{"id":"https://openalex.org/W2963615322","doi":"https://doi.org/10.1145/3337821.3337886","title":"Compiler-Assisted GPU Thread Throttling for Reduced Cache Contention","display_name":"Compiler-Assisted GPU Thread Throttling for Reduced Cache Contention","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2963615322","doi":"https://doi.org/10.1145/3337821.3337886","mag":"2963615322"},"language":"en","primary_location":{"id":"doi:10.1145/3337821.3337886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3337821.3337886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","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/A5100737610","display_name":"Hyunjun Kim","orcid":"https://orcid.org/0000-0001-6810-0903"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunjun Kim","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101027331","display_name":"Sungin Hong","orcid":"https://orcid.org/0009-0004-9960-4193"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungin Hong","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101878270","display_name":"Hyeonsu Lee","orcid":"https://orcid.org/0000-0003-3811-2449"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeonsu Lee","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062665275","display_name":"Euiseong Seo","orcid":"https://orcid.org/0000-0003-2103-8019"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Euiseong Seo","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035561846","display_name":"Hwansoo Han","orcid":"https://orcid.org/0000-0001-7182-8452"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwansoo Han","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Korea","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I848706"],"apc_list":null,"apc_paid":null,"fwci":1.51,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81404223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987999796867371,"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":0.998199999332428,"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":0.8729729652404785},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.8318864703178406},{"id":"https://openalex.org/keywords/bandwidth-throttling","display_name":"Bandwidth throttling","score":0.8176918029785156},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7526885271072388},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7515133619308472},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.5281072854995728},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4979746341705322},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.45421943068504333},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.4194238483905792},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.41501089930534363},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.3885568678379059},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.34949350357055664}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8729729652404785},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.8318864703178406},{"id":"https://openalex.org/C173061102","wikidata":"https://www.wikidata.org/wiki/Q478819","display_name":"Bandwidth throttling","level":3,"score":0.8176918029785156},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7526885271072388},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7515133619308472},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.5281072854995728},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4979746341705322},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.45421943068504333},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.4194238483905792},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.41501089930534363},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.3885568678379059},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.34949350357055664},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C131097465","wikidata":"https://www.wikidata.org/wiki/Q178898","display_name":"Gas compressor","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3337821.3337886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3337821.3337886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","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":29,"referenced_works":["https://openalex.org/W2002932832","https://openalex.org/W2012303498","https://openalex.org/W2020572638","https://openalex.org/W2027806965","https://openalex.org/W2047060659","https://openalex.org/W2050710108","https://openalex.org/W2062527253","https://openalex.org/W2080592089","https://openalex.org/W2084309410","https://openalex.org/W2091599698","https://openalex.org/W2098505406","https://openalex.org/W2100409742","https://openalex.org/W2126830109","https://openalex.org/W2128120785","https://openalex.org/W2142444503","https://openalex.org/W2147193503","https://openalex.org/W2152956697","https://openalex.org/W2153667821","https://openalex.org/W2511318867","https://openalex.org/W2536535850","https://openalex.org/W2605251767","https://openalex.org/W2626312854","https://openalex.org/W2626920052","https://openalex.org/W2735225819","https://openalex.org/W2886462140","https://openalex.org/W2887760990","https://openalex.org/W4234178886","https://openalex.org/W4239017056","https://openalex.org/W4248027902"],"related_works":["https://openalex.org/W2363769136","https://openalex.org/W2539712666","https://openalex.org/W2369103246","https://openalex.org/W2020176098","https://openalex.org/W3085471909","https://openalex.org/W2133489088","https://openalex.org/W2114386333","https://openalex.org/W2098406302","https://openalex.org/W2148571123","https://openalex.org/W2734782074"],"abstract_inverted_index":{"Modern":[0],"GPUs":[1],"concurrently":[2],"deploy":[3],"thousands":[4],"of":[5,35,53,120,151],"threads":[6,29],"to":[7,22,57,75,88,92,108,124,129,166],"maximize":[8],"thread":[9,46,55,69,113,122,169],"level":[10],"parallelism":[11,104],"(TLP)":[12],"for":[13,31],"performance.":[14,65],"For":[15],"some":[16],"applications,":[17],"however,":[18],"maximized":[19],"TLP":[20],"leads":[21],"significant":[23],"performance":[24,150,162],"degradation,":[25],"as":[26,100],"many":[27],"concurrent":[28],"compete":[30],"the":[32,36,51,64,81,93,97,103,109,130,135,149,167],"limited":[33],"amount":[34],"data":[37],"cache.":[38],"In":[39],"this":[40,159],"paper,":[41],"we":[42],"propose":[43],"a":[44],"compiler-assisted":[45],"throttling":[47,70,114,170],"scheme,":[48],"which":[49],"limits":[50],"number":[52],"active":[54,121],"groups":[56,123],"reduce":[58],"cache":[59,77,82,98,144],"contention":[60,78],"and":[61,158],"consequently":[62],"improve":[63],"A":[66],"few":[67],"dynamic":[68,94],"schemes":[71],"have":[72],"been":[73],"proposed":[74,136],"alleviate":[76],"by":[79,154],"monitoring":[80],"behavior,":[83,99],"but":[84],"they":[85,101],"often":[86],"fail":[87],"provide":[89],"timely":[90],"responses":[91],"changes":[95],"in":[96,106,164],"adjust":[102],"afterwards":[105],"response":[107],"monitored":[110],"behavior.":[111],"Our":[112,146],"scheme":[115,137],"relies":[116],"on":[117,156],"compile-time":[118],"adjustment":[119],"fit":[125],"their":[126],"memory":[127],"footprints":[128],"L1D":[131],"capacity.":[132],"We":[133],"evaluated":[134],"with":[138],"GPU":[139],"programs":[140,153],"that":[141],"suffer":[142],"from":[143],"contention.":[145],"approach":[147],"improved":[148],"original":[152],"42.96%":[155],"average,":[157],"is":[160],"8.97%":[161],"boost":[163],"comparison":[165],"static":[168],"schemes.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
