{"id":"https://openalex.org/W2889569921","doi":"https://doi.org/10.1145/3236367.3236374","title":"Full-Duplex Inter-Group All-to-All Broadcast Algorithms with Optimal Bandwidth","display_name":"Full-Duplex Inter-Group All-to-All Broadcast Algorithms with Optimal Bandwidth","publication_year":2018,"publication_date":"2018-09-19","ids":{"openalex":"https://openalex.org/W2889569921","doi":"https://doi.org/10.1145/3236367.3236374","mag":"2889569921"},"language":"en","primary_location":{"id":"doi:10.1145/3236367.3236374","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3236367.3236374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th European MPI Users' Group Meeting","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/A5013922013","display_name":"Qiao Kang","orcid":"https://orcid.org/0000-0001-8552-6551"},"institutions":[{"id":"https://openalex.org/I4210100400","display_name":"Northwestern University","ror":"https://ror.org/00m6w7z96","country_code":"PH","type":"education","lineage":["https://openalex.org/I4210100400"]}],"countries":["PH"],"is_corresponding":true,"raw_author_name":"Qiao Kang","raw_affiliation_strings":["EECS Department, Northwestern University"],"affiliations":[{"raw_affiliation_string":"EECS Department, Northwestern University","institution_ids":["https://openalex.org/I4210100400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064279948","display_name":"Jesper Larsson Tr\u00e4ff","orcid":"https://orcid.org/0000-0002-4864-9226"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Jesper Larsson Tr\u00e4ff","raw_affiliation_strings":["Vienna University of Technology"],"affiliations":[{"raw_affiliation_string":"Vienna University of Technology","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052511736","display_name":"Reda Al-Bahrani","orcid":"https://orcid.org/0000-0002-1528-0792"},"institutions":[{"id":"https://openalex.org/I4210100400","display_name":"Northwestern University","ror":"https://ror.org/00m6w7z96","country_code":"PH","type":"education","lineage":["https://openalex.org/I4210100400"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Reda Al-Bahrani","raw_affiliation_strings":["EECS Department, Northwestern University"],"affiliations":[{"raw_affiliation_string":"EECS Department, Northwestern University","institution_ids":["https://openalex.org/I4210100400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004659592","display_name":"Ankit Agrawal","orcid":"https://orcid.org/0000-0002-5519-0302"},"institutions":[{"id":"https://openalex.org/I4210100400","display_name":"Northwestern University","ror":"https://ror.org/00m6w7z96","country_code":"PH","type":"education","lineage":["https://openalex.org/I4210100400"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Ankit Agrawal","raw_affiliation_strings":["EECS Department, Northwestern University"],"affiliations":[{"raw_affiliation_string":"EECS Department, Northwestern University","institution_ids":["https://openalex.org/I4210100400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113432214","display_name":"Alok Choudhary","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100400","display_name":"Northwestern University","ror":"https://ror.org/00m6w7z96","country_code":"PH","type":"education","lineage":["https://openalex.org/I4210100400"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Alok Choudhary","raw_affiliation_strings":["EECS Department, Northwestern University"],"affiliations":[{"raw_affiliation_string":"EECS Department, Northwestern University","institution_ids":["https://openalex.org/I4210100400"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047602285","display_name":"Wei\u2010keng Liao","orcid":"https://orcid.org/0009-0008-9411-2543"},"institutions":[{"id":"https://openalex.org/I4210100400","display_name":"Northwestern University","ror":"https://ror.org/00m6w7z96","country_code":"PH","type":"education","lineage":["https://openalex.org/I4210100400"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Wei-keng Liao","raw_affiliation_strings":["EECS Department, Northwestern University"],"affiliations":[{"raw_affiliation_string":"EECS Department, Northwestern University","institution_ids":["https://openalex.org/I4210100400"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5013922013"],"corresponding_institution_ids":["https://openalex.org/I4210100400"],"apc_list":null,"apc_paid":null,"fwci":0.5536,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70445661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9991000294685364,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9991000294685364,"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":0.9983000159263611,"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":0.9980000257492065,"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":0.8501746654510498},{"id":"https://openalex.org/keywords/communication-in-small-groups","display_name":"Communication in small groups","score":0.6618148684501648},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4467313587665558},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.4298916459083557},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.419716477394104},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4162149131298065},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.41497477889060974},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.412346214056015},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33477187156677246},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2947666049003601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8501746654510498},{"id":"https://openalex.org/C44871818","wikidata":"https://www.wikidata.org/wiki/Q5154139","display_name":"Communication in small groups","level":2,"score":0.6618148684501648},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4467313587665558},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.4298916459083557},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.419716477394104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4162149131298065},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41497477889060974},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.412346214056015},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33477187156677246},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2947666049003601},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3236367.3236374","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3236367.3236374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th European MPI Users' Group Meeting","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320317220","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1509342228","https://openalex.org/W1573878051","https://openalex.org/W1978516206","https://openalex.org/W1998513618","https://openalex.org/W2020007825","https://openalex.org/W2062810083","https://openalex.org/W2104487100","https://openalex.org/W2118108504","https://openalex.org/W2131613942","https://openalex.org/W2133557963","https://openalex.org/W2144485497","https://openalex.org/W2160054705","https://openalex.org/W2615593025","https://openalex.org/W3175367423"],"related_works":["https://openalex.org/W1981780420","https://openalex.org/W2182707996","https://openalex.org/W45233828","https://openalex.org/W2964988449","https://openalex.org/W1508306925","https://openalex.org/W1530221417","https://openalex.org/W2515144809","https://openalex.org/W4200494141","https://openalex.org/W114758978","https://openalex.org/W1504437904"],"abstract_inverted_index":{"MPI":[0,73,118],"inter-group":[1,49],"collective":[2,77],"communication":[3,30,53,66,78],"patterns":[4,31],"can":[5,32],"be":[6],"viewed":[7],"as":[8,34],"bipartite":[9],"graphs":[10],"that":[11,120],"divide":[12],"processes":[13],"into":[14],"two":[15],"disjoint":[16],"groups":[17],"in":[18],"which":[19,109],"messages":[20],"are":[21],"transferred":[22],"between":[23],"but":[24],"not":[25],"within":[26],"the":[27,70,85,98,122],"groups.":[28],"Such":[29],"serve":[33],"basic":[35],"operations":[36],"for":[37,48,57],"scientific":[38],"application":[39],"workflows.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"present":[45],"parallel":[46],"algorithms":[47,71],"all-to-all":[50],"broadcast":[51],"(Allgather)":[52],"with":[54],"optimal":[55],"bandwidth":[56],"any":[58],"message":[59,91],"size":[60],"and":[61,75,80],"process":[62],"number":[63],"under":[64],"single-port":[65],"constraints.":[67],"We":[68],"implement":[69],"using":[72],"point-to-point":[74],"intra-group":[76],"functions":[79],"evaluate":[81],"their":[82],"performance":[83,103],"on":[84],"Cori":[86],"supercomputer":[87],"at":[88],"NERSC.":[89],"Using":[90],"sizes":[92],"ranging":[93],"from":[94],"256B":[95],"to":[96,112],"64MB,":[97],"experiments":[99],"show":[100],"a":[101],"significant":[102],"improvement":[104],"achieved":[105],"by":[106],"our":[107],"algorithm,":[108],"is":[110],"up":[111],"9.27":[113],"times":[114],"faster":[115],"than":[116],"production":[117],"libraries":[119],"adopt":[121],"so":[123],"called":[124],"root-gathering":[125],"algorithm.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
