{"id":"https://openalex.org/W2749357753","doi":"https://doi.org/10.1145/3127024.3127038","title":"Improving the memory access locality of hybrid MPI applications","display_name":"Improving the memory access locality of hybrid MPI applications","publication_year":2017,"publication_date":"2017-08-24","ids":{"openalex":"https://openalex.org/W2749357753","doi":"https://doi.org/10.1145/3127024.3127038","mag":"2749357753"},"language":"en","primary_location":{"id":"doi:10.1145/3127024.3127038","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3127024.3127038","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3127038&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th European MPI Users' Group Meeting","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3127038&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005902443","display_name":"Matthias Diener","orcid":"https://orcid.org/0000-0002-9064-7806"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matthias Diener","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068729435","display_name":"Sam White","orcid":"https://orcid.org/0000-0002-6019-8763"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam White","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051465480","display_name":"Laxmikant V. Kal\u00e9","orcid":"https://orcid.org/0000-0001-9673-8445"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laxmikant V. Kale","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110231021","display_name":"Michael Campbell","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Campbell","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011367707","display_name":"Daniel J. Bodony","orcid":"https://orcid.org/0000-0002-7678-7044"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel J. Bodony","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027423603","display_name":"Jonathan B. Freund","orcid":"https://orcid.org/0000-0002-7073-1365"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan B. Freund","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005902443"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.387,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.82851549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9998000264167786,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8906041383743286},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.8459860682487488},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7284829616546631},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.655222475528717},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.5820937156677246},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5346682667732239},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5238114595413208},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.48902472853660583},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.47232168912887573},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4490531086921692},{"id":"https://openalex.org/keywords/runtime-system","display_name":"Runtime system","score":0.43886199593544006},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42994213104248047},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.323455274105072},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15969008207321167},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.10742315649986267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8906041383743286},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.8459860682487488},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7284829616546631},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.655222475528717},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.5820937156677246},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5346682667732239},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5238114595413208},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.48902472853660583},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.47232168912887573},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4490531086921692},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.43886199593544006},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42994213104248047},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.323455274105072},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15969008207321167},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.10742315649986267},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3127024.3127038","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3127024.3127038","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3127038&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th European MPI Users' Group Meeting","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3127024.3127038","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3127024.3127038","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3127038&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th European MPI Users' Group Meeting","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4959510507","display_name":null,"funder_award_id":"DE-NA0002374","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G8541042884","display_name":null,"funder_award_id":"DE-NA0002374","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2749357753.pdf","grobid_xml":"https://content.openalex.org/works/W2749357753.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W787130922","https://openalex.org/W1536453769","https://openalex.org/W1575350781","https://openalex.org/W1583784092","https://openalex.org/W1602359794","https://openalex.org/W1670978437","https://openalex.org/W1842336537","https://openalex.org/W1948591071","https://openalex.org/W1963882433","https://openalex.org/W1975451955","https://openalex.org/W1980052993","https://openalex.org/W1984848758","https://openalex.org/W1986340747","https://openalex.org/W1986445598","https://openalex.org/W2017915001","https://openalex.org/W2029528428","https://openalex.org/W2036270521","https://openalex.org/W2037460365","https://openalex.org/W2053663473","https://openalex.org/W2066132324","https://openalex.org/W2067540437","https://openalex.org/W2094395054","https://openalex.org/W2098309832","https://openalex.org/W2101778912","https://openalex.org/W2105506259","https://openalex.org/W2132260309","https://openalex.org/W2133352850","https://openalex.org/W2134633067","https://openalex.org/W2138782497","https://openalex.org/W2140514001","https://openalex.org/W2146375161","https://openalex.org/W2152419477","https://openalex.org/W2157802978","https://openalex.org/W2166834428","https://openalex.org/W2175048909","https://openalex.org/W2429918913","https://openalex.org/W2496508069","https://openalex.org/W2521259554","https://openalex.org/W2528150028","https://openalex.org/W4238153174","https://openalex.org/W4239813889"],"related_works":["https://openalex.org/W2026512611","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W2353146130","https://openalex.org/W1990817968","https://openalex.org/W2111416043","https://openalex.org/W2150064838","https://openalex.org/W2138782497","https://openalex.org/W1935251877","https://openalex.org/W2309631221"],"abstract_inverted_index":{"Maintaining":[0],"memory":[1,38,57,167],"access":[2,58],"locality":[3,39,59,72,95,168],"is":[4,33],"continuing":[5],"to":[6,34,103,110,115,121,149,159],"be":[7,28],"a":[8,61,116,133,144,150,174],"challenge":[9,32],"for":[10,41,48],"parallel":[11],"applications":[12,42],"and":[13,24,36,78,106,114,137],"their":[14],"runtime":[15,85],"environments.":[16],"By":[17],"exploiting":[18],"locality,":[19],"application":[20,64],"performance,":[21,160],"resource":[22],"usage,":[23],"performance":[25,105,129],"portability":[26],"can":[27,91],"improved.":[29],"The":[30],"main":[31],"detect":[35],"fix":[37],"issues":[40,73],"that":[43,89],"use":[44],"shared-memory":[45],"programming":[46],"models":[47],"intra-node":[49],"parallelization.":[50],"In":[51,157],"this":[52],"paper,":[53],"we":[54,161],"investigate":[55],"improving":[56],"of":[60,146,166],"hybrid":[62,123],"MPI+OpenMP":[63,124],"in":[65,74,93],"two":[66],"different":[67],"ways,":[68],"by":[69,79,130,138],"manually":[70],"fixing":[71],"its":[75],"source":[76,99],"code":[77,100],"employing":[80],"the":[81,111,122,164,170],"Adaptive":[82],"MPI":[83,118,152],"(AMPI)":[84],"environment.":[86],"Results":[87],"show":[88],"AMPI":[90],"result":[92],"similar":[94],"improvements":[96],"as":[97],"manual":[98],"changes,":[101],"leading":[102],"substantial":[104],"scalability":[107],"gains":[108],"compared":[109,148],"unoptimized":[112],"version":[113],"pure":[117,151],"runtime.":[119],"Compared":[120],"baseline,":[125],"our":[126],"optimizations":[127],"improved":[128],"1.8x":[131],"on":[132,140,154,169],"single":[134],"cluster":[135],"node,":[136],"1.4x":[139],"32":[141,155],"nodes,":[142],"with":[143],"speedup":[145],"2.4x":[147],"execution":[153],"nodes.":[156],"addition":[158],"also":[162],"evaluate":[163],"impact":[165],"load":[171],"balance":[172],"within":[173],"node.":[175]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
