{"id":"https://openalex.org/W7133568927","doi":"https://doi.org/10.1109/hpca68181.2026.11408473","title":"LRM-GPU: Alleviating Synchronization Overhead for Multi-Chiplet GPU Architecture","display_name":"LRM-GPU: Alleviating Synchronization Overhead for Multi-Chiplet GPU Architecture","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7133568927","doi":"https://doi.org/10.1109/hpca68181.2026.11408473"},"language":null,"primary_location":{"id":"doi:10.1109/hpca68181.2026.11408473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca68181.2026.11408473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5128112240","display_name":"Baiqing Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baiqing Zhong","raw_affiliation_strings":["School of Microelectronics Science and Technology, Sun Yat-Sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics Science and Technology, Sun Yat-Sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034687144","display_name":"Zhirong Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhirong Ye","raw_affiliation_strings":["School of Microelectronics Science and Technology, Sun Yat-Sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics Science and Technology, Sun Yat-Sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123457842","display_name":"Xiaojie Li","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Li","raw_affiliation_strings":["School of Microelectronics Science and Technology, Sun Yat-Sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics Science and Technology, Sun Yat-Sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042310624","display_name":"Peilin Wang","orcid":"https://orcid.org/0009-0009-5646-0050"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peilin Wang","raw_affiliation_strings":["School of Microelectronics Science and Technology, Sun Yat-Sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics Science and Technology, Sun Yat-Sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008630842","display_name":"Haiqiu Huang","orcid":"https://orcid.org/0000-0003-1543-3901"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiqiu Huang","raw_affiliation_strings":["School of Microelectronics Science and Technology, Sun Yat-Sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics Science and Technology, Sun Yat-Sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057648062","display_name":"Zhaolin Li","orcid":"https://orcid.org/0009-0001-1131-3024"},"institutions":[{"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":"Zhaolin Li","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128100970","display_name":"Zhiyi Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyi Yu","raw_affiliation_strings":["School of Microelectronics Science and Technology, Sun Yat-Sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics Science and Technology, Sun Yat-Sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122990774","display_name":"Mingyu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Wang","raw_affiliation_strings":["School of Microelectronics Science and Technology, Sun Yat-Sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics Science and Technology, Sun Yat-Sen University,China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15124153,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5550000071525574,"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":0.5550000071525574,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.16290000081062317,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.10869999974966049,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5098999738693237},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.46380001306533813},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4025999903678894},{"id":"https://openalex.org/keywords/systems-architecture","display_name":"Systems architecture","score":0.29670000076293945},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.26269999146461487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6894000172615051},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5098999738693237},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.46380001306533813},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36329999566078186},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca68181.2026.11408473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca68181.2026.11408473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.7683727145195007}],"awards":[{"id":"https://openalex.org/G6980098551","display_name":null,"funder_award_id":"92373103,62204271,62334014","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":44,"referenced_works":["https://openalex.org/W1985807728","https://openalex.org/W1994999558","https://openalex.org/W1997352364","https://openalex.org/W2001738739","https://openalex.org/W2021211271","https://openalex.org/W2023999916","https://openalex.org/W2025516544","https://openalex.org/W2053776346","https://openalex.org/W2080592089","https://openalex.org/W2118231264","https://openalex.org/W2144558071","https://openalex.org/W2150618958","https://openalex.org/W2164391801","https://openalex.org/W2172654076","https://openalex.org/W2236227338","https://openalex.org/W2319071579","https://openalex.org/W2415968792","https://openalex.org/W2761710529","https://openalex.org/W2774005267","https://openalex.org/W2794887017","https://openalex.org/W2929410821","https://openalex.org/W2929862812","https://openalex.org/W2933483662","https://openalex.org/W2980104813","https://openalex.org/W3017188964","https://openalex.org/W3102510044","https://openalex.org/W3103056109","https://openalex.org/W3142875983","https://openalex.org/W3206857466","https://openalex.org/W4239826705","https://openalex.org/W4242019954","https://openalex.org/W4245911027","https://openalex.org/W4250422783","https://openalex.org/W4280604807","https://openalex.org/W4308084044","https://openalex.org/W4310054974","https://openalex.org/W4380874727","https://openalex.org/W4401211780","https://openalex.org/W4401408716","https://openalex.org/W4404954969","https://openalex.org/W4404955086","https://openalex.org/W4407196862","https://openalex.org/W4409248577","https://openalex.org/W4409310621"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,7,23,47,51,56,74,92,110,136,140,153,163,178,183,188,216,229,241,248],"slowdown":[2],"of":[3,9,25,50,59,70,76,94,113,156,165,190,220,254,260],"process":[4],"scaling":[5],"and":[6,34,66,98,257],"advancement":[8],"packaging":[10],"technologies,":[11],"multi-chiplet":[12,52,60,130,150],"GPUs":[13,61],"have":[14],"emerged":[15],"as":[16],"a":[17,175],"highly":[18],"promising":[19],"architecture":[20],"to":[21,32,45,124,134,181,208],"improve":[22],"scalability":[24],"GPU":[26,53],"performance":[27,48],"further.":[28],"Moreover,":[29,238],"requiring":[30],"adherence":[31],"atomicity":[33],"memory":[35,57],"consistency":[36,148],"models":[37],"for":[38,101,129,193],"shared":[39],"data":[40],"efficient":[41,126],"synchronization":[42,80,102,127,166,184,195,204,218],"is":[43,88],"crucial":[44],"leverage":[46],"advantages":[49],"architecture.":[54],"However,":[55],"systems":[58],"introduce":[62],"deeper":[63],"cache":[64,96,142,157,180],"hierarchies":[65],"increased":[67,90],"non-uniformity,":[68],"both":[69],"which":[71],"significantly":[72,89],"exacerbate":[73],"overhead":[75,86,137,189],"synchronization.":[77],"Specifically,":[78],"acquire/release":[79],"operations":[81,100,192],"should":[82],"invalidate/flush":[83],"caches,":[84],"an":[85,202,233],"that":[87],"by":[91,109,139],"presence":[93],"additional":[95,141,154],"level,":[97,143],"atomic":[99,191,205,210,221],"performed":[103],"across":[104,212],"chiplets":[105],"are":[106],"further":[107],"impacted":[108],"limited":[111,197],"bandwidth":[112],"inter-chiplet":[114,194,217,255],"links.":[115],"To":[116,186],"address":[117],"these":[118],"challenges,":[119],"this":[120],"paper":[121],"proposes":[122,201],"LRM-GPU":[123,144,172,200,231],"provide":[125],"support":[128],"GPUs.":[131],"In":[132],"order":[133],"reduce":[135],"caused":[138],"leverages":[145],"lazy":[146],"release":[147],"in":[149,177],"GPUs,":[151],"whereby":[152],"level":[155],"only":[158],"performs":[159],"coherence":[160],"actions":[161],"when":[162],"ownership":[164],"variables":[167],"changes":[168],"between":[169],"different":[170],"chiplets.":[171],"also":[173,246],"implements":[174],"directory":[176],"last-level":[179],"track":[182],"variables.":[185],"mitigate":[187],"under":[196],"interchiplet":[198],"bandwidth,":[199],"in-network":[203],"merging":[206],"unit":[207],"merge":[209],"requests":[211],"chiplets,":[213],"thereby":[214],"reducing":[215],"traffic":[219],"operations.":[222],"Experimental":[223],"evaluation":[224],"demonstrates":[225],"that,":[226],"compared":[227,239],"with":[228,240],"MCM-GPU,":[230],"achieves":[232,247],"average":[234],"speedup":[235,249],"of$1.33":[236],"\\times$.":[237],"state-of-the-art":[242],"work":[243],"HMG,":[244],"it":[245],"of$1.22":[250],"\\times$,":[251],"reduces":[252,258],"52%":[253],"traffic,":[256],"32%":[259],"energy":[261],"consumption":[262],"on":[263],"average.":[264]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-05T00:00:00"}
