{"id":"https://openalex.org/W4206550664","doi":"https://doi.org/10.1109/ipccc51483.2021.9679359","title":"A Simulation Study of Hardware Parameters for Future GPU-based HPC Platforms","display_name":"A Simulation Study of Hardware Parameters for Future GPU-based HPC Platforms","publication_year":2021,"publication_date":"2021-10-29","ids":{"openalex":"https://openalex.org/W4206550664","doi":"https://doi.org/10.1109/ipccc51483.2021.9679359"},"language":"en","primary_location":{"id":"doi:10.1109/ipccc51483.2021.9679359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc51483.2021.9679359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Performance, Computing, and Communications Conference (IPCCC)","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/A5082758781","display_name":"Saptarshi Bhowmik","orcid":"https://orcid.org/0009-0002-1079-4513"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saptarshi Bhowmik","raw_affiliation_strings":["Florida State University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida State University,Department of Computer Science","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025115023","display_name":"Nikhil Jain","orcid":"https://orcid.org/0009-0002-1555-9125"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"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":["GB","US"],"is_corresponding":false,"raw_author_name":"Nikhil Jain","raw_affiliation_strings":["Nvidia, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia, Inc","institution_ids":["https://openalex.org/I4210127875","https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049765501","display_name":"Xin Yuan","orcid":"https://orcid.org/0000-0002-9167-1613"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Yuan","raw_affiliation_strings":["Florida State University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida State University,Department of Computer Science","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081506338","display_name":"Abhinav Bhatel\u00e9","orcid":"https://orcid.org/0000-0003-3069-3701"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Bhatele","raw_affiliation_strings":["University of Maryland,Department of Computer Science,College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,Department of Computer Science,College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3207,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6387152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"22","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9998999834060669,"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/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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9988999962806702,"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":0.8223992586135864},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5855194330215454},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.5360475182533264},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5094178318977356},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.429882287979126},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.41715067625045776},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4072878360748291},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.37151020765304565},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.33887022733688354},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32721802592277527},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.244637131690979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223992586135864},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5855194330215454},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.5360475182533264},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5094178318977356},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.429882287979126},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.41715067625045776},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4072878360748291},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.37151020765304565},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.33887022733688354},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32721802592277527},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.244637131690979},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipccc51483.2021.9679359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc51483.2021.9679359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Performance, Computing, and Communications Conference (IPCCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1545880915","https://openalex.org/W2029407480","https://openalex.org/W2042876290","https://openalex.org/W2088219312","https://openalex.org/W2157187369","https://openalex.org/W2401404692","https://openalex.org/W2407167622","https://openalex.org/W2767749225","https://openalex.org/W2892205742","https://openalex.org/W2897422459","https://openalex.org/W2947543664","https://openalex.org/W2987265314","https://openalex.org/W3040605665","https://openalex.org/W3147460469","https://openalex.org/W3173524475","https://openalex.org/W4244682390","https://openalex.org/W4250981202","https://openalex.org/W6712712196","https://openalex.org/W6746105287"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2384867379","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4400094300","https://openalex.org/W4245975140","https://openalex.org/W2329539859","https://openalex.org/W2532592438","https://openalex.org/W1977763331"],"abstract_inverted_index":{"Compute":[0],"nodes":[1,29],"on":[2,80,89],"high":[3],"performance":[4,82],"computing":[5],"(HPC)":[6],"platforms":[7],"are":[8],"increasingly":[9],"equipped":[10],"with":[11],"multiple":[12],"GPUs.":[13],"This":[14,35],"results":[15],"in":[16,24,32,43,112],"increased":[17],"computational":[18],"capacity":[19],"per":[20,98],"node,":[21,99],"and":[22,40,71,104,122],"reduction":[23],"the":[25,33,38,64,73,81,113],"total":[26],"number":[27,95],"of":[28,55,69,75,83,96,115],"or":[30],"endpoints":[31],"system.":[34],"trend":[36],"changes":[37],"computation":[39],"communication":[41],"balance":[42],"comparison":[44],"to":[45],"pre-GPU":[46],"era":[47],"HPC":[48,85],"platforms,":[49],"which":[50],"warrants":[51],"a":[52],"new":[53],"study":[54,72],"hardware":[56,77,92],"architectural":[57],"parameters.":[58],"In":[59],"this":[60],"work,":[61],"we":[62],"leverage":[63],"end-to-end":[65],"system":[66],"simulation":[67],"capabilities":[68],"TraceR-CODES":[70],"impact":[74],"several":[76],"design":[78],"parameters":[79],"realistic":[84],"workloads.":[86],"We":[87],"focus":[88],"three":[90],"crucial":[91],"parameters:":[93],"(1)":[94],"GPUs":[97],"(2)":[100],"network":[101,106,118],"link":[102],"bandwidth,":[103],"(3)":[105],"interface":[107],"controller":[108],"(NIC)":[109],"scheduling":[110],"policies,":[111],"context":[114],"two":[116],"popular":[117],"topologies":[119],"\u2013":[120],"fat-tree":[121],"dragonfly.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}