{"id":"https://openalex.org/W7133502544","doi":"https://doi.org/10.1109/hpca68181.2026.11408538","title":"HDPAT: Hierarchical Distributed Page Address Translation for Wafer-Scale GPUs","display_name":"HDPAT: Hierarchical Distributed Page Address Translation for Wafer-Scale GPUs","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7133502544","doi":"https://doi.org/10.1109/hpca68181.2026.11408538"},"language":null,"primary_location":{"id":"doi:10.1109/hpca68181.2026.11408538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca68181.2026.11408538","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":"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/A5108149719","display_name":"Daoxuan Xu","orcid":"https://orcid.org/0009-0003-7093-5530"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daoxuan Xu","raw_affiliation_strings":["William &#x0026; Mary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"William &#x0026; Mary","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076247690","display_name":"Y. Li","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["William &#x0026; Mary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"William &#x0026; Mary","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128083315","display_name":"Yuwei Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I308392441","display_name":"International University of the Caribbean","ror":"https://ror.org/02rv57d03","country_code":"JM","type":"education","lineage":["https://openalex.org/I308392441"]}],"countries":["JM","US"],"is_corresponding":false,"raw_author_name":"Yuwei Sun","raw_affiliation_strings":["UIUC","William &#x0026; Mary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UIUC","institution_ids":["https://openalex.org/I308392441"]},{"raw_affiliation_string":"William &#x0026; Mary","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056482728","display_name":"Jie Ren","orcid":"https://orcid.org/0000-0001-5541-433X"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Ren","raw_affiliation_strings":["William &#x0026; Mary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"William &#x0026; Mary","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128118789","display_name":"Yifan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I308392441","display_name":"International University of the Caribbean","ror":"https://ror.org/02rv57d03","country_code":"JM","type":"education","lineage":["https://openalex.org/I308392441"]}],"countries":["JM","US"],"is_corresponding":false,"raw_author_name":"Yifan Sun","raw_affiliation_strings":["UIUC","William &#x0026; Mary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UIUC","institution_ids":["https://openalex.org/I308392441"]},{"raw_affiliation_string":"William &#x0026; Mary","institution_ids":["https://openalex.org/I16285277"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.22964682,"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":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6473000049591064,"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":0.6473000049591064,"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":0.09009999781847,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.07450000196695328,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.42570000886917114},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.27570000290870667},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.26759999990463257},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.2565000057220459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860999703407288},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.42570000886917114},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40049999952316284},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3068000078201294},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25609999895095825},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2363000065088272}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca68181.2026.11408538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca68181.2026.11408538","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":0.4366546869277954}],"awards":[{"id":"https://openalex.org/G7592652037","display_name":null,"funder_award_id":"OAC2402947,OAC-2505119,CCF-2402804","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":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1967373117","https://openalex.org/W2120138088","https://openalex.org/W2149234156","https://openalex.org/W2170268274","https://openalex.org/W2294528575","https://openalex.org/W2528784626","https://openalex.org/W2587914027","https://openalex.org/W2606722458","https://openalex.org/W2929862812","https://openalex.org/W2952928793","https://openalex.org/W3017302221","https://openalex.org/W3089681336","https://openalex.org/W3100877701","https://openalex.org/W3205535571","https://openalex.org/W4245911027","https://openalex.org/W4360831812","https://openalex.org/W4389491917","https://openalex.org/W4390683800","https://openalex.org/W4392353733","https://openalex.org/W4392567268","https://openalex.org/W4401211750","https://openalex.org/W4401211780","https://openalex.org/W4402475845","https://openalex.org/W4409248344","https://openalex.org/W4410322177"],"related_works":[],"abstract_inverted_index":{"A":[0,93],"Wafer-scale":[1],"GPU":[2],"connects":[3],"a":[4,10,62,102],"large":[5],"number":[6],"of":[7,21,118,159],"chiplets":[8,81],"via":[9],"high-bandwidth,":[11],"low-latency":[12],"interposer-based":[13],"network,":[14],"promising":[15],"to":[16,32,37,90,123,138],"overcome":[17],"the":[18,91,116,136],"communication":[19],"bottleneck":[20],"traditional":[22],"multi-GPU":[23],"systems.":[24],"While":[25],"prior":[26],"work":[27],"has":[28],"prototyped":[29],"wafer-scale":[30],"GPUs":[31],"demonstrate":[33],"technical":[34],"feasibility,":[35],"scaling":[36],"massive":[38,51],"chiplet":[39,104,137],"counts":[40],"creates":[41],"new":[42],"bottlenecks:":[43],"virtual-tophysical":[44],"address":[45,65,133],"translation":[46,66,84,108,134,140],"becomes":[47],"severely":[48],"constrained":[49],"by":[50,120,156],"concurrent":[52],"requests":[53],"and":[54,126],"long":[55],"multi-hop":[56],"network":[57],"latencies.":[58],"We":[59],"propose":[60],"HDPAT,":[61],"hardware-accelerated":[63],"distributed":[64],"system":[67],"that":[68,98,105,151],"addresses":[69],"this":[70],"challenge":[71],"through":[72],"three":[73],"complementary":[74],"techniques:":[75],"(1)":[76],"Concentric":[77],"caching":[78,124],"converts":[79],"near-IOMMU":[80],"into":[82,135],"hierarchical":[83],"caches":[85],"based":[86],"on":[87,146],"their":[88],"distance":[89],"IOMMU.":[92],"lightweight":[94],"rotation":[95],"mechanism":[96],"ensures":[97],"there":[99],"is":[100],"always":[101],"nearby":[103],"can":[106],"provide":[107],"caching.":[109],"(2)":[110],"The":[111],"redirection":[112],"table":[113],"further":[114],"reduces":[115],"burden":[117],"IOMMU":[119],"delegating":[121],"translations":[122],"chiplets,":[125],"(3)":[127],"Prefetching":[128],"proactively":[129],"delivers":[130],"potentially":[131],"needed":[132],"improve":[139],"cache":[141],"hit":[142],"rate.":[143],"Experimental":[144],"results":[145],"14":[147],"representative":[148],"workloads":[149],"show":[150],"HDPAT":[152],"improves":[153],"overall":[154],"performance":[155],"an":[157],"average":[158],"<tex":[160],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[161],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$1.57":[162],"\\times$</tex>.":[163]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-05T00:00:00"}
