{"id":"https://openalex.org/W3205535571","doi":"https://doi.org/10.1145/3466752.3480083","title":"Improving Address Translation in Multi-GPUs via Sharing and Spilling aware TLB Design","display_name":"Improving Address Translation in Multi-GPUs via Sharing and Spilling aware TLB Design","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205535571","doi":"https://doi.org/10.1145/3466752.3480083","mag":"3205535571"},"language":"en","primary_location":{"id":"doi:10.1145/3466752.3480083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3466752.3480083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture","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/A5102707987","display_name":"Bingyao Li","orcid":"https://orcid.org/0000-0002-6281-6799"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bingyao Li","raw_affiliation_strings":["University of Pittsburgh, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, United States of America","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082725592","display_name":"Jieming Yin","orcid":"https://orcid.org/0009-0008-2878-1853"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jieming Yin","raw_affiliation_strings":["Lehigh University, United States of America"],"affiliations":[{"raw_affiliation_string":"Lehigh University, United States of America","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026996875","display_name":"Youtao Zhang","orcid":"https://orcid.org/0000-0001-8425-8743"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youtao Zhang","raw_affiliation_strings":["University of Pittsburgh"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087859795","display_name":"Xulong Tang","orcid":"https://orcid.org/0000-0002-3385-2053"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xulong Tang","raw_affiliation_strings":["University of Pittsburgh, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, United States of America","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102707987"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":3.5145,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.93189189,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1154","last_page":"1168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9980999827384949,"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":0.9803541898727417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.887604832649231},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6333163380622864},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5071532726287842},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.49736860394477844},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.44887542724609375},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4344259202480316},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4334167540073395},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24240660667419434},{"id":"https://openalex.org/keywords/physical-address","display_name":"Physical address","score":0.16745305061340332},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1382800042629242}],"concepts":[{"id":"https://openalex.org/C116007543","wikidata":"https://www.wikidata.org/wiki/Q1071403","display_name":"Translation lookaside buffer","level":4,"score":0.9803541898727417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.887604832649231},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6333163380622864},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5071532726287842},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.49736860394477844},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.44887542724609375},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4344259202480316},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4334167540073395},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24240660667419434},{"id":"https://openalex.org/C41036726","wikidata":"https://www.wikidata.org/wiki/Q844824","display_name":"Physical address","level":3,"score":0.16745305061340332},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1382800042629242},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3466752.3480083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3466752.3480083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture","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":84,"referenced_works":["https://openalex.org/W4424585","https://openalex.org/W1864199185","https://openalex.org/W1967373117","https://openalex.org/W1973573211","https://openalex.org/W2004807638","https://openalex.org/W2020733012","https://openalex.org/W2044213522","https://openalex.org/W2047240985","https://openalex.org/W2047390994","https://openalex.org/W2049403384","https://openalex.org/W2051265981","https://openalex.org/W2062430565","https://openalex.org/W2067523571","https://openalex.org/W2071767440","https://openalex.org/W2079248286","https://openalex.org/W2093828978","https://openalex.org/W2100741459","https://openalex.org/W2100799944","https://openalex.org/W2100926301","https://openalex.org/W2101482453","https://openalex.org/W2103707825","https://openalex.org/W2120138088","https://openalex.org/W2126987530","https://openalex.org/W2135089498","https://openalex.org/W2135438094","https://openalex.org/W2136362035","https://openalex.org/W2146241244","https://openalex.org/W2149234156","https://openalex.org/W2156703074","https://openalex.org/W2160996172","https://openalex.org/W2233520879","https://openalex.org/W2238595726","https://openalex.org/W2416722775","https://openalex.org/W2418692044","https://openalex.org/W2509091023","https://openalex.org/W2528784626","https://openalex.org/W2567006428","https://openalex.org/W2576312950","https://openalex.org/W2581371485","https://openalex.org/W2604399885","https://openalex.org/W2611998574","https://openalex.org/W2626757163","https://openalex.org/W2739539165","https://openalex.org/W2758612716","https://openalex.org/W2764065518","https://openalex.org/W2766789999","https://openalex.org/W2782087530","https://openalex.org/W2792929085","https://openalex.org/W2793599434","https://openalex.org/W2793655593","https://openalex.org/W2794272546","https://openalex.org/W2884735227","https://openalex.org/W2885000039","https://openalex.org/W2904107204","https://openalex.org/W2904412652","https://openalex.org/W2906409935","https://openalex.org/W2920870926","https://openalex.org/W2949462451","https://openalex.org/W2951631461","https://openalex.org/W2952259253","https://openalex.org/W2952928793","https://openalex.org/W2953357877","https://openalex.org/W2953698097","https://openalex.org/W2980066681","https://openalex.org/W3005429556","https://openalex.org/W3005675093","https://openalex.org/W3011280959","https://openalex.org/W3034855459","https://openalex.org/W3036082746","https://openalex.org/W3043443960","https://openalex.org/W3085066009","https://openalex.org/W3089681336","https://openalex.org/W3090784541","https://openalex.org/W3098059246","https://openalex.org/W3103894541","https://openalex.org/W3143889401","https://openalex.org/W3145579537","https://openalex.org/W4230315356","https://openalex.org/W4232927161","https://openalex.org/W4233429846","https://openalex.org/W4238141842","https://openalex.org/W4242502357","https://openalex.org/W4293160463","https://openalex.org/W4301361180"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"In":[0,81],"recent":[1],"years,":[2],"the":[3,13,36,39,45,51,56,72,90,121,139,143],"ever-growing":[4],"application":[5,25,37],"complexity":[6],"and":[7,97,118,134,149],"input":[8],"dataset":[9],"sizes":[10],"have":[11],"driven":[12],"popularity":[14],"of":[15,47,50,89],"multi-GPU":[16,76,116],"systems":[17,77,117],"as":[18],"a":[19,86,107],"desirable":[20],"computing":[21],"platform":[22],"for":[23,35,115],"many":[24],"domains.":[26],"While":[27],"employing":[28],"multiple":[29],"GPUs":[30],"intuitively":[31],"exposes":[32],"substantial":[33],"parallelism":[34],"acceleration,":[38],"delivered":[40],"performance":[41,123],"rarely":[42],"scales":[43],"with":[44,124],"number":[46],"GPUs.":[48],"One":[49],"major":[52],"challenges":[53],"behind":[54],"is":[55],"address":[57,73,91],"translation":[58,74,92],"efficiency.":[59],"Many":[60],"prior":[61],"works":[62],"focus":[63],"on":[64,102,130,145],"CPUs":[65],"or":[66],"single":[67],"GPU":[68],"execution":[69,99],"scenarios":[70],"while":[71],"in":[75,94],"receives":[78],"little":[79],"attention.":[80],"this":[82],"paper,":[83],"we":[84,105],"conduct":[85],"comprehensive":[87],"investigation":[88],"efficiency":[93],"both":[95],"\u201csingle-application-multi-GPU\u201d":[96],"\u201cmulti-application-multi-GPU\u201d":[98],"paradigms.":[100],"Based":[101],"our":[103],"observations,":[104],"propose":[106],"new":[108],"TLB":[109,122],"hierarchy":[110],"design,":[111],"called":[112],"least-TLB,":[113],"tailored":[114],"effectively":[119],"improves":[120,142],"minimal":[125],"hardware":[126],"overheads.":[127],"Experimental":[128],"results":[129],"9":[131],"single-application":[132],"workloads":[133,137],"10":[135],"multi-application":[136],"indicate":[138],"proposed":[140],"least-TLB":[141],"performances,":[144],"average,":[146],"by":[147],"23.5%":[148],"16.3%,":[150],"respectively.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}
