{"id":"https://openalex.org/W2605251767","doi":"https://doi.org/10.1145/3037697.3037709","title":"Locality-Aware CTA Clustering for Modern GPUs","display_name":"Locality-Aware CTA Clustering for Modern GPUs","publication_year":2017,"publication_date":"2017-04-04","ids":{"openalex":"https://openalex.org/W2605251767","doi":"https://doi.org/10.1145/3037697.3037709","mag":"2605251767"},"language":"en","primary_location":{"id":"doi:10.1145/3037697.3037709","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3037697.3037709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems","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/A5100413657","display_name":"Ang Li","orcid":"https://orcid.org/0000-0003-3734-9137"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ang Li","raw_affiliation_strings":["Pacific Northwest National Lab, Richland, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043209884","display_name":"Shuaiwen Leon Song","orcid":"https://orcid.org/0000-0002-8402-1436"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuaiwen Leon Song","raw_affiliation_strings":["Pacific Northwest National Lab, Richland, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444152","display_name":"Weifeng Liu","orcid":"https://orcid.org/0000-0002-2150-5759"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Weifeng Liu","raw_affiliation_strings":["University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331713","display_name":"Xu Liu","orcid":"https://orcid.org/0000-0002-8984-5485"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Liu","raw_affiliation_strings":["College of William and Mary, Williamsburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of William and Mary, Williamsburg, VA, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755285","display_name":"Akash Kumar","orcid":"https://orcid.org/0000-0001-7125-1737"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Akash Kumar","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081768631","display_name":"Henk Corporaal","orcid":"https://orcid.org/0000-0003-4506-5732"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Henk Corporaal","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven , Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven , Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"297","last_page":"311"},"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":0.9983000159263611,"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":0.9966999888420105,"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":0.8904580473899841},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.8900583982467651},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6745686531066895},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6506239771842957},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.6305138468742371},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6203985810279846},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5771644115447998},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4268578886985779},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3347983956336975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8904580473899841},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.8900583982467651},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6745686531066895},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6506239771842957},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.6305138468742371},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6203985810279846},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5771644115447998},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4268578886985779},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3347983956336975},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3037697.3037709","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3037697.3037709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:publications/7961178e-c52b-44ab-ba6a-0511012d3018","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/7961178e-c52b-44ab-ba6a-0511012d3018","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, A, Song, S L, Liu, W, Liu, X, Kumar, A & Corporaal, H 2017, Locality-aware CTA Clustering for modern GPUs. in ASPLOS 2017 - 22nd International Conference on Architectural Support for Programming Languages and Operating Systems. Association for Computing Machinery, Inc., New York, pp. 297-311, 22nd International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2017), Xi'an, China, 8/04/17. https://doi.org/10.1145/3037697.3037709","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:tue:oai:pure.tue.nl:publications/7961178e-c52b-44ab-ba6a-0511012d3018","is_oa":false,"landing_page_url":"https://research.tue.nl/nl/publications/7961178e-c52b-44ab-ba6a-0511012d3018","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ASPLOS 2017 - 22nd International Conference on Architectural Support for Programming Languages and Operating Systems, 297 - 311","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1494930385","https://openalex.org/W1503700136","https://openalex.org/W1968391520","https://openalex.org/W1979527452","https://openalex.org/W1982996921","https://openalex.org/W1983235612","https://openalex.org/W1985539519","https://openalex.org/W1989061323","https://openalex.org/W1997352364","https://openalex.org/W2009946006","https://openalex.org/W2020572638","https://openalex.org/W2022490362","https://openalex.org/W2027806965","https://openalex.org/W2047060659","https://openalex.org/W2048441570","https://openalex.org/W2053744175","https://openalex.org/W2062527253","https://openalex.org/W2067441262","https://openalex.org/W2079038734","https://openalex.org/W2080592089","https://openalex.org/W2084309410","https://openalex.org/W2090584832","https://openalex.org/W2091599698","https://openalex.org/W2096661534","https://openalex.org/W2098274770","https://openalex.org/W2098505406","https://openalex.org/W2099084006","https://openalex.org/W2113622448","https://openalex.org/W2117610793","https://openalex.org/W2128120785","https://openalex.org/W2128329055","https://openalex.org/W2134427337","https://openalex.org/W2142444503","https://openalex.org/W2155503253","https://openalex.org/W2155917287","https://openalex.org/W2156144599","https://openalex.org/W2160428323","https://openalex.org/W2161402454","https://openalex.org/W2166918318","https://openalex.org/W2169880332","https://openalex.org/W2270672919","https://openalex.org/W2273440736","https://openalex.org/W2289175783","https://openalex.org/W2289349364","https://openalex.org/W2396363708","https://openalex.org/W2410071687","https://openalex.org/W2417236060","https://openalex.org/W2511683765","https://openalex.org/W2536535850","https://openalex.org/W4237024478","https://openalex.org/W6682866967","https://openalex.org/W6716903329","https://openalex.org/W6995434384"],"related_works":["https://openalex.org/W1555349535","https://openalex.org/W2583128298","https://openalex.org/W2053359564","https://openalex.org/W2161159383","https://openalex.org/W1495260638","https://openalex.org/W1511204342","https://openalex.org/W2369125128","https://openalex.org/W2369223577","https://openalex.org/W2010020348","https://openalex.org/W4238138329"],"abstract_inverted_index":{"Cache":[0],"is":[1,17,31,47,52,86,159],"designed":[2],"to":[3,90,176,184,276,285],"exploit":[4],"locality;":[5],"however,":[6],"the":[7,35,43,80,144,167,178,186,193],"role":[8],"of":[9,66,148,169,233,241,279],"on-chip":[10],"L1":[11,133],"data":[12,67],"caches":[13],"on":[14,116,132,192,207,237,266],"modern":[15,118,239],"GPUs":[16,119],"often":[18],"awkward.":[19],"The":[20,245],"locality":[21,68,85,124,150,223],"among":[22,151],"global":[23],"memory":[24],"requests":[25],"from":[26],"different":[27],"SMs":[28],"(Streaming":[29],"Multiprocessors)":[30],"predominantly":[32],"harvested":[33],"by":[34,55,261],"commonly-shared":[36],"L2":[37,258],"with":[38,75,188,294],"long":[39,72],"access":[40],"latency;":[41],"while":[42],"in-core":[44,102],"locality,":[45],"which":[46],"crucial":[48],"for":[49,220,268,292],"performance":[50,76,255,290],"delivery,":[51],"handled":[53],"explicitly":[54],"user-controlled":[56],"scratchpad":[57],"memory.":[58],"In":[59,210],"this":[60],"work,":[61],"we":[62,109,142,165,212],"disclose":[63],"another":[64],"type":[65],"that":[69,122,248],"has":[70],"been":[71],"ignored":[73],"but":[74],"boosting":[77],"potential":[78,189],"---":[79],"inter-CTA":[81,123,222,296],"locality.":[82],"Exploiting":[83],"such":[84,149,157],"rather":[87],"challenging":[88],"due":[89],"unclear":[91],"hardware":[92,200],"feasibility,":[93],"unknown":[94],"and":[95,100,120,130,146,154,171,202,272],"inaccessible":[96],"underlying":[97],"CTA":[98,180],"scheduler,":[99],"small":[101],"cache":[103,254,259],"capacity.":[104],"To":[105],"address":[106],"these":[107,163,214],"issues,":[108],"first":[110],"conduct":[111],"a":[112,230],"thorough":[113],"empirical":[114],"exploration":[115],"various":[117],"demonstrate":[121],"can":[125,203],"be":[126,204],"harvested,":[127],"both":[128],"spatially":[129],"temporally,":[131],"or":[134],"L1/Tex":[135],"unified":[136],"cache.":[137],"Through":[138],"further":[139],"quantification":[140],"process,":[141],"prove":[143],"significance":[145],"commonality":[147],"GPU":[152,235,243],"applications,":[153],"discuss":[155],"whether":[156],"reuse":[158,190],"exploitable.":[160],"By":[161],"leveraging":[162],"insights,":[164],"propose":[166],"concept":[168],"CTA-Clustering":[170],"its":[172],"associated":[173],"software-based":[174],"techniques":[175,197,215,228,251],"reshape":[177],"default":[179],"scheduling":[181],"in":[182],"order":[183],"group":[185],"CTAs":[187],"together":[191],"same":[194],"SM.":[195],"Our":[196],"require":[198],"no":[199],"modification":[201],"directly":[205],"deployed":[206],"existing":[208],"GPUs.":[209],"addition,":[211],"incorporate":[213],"into":[216],"an":[217,277],"integrated":[218],"framework":[219],"automatic":[221],"optimization.":[224],"We":[225],"evaluate":[226],"our":[227,249],"using":[229],"wide":[231],"range":[232],"popular":[234],"applications":[236,293],"all":[238],"generations":[240],"NVIDIA":[242],"architectures.":[244],"results":[246],"show":[247],"proposed":[250],"significantly":[252],"improve":[253],"through":[256],"reducing":[257],"transactions":[260],"55%,":[262],"65%,":[263],"29%,":[264],"28%":[265],"average":[267,278],"Fermi,":[269],"Kepler,":[270],"Maxwell":[271],"Pascal,":[273],"respectively,":[274],"leading":[275],"1.46x,":[280],"1.48x,":[281],"1.45x,":[282],"1.41x":[283],"(up":[284],"3.8x,":[286],"3.6x,":[287],"3.1x,":[288],"3.3x)":[289],"speedups":[291],"algorithm-related":[295],"reuse.":[297]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}