{"id":"https://openalex.org/W2899115284","doi":"https://doi.org/10.1109/cluster.2018.00016","title":"Load-Balancing-Aware Parallel Algorithms of H-Matrices with Adaptive Cross Approximation for GPUs","display_name":"Load-Balancing-Aware Parallel Algorithms of H-Matrices with Adaptive Cross Approximation for GPUs","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2899115284","doi":"https://doi.org/10.1109/cluster.2018.00016","mag":"2899115284"},"language":"en","primary_location":{"id":"doi:10.1109/cluster.2018.00016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2018.00016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Cluster Computing (CLUSTER)","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/A5101918467","display_name":"Tetsuya Hoshino","orcid":"https://orcid.org/0009-0004-5349-6852"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Hoshino","raw_affiliation_strings":["Information Technology Center, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042523389","display_name":"Akihiro Ida","orcid":"https://orcid.org/0000-0001-7751-1093"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiro Ida","raw_affiliation_strings":["Information Technology Center, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082103530","display_name":"Toshihiro Hanawa","orcid":"https://orcid.org/0000-0002-2970-6037"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshihiro Hanawa","raw_affiliation_strings":["Information Technology Center, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109365632","display_name":"Kengo Nakajima","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kengo Nakajima","raw_affiliation_strings":["Information Technology Center, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.29820649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9988999962806702,"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":0.9988999962806702,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9950000047683716,"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"}},{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.7519636154174805},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6927465200424194},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.6805405616760254},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.6370049715042114},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.602238655090332},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5943225026130676},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5485910773277283},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.4829222857952118},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.47970932722091675},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.44527560472488403},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.42859983444213867},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4146081209182739},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.4121435284614563},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1665276288986206},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.09801039099693298},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.07714059948921204}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519636154174805},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6927465200424194},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.6805405616760254},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.6370049715042114},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.602238655090332},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5943225026130676},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5485910773277283},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.4829222857952118},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.47970932722091675},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.44527560472488403},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.42859983444213867},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4146081209182739},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.4121435284614563},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1665276288986206},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.09801039099693298},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.07714059948921204},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster.2018.00016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2018.00016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G458168474","display_name":"Enhancement of H-matrix library and optimization for next generation supercomputers","funder_award_id":"17H01749","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1569304948","https://openalex.org/W1588915715","https://openalex.org/W1973786815","https://openalex.org/W1976986637","https://openalex.org/W1992979775","https://openalex.org/W1995480310","https://openalex.org/W2018419001","https://openalex.org/W2037941836","https://openalex.org/W2078704642","https://openalex.org/W2114842032","https://openalex.org/W2160774872","https://openalex.org/W2518567779","https://openalex.org/W2622400073","https://openalex.org/W2791204867","https://openalex.org/W2886763336","https://openalex.org/W4255359261"],"related_works":["https://openalex.org/W1974923383","https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W2085105049","https://openalex.org/W2526069705","https://openalex.org/W2024016913","https://openalex.org/W2019153376","https://openalex.org/W2981664121","https://openalex.org/W2796552083","https://openalex.org/W2949197156"],"abstract_inverted_index":{"Hierarchical":[0],"matrices":[1,52],"(H-matrices)":[2],"are":[3,82,90],"an":[4,171,189,196],"approximation":[5,78,84],"technique":[6],"for":[7,60,122,155,177,225,242],"dense":[8,33,51],"matrices,":[9],"such":[10],"as":[11],"the":[12,16,46,106,119,127,131,136,147,164,205,209,231,233,243],"coefficient":[13],"matrix":[14],"of":[15,28,36,43,50,99,118,208],"boundary":[17],"element":[18],"method":[19],"(BEM).":[20],"An":[21],"H-matrix":[22,173],"is":[23,58,109,133,139,170,223],"expressed":[24],"by":[25],"a":[26,219,237],"set":[27],"low-rank":[29,83],"approximated":[30],"and":[31,57,195],"small":[32,66],"sub-matrices,":[34],"each":[35,113,123],"which":[37,81,169],"has":[38],"various":[39],"ranks.":[40],"The":[41,115,180,201],"use":[42],"H-matrices":[44,156],"reduces":[45],"required":[47],"memory":[48,67],"footprint":[49],"from":[53],"O(N^2)":[54],"to":[55,70,87,93,112,145,229],"O(NlogN)":[56],"suitable":[59],"many-core":[61,95,160],"processors":[62,96],"that":[63,157],"have":[64],"relatively":[65],"capacities":[68],"compared":[69],"traditional":[71],"CPUs.":[72],"However,":[73],"existing":[74,103,226],"parallel":[75,104,152,227],"adaptive":[76],"cross":[77],"(ACA)":[79],"algorithms,":[80,105],"algorithms":[85,154,166,182,211,228,235],"used":[86],"construct":[88],"H-matrices,":[89],"not":[91],"designed":[92],"exploit":[94],"in":[97,212,218],"terms":[98],"load":[100,117],"balancing.":[101],"In":[102],"ACA":[107,120,137,153],"process":[108,121,138],"independently":[110],"applied":[111],"sub-matrix.":[114],"computational":[116],"sub-matrix":[124],"depends":[125],"on":[126,159,188],"sub-matrix's":[128],"rank;":[129],"however,":[130],"rank":[132],"defined":[134],"after":[135],"applied.":[140],"This":[141],"makes":[142],"it":[143,222],"difficult":[144,224],"balance":[146,230],"load.":[148],"We":[149,162],"propose":[150],"load-balancing-aware":[151],"focus":[158],"processors.":[161],"implemented":[163],"proposed":[165,181,210,234],"into":[167],"HACApK,":[168],"open-source":[172],"library":[174],"originally":[175],"developed":[176],"CPU-based":[178],"clusters.":[179],"were":[183],"evaluated":[184],"using":[185],"BEM":[186],"problems":[187],"NVIDIA":[190],"Tesla":[191],"P100":[192],"GPU":[193,214],"(P100)":[194],"Intel":[197],"Xeon":[198],"Broadwell":[199],"processor.":[200],"evaluation":[202],"results":[203],"demonstrate":[204],"improved":[206],"performance":[207,240],"all":[213],"cases.":[215],"For":[216],"example,":[217],"case":[220],"where":[221],"load,":[232],"achieved":[236],"12.9":[238],"times":[239],"improvement":[241],"P100.":[244]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}