{"id":"https://openalex.org/W4389491917","doi":"https://doi.org/10.1145/3613424.3614269","title":"IDYLL: Enhancing Page Translation in Multi-GPUs via Light Weight PTE Invalidations","display_name":"IDYLL: Enhancing Page Translation in Multi-GPUs via Light Weight PTE Invalidations","publication_year":2023,"publication_date":"2023-10-28","ids":{"openalex":"https://openalex.org/W4389491917","doi":"https://doi.org/10.1145/3613424.3614269"},"language":"en","primary_location":{"id":"doi:10.1145/3613424.3614269","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3614269","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3614269","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3614269","any_repository_has_fulltext":null},"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":false,"raw_author_name":"Bingyao Li","raw_affiliation_strings":["University of Pittsburgh, United States"],"raw_orcid":"https://orcid.org/0000-0002-6281-6799","affiliations":[{"raw_affiliation_string":"University of Pittsburgh, United States","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049646773","display_name":"Yanan Guo","orcid":"https://orcid.org/0000-0003-0034-0358"},"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":"Yanan Guo","raw_affiliation_strings":["University of Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0003-0034-0358","affiliations":[{"raw_affiliation_string":"University of Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102748318","display_name":"Yueqi Wang","orcid":"https://orcid.org/0009-0009-4540-2146"},"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":"Yueqi Wang","raw_affiliation_strings":["University of Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0009-0009-4540-2146","affiliations":[{"raw_affiliation_string":"University of Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078825915","display_name":"Aamer Jaleel","orcid":"https://orcid.org/0000-0002-5709-2992"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aamer Jaleel","raw_affiliation_strings":["NVIDIA, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-5709-2992","affiliations":[{"raw_affiliation_string":"NVIDIA, United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101605460","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0001-8372-6541"},"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":"Jun Yang","raw_affiliation_strings":["University of Pittsburgh, United States"],"raw_orcid":"https://orcid.org/0000-0001-8372-6541","affiliations":[{"raw_affiliation_string":"University of Pittsburgh, United States","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"],"raw_orcid":"https://orcid.org/0000-0002-3385-2053","affiliations":[{"raw_affiliation_string":"University of Pittsburgh, United States","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.693,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.96547609,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1163","last_page":"1177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9991999864578247,"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":0.892991304397583},{"id":"https://openalex.org/keywords/translation-lookaside-buffer","display_name":"Translation lookaside buffer","score":0.7458614110946655},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.653322160243988},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6525329351425171},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6385211944580078},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6346660852432251},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.5307883024215698},{"id":"https://openalex.org/keywords/page","display_name":"Page","score":0.5252133011817932},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.43263426423072815},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4183367192745209},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4175880551338196},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3089902997016907},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.30548787117004395},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.2206486463546753},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20823192596435547},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.197890043258667},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.14644166827201843},{"id":"https://openalex.org/keywords/physical-address","display_name":"Physical address","score":0.08420813083648682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.892991304397583},{"id":"https://openalex.org/C116007543","wikidata":"https://www.wikidata.org/wiki/Q1071403","display_name":"Translation lookaside buffer","level":4,"score":0.7458614110946655},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.653322160243988},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6525329351425171},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6385211944580078},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6346660852432251},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.5307883024215698},{"id":"https://openalex.org/C33925742","wikidata":"https://www.wikidata.org/wiki/Q361698","display_name":"Page","level":2,"score":0.5252133011817932},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.43263426423072815},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4183367192745209},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4175880551338196},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3089902997016907},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.30548787117004395},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.2206486463546753},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20823192596435547},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.197890043258667},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.14644166827201843},{"id":"https://openalex.org/C41036726","wikidata":"https://www.wikidata.org/wiki/Q844824","display_name":"Physical address","level":3,"score":0.08420813083648682},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3613424.3614269","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3614269","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3614269","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3613424.3614269","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3614269","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3614269","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G2023804464","display_name":"SHF: Small: Expediting the Execution of Machine Learning Applications on Multi-GPU Infrastructure with Architecture Awareness and Runtime Support","funder_award_id":"2154973","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3140292250","display_name":"SHF: Small: Architectural Support for Securing Deep Neural Networks","funder_award_id":"1910413","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G338281152","display_name":"FoMR: A Software and Hardware Co-Design for Addressing the Performance Bottlenecks in Secure Non-Volatile Memory","funder_award_id":"2011146","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4799351663","display_name":"SPX: Enabling Scalable Synchronizations for General Purpose GPUs","funder_award_id":"1725657","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G826236720","display_name":"Collaborative Research: CSR: Small: Expediting Continual Online Learning on Edge Platforms through Software-Hardware Co-designs","funder_award_id":"2312157","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389491917.pdf","grobid_xml":"https://content.openalex.org/works/W4389491917.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1538245821","https://openalex.org/W2004807638","https://openalex.org/W2020733012","https://openalex.org/W2046996113","https://openalex.org/W2047390994","https://openalex.org/W2049403384","https://openalex.org/W2062430565","https://openalex.org/W2093828978","https://openalex.org/W2100926301","https://openalex.org/W2146241244","https://openalex.org/W2149234156","https://openalex.org/W2238595726","https://openalex.org/W2416722775","https://openalex.org/W2528784626","https://openalex.org/W2576312950","https://openalex.org/W2581371485","https://openalex.org/W2587914027","https://openalex.org/W2604399885","https://openalex.org/W2626757163","https://openalex.org/W2758612716","https://openalex.org/W2793655593","https://openalex.org/W2794272546","https://openalex.org/W2885000039","https://openalex.org/W2904412652","https://openalex.org/W2949462451","https://openalex.org/W2952928793","https://openalex.org/W2953357877","https://openalex.org/W2980066681","https://openalex.org/W3011261380","https://openalex.org/W3011280959","https://openalex.org/W3017302221","https://openalex.org/W3088076788","https://openalex.org/W3089681336","https://openalex.org/W3090784541","https://openalex.org/W3130391092","https://openalex.org/W3145579537","https://openalex.org/W3153491892","https://openalex.org/W3173778203","https://openalex.org/W3205535571","https://openalex.org/W3205905794","https://openalex.org/W3209568355","https://openalex.org/W4214655995","https://openalex.org/W4232927161","https://openalex.org/W4237249260","https://openalex.org/W4240517907","https://openalex.org/W4242502357","https://openalex.org/W4245602507","https://openalex.org/W4245911027","https://openalex.org/W4253114834","https://openalex.org/W4360831812","https://openalex.org/W4360831958"],"related_works":["https://openalex.org/W2152673879","https://openalex.org/W4234213705","https://openalex.org/W4252575112","https://openalex.org/W2123492060","https://openalex.org/W2362061522","https://openalex.org/W2564829511","https://openalex.org/W2152001105","https://openalex.org/W2170052546","https://openalex.org/W1576668169","https://openalex.org/W2925163224"],"abstract_inverted_index":{"Multi-GPU":[0],"systems":[1],"have":[2],"emerged":[3],"as":[4],"a":[5],"desirable":[6],"platform":[7],"to":[8,17,54,70,137],"deliver":[9],"high":[10],"computing":[11],"capabilities":[12],"and":[13,100,128],"large":[14,19],"memory":[15,57],"capacity":[16],"accommodate":[18],"dataset":[20],"sizes.":[21],"However,":[22],"naively":[23],"employing":[24],"multi-GPU":[25,41,78],"incurs":[26,64],"non-scalable":[27],"performance.":[28],"One":[29],"major":[30],"reason":[31],"is":[32],"that":[33,143],"execution":[34],"efficiency":[35,81],"suffers":[36],"expensive":[37],"address":[38,79],"translations":[39],"in":[40],"systems.":[42],"The":[43],"data-sharing":[44],"nature":[45],"of":[46,77,119],"GPU":[47],"applications":[48],"requires":[49],"page":[50,62,66,88,107,120],"migration":[51,63],"between":[52],"GPUs":[53],"mitigate":[55],"non-uniform":[56],"access":[58],"overheads.":[59],"Unfortunately,":[60],"frequent":[61],"substantial":[65],"table":[67,89,121],"invalidation":[68,90,130,135],"overheads":[69],"ensure":[71],"translation":[72,80],"coherence.":[73],"A":[74],"comprehensive":[75],"investigation":[76],"identifies":[82],"two":[83],"significant":[84],"bottlenecks":[85],"caused":[86],"by":[87,123,132,148],"requests:":[91],"(i)":[92],"increased":[93,102],"latency":[94,104,131],"for":[95,105],"demand":[96],"TLB":[97],"miss":[98],"requests":[99,136],"(ii)":[101],"waiting":[103],"performing":[106],"migrations.":[108],"Based":[109],"on":[110,150],"observations,":[111],"we":[112],"propose":[113],"IDYLL,":[114],"which":[115],"reduces":[116,129],"the":[117],"number":[118],"invalidations":[122],"maintaining":[124],"an":[125],"\u201cin-PTE\"":[126],"directory":[127],"batching":[133],"multiple":[134],"exploit":[138],"spatial":[139],"locality.":[140],"We":[141],"show":[142],"IDYLL":[144],"improves":[145],"overall":[146],"performance":[147],"69.9%":[149],"average.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}