{"id":"https://openalex.org/W1964704819","doi":"https://doi.org/10.1145/2442516.2442539","title":"StreamScan","display_name":"StreamScan","publication_year":2013,"publication_date":"2013-02-23","ids":{"openalex":"https://openalex.org/W1964704819","doi":"https://doi.org/10.1145/2442516.2442539","mag":"1964704819"},"language":"en","primary_location":{"id":"doi:10.1145/2442516.2442539","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2442516.2442539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM SIGPLAN symposium on Principles and practice of parallel programming","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/A5049910854","display_name":"Shengen Yan","orcid":"https://orcid.org/0009-0005-3858-7972"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengen Yan","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103437255","display_name":"Guoping Long","orcid":"https://orcid.org/0009-0006-3176-7572"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoping Long","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001666028","display_name":"Yunquan Zhang","orcid":"https://orcid.org/0000-0002-2618-5088"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunquan Zhang","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.2764,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.97427653,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"229","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9973000288009644,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.996399998664856,"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":0.8836468458175659},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8003668785095215},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5605636835098267},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5282099843025208},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4980044364929199},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4320105314254761},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09630835056304932}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8836468458175659},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8003668785095215},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5605636835098267},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5282099843025208},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4980044364929199},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4320105314254761},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09630835056304932},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2442516.2442539","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2442516.2442539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM SIGPLAN symposium on Principles and practice of parallel programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1227119782","https://openalex.org/W1513982482","https://openalex.org/W1541061791","https://openalex.org/W1579666790","https://openalex.org/W1766577897","https://openalex.org/W1963965124","https://openalex.org/W1985291160","https://openalex.org/W2007000019","https://openalex.org/W2017086619","https://openalex.org/W2019708326","https://openalex.org/W2064190272","https://openalex.org/W2087977509","https://openalex.org/W2091202943","https://openalex.org/W2094488667","https://openalex.org/W2113734991","https://openalex.org/W2113841249","https://openalex.org/W2117689653","https://openalex.org/W2118558147","https://openalex.org/W2161061943","https://openalex.org/W2162707967","https://openalex.org/W2165633563","https://openalex.org/W2165707017","https://openalex.org/W2168543008","https://openalex.org/W2521313883","https://openalex.org/W2561675875","https://openalex.org/W2739266613","https://openalex.org/W4252345548","https://openalex.org/W6637964409","https://openalex.org/W6676674358","https://openalex.org/W6683923952"],"related_works":["https://openalex.org/W4399354997","https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2005148983","https://openalex.org/W2012954338","https://openalex.org/W2096672917","https://openalex.org/W2392023973","https://openalex.org/W2076165488","https://openalex.org/W2023832055","https://openalex.org/W2082485924"],"abstract_inverted_index":{"Scan":[0],"(also":[1],"known":[2],"as":[3,17],"prefix":[4],"sum)":[5],"is":[6,52,81],"a":[7,65],"very":[8],"useful":[9],"primitive":[10],"for":[11,158],"various":[12],"important":[13,117],"parallel":[14],"algorithms,":[15],"such":[16],"sort,":[18],"BFS,":[19],"SpMV,":[20],"compaction":[21],"and":[22,49,89,105,132,161,193],"so":[23],"on.":[24],"Current":[25],"state":[26],"of":[27,30,36,112],"the":[28,53,137,149],"art":[29],"GPU":[31,195],"based":[32],"scan":[33,70,174],"implementation":[34],"consists":[35],"three":[37],"consecutive":[38],"Reduce-Scan-Scan":[39],"phases.":[40],"This":[41],"approach":[42,67,98],"requires":[43,99],"at":[44],"least":[45],"two":[46,116],"global":[47,56,92,102],"barriers":[48],"3N":[50],"(N":[51],"problem":[54,140],"size)":[55],"memory":[57,103],"accesses.":[58],"In":[59],"this":[60,113],"paper":[61],"we":[62,114],"propose":[63,115],"StreamScan,":[64],"novel":[66],"to":[68,82,85,119,127,135,147,153],"implement":[69],"on":[71,138],"GPUs":[72],"with":[73,168,171],"only":[74,86,100,179],"one":[75,107],"computation":[76],"phase.":[77],"The":[78,96],"main":[79],"idea":[80],"restrict":[83],"synchronization":[84,94],"adjacent":[87],"workgroups,":[88],"thereby":[90],"eliminating":[91],"barrier":[93],"completely.":[95],"new":[97],"2N":[101],"accesses":[104],"just":[106],"kernel":[108],"invocation.":[109],"On":[110],"top":[111],"op-timizations":[118],"further":[120],"boost":[121],"performance":[122,182],"speedups,":[123,183],"namely":[124],"thread":[125],"grouping":[126],"eliminate":[128],"unnecessary":[129],"local":[130],"barriers,":[131],"register":[133],"optimization":[134,189],"expand":[136],"chip":[139],"size.":[141],"We":[142,164],"designed":[143],"an":[144],"auto-tuning":[145],"framework":[146],"search":[148],"parameter":[150],"space":[151],"automatically":[152],"generate":[154],"highly":[155],"optimized":[156],"codes":[157],"both":[159],"AMD":[160,194],"Nvidia":[162,192],"GPUs.":[163],"implemented":[165],"our":[166],"technique":[167],"OpenCL.":[169],"Compared":[170],"previous":[172],"fast":[173],"implementations,":[175],"experimental":[176],"results":[177],"not":[178],"show":[180],"promising":[181],"but":[184],"also":[185],"reveal":[186],"dramatic":[187],"different":[188],"tradeoffs":[190],"between":[191],"platforms.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":18},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":11}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2016-06-24T00:00:00"}
