{"id":"https://openalex.org/W2920870926","doi":"https://doi.org/10.1145/3309710","title":"DUCATI","display_name":"DUCATI","publication_year":2019,"publication_date":"2019-03-08","ids":{"openalex":"https://openalex.org/W2920870926","doi":"https://doi.org/10.1145/3309710","mag":"2920870926"},"language":"en","primary_location":{"id":"doi:10.1145/3309710","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3309710","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3309710","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3309710","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078825915","display_name":"Aamer Jaleel","orcid":"https://orcid.org/0000-0002-5709-2992"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aamer Jaleel","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089789557","display_name":"Eiman Ebrahimi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eiman Ebrahimi","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089099895","display_name":"Sam Duncan","orcid":"https://orcid.org/0000-0002-9974-6464"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Duncan","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078825915"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1669,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.86851031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"16","issue":"1","first_page":"1","last_page":"24"},"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/T10829","display_name":"Interconnection Networks and Systems","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"}}],"keywords":[{"id":"https://openalex.org/keywords/translation-lookaside-buffer","display_name":"Translation lookaside buffer","score":0.9962064623832703},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.818217396736145},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6854434013366699},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.5969286561012268},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5873933434486389},{"id":"https://openalex.org/keywords/page","display_name":"Page","score":0.5073489546775818},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4835934042930603},{"id":"https://openalex.org/keywords/virtual-memory","display_name":"Virtual memory","score":0.4171416163444519},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41541290283203125},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.24251458048820496},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.22906044125556946},{"id":"https://openalex.org/keywords/physical-address","display_name":"Physical address","score":0.1822216510772705},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10452550649642944}],"concepts":[{"id":"https://openalex.org/C116007543","wikidata":"https://www.wikidata.org/wiki/Q1071403","display_name":"Translation lookaside buffer","level":4,"score":0.9962064623832703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.818217396736145},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6854434013366699},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.5969286561012268},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5873933434486389},{"id":"https://openalex.org/C33925742","wikidata":"https://www.wikidata.org/wiki/Q361698","display_name":"Page","level":2,"score":0.5073489546775818},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4835934042930603},{"id":"https://openalex.org/C76399640","wikidata":"https://www.wikidata.org/wiki/Q189401","display_name":"Virtual memory","level":4,"score":0.4171416163444519},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41541290283203125},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.24251458048820496},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.22906044125556946},{"id":"https://openalex.org/C41036726","wikidata":"https://www.wikidata.org/wiki/Q844824","display_name":"Physical address","level":3,"score":0.1822216510772705},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10452550649642944},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3309710","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3309710","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3309710","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3309710","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3309710","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3309710","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2920870926.pdf","grobid_xml":"https://content.openalex.org/works/W2920870926.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1437641643","https://openalex.org/W1979978831","https://openalex.org/W1987367554","https://openalex.org/W1990260376","https://openalex.org/W1995287338","https://openalex.org/W1999621870","https://openalex.org/W2004807638","https://openalex.org/W2013626513","https://openalex.org/W2016979414","https://openalex.org/W2020733012","https://openalex.org/W2026517532","https://openalex.org/W2029577083","https://openalex.org/W2029764709","https://openalex.org/W2047240985","https://openalex.org/W2047390994","https://openalex.org/W2049403384","https://openalex.org/W2052787948","https://openalex.org/W2062430565","https://openalex.org/W2068829602","https://openalex.org/W2082982763","https://openalex.org/W2093828978","https://openalex.org/W2095258606","https://openalex.org/W2095954861","https://openalex.org/W2099911225","https://openalex.org/W2100011668","https://openalex.org/W2100692617","https://openalex.org/W2100926301","https://openalex.org/W2102843684","https://openalex.org/W2120138088","https://openalex.org/W2120715680","https://openalex.org/W2124350608","https://openalex.org/W2124861237","https://openalex.org/W2135438094","https://openalex.org/W2140455011","https://openalex.org/W2148797773","https://openalex.org/W2153806645","https://openalex.org/W2156003674","https://openalex.org/W2157802978","https://openalex.org/W2161011047","https://openalex.org/W2169865228","https://openalex.org/W2238595726","https://openalex.org/W2243228260","https://openalex.org/W2293221651","https://openalex.org/W2330672121","https://openalex.org/W2340076492","https://openalex.org/W2416722775","https://openalex.org/W2485412435","https://openalex.org/W2497599918","https://openalex.org/W2625932461","https://openalex.org/W2746871167","https://openalex.org/W2883338591","https://openalex.org/W2903659818","https://openalex.org/W3021447659","https://openalex.org/W3025363883","https://openalex.org/W4206561618","https://openalex.org/W4235500388","https://openalex.org/W4240476789","https://openalex.org/W4253160802"],"related_works":["https://openalex.org/W2152673879","https://openalex.org/W3196094483","https://openalex.org/W2362061522","https://openalex.org/W2925163224","https://openalex.org/W2501386197","https://openalex.org/W2555873975","https://openalex.org/W2116578804","https://openalex.org/W2152001105","https://openalex.org/W4293160624","https://openalex.org/W4287871880"],"abstract_inverted_index":{"Conventional":[0],"on-chip":[1,142],"TLB":[2,19,70,84,94,133,138],"hierarchies":[3],"are":[4],"unable":[5,117],"to":[6,25,79,103,118,141,164,170],"fully":[7,119],"cover":[8,120],"the":[9,26,31,57,74,127,132,171,185],"growing":[10],"application":[11,122],"working-set":[12],"sizes.":[13],"To":[14],"make":[15],"things":[16],"worse,":[17],"Last-Level":[18,77],"(LLT)":[20],"misses":[21,39],"require":[22],"multiple":[23],"accesses":[24],"page":[27,34],"table":[28],"even":[29],"with":[30],"use":[32],"of":[33,61,146,187],"walk":[35],"caches.":[36],"Consequently,":[37],"LLT":[38,63,111,190],"incur":[40],"long":[41],"address":[42,105,154],"translation":[43,155],"latency":[44],"and":[45,59,69,83,91,109,183,196],"hurt":[46],"performance.":[47],"This":[48],"article":[49],"proposes":[50],"two":[51,148],"low-overhead":[52],"hardware":[53],"mechanisms":[54],"for":[55],"reducing":[56],"frequency":[58],"penalty":[60,113],"on-die":[62,76,93],"misses.":[64],"The":[65,97,144],"first,":[66],"Unified":[67],"CAche":[68],"(UCAT)":[71],",":[72,100,151],"enables":[73],"conventional":[75],"Cache":[78],"store":[80],"cache":[81],"lines":[82],"entries":[85],"in":[86,107,131],"a":[87,188],"single":[88],"unified":[89],"structure":[90],"increases":[92,137],"capacity":[95],"significantly.":[96],"second,":[98],"DRAM-TLB":[99,124],"memoizes":[101],"virtual":[102],"physical":[104],"translations":[106],"DRAM":[108],"reduces":[110],"miss":[112],"when":[114,192],"UCAT":[115],"is":[116,152,179],"total":[121],"working-set.":[123],"serves":[125],"as":[126],"next":[128],"larger":[129],"level":[130],"hierarchy":[134],"that":[135,157,177],"significantly":[136],"coverage":[139],"relative":[140],"TLBs.":[143],"combination":[145],"these":[147],"mechanisms,":[149],"DUCATI":[150,178],"an":[153],"architecture":[156],"improves":[158],"GPU":[159],"performance":[160,186],"by":[161],"81%;":[162],"(up":[163],"4.5\u00d7)":[165],"while":[166],"requiring":[167],"minimal":[168],"changes":[169],"existing":[172],"system":[173,191],"design.":[174],"We":[175],"show":[176],"within":[180],"20%,":[181],"5%,":[182],"2%":[184],"perfect":[189],"using":[193],"4KB,":[194],"64KB,":[195],"2MB":[197],"pages,":[198],"respectively.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2019-03-22T00:00:00"}
