231380462","https://openalex.org/W4248767818","https://openalex.org/W6622620325","https://openalex.org/W6638126107","https://openalex.org/W6684724821","https://openalex.org/W6694513646","https://openalex.org/W6719401372","https://openalex.org/W6739045456"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W4245975140","https://openalex.org/W1977763331","https://openalex.org/W2062253548","https://openalex.org/W4225414539","https://openalex.org/W4289522463","https://openalex.org/W4318483369","https://openalex.org/W2002560966"],"abstract_inverted_index":{"Architecture":[0],"designers":[1],"tend":[2],"to":[3,13,23,164,205,230],"integrate":[4],"both":[5,29,59],"CPUs":[6,30,80,105,132,213],"and":[7,31,46,50,61,100,133,135,214,245,250],"GPUs":[8,32,99,134],"on":[9,33,58],"the":[10,26,52,76,92,107,151,169,207,226,231,242],"same":[11],"chip":[12],"deliver":[14],"energy-efficient":[15],"designs.":[16],"It":[17],"is":[18,70],"still":[19],"an":[20,160],"open":[21],"problem":[22],"effectively":[24],"leverage":[25],"advantages":[27],"of":[28,55,189,225],"integrated":[34,63,156],"architectures.":[35,64],"In":[36],"this":[37],"work,":[38],"we":[39,126,158,199],"port":[40],"42":[41],"programs":[42,57,88,96,102,113,152,187,236,247],"in":[43],"Rodinia,":[44],"Parboil,":[45],"Polybench":[47],"benchmark":[48],"suites":[49],"analyze":[51],"co-running":[53,68,146,170,235],"behaviors":[54],"these":[56,84],"AMD":[60],"Intel":[62],"We":[65],"find":[66,127],"that":[67,128,181,218],"performance":[69,116,171,228],"not":[71,149],"always":[72],"better":[73],"than":[74],"running":[75],"program":[77],"only":[78,86,97,103],"with":[79,238],"or":[81,176],"GPUs.":[82,215],"Among":[83],"programs,":[85],"eight":[87],"can":[89,153,221],"benefit":[90,154],"from":[91,155],"co-running,":[93],"while":[94],"24":[95],"using":[98,104],"seven":[101],"achieve":[106,222],"best":[108,232],"performance.":[109,147],"The":[110,234],"remaining":[111],"three":[112],"show":[114,180,217],"little":[115],"preference":[117],"for":[118,172,191],"different":[119],"devices.":[120],"Through":[121],"extensive":[122],"workload":[123,209],"characterization":[124],"analysis,":[125],"architecture":[129],"differences":[130],"between":[131,212],"limited":[136],"shared":[137],"memory":[138],"bandwidth":[139],"are":[140],"two":[141],"main":[142],"factors":[143],"affecting":[144],"current":[145],"Since":[148],"all":[150],"architectures,":[157],"build":[159],"automatic":[161],"decision-tree-based":[162],"model":[163,183,220],"help":[165],"application":[166],"developers":[167],"predict":[168,206],"a":[173,195,202],"given":[174],"CPU-only":[175,244],"GPU-only":[177,246],"program.":[178],"Results":[179,216],"our":[182,219,239],"correctly":[184],"predicts":[185],"14":[186],"out":[188],"15":[190],"evaluated":[192],"programs.":[193],"For":[194],"co-run":[196],"friendly":[197],"program,":[198],"further":[200],"propose":[201],"profiling-based":[203],"method":[204,240],"optimal":[208,227],"partition":[210],"ratio":[211],"87.7":[223],"percent":[224,252],"relative":[229],"partition.":[233],"acquired":[237],"outperform":[241],"original":[243],"by":[248],"34.5":[249],"20.9":[251],"respectively.":[253]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}