{"id":"https://openalex.org/W4282970470","doi":"https://doi.org/10.1145/3524059.3532380","title":"Optimized MPI collective algorithms for dragonfly topology","display_name":"Optimized MPI collective algorithms for dragonfly topology","publication_year":2022,"publication_date":"2022-06-16","ids":{"openalex":"https://openalex.org/W4282970470","doi":"https://doi.org/10.1145/3524059.3532380"},"language":"en","primary_location":{"id":"doi:10.1145/3524059.3532380","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524059.3532380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5088979128","display_name":"Guangnan Feng","orcid":"https://orcid.org/0000-0002-1382-280X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangnan Feng","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006729432","display_name":"Dezun Dong","orcid":"https://orcid.org/0000-0001-6243-8479"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezun Dong","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633465","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0001-5315-3375"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10715","display_name":"Distributed and Parallel Computing Systems","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"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","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"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9990000128746033,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7979456782341003},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7000099420547485},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.6346441507339478},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.5991507768630981},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.5901258587837219},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5485665202140808},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4742775857448578},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4475288987159729},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4393021762371063},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4201239347457886},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.3462856411933899},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3329330086708069},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.19349122047424316},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1252325475215912}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979456782341003},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7000099420547485},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.6346441507339478},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.5991507768630981},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.5901258587837219},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5485665202140808},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4742775857448578},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4475288987159729},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4393021762371063},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4201239347457886},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.3462856411933899},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3329330086708069},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.19349122047424316},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1252325475215912},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3524059.3532380","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524059.3532380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1572016165","https://openalex.org/W1865662898","https://openalex.org/W1997967900","https://openalex.org/W2013769473","https://openalex.org/W2038423000","https://openalex.org/W2082879210","https://openalex.org/W2107997203","https://openalex.org/W2131613942","https://openalex.org/W2133557963","https://openalex.org/W2138979581","https://openalex.org/W2153188937","https://openalex.org/W2244773447","https://openalex.org/W2332895340","https://openalex.org/W2344873464","https://openalex.org/W2560258068","https://openalex.org/W2760106839","https://openalex.org/W2782000683","https://openalex.org/W2887690473","https://openalex.org/W3129251660","https://openalex.org/W3147460469","https://openalex.org/W4200337537","https://openalex.org/W4200494113","https://openalex.org/W4238128135","https://openalex.org/W4241571371","https://openalex.org/W4244682390","https://openalex.org/W4251820394","https://openalex.org/W4252071697"],"related_works":["https://openalex.org/W2546696010","https://openalex.org/W2364921833","https://openalex.org/W1582405267","https://openalex.org/W2354106728","https://openalex.org/W2623111183","https://openalex.org/W1513967072","https://openalex.org/W4235217501","https://openalex.org/W2275990338","https://openalex.org/W1972664035","https://openalex.org/W2139061608"],"abstract_inverted_index":{"The":[0,133],"Message":[1],"Passing":[2],"Interface":[3],"(MPI)":[4],"is":[5,34,41],"the":[6,60,74,138],"most":[7],"prominent":[8],"and":[9,23,45,52,87,105,116,130,144,153],"dominant":[10],"programming":[11],"model":[12],"for":[13,29,37,108,156],"scientific":[14],"computing":[15],"in":[16,50,79],"super-computing":[17],"systems":[18],"today.":[19],"Although":[20],"many":[21],"general":[22],"efficient":[24],"algorithms":[25,78],"have":[26],"been":[27],"proposed":[28],"MPI":[30,64,109],"collective":[31,65,77,110],"operations,":[32],"there":[33],"still":[35],"room":[36],"topology-aware":[38],"optimization.":[39],"Dragonfly":[40,57,80],"a":[42],"high-scalability,":[43],"low-diameter,":[44],"cost-efficient":[46],"network":[47,124],"topology":[48,58,81,88],"adopted":[49],"more":[51,53],"supercomputing":[54],"networks.":[55],"However,":[56],"limits":[59],"performance":[61,139],"of":[62,76,140],"some":[63],"operations.":[66],"In":[67],"this":[68],"paper,":[69],"our":[70],"analysis":[71],"shows":[72],"that":[73,137],"bottlenecks":[75],"are":[82],"intra-job":[83],"interference,":[84,86],"inter-job":[85],"mismatch.":[89],"We":[90,118],"propose":[91],"5":[92],"different":[93],"optimizations,":[94],"i.e.,":[95],"Pseudo-random":[96],"Pairwise,":[97],"Tree-based":[98],"Shuffle,":[99],"Reversed":[100],"Recursive":[101],"Doubling,":[102],"Reordered":[103],"Bruck,":[104],"Matched":[106],"Rabenseifner,":[107],"operations":[111],"including":[112],"All-Gather,":[113,142],"All-to-All,":[114,141],"All-Reduce,":[115,143],"Reduce-Scatter.":[117],"evaluate":[119],"each":[120],"optimization":[121],"through":[122],"CODES":[123],"simulation":[125,134],"framework":[126],"with":[127,159],"minimal,":[128],"non-minimal,":[129],"adaptive":[131,160],"routing.":[132,161],"results":[135],"demonstrate":[136],"Reduce-Scatter":[145],"can":[146],"be":[147],"improved":[148],"by":[149],"4.7X,":[150],"3.4X,":[151],"12.7%,":[152],"4.1X,":[154],"respectively,":[155],"32768-node":[157],"jobs":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
