{"id":"https://openalex.org/W2767393956","doi":"https://doi.org/10.1145/3126908.3126954","title":"Scalable reduction collectives with data partitioning-based multi-leader design","display_name":"Scalable reduction collectives with data partitioning-based multi-leader design","publication_year":2017,"publication_date":"2017-11-08","ids":{"openalex":"https://openalex.org/W2767393956","doi":"https://doi.org/10.1145/3126908.3126954","mag":"2767393956"},"language":"en","primary_location":{"id":"doi:10.1145/3126908.3126954","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126908.3126954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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/A5013350491","display_name":"Mohammadreza Bayatpour","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohammadreza Bayatpour","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101626747","display_name":"Sourav Chakraborty","orcid":"https://orcid.org/0000-0001-9518-6204"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sourav Chakraborty","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034293705","display_name":"Hari Subramoni","orcid":"https://orcid.org/0000-0002-1200-2754"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hari Subramoni","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067748041","display_name":"Xiaoyi Lu","orcid":"https://orcid.org/0000-0001-7581-8905"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyi Lu","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024879682","display_name":"Dhabaleswar K. Panda","orcid":"https://orcid.org/0000-0002-0356-1781"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhabaleswar K. (DK) Panda","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5013350491"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":4.5063,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.96154304,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"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/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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991999864578247,"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/infiniband","display_name":"InfiniBand","score":0.9678287506103516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8772422075271606},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.8438408374786377},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8145102858543396},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.7344894409179688},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6544126272201538},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5894795656204224},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5495437979698181},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5227939486503601},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4725708067417145},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.4584815204143524},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.44939476251602173},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41626426577568054},{"id":"https://openalex.org/keywords/critical-path-method","display_name":"Critical path method","score":0.41498082876205444},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3361801505088806},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.28498876094818115},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.08249029517173767}],"concepts":[{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.9678287506103516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8772422075271606},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.8438408374786377},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8145102858543396},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.7344894409179688},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6544126272201538},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5894795656204224},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5495437979698181},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5227939486503601},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4725708067417145},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.4584815204143524},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.44939476251602173},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41626426577568054},{"id":"https://openalex.org/C115874739","wikidata":"https://www.wikidata.org/wiki/Q825377","display_name":"Critical path method","level":2,"score":0.41498082876205444},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3361801505088806},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.28498876094818115},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.08249029517173767},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3126908.3126954","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126908.3126954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5099999904632568,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W82183796","https://openalex.org/W112345847","https://openalex.org/W1568736435","https://openalex.org/W1572016165","https://openalex.org/W1581994707","https://openalex.org/W1920964269","https://openalex.org/W2042120213","https://openalex.org/W2043143850","https://openalex.org/W2056476515","https://openalex.org/W2059300917","https://openalex.org/W2091780466","https://openalex.org/W2102061396","https://openalex.org/W2115020004","https://openalex.org/W2129691304","https://openalex.org/W2131613942","https://openalex.org/W2136041296","https://openalex.org/W2166097017","https://openalex.org/W2535374105","https://openalex.org/W2563521659"],"related_works":["https://openalex.org/W1978254186","https://openalex.org/W4245217724","https://openalex.org/W4253931064","https://openalex.org/W1984788566","https://openalex.org/W3166154920","https://openalex.org/W1964981582","https://openalex.org/W2154082760","https://openalex.org/W4282599985","https://openalex.org/W2139382794","https://openalex.org/W4245850706"],"abstract_inverted_index":{"Existing":[0],"designs":[1,97,112],"for":[2,55,123,125,144],"MPI_Allreduce":[3,56,88,124],"do":[4],"not":[5],"take":[6,59],"advantage":[7,60],"of":[8,61,87],"the":[9,22,62,71,85,100,109,132],"vast":[10],"parallelism":[11,63],"available":[12],"in":[13,24,30,68,142],"modern":[14,35,90],"multi-/many-core":[15,66],"processors":[16],"like":[17,37],"Intel":[18],"Xeon/Xeon":[19],"Phis":[20],"or":[21],"increases":[23],"communication":[25,101,143],"throughput":[26,73],"and":[27,39,48,74,80,137,146],"recent":[28],"advances":[29],"high-end":[31,75],"features":[32,76],"seen":[33,141],"with":[34,70],"interconnects":[36],"InfiniBand":[38,79],"Omni-Path.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"propose":[45],"a":[46],"high-performance":[47],"scalable":[49],"<u>D</u>ata":[50],"<u>P</u>artitioning-based":[51],"<u>M</u>ulti-<u>L</u>eader":[52],"(DPML)":[53],"solution":[54],"that":[57,108],"can":[58],"offered":[64,77],"by":[65,78],"architectures":[67],"conjunction":[69],"high":[72],"Omni-Path":[81],"to":[82,98,115,118,135],"significantly":[83],"enhance":[84],"performance":[86,121],"on":[89],"HPC":[91,127],"systems.":[92],"We":[93],"also":[94],"model":[95],"DPML-based":[96,111],"analyze":[99],"costs":[102],"theoretically.":[103],"Microbenchmark":[104],"level":[105],"evaluations":[106],"show":[107],"proposed":[110],"are":[113],"able":[114],"deliver":[116],"up":[117,134],"3.5":[119],"times":[120],"improvement":[122,139],"multiple":[126],"systems":[128],"at":[129],"scale.":[130],"At":[131],"application-level,":[133],"35%":[136],"60%":[138],"is":[140],"HPCG":[145],"miniAMR":[147],"respectively.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}