{"id":"https://openalex.org/W2998062016","doi":"https://doi.org/10.1109/mchpc49590.2019.00014","title":"Performance Evaluation of Advanced Features in CUDA Unified Memory","display_name":"Performance Evaluation of Advanced Features in CUDA Unified Memory","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2998062016","doi":"https://doi.org/10.1109/mchpc49590.2019.00014","mag":"2998062016"},"language":"en","primary_location":{"id":"doi:10.1109/mchpc49590.2019.00014","doi":"https://doi.org/10.1109/mchpc49590.2019.00014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mchpc49590.2019.00014","pdf_url":null,"source":{"id":"https://openalex.org/S7407107811","display_name":"IEEE/ACM Workshop on Memory Centric High Performance Computing (MCHPC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM Workshop on Memory Centric High Performance Computing (MCHPC)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.09598","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109478420","display_name":"Steven W. D. Chien","orcid":"https://orcid.org/0000-0001-6408-3333","observed_orcids":["https://orcid.org/0000-0001-6408-3333"]},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Steven Chien","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037069204","display_name":"Ivy Bo Peng","orcid":"https://orcid.org/0000-0003-4158-3583","observed_orcids":["https://orcid.org/0000-0003-4158-3583"]},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivy Peng","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085178088","display_name":"Stefano Markidis","orcid":"https://orcid.org/0000-0003-0639-0639","observed_orcids":["https://orcid.org/0000-0003-0639-0639"]},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Stefano Markidis","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9536,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.92591248,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.0,"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/nvlink","display_name":"NVLink","score":0.6269999742507935},{"id":"https://openalex.org/keywords/benchmark-suite","display_name":"benchmark suite","score":0.5270000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993999719619751},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6164000034332275},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5701000094413757},{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.5342000126838684},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49320000410079956},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.4896000027656555},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.45559999346733093},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38909998536109924},{"id":"https://openalex.org/C171675096","wikidata":"https://www.wikidata.org/wiki/Q1143380","display_name":"Extended memory","level":4,"score":0.37299999594688416},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.37049999833106995},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.3395000100135803},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.33880001306533813},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C39528615","wikidata":"https://www.wikidata.org/wiki/Q1229610","display_name":"Distributed shared memory","level":5,"score":0.31220000982284546},{"id":"https://openalex.org/C74426580","wikidata":"https://www.wikidata.org/wiki/Q719484","display_name":"Memory map","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C123593499","wikidata":"https://www.wikidata.org/wiki/Q6008583","display_name":"In-Memory Processing","level":5,"score":0.3025999963283539},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.290800005197525},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C93446704","wikidata":"https://www.wikidata.org/wiki/Q449328","display_name":"Registered memory","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/mchpc49590.2019.00014","doi":"https://doi.org/10.1109/mchpc49590.2019.00014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mchpc49590.2019.00014","pdf_url":null,"source":{"id":"https://openalex.org/S7407107811","display_name":"IEEE/ACM Workshop on Memory Centric High Performance Computing (MCHPC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM Workshop on Memory Centric High Performance Computing (MCHPC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.09598","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09598","pdf_url":"https://arxiv.org/pdf/1910.09598","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1910.09598","doi":"https://doi.org/10.48550/arxiv.1910.09598","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.09598","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.09598","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09598","pdf_url":"https://arxiv.org/pdf/1910.09598","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1541729506","https://openalex.org/W2506485539","https://openalex.org/W2521614036","https://openalex.org/W2767028519","https://openalex.org/W2791673912","https://openalex.org/W2903901007","https://openalex.org/W2913640523","https://openalex.org/W2930869794","https://openalex.org/W2934021599","https://openalex.org/W2949486320"],"related_works":["https://openalex.org/W2969925465","https://openalex.org/W3186076368","https://openalex.org/W2600365670","https://openalex.org/W2985308940","https://openalex.org/W4289656775","https://openalex.org/W4287323594","https://openalex.org/W7137738422","https://openalex.org/W2041679393","https://openalex.org/W7222231104","https://openalex.org/W3043528907"],"abstract_inverted_index":{"CUDA":[0,106,152],"Unified":[1,107],"Memory":[2],"improves":[3,164],"the":[4,32,51,55,72,104,111,160,171,179],"GPU":[5,11,85,131,142],"pro-":[6],"grammability":[7],"and":[8,21,43,53,62,145],"also":[9,154],"enables":[10],"memory":[12,17,19,56,69,86,93,118,132,139],"oversubscription.":[13],"Recently,":[14],"two":[15,36,161],"advanced":[16],"features,":[18],"advises":[20,70,94,140],"asynchronous":[22],"prefetch,":[23],"have":[24],"been":[25],"introduced.":[26],"In":[27,109],"this":[28,136],"work,":[29],"we":[30],"evaluate":[31,59],"new":[33],"features":[34],"on":[35,71,135,159,170],"platforms":[37],"that":[38,68],"feature":[39],"different":[40,156],"CPUs,":[41],"GPUs,":[42],"interconnects.":[44],"We":[45],"derive":[46],"a":[47],"benchmark":[48],"suite":[49],"for":[50,79,126],"experiments":[52],"stress":[54],"system":[57],"to":[58,98,103,122,168,178],"both":[60],"in-memory":[61,80,127],"oversubscription":[63],"performance.":[64],"The":[65,151],"results":[66,95,146],"show":[67],"Intel-Volta/Pascal-":[73],"PCIe":[74],"platform":[75,113,173],"bring":[76],"negligible":[77],"improvement":[78,101],"exe-":[81],"cutions.":[82],"However,":[83,129],"when":[84,130],"is":[87,133],"oversubscribed":[88,134],"by":[89,166],"about":[90],"50%,":[91],"using":[92,138],"in":[96,147],"up":[97,121,167],"25%":[99],"performance":[100,124,149,157,165],"compared":[102],"basic":[105],"Memory.":[108],"contrast,":[110],"Power9-Volta-NVLink":[112,180],"can":[114],"substantially":[115],"benefit":[116,177],"from":[117],"advises,":[119],"achieving":[120],"34%":[123],"gain":[125],"executions.":[128],"platform,":[137],"increases":[141],"page":[143],"faults":[144],"considerable":[148],"loss.":[150],"prefetch":[153],"shows":[155],"impact":[158],"platforms.":[162],"It":[163],"50%":[169],"Intel-Volta/Pascal-PCI-E":[172],"but":[174],"brings":[175],"little":[176],"platform.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2020-01-10T00:00:00"}