{"id":"https://openalex.org/W4360831812","doi":"https://doi.org/10.1109/hpca56546.2023.10071054","title":"Trans-FW: Short Circuiting Page Table Walk in Multi-GPU Systems via Remote Forwarding","display_name":"Trans-FW: Short Circuiting Page Table Walk in Multi-GPU Systems via Remote Forwarding","publication_year":2023,"publication_date":"2023-02-01","ids":{"openalex":"https://openalex.org/W4360831812","doi":"https://doi.org/10.1109/hpca56546.2023.10071054"},"language":"en","primary_location":{"id":"doi:10.1109/hpca56546.2023.10071054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca56546.2023.10071054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/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,Pittsburgh,Pennsylvania,USA","University of Pittsburgh, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Pittsburgh,Pennsylvania,USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, Pennsylvania, USA","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,Bethlehem,Pennsylvania,USA","Lehigh University, Bethlehem, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Lehigh University,Bethlehem,Pennsylvania,USA","institution_ids":["https://openalex.org/I186143895"]},{"raw_affiliation_string":"Lehigh University, Bethlehem, Pennsylvania, USA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081328680","display_name":"Anup Holey","orcid":null},"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":"Anup Holey","raw_affiliation_strings":["NVIDIA,Santa Clara,California,USA","NVIDIA, Santa Clara, California, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,California,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, Santa Clara, California, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"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,Pittsburgh,Pennsylvania,USA","University of Pittsburgh, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Pittsburgh,Pennsylvania,USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"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,Pittsburgh,Pennsylvania,USA","University of Pittsburgh, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Pittsburgh,Pennsylvania,USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, Pennsylvania, USA","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,Pittsburgh,Pennsylvania,USA","University of Pittsburgh, Pittsburgh, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Pittsburgh,Pennsylvania,USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102707987"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":5.5881,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96653876,"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":"456","last_page":"470"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"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":0.8898904323577881},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5518126487731934},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5374264121055603},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.523313045501709},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4970729649066925},{"id":"https://openalex.org/keywords/translation-lookaside-buffer","display_name":"Translation lookaside buffer","score":0.4970076382160187},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4876750707626343},{"id":"https://openalex.org/keywords/virtual-memory","display_name":"Virtual memory","score":0.4853183627128601},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4717104136943817},{"id":"https://openalex.org/keywords/demand-paging","display_name":"Demand paging","score":0.44875064492225647},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41763025522232056},{"id":"https://openalex.org/keywords/page-fault","display_name":"Page fault","score":0.41166073083877563},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.34139400720596313},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.2953416705131531},{"id":"https://openalex.org/keywords/physical-address","display_name":"Physical address","score":0.223626971244812},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.18115583062171936},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11062529683113098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8898904323577881},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5518126487731934},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5374264121055603},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.523313045501709},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4970729649066925},{"id":"https://openalex.org/C116007543","wikidata":"https://www.wikidata.org/wiki/Q1071403","display_name":"Translation lookaside buffer","level":4,"score":0.4970076382160187},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4876750707626343},{"id":"https://openalex.org/C76399640","wikidata":"https://www.wikidata.org/wiki/Q189401","display_name":"Virtual memory","level":4,"score":0.4853183627128601},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4717104136943817},{"id":"https://openalex.org/C188873839","wikidata":"https://www.wikidata.org/wiki/Q5255045","display_name":"Demand paging","level":5,"score":0.44875064492225647},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41763025522232056},{"id":"https://openalex.org/C193343404","wikidata":"https://www.wikidata.org/wiki/Q1928607","display_name":"Page fault","level":5,"score":0.41166073083877563},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.34139400720596313},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.2953416705131531},{"id":"https://openalex.org/C41036726","wikidata":"https://www.wikidata.org/wiki/Q844824","display_name":"Physical address","level":3,"score":0.223626971244812},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.18115583062171936},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11062529683113098},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca56546.2023.10071054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca56546.2023.10071054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310174","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W1263049605","https://openalex.org/W1864199185","https://openalex.org/W1967373117","https://openalex.org/W2004807638","https://openalex.org/W2020733012","https://openalex.org/W2044213522","https://openalex.org/W2047390994","https://openalex.org/W2049403384","https://openalex.org/W2062430565","https://openalex.org/W2067523571","https://openalex.org/W2071767440","https://openalex.org/W2093828978","https://openalex.org/W2100926301","https://openalex.org/W2102843684","https://openalex.org/W2126987530","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/W2587914027","https://openalex.org/W2604399885","https://openalex.org/W2604595776","https://openalex.org/W2612387305","https://openalex.org/W2626757163","https://openalex.org/W2739539165","https://openalex.org/W2761710529","https://openalex.org/W2764065518","https://openalex.org/W2793599434","https://openalex.org/W2793655593","https://openalex.org/W2794272546","https://openalex.org/W2867345499","https://openalex.org/W2884735227","https://openalex.org/W2885000039","https://openalex.org/W2903659818","https://openalex.org/W2904107204","https://openalex.org/W2904412652","https://openalex.org/W2920870926","https://openalex.org/W2949462451","https://openalex.org/W2952928793","https://openalex.org/W2953357877","https://openalex.org/W2980066681","https://openalex.org/W3005675093","https://openalex.org/W3011261380","https://openalex.org/W3011280959","https://openalex.org/W3011293047","https://openalex.org/W3017302221","https://openalex.org/W3042369493","https://openalex.org/W3085066009","https://openalex.org/W3089681336","https://openalex.org/W3090784541","https://openalex.org/W3117512411","https://openalex.org/W3143889401","https://openalex.org/W3145579537","https://openalex.org/W3153491892","https://openalex.org/W3159945917","https://openalex.org/W3173778203","https://openalex.org/W3188005507","https://openalex.org/W3205535571","https://openalex.org/W3206003350","https://openalex.org/W3209568355","https://openalex.org/W4214655995","https://openalex.org/W4232854706","https://openalex.org/W4232927161","https://openalex.org/W4238135788","https://openalex.org/W4238398050","https://openalex.org/W4240517907","https://openalex.org/W4245911027","https://openalex.org/W4289388825","https://openalex.org/W4301361180","https://openalex.org/W4312053794","https://openalex.org/W4320729330","https://openalex.org/W6731837222","https://openalex.org/W6742019887","https://openalex.org/W6756526789"],"related_works":["https://openalex.org/W1437641643","https://openalex.org/W3196094483","https://openalex.org/W2888832568","https://openalex.org/W3145425992","https://openalex.org/W2355566153","https://openalex.org/W2983972592","https://openalex.org/W4250481301","https://openalex.org/W2514064736","https://openalex.org/W2576253365","https://openalex.org/W2564829511"],"abstract_inverted_index":{"Multi-GPU":[0],"systems":[1,65],"have":[2,26],"become":[3],"a":[4],"popular":[5],"platform":[6],"to":[7,31],"meet":[8],"the":[9,29,33,39,50,59,75,118,145],"ever-growing":[10],"application":[11],"demands.":[12],"However,":[13],"employing":[14],"multiple":[15],"GPUs":[16],"does":[17],"not":[18],"guarantee":[19],"proportional":[20],"performance":[21,147],"improvements.":[22],"While":[23],"prior":[24],"works":[25],"extensively":[27],"studied":[28],"optimizations":[30],"mitigate":[32],"non-uniform":[34],"memory":[35,69,96],"accesses":[36,97],"(NUMA)":[37],"overheads,":[38],"address":[40,60],"translation":[41,61,125,130],"process":[42,62],"also":[43],"plays":[44],"an":[45],"important":[46],"role":[47],"in":[48,63],"shaping":[49],"overall":[51,146],"execution":[52],"performance.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,112],"investigate":[58],"multi-GPU":[64,137],"under":[66],"unified":[67],"virtual":[68],"(UVM).":[70],"We":[71],"specifically":[72],"focus":[73],"on":[74,109,134,150],"efficiency":[76],"of":[77],"page":[78,91,99,106,119],"table":[79,92,120],"walk":[80,93,100,121],"and":[81,103,127],"identify":[82],"three":[83],"major":[84],"latency":[85],"penalties:":[86],"i)":[87],"queuing":[88],"for":[89,98],"available":[90],"threads,":[94],"ii)":[95],"cache":[101],"misses,":[102],"iii)":[104],"handling":[105],"faults.":[107],"Based":[108],"our":[110,141],"observations,":[111],"propose":[113],"Trans-FW,":[114],"which":[115],"short":[116],"circuits":[117],"by":[122,148],"leveraging":[123],"substantial":[124],"sharing":[126],"eager":[128],"remote":[129],"forwarding.":[131],"Experimental":[132],"results":[133],"10":[135],"representative":[136],"applications":[138],"show":[139],"that":[140],"proposed":[142],"approach":[143],"improves":[144],"53.8%":[149],"average.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}
