{"id":"https://openalex.org/W2126118553","doi":"https://doi.org/10.1109/hpcsim.2011.5999803","title":"Exploiting concurrent kernel execution on graphic processing units","display_name":"Exploiting concurrent kernel execution on graphic processing units","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W2126118553","doi":"https://doi.org/10.1109/hpcsim.2011.5999803","mag":"2126118553"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2011.5999803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2011.5999803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Conference on High Performance Computing & Simulation","raw_type":"proceedings-article"},"type":"conference-paper","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, USA","the George Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"the 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, USA","University Of Arkansas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]},{"raw_affiliation_string":"University Of Arkansas","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001914825","display_name":"Tarek El\u2010Ghazawi","orcid":"https://orcid.org/0000-0001-9687-7939"},"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, USA","the George Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"the 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":null,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.995199978351593,"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":0.8906385898590088},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.7382633090019226},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7036564350128174},{"id":"https://openalex.org/keywords/context-switch","display_name":"Context switch","score":0.6892613172531128},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6475139856338501},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.644127368927002},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5649169683456421},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5522980093955994},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5328555107116699},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4888896048069},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4585575461387634},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.45838895440101624},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4442596137523651},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.428870290517807},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4209457039833069},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3726142346858978},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34492337703704834}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8906385898590088},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.7382633090019226},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7036564350128174},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.6892613172531128},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6475139856338501},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.644127368927002},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5649169683456421},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5522980093955994},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5328555107116699},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4888896048069},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4585575461387634},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.45838895440101624},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4442596137523651},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.428870290517807},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4209457039833069},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3726142346858978},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34492337703704834},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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":2,"locations":[{"id":"doi:10.1109/hpcsim.2011.5999803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2011.5999803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Conference on High Performance Computing & Simulation","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.715.444","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.715.444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csce.uark.edu/%7Emqhuang/papers/2011_ConcurrentKernel_HPCS.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2016706026","https://openalex.org/W2050612421","https://openalex.org/W2060321634","https://openalex.org/W2121893797","https://openalex.org/W2147353629","https://openalex.org/W2159481344"],"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/W2370314112"],"abstract_inverted_index":{"Graphics":[0],"processing":[1],"units":[2],"(CPUs)":[3],"have":[4],"been":[5],"accepted":[6],"as":[7],"a":[8,27,30,38,79,83,95,184],"powerful":[9],"and":[10,162],"viable":[11],"coprocessor":[12],"solution":[13],"in":[14,37,69,82],"high-performance":[15],"computing":[16,44],"domain.":[17],"In":[18,71],"order":[19,72],"to":[20,41,73,92],"maximize":[21],"the":[22,53,63,75,90,112,134,146,154,159,178],"benefit":[23,135],"of":[24,55,62,78,132,136,180],"CPUs":[25],"for":[26,34,46],"multicore":[28],"platform,":[29],"mechanism":[31,157],"is":[32],"needed":[33],"CPU":[35],"threads":[36],"parallel":[39],"application":[40,85,107,148,186],"share":[42,94],"this":[43,87],"resource":[45],"efficient":[47],"execution.":[48],"NVIDIA's":[49],"Fermi":[50],"architecture":[51],"pioneers":[52],"feature":[54],"concurrent":[56,137],"kernel":[57,138],"execution;":[58],"however,":[59],"only":[60],"kernels":[61],"same":[64],"thread":[65],"context":[66,98,142],"can":[67],"execute":[68],"parallel.":[70],"get":[74],"best":[76],"use":[77],"GPU":[80,113],"device":[81],"multi-threaded":[84],"environment,":[86],"paper":[88],"explores":[89],"techniques":[91,182],"effectively":[93],"context,":[96],"i.e.,":[97],"funneling,":[99],"which":[100],"could":[101],"be":[102],"done":[103],"either":[104],"manually":[105],"at":[106,111],"level,":[108],"or":[109],"automatically":[110],"runtime":[114],"starting":[115],"from":[116],"CUDA":[117,167],"v4.0.":[118],"For":[119],"synthetic":[120],"microbenchmark":[121],"tests,":[122],"we":[123,176],"find":[124,152],"that":[125,153],"both":[126],"funneling":[127,156],"mechanisms":[128],"are":[129],"more":[130,163],"capable":[131],"exploring":[133],"execution":[139],"than":[140],"traditional":[141],"switching,":[143],"therefore":[144],"improving":[145],"overall":[147],"performance.":[149,174],"We":[150],"also":[151],"manual":[155],"provides":[158,169],"highest":[160],"performance":[161],"explicit":[164],"control,":[165],"while":[166],"v4.0":[168],"better":[170],"productivity":[171],"with":[172],"good":[173],"Finally,":[175],"assess":[177],"impact":[179],"such":[181],"on":[183],"compact":[185],"benchmark,":[187],"SSCA#3":[188],"-":[189],"SAR":[190],"sensor":[191],"processing.":[192]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}