{"id":"https://openalex.org/W4214919326","doi":"https://doi.org/10.1109/paap54281.2021.9720477","title":"Reducing TLB Miss Penalty on GPUs via Unified Multi-level PWB and PWC","display_name":"Reducing TLB Miss Penalty on GPUs via Unified Multi-level PWB and PWC","publication_year":2021,"publication_date":"2021-12-10","ids":{"openalex":"https://openalex.org/W4214919326","doi":"https://doi.org/10.1109/paap54281.2021.9720477"},"language":"en","primary_location":{"id":"doi:10.1109/paap54281.2021.9720477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/paap54281.2021.9720477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP)","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/A5101884318","display_name":"Lin Yang","orcid":"https://orcid.org/0000-0003-4341-7132"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Lin","raw_affiliation_strings":["School of Computer NUDT,Changsha,China","School of Computer NUDT, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer NUDT,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"School of Computer NUDT, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025499211","display_name":"Dunbo Zhang","orcid":"https://orcid.org/0009-0001-8854-4752"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dunbo Zhang","raw_affiliation_strings":["School of Computer NUDT,Changsha,China","School of Computer NUDT, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer NUDT,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"School of Computer NUDT, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044143520","display_name":"Chaoyang Jia","orcid":"https://orcid.org/0009-0009-1005-1104"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoyang Jia","raw_affiliation_strings":["School of Computer NUDT,Changsha,China","School of Computer NUDT, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer NUDT,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"School of Computer NUDT, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417401","display_name":"Qiong Wang","orcid":"https://orcid.org/0000-0003-3755-6267"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiong Wang","raw_affiliation_strings":["School of Computer NUDT,Changsha,China","School of Computer NUDT, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer NUDT,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"School of Computer NUDT, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101790620","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-9043-2998"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["School of Computer NUDT,Changsha,China","School of Computer NUDT, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer NUDT,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"School of Computer NUDT, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101884318"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.2303,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53865573,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"14","issue":null,"first_page":"1","last_page":"8"},"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":0.9998000264167786,"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":0.9990000128746033,"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/translation-lookaside-buffer","display_name":"Translation lookaside buffer","score":0.9193294048309326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8285243511199951},{"id":"https://openalex.org/keywords/virtual-memory","display_name":"Virtual memory","score":0.5928597450256348},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5858311653137207},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5504667162895203},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.48917701840400696},{"id":"https://openalex.org/keywords/physical-address","display_name":"Physical address","score":0.4540981352329254},{"id":"https://openalex.org/keywords/paging","display_name":"Paging","score":0.45160165429115295},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.41466063261032104},{"id":"https://openalex.org/keywords/page","display_name":"Page","score":0.411301851272583},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.3473619818687439},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3227831721305847},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2763057351112366},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.14745095372200012}],"concepts":[{"id":"https://openalex.org/C116007543","wikidata":"https://www.wikidata.org/wiki/Q1071403","display_name":"Translation lookaside buffer","level":4,"score":0.9193294048309326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8285243511199951},{"id":"https://openalex.org/C76399640","wikidata":"https://www.wikidata.org/wiki/Q189401","display_name":"Virtual memory","level":4,"score":0.5928597450256348},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5858311653137207},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5504667162895203},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.48917701840400696},{"id":"https://openalex.org/C41036726","wikidata":"https://www.wikidata.org/wiki/Q844824","display_name":"Physical address","level":3,"score":0.4540981352329254},{"id":"https://openalex.org/C50954386","wikidata":"https://www.wikidata.org/wiki/Q656083","display_name":"Paging","level":2,"score":0.45160165429115295},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.41466063261032104},{"id":"https://openalex.org/C33925742","wikidata":"https://www.wikidata.org/wiki/Q361698","display_name":"Page","level":2,"score":0.411301851272583},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3473619818687439},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3227831721305847},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2763057351112366},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.14745095372200012},{"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":1,"locations":[{"id":"doi:10.1109/paap54281.2021.9720477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/paap54281.2021.9720477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP)","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":22,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W1980136882","https://openalex.org/W1981473264","https://openalex.org/W1997162567","https://openalex.org/W2047060659","https://openalex.org/W2047390994","https://openalex.org/W2049403384","https://openalex.org/W2050710108","https://openalex.org/W2062430565","https://openalex.org/W2080592089","https://openalex.org/W2098505406","https://openalex.org/W2145866640","https://openalex.org/W2146757372","https://openalex.org/W2416722775","https://openalex.org/W2528928843","https://openalex.org/W2774112409","https://openalex.org/W2792929085","https://openalex.org/W2904412652","https://openalex.org/W2994206871","https://openalex.org/W2997732597","https://openalex.org/W3013490664","https://openalex.org/W6666136284"],"related_works":["https://openalex.org/W2521131576","https://openalex.org/W3196094483","https://openalex.org/W2017119312","https://openalex.org/W4287871880","https://openalex.org/W2362061522","https://openalex.org/W3004976154","https://openalex.org/W2475386486","https://openalex.org/W3015096516","https://openalex.org/W2514064736","https://openalex.org/W4250481301"],"abstract_inverted_index":{"Recently,":[0],"GPUs":[1],"are":[2,47],"found":[3],"to":[4,31,82,163],"be":[5],"used":[6],"across":[7],"a":[8,139],"broad":[9],"range":[10],"of":[11,95,103,111,167],"domains.":[12],"To":[13],"support":[14],"virtual":[15],"memory,":[16],"which":[17,45,106,129],"is":[18,29],"required":[19],"by":[20,90],"most":[21],"applications":[22,36],"at":[23],"present,":[24],"the":[25,91,109,119,149,165,168],"address":[26,60,84,160],"translation":[27,161],"process":[28],"introduced":[30],"GPU":[32],"side.":[33],"However,":[34],"many":[35],"demonstrate":[37],"that":[38,146,183],"an":[39],"irregular":[40,112],"memory":[41,63],"access":[42],"pattern,":[43],"in":[44],"accesses":[46],"poor":[48],"structured":[49],"and":[50,74,79,98,127,143],"often":[51],"data":[52],"dependent,":[53],"makes":[54],"performance":[55,110,132],"worse":[56],"especially":[57],"with":[58,175],"virtual-to-physical":[59],"translations.":[61],"Modern":[62],"management":[64],"unit":[65],"(MMU)":[66],"employs":[67],"caching,":[68],"e.g.":[69],"page":[70,75],"walk":[71,76],"buffer":[72],"(PWB)":[73],"cache":[77],"(PWC),":[78],"scheduling":[80],"mechanisms":[81],"accelerate":[83],"translations":[85],"after":[86],"TLB":[87],"misses.":[88],"Constrained":[89],"linear":[92],"table":[93],"structure":[94,116,145],"traditional":[96],"PWB":[97,126,142],"PWC,":[99,128],"they":[100],"hold":[101],"lots":[102],"redundant":[104],"information,":[105],"further":[107],"limits":[108],"applications.":[113],"Although":[114],"nonlinear":[115],"can":[117,147],"eliminate":[118,148],"redundancy,":[120],"it":[121],"requires":[122],"sequential":[123],"look-up":[124],"on":[125],"brings":[130],"greater":[131],"loss.":[133],"In":[134],"this":[135],"paper,":[136],"we":[137],"propose":[138],"unified":[140],"multi-level":[141],"PWC":[144],"redundancy":[150],"while":[151],"enabling":[152],"parallel":[153],"look-up.":[154],"We":[155,171],"also":[156],"design":[157,174,185],"four":[158],"corresponding":[159],"processes":[162],"ensure":[164],"efficiency":[166],"new":[169],"structure.":[170],"evaluate":[172],"our":[173,184],"real-world":[176],"benchmarks":[177],"under":[178],"GPGPU-Sim":[179],"simulator.":[180],"Results":[181],"show":[182],"achieves":[186],"42.6%":[187],"IPC":[188],"improvement.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}