{"id":"https://openalex.org/W2178430749","doi":"https://doi.org/10.1145/2381056.2381081","title":"Towards efficient GPU sharing on multicore processors","display_name":"Towards efficient GPU sharing on multicore processors","publication_year":2012,"publication_date":"2012-10-08","ids":{"openalex":"https://openalex.org/W2178430749","doi":"https://doi.org/10.1145/2381056.2381081","mag":"2178430749"},"language":"en","primary_location":{"id":"doi:10.1145/2381056.2381081","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2381056.2381081","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"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 SIGMETRICS Performance Evaluation Review","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/A5061009703","display_name":"Lingyuan Wang","orcid":"https://orcid.org/0009-0006-6481-2464"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingyuan Wang","raw_affiliation_strings":["George Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069173833","display_name":"Miaoqing Huang","orcid":"https://orcid.org/0000-0001-7376-3744"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miaoqing Huang","raw_affiliation_strings":["University of Arkansas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arkansas","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110271535","display_name":"Tarek El\u2010Ghazawi","orcid":null},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tarek El-Ghazawi","raw_affiliation_strings":["George Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4484,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82890719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"40","issue":"2","first_page":"119","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9958000183105469,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9954000115394592,"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":0.9043657779693604},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7482930421829224},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7398396730422974},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.7248603701591492},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6944026350975037},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6427905559539795},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6347803473472595},{"id":"https://openalex.org/keywords/context-switch","display_name":"Context switch","score":0.5710012316703796},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5071432590484619},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4998154640197754},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43970224261283875},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4374810457229614},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41788867115974426},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3467240333557129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9043657779693604},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7482930421829224},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7398396730422974},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.7248603701591492},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6944026350975037},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6427905559539795},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6347803473472595},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.5710012316703796},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5071432590484619},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4998154640197754},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43970224261283875},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4374810457229614},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41788867115974426},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3467240333557129},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2381056.2381081","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2381056.2381081","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"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 SIGMETRICS Performance Evaluation Review","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2060321634","https://openalex.org/W2109217687","https://openalex.org/W2121444153","https://openalex.org/W2126118553","https://openalex.org/W2142421493","https://openalex.org/W2163552442","https://openalex.org/W2170634604"],"related_works":["https://openalex.org/W2056717482","https://openalex.org/W2017587301","https://openalex.org/W2030707850","https://openalex.org/W2170611190","https://openalex.org/W2566934642","https://openalex.org/W2092007952","https://openalex.org/W2548246577","https://openalex.org/W2096672917","https://openalex.org/W3106557793","https://openalex.org/W2019821619"],"abstract_inverted_index":{"Scalable":[0],"systems":[1],"employing":[2],"a":[3,36,53,59,66],"mix":[4],"of":[5,18,39,50,61],"GPUs":[6],"with":[7],"CPUs":[8],"are":[9],"becoming":[10],"increasingly":[11],"prevalent":[12],"in":[13],"high-performance":[14],"computing.":[15],"The":[16],"presence":[17],"such":[19],"accelerators":[20],"introduces":[21],"significant":[22],"challenges":[23],"and":[24,30,63,73,91],"complexities":[25],"to":[26,43,52,113],"both":[27,87],"language":[28],"developers":[29],"end":[31],"users.":[32],"This":[33],"paper":[34],"provides":[35],"close":[37],"study":[38],"efficient":[40],"coordination":[41],"mechanisms":[42],"handle":[44],"parallel":[45],"requests":[46],"from":[47],"multiple":[48],"hosts":[49],"control":[51],"GPU":[54,67],"under":[55],"hybrid":[56],"programming.":[57],"Using":[58],"set":[60],"microbenchmarks":[62],"applications":[64],"on":[65,82,98],"cluster,":[68],"we":[69],"show":[70],"that":[71,86],"thread":[72],"process-based":[74,92],"context":[75,89,93,106],"hosting":[76],"have":[77],"different":[78],"tradeoffs.":[79],"Experimental":[80],"results":[81],"application":[83],"benchmarks":[84],"suggest":[85],"thread-based":[88],"funneling":[90,107],"switching":[94],"natively":[95],"perform":[96],"similarly":[97],"the":[99,110],"latest":[100],"Fermi":[101],"GPUs,":[102],"while":[103],"manually":[104],"guided":[105],"is":[108],"currently":[109],"best":[111],"way":[112],"achieve":[114],"optimal":[115],"performance.":[116]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}