{"id":"https://openalex.org/W4381389677","doi":"https://doi.org/10.1145/3589236.3589237","title":"Understanding Scalability of Multi-GPU Systems","display_name":"Understanding Scalability of Multi-GPU Systems","publication_year":2023,"publication_date":"2023-02-25","ids":{"openalex":"https://openalex.org/W4381389677","doi":"https://doi.org/10.1145/3589236.3589237"},"language":"en","primary_location":{"id":"doi:10.1145/3589236.3589237","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589236.3589237","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589236.3589237","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Workshop on General Purpose Processing Using GPU","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589236.3589237","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065152581","display_name":"Yuan Feng","orcid":"https://orcid.org/0009-0004-2451-9568"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuan Feng","raw_affiliation_strings":["University of California Merced, United States"],"raw_orcid":"https://orcid.org/0009-0004-2451-9568","affiliations":[{"raw_affiliation_string":"University of California Merced, United States","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081531196","display_name":"Hyeran Jeon","orcid":"https://orcid.org/0000-0002-1767-8198"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyeran Jeon","raw_affiliation_strings":["University of California Merced, United States"],"raw_orcid":"https://orcid.org/0000-0002-1767-8198","affiliations":[{"raw_affiliation_string":"University of California Merced, United States","institution_ids":["https://openalex.org/I156087764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065152581"],"corresponding_institution_ids":["https://openalex.org/I156087764"],"apc_list":null,"apc_paid":null,"fwci":1.197,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76318196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"37"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994000196456909,"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/scalability","display_name":"Scalability","score":0.8817378878593445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8809198141098022},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6154171824455261},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6137715578079224},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.41777849197387695},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.39803028106689453},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1828252673149109}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8817378878593445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8809198141098022},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6154171824455261},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6137715578079224},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.41777849197387695},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39803028106689453},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1828252673149109},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589236.3589237","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589236.3589237","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589236.3589237","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Workshop on General Purpose Processing Using GPU","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3589236.3589237","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589236.3589237","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589236.3589237","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Workshop on General Purpose Processing Using GPU","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8283683674","display_name":null,"funder_award_id":"CCF-2114514","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8535895009","display_name":"Collaborative Research: SHF: Small: Towards Robust Deep Learning Computing on GPUs","funder_award_id":"2114514","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381389677.pdf"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2625200202","https://openalex.org/W2952928793","https://openalex.org/W4320063633"],"related_works":["https://openalex.org/W1982914007","https://openalex.org/W3212136884","https://openalex.org/W2159583675","https://openalex.org/W1852113167","https://openalex.org/W1824242903","https://openalex.org/W2103851758","https://openalex.org/W2155470929","https://openalex.org/W1493858311","https://openalex.org/W2111125783","https://openalex.org/W2159682405"],"abstract_inverted_index":{"Multi-GPU":[0],"systems":[1,51],"are":[2,52],"considered":[3],"as":[4],"one":[5,72],"of":[6,44,73],"the":[7,42,66,74],"most":[8],"promising":[9],"scalable":[10],"accelerator":[11],"systems.":[12],"There":[13],"have":[14],"been":[15],"several":[16],"studies":[17],"that":[18,49,77],"tackled":[19],"communication":[20],"and":[21],"scheduling":[22],"efficiencies":[23],"with":[24,30],"a":[25],"small-scale":[26],"multi-GPU":[27,50],"system":[28],"(mostly":[29],"four":[31],"GPU":[32],"modules).":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"examine":[38],"scalability":[39],"by":[40],"increasing":[41],"number":[43],"GPUs.":[45],"Our":[46],"observations":[47],"show":[48],"yet":[53],"to":[54,59],"be":[55],"scalable,":[56],"mainly":[57],"due":[58],"Non-Uniform":[60],"Memory":[61],"Access":[62],"(NUMA)":[63],"effects;":[64],"furthermore,":[65],"state-of-the-art":[67],"aggressive":[68],"page":[69],"distribution":[70],"is":[71],"main":[75],"reasons":[76],"increase":[78],"slow":[79],"remote":[80],"accesses.":[81]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}