{"id":"https://openalex.org/W2890579947","doi":"https://doi.org/10.1145/3236367.3236384","title":"Cellular automata beyond 100k cores","display_name":"Cellular automata beyond 100k cores","publication_year":2018,"publication_date":"2018-09-19","ids":{"openalex":"https://openalex.org/W2890579947","doi":"https://doi.org/10.1145/3236367.3236384","mag":"2890579947"},"language":"en","primary_location":{"id":"doi:10.1145/3236367.3236384","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3236367.3236384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th European MPI Users' Group Meeting","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/A5069393800","display_name":"Anton Shterenlikht","orcid":"https://orcid.org/0000-0003-2517-0420"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Anton Shterenlikht","raw_affiliation_strings":["Mech Eng Dept, The University of Bristol, Bristol, UK"],"affiliations":[{"raw_affiliation_string":"Mech Eng Dept, The University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090269033","display_name":"Luis Cebamanos","orcid":"https://orcid.org/0000-0001-6594-211X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luis Cebamanos","raw_affiliation_strings":["EPCC, The University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"EPCC, The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069393800"],"corresponding_institution_ids":["https://openalex.org/I36234482"],"apc_list":null,"apc_paid":null,"fwci":0.3691,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64542611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983000159263611,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983000159263611,"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/T10049","display_name":"Magnetic properties of thin films","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8561094403266907},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7396934032440186},{"id":"https://openalex.org/keywords/fortran","display_name":"Fortran","score":0.6862809658050537},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5728791356086731},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.44198769330978394},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.42616650462150574},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22061830759048462}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8561094403266907},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7396934032440186},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.6862809658050537},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5728791356086731},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.44198769330978394},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.42616650462150574},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22061830759048462},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3236367.3236384","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3236367.3236384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th European MPI Users' Group Meeting","raw_type":"proceedings-article"},{"id":"pmh:oai:research-information.bris.ac.uk:openaire_cris_publications/713fc23d-69cc-43b1-9d41-13c9c8035472","is_oa":false,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/713fc23d-69cc-43b1-9d41-13c9c8035472","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Shterenlikht, A & Cebamanos, L 2018, Cellular automata beyond 100k cores: MPI vs Fortran coarrays. in EuroMPI'18 Proceedings of the 25th European MPI Users' Group Meeting . https://doi.org/10.1145/3236367.3236384","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G2355167868","display_name":null,"funder_award_id":"EP/R013047/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5575348898","display_name":"Reducing risk through uncertainty quantification for past, present and future generations of nuclear power plants","funder_award_id":"EP/R013047/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W322115986","https://openalex.org/W1563514727","https://openalex.org/W1968509977","https://openalex.org/W1968845187","https://openalex.org/W2026941724","https://openalex.org/W2052995264","https://openalex.org/W2054372636","https://openalex.org/W2062387044","https://openalex.org/W2079678915","https://openalex.org/W2096050640","https://openalex.org/W2097495737","https://openalex.org/W2115421099","https://openalex.org/W2144413143","https://openalex.org/W2149703470","https://openalex.org/W2151844571","https://openalex.org/W2165941516","https://openalex.org/W2170140912","https://openalex.org/W2402053059","https://openalex.org/W2476410554","https://openalex.org/W2565183761","https://openalex.org/W2748925989","https://openalex.org/W2758035875","https://openalex.org/W2768139418","https://openalex.org/W2889070002","https://openalex.org/W4301321901"],"related_works":["https://openalex.org/W1837558792","https://openalex.org/W2098482419","https://openalex.org/W1982466989","https://openalex.org/W2070983336","https://openalex.org/W4254638342","https://openalex.org/W4384344236","https://openalex.org/W2465501459","https://openalex.org/W2033847453","https://openalex.org/W2995170196","https://openalex.org/W2120518487"],"abstract_inverted_index":{"Fortran":[0,12,60,122],"coarrays":[1,24,92,131,192,234],"are":[2,85],"an":[3],"attractive":[4],"alternative":[5],"to":[6,9,30,73,98,127,130,196,228],"MPI":[7,89,101,119,128,190],"due":[8,195],"a":[10],"familiar":[11],"syntax,":[13],"single":[14],"sided":[15],"communications":[16],"and":[17,53,59,82,90,139,162,167,191,202,235],"implementation":[18],"in":[19,27,133,142,174,176,181,187],"the":[20,42,49,74,147,157,185,203,212,230],"compiler.":[21],"Scaling":[22],"of":[23],"is":[25,111,154,160,193,226],"compared":[26],"this":[28],"work":[29,65],"MPI,":[31],"using":[32],"cellular":[33],"automata":[34],"(CA)":[35],"3D":[36],"Ising":[37,51],"magnetisation":[38,54],"miniapps,":[39,178],"built":[40],"with":[41,57,88,91],"CASUP":[43],"CA":[44,158],"library,":[45],"https://cgpack.sourceforge.io,":[46],"developed":[47],"by":[48],"authors.":[50],"energy":[52],"were":[55,150],"calculated":[56],"MPI_ALLREDUCE":[58],"2018":[61],"co_sum":[62],"collectives.":[63],"The":[64,165],"was":[66],"done":[67],"on":[68],"ARCHER":[69],"(Cray":[70],"XC30)":[71],"up":[72],"full":[75],"machine":[76],"capacity:":[77],"109,056":[78],"cores.":[79,221],"Ping-pong":[80],"latency":[81],"bandwidth":[83],"results":[84,213],"very":[86],"similar":[87],"for":[93,216],"message":[94],"sizes":[95],"from":[96],"1B":[97],"several":[99],"MB.":[100],"halo":[102],"exchange":[103],"(HX)":[104],"scaled":[105],"better":[106],"than":[107],"coarray":[108,217,224],"HX,":[109],"which":[110],"surprising":[112],"because":[113,156],"both":[114],"algorithms":[115],"use":[116,218],"pair-wise":[117],"communications:":[118],"IRECV/ISEND/WAITALL":[120],"vs":[121,200,209],"sync":[123],"images.":[124],"Adding":[125],"OpenMP":[126],"or":[129],"resulted":[132],"worse":[134],"L2":[135],"cache":[136],"hit":[137],"ratio,":[138],"lower":[140],"performance":[141,188,231],"all":[143,177],"cases,":[144],"even":[145],"though":[146],"NUMA":[148],"effects":[149],"ruled":[151],"out.":[152],"This":[153],"likely":[155,194],"algorithm":[159],"memory":[161],"network":[163],"bound.":[164],"sampling":[166],"tracing":[168],"analysis":[169],"shows":[170],"good":[171],"load":[172],"balancing":[173],"compute":[175],"but":[179],"imbalance":[180],"communication,":[182],"indicating":[183],"that":[184],"difference":[186],"between":[189,233],"parallel":[197],"libraries":[198,207],"(MPICH2":[199],"libpgas)":[201],"Cray":[204],"hardware":[205],"specific":[206],"(uGNI":[208],"DMAPP).":[210],"Overall,":[211],"look":[214],"promising":[215],"beyond":[219],"100k":[220],"However,":[222],"further":[223],"optimisation":[225],"needed":[227],"narrow":[229],"gap":[232],"MPI.":[236]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
