{"id":"https://openalex.org/W3089681336","doi":"https://doi.org/10.1145/3410463.3414639","title":"Valkyrie","display_name":"Valkyrie","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3089681336","doi":"https://doi.org/10.1145/3410463.3414639","mag":"3089681336"},"language":"en","primary_location":{"id":"doi:10.1145/3410463.3414639","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3410463.3414639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques","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/A5000058073","display_name":"Trinayan Baruah","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Trinayan Baruah","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041025969","display_name":"Yifan Sun","orcid":"https://orcid.org/0000-0003-3532-6521"},"institutions":[{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]},{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"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":"Yifan Sun","raw_affiliation_strings":["Northeastern University and William & Mary, Williamsburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University and William & Mary, Williamsburg, VA, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I12912129","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072286447","display_name":"Saiful A. Mojumder","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saiful A. Mojumder","raw_affiliation_strings":["Boston University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Boston University, Boston, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007832959","display_name":"Jos\u00e9 Luis Abell\u00e1n","orcid":"https://orcid.org/0000-0003-3550-720X"},"institutions":[{"id":"https://openalex.org/I68763199","display_name":"Universidad Cat\u00f3lica San Antonio de Murcia","ror":"https://ror.org/05b1rsv17","country_code":"ES","type":"education","lineage":["https://openalex.org/I68763199"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 L. Abell\u00e1n","raw_affiliation_strings":["Universidad Cat\u00f3lica San Antonio de Murcia, Murcia, Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Cat\u00f3lica San Antonio de Murcia, Murcia, Spain","institution_ids":["https://openalex.org/I68763199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019687323","display_name":"Yash Ukidave","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147799","display_name":"Millennium Engineering and Integration (United States)","ror":"https://ror.org/05qmdfk04","country_code":"US","type":"company","lineage":["https://openalex.org/I4210147799"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yash Ukidave","raw_affiliation_strings":["Millennium USA, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Millennium USA, Boston, MA, USA","institution_ids":["https://openalex.org/I4210147799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089428659","display_name":"Ajay Joshi","orcid":"https://orcid.org/0000-0002-3256-9942"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ajay Joshi","raw_affiliation_strings":["Boston University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Boston University, Boston, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036463155","display_name":"Norman Rubin","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Norman Rubin","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100698124","display_name":"John Kim","orcid":"https://orcid.org/0000-0003-3958-3891"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"John Kim","raw_affiliation_strings":["KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061128237","display_name":"David Kaeli","orcid":"https://orcid.org/0000-0002-5692-0151"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kaeli","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5000058073"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":3.0405,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.91732955,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"455","last_page":"466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9987000226974487,"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":0.9861805438995361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8707011342048645},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7008916139602661},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6329457759857178},{"id":"https://openalex.org/keywords/pointer","display_name":"Pointer (user interface)","score":0.5059205889701843},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4988405704498291},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4465552866458893},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.4454006850719452},{"id":"https://openalex.org/keywords/virtual-memory","display_name":"Virtual memory","score":0.4452963173389435},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4142428934574127},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.336224228143692},{"id":"https://openalex.org/keywords/physical-address","display_name":"Physical address","score":0.17646583914756775},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.15851867198944092}],"concepts":[{"id":"https://openalex.org/C116007543","wikidata":"https://www.wikidata.org/wiki/Q1071403","display_name":"Translation lookaside buffer","level":4,"score":0.9861805438995361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8707011342048645},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7008916139602661},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6329457759857178},{"id":"https://openalex.org/C150202949","wikidata":"https://www.wikidata.org/wiki/Q107602","display_name":"Pointer (user interface)","level":2,"score":0.5059205889701843},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4988405704498291},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4465552866458893},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.4454006850719452},{"id":"https://openalex.org/C76399640","wikidata":"https://www.wikidata.org/wiki/Q189401","display_name":"Virtual memory","level":4,"score":0.4452963173389435},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4142428934574127},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.336224228143692},{"id":"https://openalex.org/C41036726","wikidata":"https://www.wikidata.org/wiki/Q844824","display_name":"Physical address","level":3,"score":0.17646583914756775},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.15851867198944092},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"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/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3410463.3414639","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3410463.3414639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307757","display_name":"Advanced Micro Devices","ror":"https://ror.org/04kd6c783"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1573897044","https://openalex.org/W1978187377","https://openalex.org/W1997352364","https://openalex.org/W2004807638","https://openalex.org/W2028173051","https://openalex.org/W2048621586","https://openalex.org/W2051815842","https://openalex.org/W2062430565","https://openalex.org/W2082000934","https://openalex.org/W2106404421","https://openalex.org/W2110815624","https://openalex.org/W2120138088","https://openalex.org/W2130820665","https://openalex.org/W2133584134","https://openalex.org/W2149234156","https://openalex.org/W2153806645","https://openalex.org/W2155893237","https://openalex.org/W2169150396","https://openalex.org/W2171721604","https://openalex.org/W2330672121","https://openalex.org/W2416722775","https://openalex.org/W2528784626","https://openalex.org/W2566040696","https://openalex.org/W2581371485","https://openalex.org/W2621048050","https://openalex.org/W2760957981","https://openalex.org/W2764065518","https://openalex.org/W2793655593","https://openalex.org/W2885000039","https://openalex.org/W2903659818","https://openalex.org/W2904412652","https://openalex.org/W2920870926","https://openalex.org/W2934021599","https://openalex.org/W2949486320","https://openalex.org/W2952928793","https://openalex.org/W2963688890","https://openalex.org/W2980066681","https://openalex.org/W3005429556","https://openalex.org/W3022971582","https://openalex.org/W4232854706","https://openalex.org/W4246379307","https://openalex.org/W4255807648"],"related_works":["https://openalex.org/W4248908839","https://openalex.org/W2501386197","https://openalex.org/W3196094483","https://openalex.org/W2116578804","https://openalex.org/W1520879682","https://openalex.org/W2355566153","https://openalex.org/W2381395788","https://openalex.org/W2238595726","https://openalex.org/W2967987264","https://openalex.org/W4244002525"],"abstract_inverted_index":{"Programming":[0],"on":[1,31,61],"a":[2,32,54,62,80,115,126,131,182],"GPU":[3,33,63,84,154,186],"has":[4],"been":[5],"made":[6],"considerably":[7],"easier":[8],"with":[9,35,41],"the":[10,22,25,42,46,66,75,122,149],"introduction":[11],"of":[12,57,74,83,111,118,125,185,198],"Virtual":[13],"Memory":[14],"features,":[15],"which":[16,97],"support":[17,47,148],"common":[18],"pointer-based":[19],"semantics":[20],"between":[21],"CPU":[23],"and":[24,39,165],"GPU.":[26,127],"However,":[27],"supporting":[28],"virtual":[29],"memory":[30,144],"comes":[34],"some":[36],"additional":[37],"costs":[38],"overhead,":[40],"largest":[43],"being":[44],"from":[45],"for":[48],"address":[49],"translation.":[50],"The":[51],"fact":[52],"that":[53,65,87,171,189],"massive":[55],"number":[56],"threads":[58],"run":[59],"concurrently":[60],"means":[64],"translation":[67],"lookaside":[68],"buffers":[69],"(TLBs)":[70],"are":[71],"oversubscribed":[72],"most":[73],"time.":[76],"Our":[77,109,179],"investigation":[78],"into":[79],"diverse":[81,183],"set":[82,184],"workloads":[85,113,187],"shows":[86],"TLB":[88,162,175],"misses":[89],"can":[90,133,172],"be":[91,134],"extremely":[92],"high":[93,116],"(up":[94],"to":[95,100,105,193],"99%),":[96],"inevitably":[98],"leads":[99],"significant":[101],"performance":[102],"degradation":[103],"due":[104],"long-latency":[106],"page-table":[107],"walks.":[108],"profiling":[110],"TLB-sensitive":[112],"reveals":[114,188],"degree":[117],"page":[119,132],"sharing":[120,151],"across":[121],"different":[123],"cores":[124],"In":[128],"many":[129],"applications,":[130],"accessed":[135],"in":[136,153,177],"temporal":[137],"proximity":[138],"by":[139],"multiple":[140],"cores,":[141],"following":[142],"similar":[143],"access":[145],"patterns.":[146],"To":[147],"inherent":[150],"present":[152],"workloads,":[155],"we":[156],"propose":[157],"Valkyrie,":[158],"an":[159,166,195],"integrated":[160],"cooperative":[161],"prefetching":[163],"mechanism":[164],"inter":[167],"L1-TLB":[168],"probing":[169],"scheme":[170],"efficiently":[173],"reduce":[174],"bottlenecks":[176],"GPUs.":[178],"evaluation":[180],"using":[181],"Valkyrie":[190],"is":[191],"able":[192],"achieve":[194],"average":[196],"speedup":[197],"1.95x,":[199],"while":[200],"adding":[201],"modest":[202],"hardware":[203],"overhead.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2020-10-08T00:00:00"}