{"id":"https://openalex.org/W2160709036","doi":"https://doi.org/10.1177/1094342011429952","title":"A tuned and scalable fast multipole method as a preeminent algorithm for exascale systems","display_name":"A tuned and scalable fast multipole method as a preeminent algorithm for exascale systems","publication_year":2012,"publication_date":"2012-01-24","ids":{"openalex":"https://openalex.org/W2160709036","doi":"https://doi.org/10.1177/1094342011429952","mag":"2160709036"},"language":"en","primary_location":{"id":"doi:10.1177/1094342011429952","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342011429952","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1106.2176","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024747717","display_name":"Rio Yokota","orcid":"https://orcid.org/0000-0001-7573-7873"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rio Yokota","raw_affiliation_strings":["Mechanical Engineering Department, Boston University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mechanical Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028603986","display_name":"Lorena A. Barba","orcid":"https://orcid.org/0000-0001-5812-2711"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lorena A Barba","raw_affiliation_strings":["Mechanical Engineering Department, Boston University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mechanical Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028603986"],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":null,"apc_paid":null,"fwci":4.4799,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.95214592,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"26","issue":"4","first_page":"337","last_page":"346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.991100013256073,"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"}},"topics":[{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.991100013256073,"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/T11312","display_name":"Soil Moisture and Remote Sensing","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11609","display_name":"Geophysical Methods and Applications","score":0.9814000129699707,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/simd","display_name":"SIMD","score":0.8243016600608826},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8002699613571167},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.772122859954834},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7625277042388916},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.7314763069152832},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6155478954315186},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5421906113624573},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5307737588882446},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4692147970199585},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4305008351802826},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36871224641799927},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08387163281440735},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07903265953063965}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8243016600608826},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8002699613571167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.772122859954834},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7625277042388916},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.7314763069152832},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6155478954315186},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5421906113624573},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5307737588882446},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4692147970199585},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4305008351802826},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36871224641799927},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08387163281440735},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07903265953063965},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1177/1094342011429952","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342011429952","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1106.2176","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1106.2176","pdf_url":"https://arxiv.org/pdf/1106.2176","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.753.3623","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.753.3623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1106.2176.pdf","raw_type":"text"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50272235","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100686128","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1106.2176","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1106.2176","pdf_url":"https://arxiv.org/pdf/1106.2176","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1977737756","https://openalex.org/W1984341156","https://openalex.org/W1997494092","https://openalex.org/W2007648666","https://openalex.org/W2014008637","https://openalex.org/W2067178485","https://openalex.org/W2083206954","https://openalex.org/W2084831289","https://openalex.org/W2099813373","https://openalex.org/W2113691861","https://openalex.org/W2117926105","https://openalex.org/W2129003192","https://openalex.org/W2129152507","https://openalex.org/W2136770272","https://openalex.org/W2139205226","https://openalex.org/W2143131337","https://openalex.org/W2164754386","https://openalex.org/W2165384099","https://openalex.org/W2168963553","https://openalex.org/W2208101261","https://openalex.org/W2540569505","https://openalex.org/W2912779084","https://openalex.org/W3098088416","https://openalex.org/W4249563210"],"related_works":["https://openalex.org/W2021702679","https://openalex.org/W3038449658","https://openalex.org/W1582746211","https://openalex.org/W3129378740","https://openalex.org/W2099629705","https://openalex.org/W2607572736","https://openalex.org/W2266027327","https://openalex.org/W2278366184","https://openalex.org/W1486544172","https://openalex.org/W4206324154"],"abstract_inverted_index":{"Among":[0],"the":[1,15,41,82,88,114,130,170,176,204,241,247,257,273],"algorithms":[2],"that":[3,226,249],"are":[4],"likely":[5],"to":[6,50,56,211,230],"play":[7,231],"a":[8,22,70,95,104,232,244,252],"major":[9],"role":[10,234],"in":[11,87,103,125,146,162,197,235],"future":[12],"exascale":[13,236],"computing,":[14,237],"fast":[16],"multipole":[17],"method":[18],"(fmm)":[19],"appears":[20],"as":[21],"rising":[23],"star.":[24],"Our":[25],"previous":[26],"recent":[27],"work":[28,48,219],"showed":[29,106],"scaling":[30,55,154,187],"of":[31,40,43,45,58,62,64,72,113,129,246],"an":[32,51],"fmm":[33,89,227],"on":[34,69,81,109,133,166,200],"gpu":[35],"clusters,":[36],"with":[37,136,203,243],"problem":[38],"sizes":[39],"order":[42],"billions":[44],"unknowns.":[46,217],"That":[47],"led":[49],"extremely":[52],"parallel":[53,164,262],"fmm,":[54],"thousands":[57,63],"gpus":[59],"or":[60],"tens":[61],"cpus.":[65],"This":[66,218],"paper":[67,242],"reports":[68],"campaign":[71],"performance":[73],"tuning":[74],"and":[75,94,149,160,173,195,238,260],"scalability":[76,143],"studies":[77],"using":[78,92,97,117],"multi-core":[79],"cpus,":[80],"Kraken":[83],"supercomputer.":[84],"All":[85],"kernels":[86],"were":[90],"parallelized":[91],"OpenMP,":[93],"test":[96,155,188],"10":[98,137,157,190],"7":[99,140],"particles":[100,159,192],"randomly":[101],"distributed":[102],"cube":[105],"78%":[107],"efficiency":[108,165,199],"8":[110,158],"threads.":[111],"Tuning":[112],"particle-to-particle":[115],"kernel":[116],"single":[118],"instruction":[119],"multiple":[120],"data":[121],"(SIMD)":[122],"instructions":[123],"resulted":[124,161,196],"4":[126],"\u00d7":[127,183],"speed-up":[128],"overall":[131],"algorithm":[132,255],"single-core":[134],"tests":[135],"3":[138],"\u201310":[139],"particles.":[141],"Parallel":[142],"was":[144,180],"studied":[145],"both":[147],"strong":[148,153],"weak":[150,186],"scaling.":[151],"The":[152,185,265],"used":[156,189],"93%":[163],"2048":[167],"processes":[168],"for":[169,175,223,256,269],"non-SIMD":[171],"code":[172,178,266],"54%":[174],"SIMD-optimized":[177],"(which":[179],"still":[181],"2":[182],"faster).":[184],"6":[191],"per":[193],"process,":[194],"72%":[198],"32,768":[201],"processes,":[202],"largest":[205],"calculation":[206],"taking":[207],"about":[208],"40":[209],"seconds":[210],"evaluate":[212],"more":[213],"than":[214],"32":[215],"billion":[216],"builds":[220],"up":[221],"evidence":[222],"our":[224],"view":[225],"is":[228,267],"poised":[229],"leading":[233],"we":[239],"end":[240],"discussion":[245],"features":[248],"make":[250],"it":[251],"particularly":[253],"favorable":[254],"emerging":[258],"heterogeneous":[259],"massively":[261],"architectural":[263],"landscape.":[264],"open":[268],"unrestricted":[270],"use":[271],"under":[272],"MIT":[274],"license.":[275]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}