{"id":"https://openalex.org/W2041679393","doi":"https://doi.org/10.1109/hpec.2014.7040988","title":"An investigation of Unified Memory Access performance in CUDA","display_name":"An investigation of Unified Memory Access performance in CUDA","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2041679393","doi":"https://doi.org/10.1109/hpec.2014.7040988","mag":"2041679393","pmid":"https://pubmed.ncbi.nlm.nih.gov/26594668"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2014.7040988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2014.7040988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034944325","display_name":"Raphael Landaverde","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Raphael Landaverde","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","Electrical and Computer Engineering department, Boston University, MA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Electrical and Computer Engineering department, Boston University, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007463921","display_name":"Tiansheng Zhang","orcid":"https://orcid.org/0000-0002-8977-6117"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiansheng Zhang","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","Electrical and Computer Engineering department, Boston University, MA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Electrical and Computer Engineering department, Boston University, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064676631","display_name":"Ayse K. Coskun","orcid":"https://orcid.org/0000-0002-6554-088X"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayse K. Coskun","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","Electrical and Computer Engineering department, Boston University, MA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Electrical and Computer Engineering department, Boston University, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021051610","display_name":"Martin Herbordt","orcid":"https://orcid.org/0000-0002-3443-9113"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Herbordt","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","Electrical and Computer Engineering department, Boston University, MA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Electrical and Computer Engineering department, Boston University, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034944325"],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":null,"apc_paid":null,"fwci":6.9156,"has_fulltext":false,"cited_by_count":109,"citation_normalized_percentile":{"value":0.97239499,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"2014","issue":null,"first_page":"1","last_page":"6"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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":0.8844371438026428},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6908760666847229},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.6471473574638367},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6307983994483948},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5661019086837769},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.5487695932388306},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.5261613726615906},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.47202983498573303},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.41850149631500244},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.31677329540252686},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18708032369613647},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.146656334400177},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.08532604575157166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8844371438026428},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6908760666847229},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.6471473574638367},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6307983994483948},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5661019086837769},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.5487695932388306},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.5261613726615906},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.47202983498573303},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.41850149631500244},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.31677329540252686},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18708032369613647},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.146656334400177},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.08532604575157166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/hpec.2014.7040988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2014.7040988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},{"id":"pmid:26594668","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26594668","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"... IEEE conference on high performance extreme computing. IEEE Conference on High Performance Extreme Computing","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:4652951","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:4652951","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4652951","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Conf High Perform Extreme Comput","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:4652951","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1841716671","https://openalex.org/W1979717209","https://openalex.org/W2080592089","https://openalex.org/W2107583974","https://openalex.org/W2111530316","https://openalex.org/W2150056503","https://openalex.org/W2155503253","https://openalex.org/W2167728712","https://openalex.org/W6638752821","https://openalex.org/W6645075276"],"related_works":["https://openalex.org/W4317827391","https://openalex.org/W2349791858","https://openalex.org/W1839004754","https://openalex.org/W2130211179","https://openalex.org/W254684032","https://openalex.org/W120214571","https://openalex.org/W2160556182","https://openalex.org/W2811273125","https://openalex.org/W1512842870","https://openalex.org/W2186451538"],"abstract_inverted_index":{"Managing":[0],"memory":[1,32,113],"between":[2],"the":[3,29,68,70,108,116,125,128],"CPU":[4],"and":[5,47,51,98,112],"GPU":[6,12,71],"is":[7,72],"a":[8],"major":[9],"challenge":[10],"in":[11],"computing.":[13],"A":[14],"programming":[15,45,52,129],"model,":[16],"Unified":[17],"Memory":[18],"Access":[19],"(UMA),":[20],"has":[21],"been":[22],"recently":[23],"introduced":[24],"by":[25],"Nvidia":[26],"to":[27,67,75,88,127],"simplify":[28],"complexities":[30],"of":[31,78,110],"management":[33],"while":[34,124],"claiming":[35],"good":[36],"overall":[37],"performance.":[38],"In":[39],"this":[40,44],"paper,":[41],"we":[42],"investigate":[43],"model":[46,53,130],"evaluate":[48],"its":[49],"performance":[50,117],"simplifications":[54,126],"based":[55],"on":[56,82],"our":[57],"experimental":[58],"results.":[59],"We":[60,102],"find":[61],"that":[62,106],"beyond":[63],"on-demand":[64],"data":[65,79,91,100],"transfers":[66],"CPU,":[69],"also":[73,103],"able":[74],"request":[76],"subsets":[77],"it":[80],"requires":[81],"demand.":[83],"This":[84],"feature":[85],"allows":[86],"UMA":[87,121],"outperform":[89],"full":[90],"transfer":[92],"methods":[93],"for":[94,107,133],"certain":[95],"parallel":[96],"applications":[97,111],"small":[99],"sizes.":[101],"find,":[104],"however,":[105],"majority":[109],"access":[114],"patterns,":[115],"overheads":[118],"associated":[119],"with":[120],"are":[122],"significant,":[123],"restrict":[131],"flexibility":[132],"adding":[134],"future":[135],"optimizations.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}