{"id":"https://openalex.org/W4388101525","doi":"https://doi.org/10.1145/3581784.3607074","title":"Optimizing MPI Collectives on Shared Memory Multi-Cores","display_name":"Optimizing MPI Collectives on Shared Memory Multi-Cores","publication_year":2023,"publication_date":"2023-10-30","ids":{"openalex":"https://openalex.org/W4388101525","doi":"https://doi.org/10.1145/3581784.3607074"},"language":"en","primary_location":{"id":"doi:10.1145/3581784.3607074","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581784.3607074","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/A5037392776","display_name":"Jintao Peng","orcid":"https://orcid.org/0000-0002-3056-9391"},"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":true,"raw_author_name":"Jintao Peng","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083171604","display_name":"Jianbin Fang","orcid":"https://orcid.org/0000-0003-3542-4869"},"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":"Jianbin Fang","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454211","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0003-3745-7541"},"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":"Jie Liu","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Chile"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Chile","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006981609","display_name":"Min Xie","orcid":"https://orcid.org/0009-0000-3265-9772"},"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":"Min Xie","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101627322","display_name":"Yi Dai","orcid":"https://orcid.org/0000-0002-9929-6459"},"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":"Yi Dai","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101987155","display_name":"Bo Yang","orcid":"https://orcid.org/0000-0002-9035-1538"},"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":"Bo Yang","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, ChangSha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, ChangSha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087730416","display_name":"Shengguo Li","orcid":"https://orcid.org/0000-0001-7827-6304"},"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":"Shengguo Li","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100401045","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0001-6157-0662"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["School of Computing, University of Leeds, Leeds, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Leeds, Leeds, United Kingdom","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5037392776"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":2.4239,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.88871951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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":0.9980000257492065,"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":0.9056044816970825},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.662525475025177},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5559252500534058},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5538576245307922},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.5414178371429443},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5046643018722534},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.49300381541252136},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.4668344557285309},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4633164405822754},{"id":"https://openalex.org/keywords/broadcasting","display_name":"Broadcasting (networking)","score":0.44179767370224},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.44176143407821655},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.4152162969112396},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.41331273317337036},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.267985463142395},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13603505492210388},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1227857768535614},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.07382789254188538}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9056044816970825},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.662525475025177},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5559252500534058},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5538576245307922},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.5414178371429443},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5046643018722534},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.49300381541252136},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4668344557285309},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4633164405822754},{"id":"https://openalex.org/C110157686","wikidata":"https://www.wikidata.org/wiki/Q922122","display_name":"Broadcasting (networking)","level":2,"score":0.44179767370224},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44176143407821655},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4152162969112396},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.41331273317337036},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.267985463142395},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13603505492210388},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1227857768535614},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.07382789254188538},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581784.3607074","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581784.3607074","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"},{"id":"pmh:oai:eprints.whiterose.ac.uk:202767","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G503725912","display_name":null,"funder_award_id":"61972408","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6714216625","display_name":null,"funder_award_id":"2021YFB0300101","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1498011047","https://openalex.org/W1574750619","https://openalex.org/W1670978437","https://openalex.org/W1937799376","https://openalex.org/W1986445598","https://openalex.org/W1990538672","https://openalex.org/W2017290301","https://openalex.org/W2017915001","https://openalex.org/W2057332538","https://openalex.org/W2073875590","https://openalex.org/W2078636996","https://openalex.org/W2111144707","https://openalex.org/W2118646353","https://openalex.org/W2131613942","https://openalex.org/W2155462575","https://openalex.org/W2257508639","https://openalex.org/W2601366465","https://openalex.org/W2725179571","https://openalex.org/W2758990545","https://openalex.org/W2766672944","https://openalex.org/W2767393956","https://openalex.org/W2886520239","https://openalex.org/W2899266172","https://openalex.org/W2902551881","https://openalex.org/W2955374581","https://openalex.org/W2998841280","https://openalex.org/W3046404449","https://openalex.org/W3096262771","https://openalex.org/W3127904641","https://openalex.org/W3141418934","https://openalex.org/W3207691478","https://openalex.org/W4220660085","https://openalex.org/W4236614409","https://openalex.org/W4238128135","https://openalex.org/W4241252669","https://openalex.org/W4252163020","https://openalex.org/W4252494515"],"related_works":["https://openalex.org/W2366325093","https://openalex.org/W1998761481","https://openalex.org/W2498758832","https://openalex.org/W2154020360","https://openalex.org/W184749201","https://openalex.org/W98999783","https://openalex.org/W2314805133","https://openalex.org/W1544002944","https://openalex.org/W2556310971","https://openalex.org/W2133825528"],"abstract_inverted_index":{"Message":[0],"Passing":[1],"Interface":[2],"(MPI)":[3],"programs":[4],"often":[5],"experience":[6],"performance":[7,129,153],"slowdowns":[8],"due":[9],"to":[10,32,48,89],"collective":[11,51,59],"communication":[12],"operations,":[13],"like":[14],"broadcasting":[15],"and":[16,79,108,126,132],"reductions.":[17],"As":[18],"modern":[19],"CPUs":[20],"integrate":[21],"more":[22],"processor":[23],"cores,":[24],"running":[25,135],"multiple":[26],"MPI":[27,50,58],"processes":[28],"on":[29,61,136],"shared-memory":[30,54,62],"machines":[31],"take":[33],"advantage":[34],"of":[35,86,112],"hardware":[36],"parallelism":[37],"is":[38,46,70,82],"becoming":[39],"increasingly":[40],"common.":[41],"In":[42],"this":[43,98],"context,":[44],"it":[45],"crucial":[47],"optimize":[49,90],"communications":[52],"for":[53],"execution.":[55],"However,":[56],"existing":[57,148],"implementations":[60],"systems":[63],"have":[64],"two":[65,101,137],"primary":[66],"drawbacks.":[67],"The":[68],"first":[69],"extensive":[71],"redundant":[72],"data":[73,92,106],"movements":[74,107],"when":[75],"performing":[76],"reduction":[77],"collectives,":[78],"the":[80,83,110,123],"second":[81],"ineffective":[84],"use":[85,111],"non-temporal":[87,113],"instructions":[88],"streamed":[91],"processing.":[93],"To":[94],"address":[95],"these":[96],"limitations,":[97],"paper":[99],"proposes":[100],"optimization":[102],"techniques":[103,118],"that":[104,143],"minimize":[105],"enhance":[109],"instructions.":[114],"We":[115],"evaluated":[116],"our":[117,144],"by":[119],"integrating":[120],"them":[121],"into":[122],"OpenMPI":[124],"library":[125],"tested":[127],"their":[128],"using":[130],"micro-benchmarks":[131],"real-world":[133],"applications":[134],"multi-core":[138],"clusters.":[139],"Experimental":[140],"results":[141],"show":[142],"approach":[145],"significantly":[146],"outperforms":[147],"techniques,":[149],"yielding":[150],"a":[151],"1.2--6.4x":[152],"improvement.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
