{"id":"https://openalex.org/W2021352628","doi":"https://doi.org/10.1145/1995896.1995900","title":"An execution strategy and optimized runtime support for parallelizing irregular reductions on modern GPUs","display_name":"An execution strategy and optimized runtime support for parallelizing irregular reductions on modern GPUs","publication_year":2011,"publication_date":"2011-05-31","ids":{"openalex":"https://openalex.org/W2021352628","doi":"https://doi.org/10.1145/1995896.1995900","mag":"2021352628"},"language":"en","primary_location":{"id":"doi:10.1145/1995896.1995900","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1995896.1995900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the international conference on Supercomputing","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/A5084205231","display_name":"Xin Huo","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Huo","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA","The Ohio State University, Columbus, OH, USA.;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA.;","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086667064","display_name":"Vignesh T. Ravi","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vignesh Ravi","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA","The Ohio State University, Columbus, OH, USA.;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA.;","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695928","display_name":"Wenjing Ma","orcid":"https://orcid.org/0000-0002-1795-4498"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenjing Ma","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA","The Ohio State University, Columbus, OH, USA.;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA.;","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025342178","display_name":"Gagan Agrawal","orcid":"https://orcid.org/0000-0002-2923-5327"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gagan Agrawal","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA","The Ohio State University, Columbus, OH, USA.;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA.;","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":1.1401,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.75978162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2","last_page":"11"},"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":0.9990000128746033,"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":0.9986000061035156,"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":0.8526545166969299},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8060674667358398},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.41987815499305725},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4045097529888153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8526545166969299},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8060674667358398},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.41987815499305725},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4045097529888153}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1995896.1995900","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1995896.1995900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the international conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W24451458","https://openalex.org/W1496148647","https://openalex.org/W1537323515","https://openalex.org/W1595115343","https://openalex.org/W1964730929","https://openalex.org/W1970652797","https://openalex.org/W1973858832","https://openalex.org/W1980999196","https://openalex.org/W1985571147","https://openalex.org/W1993385165","https://openalex.org/W1993464114","https://openalex.org/W1994425593","https://openalex.org/W2013419729","https://openalex.org/W2028914463","https://openalex.org/W2029430412","https://openalex.org/W2039781906","https://openalex.org/W2059599783","https://openalex.org/W2078900897","https://openalex.org/W2093440799","https://openalex.org/W2094333709","https://openalex.org/W2101925235","https://openalex.org/W2116963870","https://openalex.org/W2120062497","https://openalex.org/W2126026097","https://openalex.org/W2127282737","https://openalex.org/W2128131218","https://openalex.org/W2128539477","https://openalex.org/W2129232868","https://openalex.org/W2144263584","https://openalex.org/W2145460501","https://openalex.org/W2146606012","https://openalex.org/W2152044434","https://openalex.org/W2161455936","https://openalex.org/W2163488221","https://openalex.org/W2163691271","https://openalex.org/W2167548825","https://openalex.org/W2170634604","https://openalex.org/W2333521678","https://openalex.org/W4252430366"],"related_works":["https://openalex.org/W4243252198","https://openalex.org/W2118300983","https://openalex.org/W2117014006","https://openalex.org/W2112962394","https://openalex.org/W3137189469","https://openalex.org/W4233815414","https://openalex.org/W1569389315","https://openalex.org/W2503642292","https://openalex.org/W162708450","https://openalex.org/W320545226"],"abstract_inverted_index":{"GPUs":[0],"have":[1,107,194,210],"rapidly":[2],"emerged":[3],"as":[4],"a":[5,148],"very":[6],"significant":[7,21,125],"player":[8],"in":[9,23,57,66,79],"high":[10],"performance":[11,100],"computing.":[12],"However,":[13,105],"despite":[14],"the":[15,37,52,80,177,189],"popularity":[16],"of":[17,27,39,54,76,132,151,159],"CUDA,":[18],"there":[19,106],"are":[20,121,172],"challenges":[22,38,126],"porting":[24,129],"different":[25,85],"classes":[26],"HPC":[28],"applications":[29,42,116,133],"on":[30,36,47,102,113,117,134],"modern":[31,48,118,135],"GPUs.":[32,50,119,136],"This":[33,180],"paper":[34,181],"focuses":[35],"implementing":[40],"irregular":[41,55],"arising":[43],"from":[44],"unstructured":[45],"grids":[46],"NVIDIA":[49],"Considering":[51],"importance":[53],"reductions":[56],"scientific":[58],"and":[59,69,143,207],"engineering":[60],"codes,":[61],"substantial":[62],"effort":[63],"was":[64],"made":[65],"developing":[67],"compiler":[68],"runtime":[70,169,198,208],"support":[71,201],"for":[72,174],"parallelization":[73,145],"or":[74,98],"optimization":[75],"these":[77,115],"codes":[78],"previous":[81],"two":[82,124,191,215],"decades,":[83],"with":[84,128],"efforts":[86],"targeting":[87],"distributed":[88,91],"memory":[89,93,96],"machines,":[90,94,97],"shared":[92,95,160,178],"cache":[99],"improvement":[101],"uniprocessor":[103],"machines.":[104],"not":[108],"been":[109,211],"any":[110],"systematic":[111],"studies":[112],"parallelizing":[114],"There":[120],"at":[122],"least":[123],"associated":[127],"this":[130],"class":[131],"The":[137,153],"first":[138],"is":[139,156],"related":[140],"to":[141,200],"correct":[142],"efficient":[144],"while":[146],"using":[147,176,214],"large":[149],"number":[150],"threads.":[152],"second":[154],"challenge":[155],"effective":[157],"use":[158],"memory.":[161,179],"Since":[162],"data":[163],"accesses":[164],"cannot":[165],"be":[166],"determined":[167],"statically,":[168],"partitioning":[170],"methods":[171,209],"needed":[173],"effectively":[175],"describes":[182],"an":[183],"execution":[184,203],"methodology":[185],"that":[186],"can":[187],"address":[188],"above":[190],"challenges.":[192],"We":[193],"also":[195],"developed":[196],"optimized":[197],"modules":[199],"our":[202],"methodology.":[204],"Our":[205],"approach":[206],"extensively":[212],"evaluated":[213],"indirection":[216],"array":[217],"based":[218],"applications.":[219]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}