{"id":"https://openalex.org/W3094223918","doi":"https://doi.org/10.1109/hpec49654.2021.9622742","title":"Modeling Data Movement Performance on Heterogeneous Architectures","display_name":"Modeling Data Movement Performance on Heterogeneous Architectures","publication_year":2021,"publication_date":"2021-09-20","ids":{"openalex":"https://openalex.org/W3094223918","doi":"https://doi.org/10.1109/hpec49654.2021.9622742","mag":"3094223918"},"language":"en","primary_location":{"id":"doi:10.1109/hpec49654.2021.9622742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1846269","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075734006","display_name":"Amanda Bienz","orcid":"https://orcid.org/0000-0002-8891-934X"},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amanda Bienz","raw_affiliation_strings":["University of New Mexico, Albuquerque, USA"],"affiliations":[{"raw_affiliation_string":"University of New Mexico, Albuquerque, USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027808971","display_name":"Luke N. Olson","orcid":"https://orcid.org/0000-0002-5283-6104"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luke N. Olson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017241944","display_name":"William Gropp","orcid":"https://orcid.org/0000-0003-2905-3029"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William D. Gropp","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080648979","display_name":"Shelby Lockhart","orcid":"https://orcid.org/0000-0003-4938-6111"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shelby Lockhart","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5075734006"],"corresponding_institution_ids":["https://openalex.org/I169521973"],"apc_list":null,"apc_paid":null,"fwci":1.4148,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.79153893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.8455103039741516},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6246345639228821},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5845375061035156},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5313224196434021},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49540412425994873},{"id":"https://openalex.org/keywords/copying","display_name":"Copying","score":0.49531927704811096},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.41000980138778687},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.342507541179657}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8455103039741516},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6246345639228821},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5845375061035156},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5313224196434021},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49540412425994873},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.49531927704811096},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.41000980138778687},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.342507541179657},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpec49654.2021.9622742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1846269","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1846269","pdf_url":"https://www.osti.gov/servlets/purl/1846269","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1846269","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1846269","pdf_url":"https://www.osti.gov/servlets/purl/1846269","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G3382749912","display_name":null,"funder_award_id":"DE-NA0003966","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8541042884","display_name":null,"funder_award_id":"DE-NA0002374","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3094223918.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1964981582","https://openalex.org/W1974299554","https://openalex.org/W1992299697","https://openalex.org/W2041351581","https://openalex.org/W2070468128","https://openalex.org/W2102061396","https://openalex.org/W2136214128","https://openalex.org/W2535045667","https://openalex.org/W2805739788","https://openalex.org/W2902041647","https://openalex.org/W2932898043","https://openalex.org/W2995761656","https://openalex.org/W2998841280","https://openalex.org/W3034899595","https://openalex.org/W4251681643"],"related_works":["https://openalex.org/W2588206991","https://openalex.org/W4308771405","https://openalex.org/W2355873265","https://openalex.org/W2963669501","https://openalex.org/W3080197661","https://openalex.org/W4318471783","https://openalex.org/W2760667490","https://openalex.org/W2991781269","https://openalex.org/W775724729","https://openalex.org/W2527790800"],"abstract_inverted_index":{"The":[0],"cost":[1,24],"of":[2,25,54,71],"data":[3,26,47],"movement":[4,27,48],"on":[5,74,98],"parallel":[6],"systems":[7],"varies":[8],"greatly":[9],"with":[10],"machine":[11],"architecture,":[12],"job":[13],"partition,":[14],"and":[15,84],"nearby":[16],"jobs.":[17],"Performance":[18],"models":[19,66],"that":[20],"accurately":[21],"capture":[22],"the":[23,68,79],"provide":[28],"a":[29,52,91],"tool":[30],"for":[31,34,57,67,94,114],"analysis,":[32],"allowing":[33],"communication":[35,73,83,96],"bottlenecks":[36],"to":[37,86],"be":[38],"pinpointed.":[39],"Modern":[40],"heterogeneous":[41,76],"architectures":[42],"yield":[43],"increased":[44],"variance":[45],"in":[46],"as":[49],"there":[50],"are":[51],"number":[53],"viable":[55],"paths":[56,70],"inter-GPU":[58],"communication.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,89,109],"present":[64,90],"performance":[65,112],"various":[69],"inter-node":[72,95],"modern":[75],"architectures,":[77],"including":[78],"trade-off":[80],"between":[81],"GPUDirect":[82],"copying":[85],"CPUs.":[87],"Furthermore,":[88],"novel":[92],"optimization":[93],"based":[97],"these":[99],"models,":[100],"utilizing":[101],"all":[102],"available":[103],"CPU":[104],"cores":[105],"per":[106],"node.":[107],"Finally,":[108],"show":[110],"associated":[111],"improvements":[113],"MPI":[115],"collective":[116],"operations.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
