{"id":"https://openalex.org/W2157749636","doi":"https://doi.org/10.1145/2063384.2063432","title":"Scalable fast multipole methods on distributed heterogeneous architectures","display_name":"Scalable fast multipole methods on distributed heterogeneous architectures","publication_year":2011,"publication_date":"2011-11-08","ids":{"openalex":"https://openalex.org/W2157749636","doi":"https://doi.org/10.1145/2063384.2063432","mag":"2157749636"},"language":"en","primary_location":{"id":"doi:10.1145/2063384.2063432","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063384.2063432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110368037","display_name":"Qi Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Hu","raw_affiliation_strings":["University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043329271","display_name":"Nail A. Gumerov","orcid":"https://orcid.org/0000-0002-6758-0391"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nail A. Gumerov","raw_affiliation_strings":["University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013222310","display_name":"Ramani Duraiswami","orcid":"https://orcid.org/0000-0002-5596-8460"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramani Duraiswami","raw_affiliation_strings":["University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9947999715805054,"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/T11392","display_name":"Energy Harvesting in Wireless Networks","score":0.9850999712944031,"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":0.8490028977394104},{"id":"https://openalex.org/keywords/fast-multipole-method","display_name":"Fast multipole method","score":0.7825881242752075},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7424114942550659},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6760385036468506},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.67499178647995},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6231265068054199},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6093393564224243},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.5430445671081543},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.36219513416290283},{"id":"https://openalex.org/keywords/multipole-expansion","display_name":"Multipole expansion","score":0.32314538955688477},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11875244975090027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8490028977394104},{"id":"https://openalex.org/C135115559","wikidata":"https://www.wikidata.org/wiki/Q5437040","display_name":"Fast multipole method","level":3,"score":0.7825881242752075},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7424114942550659},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6760385036468506},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.67499178647995},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6231265068054199},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6093393564224243},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.5430445671081543},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.36219513416290283},{"id":"https://openalex.org/C52765159","wikidata":"https://www.wikidata.org/wiki/Q1027847","display_name":"Multipole expansion","level":2,"score":0.32314538955688477},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11875244975090027},{"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/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},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2063384.2063432","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063384.2063432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.1573","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.1573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.umiacs.umd.edu/%7Eramani/pubs/Qi_Gumerov_Duraiswami_SC11_FMM_Heterogeneous.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.365.8751","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.365.8751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umd.edu/~huqi/QGD_SC11.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3210241350","display_name":null,"funder_award_id":"W911NF0410176","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G3808135318","display_name":null,"funder_award_id":"403313","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7751510029","display_name":null,"funder_award_id":"G34.31.0040","funder_id":"https://openalex.org/F4320321912","funder_display_name":"Ministry of Education and Science of the Russian Federation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321912","display_name":"Ministry of Education and Science of the Russian Federation","ror":"https://ror.org/00ghqgy32"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W42106223","https://openalex.org/W130191466","https://openalex.org/W1497953515","https://openalex.org/W1976460851","https://openalex.org/W1985759756","https://openalex.org/W1987397719","https://openalex.org/W1996639891","https://openalex.org/W1997735430","https://openalex.org/W2019504893","https://openalex.org/W2041431621","https://openalex.org/W2044762488","https://openalex.org/W2054622952","https://openalex.org/W2069883496","https://openalex.org/W2081188973","https://openalex.org/W2082553748","https://openalex.org/W2083206954","https://openalex.org/W2087977509","https://openalex.org/W2095760815","https://openalex.org/W2099813373","https://openalex.org/W2116941322","https://openalex.org/W2117926105","https://openalex.org/W2129003192","https://openalex.org/W2132820941","https://openalex.org/W2139205226","https://openalex.org/W2146847742","https://openalex.org/W2153347070","https://openalex.org/W2156046515","https://openalex.org/W2159497832","https://openalex.org/W2161061943","https://openalex.org/W2540569505","https://openalex.org/W2619104765","https://openalex.org/W6649760400","https://openalex.org/W6683923952"],"related_works":["https://openalex.org/W2952819168","https://openalex.org/W1822333417","https://openalex.org/W2158582466","https://openalex.org/W2076771790","https://openalex.org/W3105194265","https://openalex.org/W599820626","https://openalex.org/W2125081029","https://openalex.org/W47721382","https://openalex.org/W9152652","https://openalex.org/W4385486246"],"abstract_inverted_index":{"We":[0,109],"fundamentally":[1],"reconsider":[2],"implementation":[3,154],"of":[4,35,76,92],"the":[5,65,68,72,77,86,93,102,106,117,125,146,157,176],"Fast":[6],"Multipole":[7],"Method":[8],"(FMM)":[9],"on":[10,31,163,178],"a":[11,15,41,46,51,59,112,169],"computing":[12],"node":[13,114,148],"with":[14,19,141],"heterogeneous":[16],"CPU-GPU":[17],"architecture":[18],"multicore":[20,103],"CPU(s)":[21],"and":[22,54,71,88,105,124,149],"one":[23],"or":[24,61],"more":[25],"GPU":[26,107,126],"accelerators,":[27],"as":[28,30],"well":[29],"an":[32],"interconnected":[33],"cluster":[34],"such":[36,179],"nodes.":[37],"The":[38],"FMM":[39,78,94,135],"is":[40,55,95,120],"divide-and-conquer":[42],"algorithm":[43],"that":[44,67],"performs":[45],"fast":[47],"N-body":[48,158],"sum":[49,159],"using":[50,122],"spatial":[52],"decomposition":[53],"often":[56],"used":[57],"in":[58,166,175],"time-stepping":[60],"iterative":[62],"loop.":[63],"Using":[64],"observation":[66],"local":[69],"summation":[70],"analysis-based":[73],"translation":[74],"parts":[75],"are":[79,138],"independent,":[80],"we":[81],"map":[82],"these":[83],"respectively":[84],"to":[85,97],"GPUs":[87],"CPUs.":[89],"Careful":[90],"analysis":[91],"performed":[96],"distribute":[98],"work":[99],"optimally":[100],"between":[101],"CPUs":[104],"accelerators.":[108],"first":[110],"develop":[111],"single":[113,147],"version":[115,127],"where":[116],"CPU":[118],"part":[119],"parallelized":[121],"OpenMP":[123],"via":[128],"CUDA.":[129],"New":[130],"parallel":[131],"algorithms":[132],"for":[133,145,160],"creating":[134],"data":[136],"structures":[137],"presented":[139],"together":[140],"load":[142],"balancing":[143],"strategies":[144],"distributed":[150],"multiple-node":[151],"versions.":[152],"Our":[153],"can":[155],"perform":[156],"128M":[161],"particles":[162],"16":[164],"nodes":[165],"4.23":[167],"seconds,":[168],"performance":[170],"not":[171],"achieved":[172],"by":[173],"others":[174],"literature":[177],"clusters.":[180]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}