{"id":"https://openalex.org/W2751225241","doi":"https://doi.org/10.1109/nas.2017.8026851","title":"DD-L1D: Improving the Decoupled L1D Efficiency for GPU Architecture","display_name":"DD-L1D: Improving the Decoupled L1D Efficiency for GPU Architecture","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2751225241","doi":"https://doi.org/10.1109/nas.2017.8026851","mag":"2751225241"},"language":"en","primary_location":{"id":"doi:10.1109/nas.2017.8026851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas.2017.8026851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Networking, Architecture, and Storage (NAS)","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/A5103775721","display_name":"Weiguang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiguang Yang","raw_affiliation_strings":["Dalian University of Technology, School of Software Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, School of Software Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427475","display_name":"Yuxin Wang","orcid":"https://orcid.org/0000-0002-5133-3978"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Wang","raw_affiliation_strings":["Dalian University of Technology, School of Computer Science and Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, School of Computer Science and Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088901322","display_name":"Yulong Yu","orcid":"https://orcid.org/0000-0003-0170-087X"},"institutions":[{"id":"https://openalex.org/I4210134419","display_name":"Neusoft (China)","ror":"https://ror.org/02zc84r97","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210134419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulong Yu","raw_affiliation_strings":["Neusoft Corporation, Network Security Department, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Neusoft Corporation, Network Security Department, Shenyang, China","institution_ids":["https://openalex.org/I4210134419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016435310","display_name":"Guangyuan Kan","orcid":"https://orcid.org/0000-0002-0467-4366"},"institutions":[{"id":"https://openalex.org/I4210092032","display_name":"China Institute of Water Resources and Hydropower Research","ror":"https://ror.org/00m4czf33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210092032"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyuan Kan","raw_affiliation_strings":["China Institute of Water Resources and Hydropower Research, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Institute of Water Resources and Hydropower Research, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I4210092032","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059541676","display_name":"He Guo","orcid":"https://orcid.org/0000-0003-0955-7692"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Guo","raw_affiliation_strings":["Dalian University of Technology, School of Software Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, School of Software Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.12730117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"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":0.9991999864578247,"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":0.9983000159263611,"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/cache","display_name":"Cache","score":0.879551887512207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8698770403862},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7469875812530518},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.6997549533843994},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.6791608333587646},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.6653577089309692},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.652542233467102},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6280924677848816},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.6190779805183411},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.5167345404624939},{"id":"https://openalex.org/keywords/mesi-protocol","display_name":"MESI protocol","score":0.489626944065094},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.47997093200683594},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4707534909248352},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.44068387150764465},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.42660781741142273},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4182325303554535},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.335116446018219}],"concepts":[{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.879551887512207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8698770403862},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7469875812530518},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.6997549533843994},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.6791608333587646},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.6653577089309692},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.652542233467102},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6280924677848816},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.6190779805183411},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.5167345404624939},{"id":"https://openalex.org/C120936851","wikidata":"https://www.wikidata.org/wiki/Q1408065","display_name":"MESI protocol","level":5,"score":0.489626944065094},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.47997093200683594},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4707534909248352},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.44068387150764465},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.42660781741142273},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4182325303554535},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.335116446018219},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nas.2017.8026851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas.2017.8026851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Networking, Architecture, and Storage (NAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1971421905","https://openalex.org/W1979527452","https://openalex.org/W1982996921","https://openalex.org/W1983235612","https://openalex.org/W2020572638","https://openalex.org/W2025358418","https://openalex.org/W2027806965","https://openalex.org/W2033486618","https://openalex.org/W2047060659","https://openalex.org/W2048441570","https://openalex.org/W2053744175","https://openalex.org/W2062527253","https://openalex.org/W2065562952","https://openalex.org/W2067441262","https://openalex.org/W2080592089","https://openalex.org/W2084309410","https://openalex.org/W2090584832","https://openalex.org/W2091599698","https://openalex.org/W2097336080","https://openalex.org/W2098505406","https://openalex.org/W2109432325","https://openalex.org/W2124350608","https://openalex.org/W2128120785","https://openalex.org/W2129817042","https://openalex.org/W2142444503","https://openalex.org/W2161402454","https://openalex.org/W2163188020","https://openalex.org/W2166918318","https://openalex.org/W2273440736","https://openalex.org/W2342496780","https://openalex.org/W3006039064","https://openalex.org/W3145885533","https://openalex.org/W4237024478","https://openalex.org/W6662382780","https://openalex.org/W6674334183"],"related_works":["https://openalex.org/W4312759433","https://openalex.org/W2098406302","https://openalex.org/W2535115842","https://openalex.org/W1584415117","https://openalex.org/W2184371594","https://openalex.org/W2121191383","https://openalex.org/W1998391448","https://openalex.org/W1652973653","https://openalex.org/W273173017","https://openalex.org/W2539551105"],"abstract_inverted_index":{"GPU":[0,163],"L1":[1,101,125],"data":[2,57,102],"cache":[3,16,23,51,103,126,153,164],"contention,":[4],"caused":[5],"by":[6,54,73,108,148],"a":[7,29,42,89],"huge":[8],"amount":[9],"of":[10,59],"concurrent":[11],"threads,":[12],"leads":[13],"to":[14,33,78,104,122],"insufficient":[15],"utilization":[17],"and":[18,37,66,129,160,171],"poor":[19],"performance,":[20],"especially":[21],"for":[22,50,152],"unfriendly":[24,52,154],"applications.":[25],"Cache":[26],"bypassing":[27,44,91,127,131,165],"is":[28,41,75],"widely-":[30],"used":[31],"method":[32],"alleviate":[34],"this":[35,85],"problem,":[36],"Decoupled":[38],"L1D":[39],"(D-L1D)":[40],"preventive":[43],"scheme,":[45],"which":[46],"achieves":[47],"performance":[48,71,147],"improvement":[49],"applications":[53],"considering":[55],"the":[56,79,100,105,111,124,145,161],"locality":[58,81,112],"memory":[60,172],"access":[61],"streams.":[62],"However,":[63],"our":[64,135],"experiments":[65],"analyses":[67],"show":[68],"that":[69,98,142],"limited":[70],"gain":[72],"D-L1D":[74,96,159],"attained":[76],"due":[77],"pre-defined":[80],"threshold.":[82],"To":[83],"address":[84],"issue,":[86],"we":[87],"propose":[88],"novel":[90],"scheme":[92],"named":[93],"as":[94],"Dynamic":[95],"(DD-L1D)":[97],"directs":[99],"less":[106],"contention":[107],"dynamically":[109],"updating":[110],"threshold":[113],"during":[114],"runtime.":[115],"We":[116],"evaluate":[117],"four":[118],"metrics":[119],"in":[120,134],"DD-L1D":[121,143],"indicate":[123],"state,":[128],"choose":[130],"miss":[132],"rate":[133],"final":[136],"configuration.":[137],"The":[138],"experimental":[139],"results":[140],"demonstrate":[141],"improves":[144],"baseline":[146],"1.45X":[149],"on":[150],"average":[151],"benchmarks.":[155],"It":[156],"also":[157],"outperforms":[158],"state-of-the-art":[162],"schemes":[166],"with":[167],"lower":[168],"hardware":[169],"overhead":[170],"traffic.":[173]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}