{"id":"https://openalex.org/W3174859758","doi":"https://doi.org/10.1145/3431379.3460651","title":"Scalable All-pairs Shortest Paths for Huge Graphs on Multi-GPU Clusters","display_name":"Scalable All-pairs Shortest Paths for Huge Graphs on Multi-GPU Clusters","publication_year":2021,"publication_date":"2021-06-17","ids":{"openalex":"https://openalex.org/W3174859758","doi":"https://doi.org/10.1145/3431379.3460651","mag":"3174859758"},"language":"en","primary_location":{"id":"doi:10.1145/3431379.3460651","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3431379.3460651","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3431379.3460651","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th International Symposium on High-Performance Parallel and Distributed Computing","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/10.1145/3431379.3460651","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048170299","display_name":"Piyush Sao","orcid":"https://orcid.org/0000-0002-9432-5855"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"piyush sao","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058248684","display_name":"Hao Lu","orcid":"https://orcid.org/0000-0001-8941-870X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao lu","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014168997","display_name":"Ramakrishnan Kannan","orcid":"https://orcid.org/0000-0002-5852-4806"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramakrishnan Kannan","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086615721","display_name":"Vijay Thakkar","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Thakkar","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016738770","display_name":"Richard Vuduc","orcid":"https://orcid.org/0000-0003-2178-138X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Vuduc","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000241304","display_name":"Thomas E. Potok","orcid":"https://orcid.org/0000-0001-6687-3435"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Potok","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048170299"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.2913,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.55104283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11478","display_name":"Caching and Content Delivery","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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8878579139709473},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7897636890411377},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6803995370864868},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4884859323501587},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.4660675823688507},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4508329927921295},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.443193256855011},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4389103651046753},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4354492425918579},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14543160796165466},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11944502592086792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8878579139709473},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7897636890411377},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6803995370864868},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4884859323501587},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.4660675823688507},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4508329927921295},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.443193256855011},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4389103651046753},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4354492425918579},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14543160796165466},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11944502592086792},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3431379.3460651","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3431379.3460651","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3431379.3460651","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3431379.3460651","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3431379.3460651","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3431379.3460651","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1489425746","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1719536385","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2296932962","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3299391273","display_name":null,"funder_award_id":"E-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4370606643","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G4694431782","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4865274590","display_name":null,"funder_award_id":"1710371","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6488227018","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G6495930337","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G691578896","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8414908677","display_name":null,"funder_award_id":"DE-AC0","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8799952057","display_name":null,"funder_award_id":"DE-AC05-00OR22","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8812230059","display_name":null,"funder_award_id":"1533768","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G895001607","display_name":null,"funder_award_id":"Grant","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"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3174859758.pdf","grobid_xml":"https://content.openalex.org/works/W3174859758.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W26556108","https://openalex.org/W54170965","https://openalex.org/W127166643","https://openalex.org/W625657276","https://openalex.org/W1039385342","https://openalex.org/W1539063269","https://openalex.org/W1566326249","https://openalex.org/W1572663059","https://openalex.org/W1587659039","https://openalex.org/W1999545213","https://openalex.org/W2014211132","https://openalex.org/W2022980325","https://openalex.org/W2024960454","https://openalex.org/W2044953540","https://openalex.org/W2057112598","https://openalex.org/W2060072995","https://openalex.org/W2071974437","https://openalex.org/W2073428179","https://openalex.org/W2084224084","https://openalex.org/W2084803275","https://openalex.org/W2107651134","https://openalex.org/W2117946984","https://openalex.org/W2141380216","https://openalex.org/W2162322364","https://openalex.org/W2169528473","https://openalex.org/W2170611190","https://openalex.org/W2170996201","https://openalex.org/W2227557434","https://openalex.org/W2403822450","https://openalex.org/W2461193710","https://openalex.org/W2494652507","https://openalex.org/W2572767837","https://openalex.org/W2889082215","https://openalex.org/W2898839814","https://openalex.org/W2942021433","https://openalex.org/W2965423625","https://openalex.org/W3000173590","https://openalex.org/W3013163801","https://openalex.org/W3098650335","https://openalex.org/W3129367612","https://openalex.org/W4205868507","https://openalex.org/W4246466944","https://openalex.org/W4285719527","https://openalex.org/W6638753708","https://openalex.org/W6661713193","https://openalex.org/W6764615779"],"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":{"We":[0],"present":[1],"an":[2,95],"optimized":[3,123],"Floyd-Warshall":[4,19,125],"(Floyd-Warshall)":[5],"algorithm":[6,20,165],"that":[7],"computes":[8],"the":[9,63,99,103,143,156],"All-pairs":[10],"shortest":[11],"path":[12],"(APSP)":[13],"for":[14,31,120],"GPU":[15,34,54,91,109],"accelerated":[16],"clusters.":[17],"The":[18,111,163],"due":[21],"to":[22,26,66,108,129],"its":[23],"structural":[24],"similarities":[25],"matrix-multiplication":[27],"is":[28,106,127],"well":[29],"suited":[30],"highly":[32],"parallel":[33,39,64,124,161],"architectures.":[35],"To":[36,56,87],"achieve":[37],"high":[38,48,58],"efficiency,":[40],"we":[41,61,93],"address":[42],"two":[43],"key":[44],"algorithmic":[45],"challenges:":[46],"reducing":[47],"communication":[49,59,73],"overhead":[50],"and":[51,74,78,83,105,136,159],"addressing":[52],"limited":[53,90],"memory.":[55],"reduce":[57],"costs,":[60],"redesign":[62],"(a)":[65],"expose":[67],"more":[68],"parallelism,":[69],"(b)":[70],"aggressively":[71],"overlap":[72],"computation":[75],"with":[76,89,116,171],"pipelined":[77],"asynchronous":[79],"scheduling":[80],"of":[81,142,155],"operations,":[82],"(c)":[84],"tailored":[85],"MPI-collective.":[86],"cope":[88],"memory,":[92],"employ":[94],"offload":[96,164],"model,":[97],"where":[98],"data":[100],"resides":[101],"on":[102,140],"host":[104],"transferred":[107],"on-demand.":[110],"proposed":[112],"optimizations":[113],"are":[114],"supported":[115],"detailed":[117],"performance":[118,152],"models":[119],"tuning.":[121],"Our":[122],"implementation":[126],"up":[128],"5x":[130],"faster":[131],"than":[132],"a":[133,172],"strong":[134],"baseline":[135],"achieves":[137],"8.1":[138],"PetaFLOPS/sec":[139],"256~nodes":[141],"Summit":[144],"supercomputer":[145],"at":[146],"Oak":[147],"Ridge":[148],"National":[149],"Laboratory.":[150],"This":[151],"represents":[153],"70%":[154],"theoretical":[157],"peak":[158],"80%":[160],"efficiency.":[162],"can":[166],"handle":[167],"2.5x":[168],"larger":[169],"graphs":[170],"20%":[173],"increase":[174],"in":[175],"overall":[176],"running":[177],"time.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}