{"id":"https://openalex.org/W2041924591","doi":"https://doi.org/10.1137/130915662","title":"Task-Based FMM for Multicore Architectures","display_name":"Task-Based FMM for Multicore Architectures","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2041924591","doi":"https://doi.org/10.1137/130915662","mag":"2041924591"},"language":"en","primary_location":{"id":"doi:10.1137/130915662","is_oa":false,"landing_page_url":"https://doi.org/10.1137/130915662","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-00807368","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074132178","display_name":"Emmanuel Agullo","orcid":"https://orcid.org/0000-0003-0655-6934"},"institutions":[{"id":"https://openalex.org/I4210142254","display_name":"Laboratoire Bordelais de Recherche en Informatique","ror":"https://ror.org/03adqg323","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I4210159245","https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Agullo","raw_affiliation_strings":["LaBRI - Laboratoire Bordelais de Recherche en Informatique (Domaine Universitaire 351, cours de la Lib\u00e9ration 33405 Talence Cedex - France)","HiePACS - High-End Parallel Algorithms for Challenging Numerical Simulations (200, avenue de la Vieille Tour \r\n33405 Talence cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LaBRI - Laboratoire Bordelais de Recherche en Informatique (Domaine Universitaire 351, cours de la Lib\u00e9ration 33405 Talence Cedex - France)","institution_ids":["https://openalex.org/I4210142254"]},{"raw_affiliation_string":"HiePACS - High-End Parallel Algorithms for Challenging Numerical Simulations (200, avenue de la Vieille Tour \r\n33405 Talence cedex - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081443384","display_name":"B\u00e9renger Bramas","orcid":"https://orcid.org/0000-0003-0281-9709"},"institutions":[{"id":"https://openalex.org/I4210142254","display_name":"Laboratoire Bordelais de Recherche en Informatique","ror":"https://ror.org/03adqg323","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I4210159245","https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"B\u00e9renger Bramas","raw_affiliation_strings":["LaBRI - Laboratoire Bordelais de Recherche en Informatique (Domaine Universitaire 351, cours de la Lib\u00e9ration 33405 Talence Cedex - France)","HiePACS - High-End Parallel Algorithms for Challenging Numerical Simulations (200, avenue de la Vieille Tour \r\n33405 Talence cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LaBRI - Laboratoire Bordelais de Recherche en Informatique (Domaine Universitaire 351, cours de la Lib\u00e9ration 33405 Talence Cedex - France)","institution_ids":["https://openalex.org/I4210142254"]},{"raw_affiliation_string":"HiePACS - High-End Parallel Algorithms for Challenging Numerical Simulations (200, avenue de la Vieille Tour \r\n33405 Talence cedex - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062845535","display_name":"Olivier Coulaud","orcid":"https://orcid.org/0000-0003-2924-284X"},"institutions":[{"id":"https://openalex.org/I4210142254","display_name":"Laboratoire Bordelais de Recherche en Informatique","ror":"https://ror.org/03adqg323","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I4210159245","https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Coulaud","raw_affiliation_strings":["LaBRI - Laboratoire Bordelais de Recherche en Informatique (Domaine Universitaire 351, cours de la Lib\u00e9ration 33405 Talence Cedex - France)","HiePACS - High-End Parallel Algorithms for Challenging Numerical Simulations (200, avenue de la Vieille Tour \r\n33405 Talence cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LaBRI - Laboratoire Bordelais de Recherche en Informatique (Domaine Universitaire 351, cours de la Lib\u00e9ration 33405 Talence Cedex - France)","institution_ids":["https://openalex.org/I4210142254"]},{"raw_affiliation_string":"HiePACS - High-End Parallel Algorithms for Challenging Numerical Simulations (200, avenue de la Vieille Tour \r\n33405 Talence cedex - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061822097","display_name":"Eric Darve","orcid":"https://orcid.org/0000-0002-1938-3836"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Darve","raw_affiliation_strings":["Department of Mechanical Engineering [Stanford] (Stanford University, School of Engineering, 295 Galvez Street, Stanford, California 94305-6104 - United States)","ICME - Institute for Computational and Mathematical Engineering [Stanford] (Stanford University, School of Engineering, Huang Building 475 Via Ortega, Stanford, CA 94305-4042 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering [Stanford] (Stanford University, School of Engineering, 295 Galvez Street, Stanford, California 94305-6104 - United States)","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"ICME - Institute for Computational and Mathematical Engineering [Stanford] (Stanford University, School of Engineering, Huang Building 475 Via Ortega, Stanford, CA 94305-4042 - United States)","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109904648","display_name":"Matthias Messner","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142254","display_name":"Laboratoire Bordelais de Recherche en Informatique","ror":"https://ror.org/03adqg323","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I4210159245","https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthias Messner","raw_affiliation_strings":["LaBRI - Laboratoire Bordelais de Recherche en Informatique (Domaine Universitaire 351, cours de la Lib\u00e9ration 33405 Talence Cedex - France)","HiePACS - High-End Parallel Algorithms for Challenging Numerical Simulations (200, avenue de la Vieille Tour \r\n33405 Talence cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LaBRI - Laboratoire Bordelais de Recherche en Informatique (Domaine Universitaire 351, cours de la Lib\u00e9ration 33405 Talence Cedex - France)","institution_ids":["https://openalex.org/I4210142254"]},{"raw_affiliation_string":"HiePACS - High-End Parallel Algorithms for Challenging Numerical Simulations (200, avenue de la Vieille Tour \r\n33405 Talence cedex - France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057346988","display_name":"Toru TAKAHASHI","orcid":"https://orcid.org/0000-0003-4232-7143"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Takahashi","raw_affiliation_strings":["Department of Mechanical Science and Engineering (Furo-cho, Chikusa-ku, Nagoya, 464-8603 - Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Science and Engineering (Furo-cho, Chikusa-ku, Nagoya, 464-8603 - Japan)","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2318,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.96031268,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"36","issue":"1","first_page":"C66","last_page":"C93"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11263","display_name":"Electromagnetic Simulation and Numerical Methods","score":0.9979000091552734,"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"}},{"id":"https://openalex.org/T11851","display_name":"Electromagnetic Compatibility and Measurements","score":0.9814000129699707,"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/fast-multipole-method","display_name":"Fast multipole method","score":0.8282157182693481},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7644742727279663},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6626476645469666},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6500972509384155},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5947839021682739},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5715045928955078},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5487667918205261},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.47950035333633423},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.45920923352241516},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4383637011051178},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43535006046295166},{"id":"https://openalex.org/keywords/multipole-expansion","display_name":"Multipole expansion","score":0.4310295581817627},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3715498447418213},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35268911719322205},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.1920836865901947},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18540042638778687},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0917614996433258}],"concepts":[{"id":"https://openalex.org/C135115559","wikidata":"https://www.wikidata.org/wiki/Q5437040","display_name":"Fast multipole method","level":3,"score":0.8282157182693481},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7644742727279663},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6626476645469666},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6500972509384155},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5947839021682739},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5715045928955078},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5487667918205261},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.47950035333633423},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.45920923352241516},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4383637011051178},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43535006046295166},{"id":"https://openalex.org/C52765159","wikidata":"https://www.wikidata.org/wiki/Q1027847","display_name":"Multipole expansion","level":2,"score":0.4310295581817627},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3715498447418213},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35268911719322205},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.1920836865901947},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18540042638778687},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0917614996433258},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1137/130915662","is_oa":false,"landing_page_url":"https://doi.org/10.1137/130915662","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-00807368v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00807368","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"[Research Report] RR-8277, INRIA. 2013, pp.33","raw_type":"Reports"},{"id":"pmh:oai:HAL:hal-00911856v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00911856","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIAM Journal on Scientific Computing, 2014, 36 (1), pp.66-93. &#x27E8;10.1137/130915662&#x27E9;","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00807368v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00807368","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"[Research Report] RR-8277, INRIA. 2013, pp.33","raw_type":"Reports"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1731033096","https://openalex.org/W2008114971","https://openalex.org/W2051395078","https://openalex.org/W2083206954","https://openalex.org/W2103241610","https://openalex.org/W2116941322","https://openalex.org/W2128601600","https://openalex.org/W2132820941","https://openalex.org/W2139205226","https://openalex.org/W2160709036","https://openalex.org/W2165977514"],"related_works":["https://openalex.org/W1822333417","https://openalex.org/W2952819168","https://openalex.org/W2158582466","https://openalex.org/W2076771790","https://openalex.org/W3105194265","https://openalex.org/W599820626","https://openalex.org/W9152652","https://openalex.org/W2034268890","https://openalex.org/W47721382","https://openalex.org/W2167163880"],"abstract_inverted_index":{"Fast":[0],"multipole":[1],"methods":[2,20],"(FMM)":[3],"are":[4,99],"a":[5,41,59,64,105],"fundamental":[6],"operation":[7],"for":[8,28],"the":[9,26,30,34,55,71,74,81,84],"simulation":[10],"of":[11,18,53],"many":[12],"physical":[13],"problems.":[14],"The":[15],"high-performance":[16],"design":[17,80],"such":[19],"usually":[21],"requires":[22],"to":[23,69],"carefully":[24,79],"tune":[25],"algorithm":[27,57],"both":[29],"targeted":[31],"physics":[32],"and":[33,62,89,93,112],"hardware.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39],"propose":[40],"new":[42],"approach":[43],"that":[44],"achieves":[45],"high":[46],"performance":[47],"across":[48],"architectures.":[49],"Our":[50],"method":[51],"consists":[52],"expressing":[54],"FMM":[56],"as":[58],"task":[60,82],"flow":[61],"employing":[63],"state-of-the-art":[65],"runtime":[66],"system,":[67],"StarPU,":[68],"process":[70],"tasks":[72],"on":[73,95,104],"different":[75],"computing":[76],"units.":[77],"We":[78],"flow,":[83],"mathematical":[85],"operators,":[86],"their":[87],"implementations,":[88],"scheduling":[90],"schemes.":[91],"Potentials":[92],"forces":[94],"200":[96],"million":[97],"particles":[98],"computed":[100],"in":[101],"42.3":[102],"seconds":[103],"homogeneous":[106],"160-core":[107],"SGI":[108],"Altix":[109],"UV":[110],"100":[111],"good":[113],"scalability":[114],"is":[115],"shown.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
