{"id":"https://openalex.org/W4391053262","doi":"https://doi.org/10.1145/3635035.3635047","title":"Bruck Algorithm Performance Analysis for Multi-GPU All-to-All Communication","display_name":"Bruck Algorithm Performance Analysis for Multi-GPU All-to-All Communication","publication_year":2024,"publication_date":"2024-01-18","ids":{"openalex":"https://openalex.org/W4391053262","doi":"https://doi.org/10.1145/3635035.3635047"},"language":"en","primary_location":{"id":"doi:10.1145/3635035.3635047","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3635035.3635047","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3635035.3635047","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 International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3635035.3635047","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093752389","display_name":"Andres Sewell","orcid":"https://orcid.org/0009-0004-3262-8588"},"institutions":[{"id":"https://openalex.org/I121980950","display_name":"Utah State University","ror":"https://ror.org/00h6set76","country_code":"US","type":"education","lineage":["https://openalex.org/I121980950"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andres Sewell","raw_affiliation_strings":["Utah State University, United States of America"],"raw_orcid":"https://orcid.org/0009-0004-3262-8588","affiliations":[{"raw_affiliation_string":"Utah State University, United States of America","institution_ids":["https://openalex.org/I121980950"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086407525","display_name":"Ke Fan","orcid":"https://orcid.org/0000-0002-9563-6129"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Fan","raw_affiliation_strings":["University of Illinois Chicago, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-9563-6129","affiliations":[{"raw_affiliation_string":"University of Illinois Chicago, United States of America","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016472841","display_name":"Ahmedur Rahman Shovon","orcid":"https://orcid.org/0000-0002-5718-4977"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmedur Rahman Shovon","raw_affiliation_strings":["University of Illinois Chicago, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-5718-4977","affiliations":[{"raw_affiliation_string":"University of Illinois Chicago, United States of America","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029794508","display_name":"Landon Dyken","orcid":"https://orcid.org/0009-0008-9546-6685"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Landon Dyken","raw_affiliation_strings":["University of Illinois Chicago, United States of America"],"raw_orcid":"https://orcid.org/0009-0008-9546-6685","affiliations":[{"raw_affiliation_string":"University of Illinois Chicago, United States of America","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101815397","display_name":"Sidharth Kumar","orcid":"https://orcid.org/0009-0007-0418-9962"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sidharth Kumar","raw_affiliation_strings":["University of Illinois Chicago, United States of America"],"raw_orcid":"https://orcid.org/0009-0007-0418-9962","affiliations":[{"raw_affiliation_string":"University of Illinois Chicago, United States of America","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002575061","display_name":"Steve Petruzza","orcid":"https://orcid.org/0000-0002-2649-1595"},"institutions":[{"id":"https://openalex.org/I121980950","display_name":"Utah State University","ror":"https://ror.org/00h6set76","country_code":"US","type":"education","lineage":["https://openalex.org/I121980950"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steve Petruzza","raw_affiliation_strings":["Utah State University, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-2649-1595","affiliations":[{"raw_affiliation_string":"Utah State University, United States of America","institution_ids":["https://openalex.org/I121980950"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.4107,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.9787058,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987000226974487,"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":0.8489564061164856},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.7815256118774414},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7125934362411499},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5480991005897522},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.506531834602356},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36506420373916626},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3268645703792572},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.14731016755104065},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10958436131477356},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.10109663009643555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8489564061164856},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.7815256118774414},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7125934362411499},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5480991005897522},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.506531834602356},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36506420373916626},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3268645703792572},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.14731016755104065},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10958436131477356},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.10109663009643555}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3635035.3635047","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3635035.3635047","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3635035.3635047","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 International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/26170144","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Bruck_Algorithm_Performance_Analysis_for_Multi-GPU_All-to-All_Communication/26170144","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},{"id":"doi:10.25417/uic.26170144.v1","is_oa":true,"landing_page_url":"https://doi.org/10.25417/uic.26170144.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407051395","display_name":"University of Illinois Chicago","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Other"}],"best_oa_location":{"id":"doi:10.1145/3635035.3635047","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3635035.3635047","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3635035.3635047","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 International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2921966072","display_name":"Collaborative Research: SHF: Small: Scalable and Extensible I/O Runtime and Tools for Next Generation Adaptive Data Layouts","funder_award_id":"2221812","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G348894000","display_name":"RII Track-4:NSF: Relational Algebra on Heterogeneous Extreme-scale Systems","funder_award_id":"2132013","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G363018860","display_name":null,"funder_award_id":"2132013, 2221811, 2221812, 2217036, 2316157","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G3698157498","display_name":"Collaborative Research: PPoSS: Large: A Full-stack Approach to Declarative Analytics at Scale","funder_award_id":"2316157","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4733759933","display_name":"Collaborative Research: SHF: Small: Scalable and Extensible I/O Runtime and Tools for Next Generation Adaptive Data Layouts","funder_award_id":"2221811","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5332995977","display_name":"Collaborative Research: PPoSS: A Full-stack Approach to Declarative Analytics at Scale","funder_award_id":"2217036","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/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391053262.pdf","grobid_xml":"https://content.openalex.org/works/W4391053262.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1825216778","https://openalex.org/W1962931680","https://openalex.org/W1963882433","https://openalex.org/W2032484463","https://openalex.org/W2097493498","https://openalex.org/W2123287621","https://openalex.org/W2131613942","https://openalex.org/W2133557963","https://openalex.org/W2141351738","https://openalex.org/W2147418091","https://openalex.org/W2152556309","https://openalex.org/W2170613462","https://openalex.org/W2985108934","https://openalex.org/W3035481050","https://openalex.org/W4283397908","https://openalex.org/W4295780299","https://openalex.org/W4323895137","https://openalex.org/W4388662129"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2505380084","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2002978035","https://openalex.org/W2610007503","https://openalex.org/W1980160788"],"abstract_inverted_index":{"In":[0],"high-performance":[1],"computing,":[2],"collective":[3,26],"communication":[4,39,44,53,102],"is":[5,79],"critical":[6],"for":[7,55,100,125,138],"facilitating":[8],"comprehensive":[9],"data":[10,34,57,72],"exchange":[11],"involving":[12,59],"all":[13],"processes":[14],"within":[15],"an":[16,146],"MPI":[17,87],"communicator.":[18],"Due":[19],"to":[20,51,69,156],"their":[21],"inherently":[22],"global":[23,71],"nature,":[24],"many":[25],"operations":[27],"present":[28],"scalability":[29],"challenges,":[30],"particularly":[31],"the":[32,46,83,92,97,107,119,132,166],"all-to-all":[33,56,101,159],"shuffle":[35],"with":[36],"its":[37],"quadratic":[38],"pattern.":[40],"Using":[41],"a":[42,75,129],"logarithmic":[43],"pattern,":[45],"Bruck":[47,63,98,120,148],"algorithm":[48,64,99,121,149],"was":[49],"designed":[50],"provide":[52],"efficiency":[54],"shuffles":[58,73],"short-sized":[60],"messages.":[61],"The":[62],"has":[65],"been":[66],"extensively":[67],"used":[68],"facilitate":[70],"in":[74,103,128,151],"multi-CPU":[76,130],"environment":[77],"and":[78,85,144,153,160,168],"also":[80],"part":[81],"of":[82,95,170],"MPICH":[84],"Open":[86],"implementations.":[88,162],"This":[89],"work":[90],"presents":[91],"first":[93],"investigation":[94],"using":[96,106,175],"multi-GPU":[104,139,173],"systems":[105],"NVIDIA":[108],"Collective":[109],"Communications":[110],"Library":[111],"(NCCL).":[112],"Our":[113],"experimental":[114],"study":[115],"demonstrates":[116],"that":[117],"while":[118],"exhibits":[122],"superior":[123],"performance":[124],"small-sized":[126],"messages":[127],"environment,":[131],"same":[133],"advantages":[134],"are":[135],"not":[136],"evident":[137],"environments.":[140],"Furthermore,":[141],"we":[142,164],"describe":[143],"compare":[145,154],"optimized":[147],"implementation":[150],"NCCL":[152],"it":[155],"NCCL\u2019s":[157,176],"default":[158],"MPI-based":[161],"Finally,":[163],"discuss":[165],"challenges":[167],"opportunities":[169],"implementing":[171],"new":[172],"collectives":[174],"public-facing":[177],"API.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}