{"id":"https://openalex.org/W2795117369","doi":"https://doi.org/10.1137/18m1173599","title":"Extreme Scale FMM-Accelerated Boundary Integral Equation Solver for Wave Scattering","display_name":"Extreme Scale FMM-Accelerated Boundary Integral Equation Solver for Wave Scattering","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2795117369","doi":"https://doi.org/10.1137/18m1173599","mag":"2795117369"},"language":"en","primary_location":{"id":"doi:10.1137/18m1173599","is_oa":false,"landing_page_url":"https://doi.org/10.1137/18m1173599","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1803.09948","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032141491","display_name":"Mustafa Abduljabbar","orcid":"https://orcid.org/0000-0003-1280-130X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mustafa Abduljabbar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045148446","display_name":"Mohammed Al Farhan","orcid":"https://orcid.org/0000-0002-4988-4674"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammed Al Farhan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4988-4674","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087577348","display_name":"Noha Al-Harthi","orcid":"https://orcid.org/0000-0003-1746-8833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noha Al-Harthi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007110891","display_name":"Rui Chen","orcid":"https://orcid.org/0000-0002-3250-5615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024747717","display_name":"Rio Yokota","orcid":"https://orcid.org/0000-0001-7573-7873"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rio Yokota","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001869485","display_name":"Hakan Ba\u011fc\u0131","orcid":"https://orcid.org/0000-0003-3867-5786"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hakan Bagci","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021283893","display_name":"David E. Keyes","orcid":"https://orcid.org/0000-0002-4052-7224"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Keyes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1502,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49999204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"41","issue":"3","first_page":"C245","last_page":"C268"},"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":0.9976000189781189,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/parallel-computing","display_name":"Parallel computing","score":0.7942295074462891},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.766250729560852},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6269283890724182},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5230318307876587},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.5061284899711609},{"id":"https://openalex.org/keywords/single-precision-floating-point-format","display_name":"Single-precision floating-point format","score":0.48483598232269287},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.4587547779083252},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.457842081785202},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.45065686106681824},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.4274333715438843},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4095659852027893},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26118919253349304}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7942295074462891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766250729560852},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6269283890724182},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5230318307876587},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.5061284899711609},{"id":"https://openalex.org/C133095886","wikidata":"https://www.wikidata.org/wiki/Q1307173","display_name":"Single-precision floating-point format","level":3,"score":0.48483598232269287},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4587547779083252},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.457842081785202},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.45065686106681824},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.4274333715438843},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4095659852027893},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26118919253349304},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1137/18m1173599","is_oa":false,"landing_page_url":"https://doi.org/10.1137/18m1173599","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:arXiv.org:1803.09948","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.09948","pdf_url":"https://arxiv.org/pdf/1803.09948","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":"mag:2795117369","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1803.09948","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0004347711","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100815304","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal article"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/627504","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/627504","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"doi:10.48550/arxiv.1803.09948","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1803.09948","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.09948","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.09948","pdf_url":"https://arxiv.org/pdf/1803.09948","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":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8500000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2795117369.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1517282106","https://openalex.org/W1525968066","https://openalex.org/W1570934444","https://openalex.org/W1795455446","https://openalex.org/W1963750172","https://openalex.org/W1963960519","https://openalex.org/W1965277013","https://openalex.org/W1965754619","https://openalex.org/W1971676041","https://openalex.org/W1972234329","https://openalex.org/W2000882268","https://openalex.org/W2006808706","https://openalex.org/W2017654099","https://openalex.org/W2022874901","https://openalex.org/W2022916138","https://openalex.org/W2030971498","https://openalex.org/W2037512470","https://openalex.org/W2046842734","https://openalex.org/W2048145697","https://openalex.org/W2054357898","https://openalex.org/W2076450467","https://openalex.org/W2083206954","https://openalex.org/W2086641099","https://openalex.org/W2111148770","https://openalex.org/W2118031182","https://openalex.org/W2120229493","https://openalex.org/W2127570421","https://openalex.org/W2128556617","https://openalex.org/W2142362669","https://openalex.org/W2161612777","https://openalex.org/W2163118868","https://openalex.org/W2166453857","https://openalex.org/W2167846346","https://openalex.org/W2168963553","https://openalex.org/W2417194949","https://openalex.org/W2474724963","https://openalex.org/W2509857574","https://openalex.org/W2544527082","https://openalex.org/W2604937039","https://openalex.org/W2740116753","https://openalex.org/W2752932982","https://openalex.org/W2758612127","https://openalex.org/W2801656560","https://openalex.org/W2950888753","https://openalex.org/W2962927345","https://openalex.org/W3104266598"],"related_works":["https://openalex.org/W2055821122","https://openalex.org/W2971796967","https://openalex.org/W2253091535","https://openalex.org/W2579886509","https://openalex.org/W3213294124","https://openalex.org/W2607752035","https://openalex.org/W2758285411","https://openalex.org/W2953672018","https://openalex.org/W2804126825","https://openalex.org/W2900251117","https://openalex.org/W2994869848","https://openalex.org/W2093379922","https://openalex.org/W2120120433","https://openalex.org/W2964124509","https://openalex.org/W3038057449","https://openalex.org/W2772864661","https://openalex.org/W2575711770","https://openalex.org/W3119652125","https://openalex.org/W2806115898","https://openalex.org/W2775027130"],"abstract_inverted_index":{"We":[0,39,58,83,150],"present":[1],"a":[2,104,127,133,271,319,328],"boundary":[3],"integral":[4,228,266],"equation":[5,229],"solver":[6],"for":[7,11,35,63,74,223,249,259,294,315],"wave":[8],"scattering":[9,216],"suited":[10],"many-core":[12],"processors,":[13],"which":[14,28,247,268],"are":[15,33,275,289,302],"expected":[16,290],"to":[17,51,96,99,145,175,241,257,263,291,304],"be":[18,292],"the":[19,41,46,53,76,119,146,157,165,193,199,202,211,214,224,242,282,312,316],"building":[20],"blocks":[21],"of":[22,81,103,118,126,169,185,189,201,205,213,226,239,251,311],"energy-austere":[23],"exascale":[24],"systems,":[25],"and":[26,30,45,66,69,87,92,116,132,164,234,284,318],"on":[27,192],"algorithmic":[29],"architecture-oriented":[31],"optimizations":[32],"essential":[34],"achieving":[36],"worthy":[37],"performance.":[38],"use":[40,208],"GMRES":[42],"iterative":[43],"method":[44,49],"fast":[47],"multipole":[48],"(FMM)":[50],"implement":[52,59],"matrix-vector":[54],"product":[55],"(MatVec)":[56],"kernel.":[57],"highly":[60],"optimized":[61],"kernels":[62],"both":[64],"shared-":[65],"distributed-memory":[67],"architectures":[68],"provide":[70],"various":[71],"performance":[72,125],"models":[73],"tuning":[75],"task-based":[77],"tree":[78],"traversal":[79,112],"implementation":[80,204,250],"FMM.":[82,170],"develop":[84],"optimal":[85],"architecture-specific":[86],"algorithm-aware":[88],"partitioning,":[89],"load":[90],"balancing,":[91],"communication":[93,162],"reducing":[94],"mechanisms":[95],"scale":[97],"up":[98,174],"6,144":[100],"compute":[101],"nodes":[102],"Cray":[105,195],"XC40":[106],"with":[107,156,230],"196,608":[108],"hardware":[109],"cores.":[110],"Task-based":[111],"achieves":[113],"roughly":[114],"77%":[115],"60%":[117],"peak":[120],"single":[121],"precision":[122],"floating":[123],"point":[124],"56-core":[128],"Skylake":[129],"Scalable":[130],"processor":[131],"72-core":[134],"Knights":[135],"Landing":[136],"processor,":[137],"respectively.":[138],"These":[139,171],"represent":[140],"approximately":[141],"sevenfold":[142],"speedups":[143],"compared":[144],"baseline":[147],"scalar":[148],"code.":[149],"report":[151],"weak":[152],"scalability":[153,285],"in":[154,173,178,183,210,270,278,327],"accordance":[155],"best":[158],"possible":[159],"$O(\\log":[160],"P)$":[161],"complexity":[163,168],"theoretical":[166],"scaling":[167,180],"result":[172],"85%":[176],"efficiency":[177,283],"strong":[179],"while":[181],"computing":[182],"excess":[184],"2":[186],"billion":[187],"degrees":[188],"freedom":[190],"(DoFs)":[191],"full-scale":[194],"XC40.":[196],"To":[197],"demonstrate":[198],"applicability":[200],"proposed":[203],"FMM,":[206],"we":[207],"it":[209],"solution":[212,314],"acoustic":[215],"problem":[217],"involving":[218,244],"soft":[219],"targets.":[220],"This":[221],"calls":[222],"discretization":[225],"an":[227,231],"oscillatory":[232],"kernel":[233],"(weak)":[235],"$1/R$":[236],"singularity.":[237],"Applications":[238],"FMM":[240],"problems":[243],"hard":[245],"targets,":[246],"call":[248],"more":[252,329],"complicated":[253],"singularity":[254],"extraction/cancellation":[255],"schemes":[256],"account":[258],"$1/R^2$":[260],"singularity,":[261],"or":[262],"Burton--Miller":[264],"surface":[265],"formulation,":[267],"results":[269,286,301],"well-conditioned":[272],"matrix":[273],"system,":[274],"not":[276],"considered":[277],"this":[279],"work,":[280],"but":[281],"demonstrated":[287],"here":[288],"observed":[293],"these":[295],"cases":[296],"as":[297],"well.":[298],"The":[299],"numerical":[300],"converged":[303],"within":[305],"1.0e-4":[306],"relative":[307],"2-norm":[308],"residual":[309],"accuracy":[310],"analytical":[313],"sphere,":[317],"multiple":[320],"flower-shaped":[321],"scatterer":[322],"displays":[323],"comparable":[324],"algebraic":[325],"convergence":[326],"general":[330],"setting.":[331]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}