{"id":"https://openalex.org/W4386915060","doi":"https://doi.org/10.1145/3615318.3615327","title":"Optimizing Communication in 2D Grid-Based MPI Applications at Exascale","display_name":"Optimizing Communication in 2D Grid-Based MPI Applications at Exascale","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386915060","doi":"https://doi.org/10.1145/3615318.3615327"},"language":"en","primary_location":{"id":"doi:10.1145/3615318.3615327","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3615318.3615327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th European MPI Users' Group Meeting","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/2438993","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058248684","display_name":"Hao Lu","orcid":"https://orcid.org/0000-0001-8941-870X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Lu","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048170299","display_name":"Piyush Sao","orcid":"https://orcid.org/0000-0002-9432-5855"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piyush Sao","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012951247","display_name":"Michael A. Matheson","orcid":"https://orcid.org/0000-0003-1512-5255"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Matheson","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014168997","display_name":"Ramakrishnan Kannan","orcid":"https://orcid.org/0000-0002-5852-4806"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramakrishnan Kannan","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101916963","display_name":"Feiyi Wang","orcid":"https://orcid.org/0000-0002-0099-1559"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feiyi Wang","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000241304","display_name":"Thomas E. Potok","orcid":"https://orcid.org/0000-0001-6687-3435"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Potok","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058248684"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.3025,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51465398,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9995999932289124,"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":0.9973999857902527,"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":0.8590071201324463},{"id":"https://openalex.org/keywords/exascale-computing","display_name":"Exascale computing","score":0.6633318662643433},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5917614698410034},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5874642729759216},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.5568923950195312},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.5424774885177612},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.495580792427063},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4729428291320801},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4637729525566101},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4458337128162384},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43348583579063416},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2540512681007385},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.20719516277313232}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8590071201324463},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.6633318662643433},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5917614698410034},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5874642729759216},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.5568923950195312},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.5424774885177612},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.495580792427063},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4729428291320801},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4637729525566101},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4458337128162384},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43348583579063416},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2540512681007385},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.20719516277313232},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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":2,"locations":[{"id":"doi:10.1145/3615318.3615327","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3615318.3615327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th European MPI Users' Group Meeting","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:2438993","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2438993","pdf_url":"https://www.osti.gov/servlets/purl/2438993","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:2438993","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2438993","pdf_url":"https://www.osti.gov/servlets/purl/2438993","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4000000059604645,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386915060.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1947869163","https://openalex.org/W2016279572","https://openalex.org/W2024960454","https://openalex.org/W2043889645","https://openalex.org/W2080038255","https://openalex.org/W2090409324","https://openalex.org/W2117758387","https://openalex.org/W2141380216","https://openalex.org/W2151156597","https://openalex.org/W2259651019","https://openalex.org/W2895305554","https://openalex.org/W2983126917","https://openalex.org/W2995872593","https://openalex.org/W3000173590","https://openalex.org/W3022909171","https://openalex.org/W3080244561","https://openalex.org/W3108141724","https://openalex.org/W3129367612","https://openalex.org/W3130650642","https://openalex.org/W3174859758","https://openalex.org/W4205868507","https://openalex.org/W4300421229","https://openalex.org/W4321636633"],"related_works":["https://openalex.org/W2251285835","https://openalex.org/W2124048060","https://openalex.org/W1902983110","https://openalex.org/W4386915331","https://openalex.org/W2378910916","https://openalex.org/W2086666199","https://openalex.org/W1511717675","https://openalex.org/W2116006827","https://openalex.org/W2361929291","https://openalex.org/W1493716264"],"abstract_inverted_index":{"The":[0],"new":[1],"reality":[2],"of":[3,16,25,47,167],"exascale":[4,149],"computing":[5],"faces":[6],"many":[7],"challenges":[8,155],"in":[9,65],"achieving":[10],"optimal":[11],"performance":[12,83,166,178,211],"on":[13,52,136],"large":[14,214],"numbers":[15],"nodes.":[17],"A":[18],"key":[19],"challenge":[20],"is":[21],"the":[22,26,44,122,137,153,165,185,202],"efficient":[23],"utilization":[24],"message-passing":[27],"interface":[28],"(MPI),":[29],"a":[30,58,62,74,194,198],"critical":[31],"component":[32],"for":[33,181,207],"process":[34,60],"communication.":[35],"This":[36,71],"paper":[37],"explores":[38],"communication":[39,169],"optimization":[40],"strategies":[41,80,170],"to":[42,77,81,143,148,157,201],"harness":[43],"GPU-accelerated":[45],"architectures":[46],"these":[48],"supercomputers.":[49],"We":[50,89,140,162],"focus":[51],"MPI":[53,154],"applications":[54,66,147],"where":[55],"processors":[56],"form":[57],"two-dimensional":[59],"grid,":[61],"common":[63],"arrangement":[64],"involving":[67],"dense":[68],"matrix":[69],"operations.":[70],"configuration":[72],"offers":[73],"unique":[75],"opportunity":[76],"implement":[78],"innovative":[79],"improve":[82],"and":[84,95,108,111,115,129,134,151,160],"maintain":[85],"effective":[86],"load":[87],"distribution.":[88],"study":[90],"two":[91,102],"applications\u2014":[92],"Dist-FW":[93],"(Apsp:all-pair-shortest-path)":[94],"HPL-MxP":[96],"(LU":[97],"factorization":[98],"with":[99],"Mixed":[100],"precision)\u2014on":[101],"accelerated":[103],"systems:":[104],"Summit":[105],"(IBM":[106],"Power":[107],"NVIDIA":[109],"V100)":[110],"Frontier":[112],"(AMD":[113],"EPYC":[114],"MI250X).":[116],"These":[117],"supercomputers":[118],"are":[119,130],"operated":[120],"by":[121],"Oak":[123],"Ridge":[124],"Leadership":[125],"Computing":[126],"Facility":[127],"(OLCF)":[128],"currently":[131],"ranked":[132],"#1":[133],"#5":[135],"Top500":[138],"list.":[139],"show":[141],"how":[142],"scale":[144,187],"up":[145],"both":[146],"levels":[150],"tackle":[152],"related":[156],"implementation,":[158],"synchronization,":[159],"performance.":[161],"also":[163],"compare":[164],"several":[168],"at":[171,212],"an":[172],"unprecedented":[173],"scale.":[174],"Accurately":[175],"predicting":[176,208],"application":[177,210],"becomes":[179],"crucial":[180],"cost":[182],"reduction":[183],"as":[184,197],"computational":[186],"grows.":[188],"To":[189],"address":[190],"this,":[191],"we":[192],"suggest":[193],"hyperbolic":[195],"model":[196,206],"better":[199],"alternative":[200],"traditional":[203],"one-sided":[204],"asymptotic":[205],"future":[209],"such":[213],"scales.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
