{"id":"https://openalex.org/W1968391520","doi":"https://doi.org/10.1145/2751205.2751213","title":"Enabling and Exploiting Flexible Task Assignment on GPU through SM-Centric Program Transformations","display_name":"Enabling and Exploiting Flexible Task Assignment on GPU through SM-Centric Program Transformations","publication_year":2015,"publication_date":"2015-06-02","ids":{"openalex":"https://openalex.org/W1968391520","doi":"https://doi.org/10.1145/2751205.2751213","mag":"1968391520"},"language":"en","primary_location":{"id":"doi:10.1145/2751205.2751213","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2751205.2751213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM on International Conference on Supercomputing","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/A5059368105","display_name":"Bo Wu","orcid":"https://orcid.org/0000-0001-6658-6452"},"institutions":[{"id":"https://openalex.org/I167576493","display_name":"Colorado School of Mines","ror":"https://ror.org/04raf6v53","country_code":"US","type":"education","lineage":["https://openalex.org/I167576493"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bo Wu","raw_affiliation_strings":["Colorado School of Mines, Golden, CO, USA","Colorado School of Mines, Golden, CO, USA,"],"affiliations":[{"raw_affiliation_string":"Colorado School of Mines, Golden, CO, USA","institution_ids":["https://openalex.org/I167576493"]},{"raw_affiliation_string":"Colorado School of Mines, Golden, CO, USA,","institution_ids":["https://openalex.org/I167576493"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103032013","display_name":"Guoyang Chen","orcid":"https://orcid.org/0000-0002-5531-8986"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guoyang Chen","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407387","display_name":"Dong Li","orcid":"https://orcid.org/0000-0001-9336-0694"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Li","raw_affiliation_strings":["University of California, Merced, Merced, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Merced, Merced, CA, USA","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624451","display_name":"Xipeng Shen","orcid":"https://orcid.org/0000-0003-3599-8010"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xipeng Shen","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061838490","display_name":"Jeffrey S. Vetter","orcid":"https://orcid.org/0000-0002-2449-6720"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Vetter","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059368105"],"corresponding_institution_ids":["https://openalex.org/I167576493"],"apc_list":null,"apc_paid":null,"fwci":14.269,"has_fulltext":false,"cited_by_count":101,"citation_normalized_percentile":{"value":0.99240639,"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":"119","last_page":"130"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9997000098228455,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9994999766349792,"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":0.8921102285385132},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6579815149307251},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6216564178466797},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6178006529808044},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5966167449951172},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5780143737792969},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.46215206384658813},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45557159185409546},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4235127568244934},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.42298686504364014},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4160689413547516},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3381385803222656},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29635152220726013},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19553181529045105},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.19088909029960632}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8921102285385132},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6579815149307251},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6216564178466797},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6178006529808044},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5966167449951172},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5780143737792969},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46215206384658813},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45557159185409546},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4235127568244934},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.42298686504364014},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4160689413547516},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3381385803222656},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29635152220726013},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19553181529045105},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.19088909029960632},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2751205.2751213","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2751205.2751213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM on International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G2641352468","display_name":null,"funder_award_id":"1464216,1320796, CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1517684295","https://openalex.org/W1974165977","https://openalex.org/W1983235612","https://openalex.org/W1991707635","https://openalex.org/W1991709203","https://openalex.org/W1993338334","https://openalex.org/W1993464114","https://openalex.org/W1995516682","https://openalex.org/W1997162567","https://openalex.org/W2003117296","https://openalex.org/W2013247896","https://openalex.org/W2016706026","https://openalex.org/W2020572638","https://openalex.org/W2028914463","https://openalex.org/W2032404709","https://openalex.org/W2037018253","https://openalex.org/W2048441570","https://openalex.org/W2067313328","https://openalex.org/W2072680607","https://openalex.org/W2080592089","https://openalex.org/W2087725506","https://openalex.org/W2090584832","https://openalex.org/W2091553595","https://openalex.org/W2098274770","https://openalex.org/W2100409742","https://openalex.org/W2101587002","https://openalex.org/W2103838950","https://openalex.org/W2107251158","https://openalex.org/W2117197583","https://openalex.org/W2117444998","https://openalex.org/W2117689653","https://openalex.org/W2121717408","https://openalex.org/W2128329055","https://openalex.org/W2129381159","https://openalex.org/W2132366470","https://openalex.org/W2134427337","https://openalex.org/W2134953833","https://openalex.org/W2138708064","https://openalex.org/W2140348470","https://openalex.org/W2141170493","https://openalex.org/W2142444503","https://openalex.org/W2149234156","https://openalex.org/W2150476673","https://openalex.org/W2150851481","https://openalex.org/W2160786443","https://openalex.org/W3112784795","https://openalex.org/W4233973673"],"related_works":["https://openalex.org/W4240253816","https://openalex.org/W3096456556","https://openalex.org/W2169584677","https://openalex.org/W2979513934","https://openalex.org/W4232954277","https://openalex.org/W1556451512","https://openalex.org/W2020341030","https://openalex.org/W2749133591","https://openalex.org/W1555349535","https://openalex.org/W2367473450"],"abstract_inverted_index":{"A":[0],"GPU's":[1,41],"computing":[2],"power":[3],"lies":[4],"in":[5,107],"its":[6,14],"abundant":[7],"memory":[8],"bandwidth":[9],"and":[10],"massive":[11],"parallelism.":[12],"However,":[13],"hardware":[15,85],"thread":[16,56],"schedulers,":[17],"despite":[18],"being":[19],"able":[20],"to":[21,25,29,53,79],"quickly":[22],"distribute":[23],"computation":[24],"processors,":[26],"often":[27],"fail":[28],"capitalize":[30],"on":[31,72,100],"program":[32,64],"characteristics":[33],"effectively,":[34],"achieving":[35],"only":[36],"a":[37,69],"fraction":[38],"of":[39,83,91,97],"the":[40,63,81,84,102],"full":[42],"potential.":[43],"Moreover,":[44],"current":[45],"GPUs":[46],"do":[47],"not":[48],"allow":[49],"programmers":[50],"or":[51],"compilers":[52],"control":[54,90,96],"this":[55,76],"scheduling,":[57],"forfeiting":[58],"important":[59],"optimization":[60],"opportunities":[61],"at":[62],"level.":[65],"This":[66],"paper":[67],"presents":[68],"transformation":[70,103],"centered":[71],"Streaming":[73],"Multiprocessors":[74],"(SM);":[75],"software":[77],"approach":[78],"circumventing":[80],"limitations":[82,106],"scheduler":[86],"allows":[87],"flexible":[88],"program-level":[89],"scheduling.":[92],"By":[93],"permitting":[94],"precise":[95],"job":[98],"locality":[99],"SMs,":[101],"overcomes":[104],"inherent":[105],"prior":[108],"methods.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":23},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}
