{"id":"https://openalex.org/W2791204867","doi":"https://doi.org/10.1007/978-3-319-69953-0_16","title":"Optimization of Hierarchical Matrix Computation on GPU","display_name":"Optimization of Hierarchical Matrix Computation on GPU","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2791204867","doi":"https://doi.org/10.1007/978-3-319-69953-0_16","mag":"2791204867"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-69953-0_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-69953-0_16","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-319-69953-0_16.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-319-69953-0_16.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080142917","display_name":"Satoshi Ohshima","orcid":"https://orcid.org/0000-0003-4073-5688"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Satoshi Ohshima","raw_affiliation_strings":["Kyushu University, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052397462","display_name":"Ichitaro Yamazaki","orcid":"https://orcid.org/0000-0002-6196-2508"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ichitaro Yamazaki","raw_affiliation_strings":["University of Tennessee, Knoxville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"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":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024747717","display_name":"Rio Yokota","orcid":"https://orcid.org/0000-0001-7573-7873"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rio Yokota","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5080142917"],"corresponding_institution_ids":["https://openalex.org/I135598925"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.8811,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.67133847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"274","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9962999820709229,"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/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9918000102043152,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8061835765838623},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.79639732837677},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7708194255828857},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7559511661529541},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.6124579310417175},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5977204442024231},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5935146808624268},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5857712030410767},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.569373607635498},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4908679127693176},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4161324203014374},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4128054678440094},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.131095290184021},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.1156153678894043},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08971315622329712},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08543708920478821}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8061835765838623},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.79639732837677},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7708194255828857},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7559511661529541},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.6124579310417175},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5977204442024231},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5935146808624268},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5857712030410767},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.569373607635498},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4908679127693176},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4161324203014374},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4128054678440094},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.131095290184021},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.1156153678894043},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08971315622329712},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08543708920478821},{"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-319-69953-0_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-69953-0_16","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-319-69953-0_16.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50404000","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100759346","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":"Conference Paper"}],"best_oa_location":{"id":"doi:10.1007/978-3-319-69953-0_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-69953-0_16","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-319-69953-0_16.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5}],"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"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320322832","display_name":"University of Tokyo","ror":"https://ror.org/057zh3y96"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320336976","display_name":"Research Institute for Information Technology, Kyushu University","ror":null},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2791204867.pdf","grobid_xml":"https://content.openalex.org/works/W2791204867.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W157521421","https://openalex.org/W1940191795","https://openalex.org/W1992979775","https://openalex.org/W2018419001","https://openalex.org/W2141719776","https://openalex.org/W2340769696","https://openalex.org/W2622400073","https://openalex.org/W2623469754","https://openalex.org/W2886763336","https://openalex.org/W2887740241","https://openalex.org/W2906218028"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W4206811032","https://openalex.org/W2995605830","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2093666864"],"abstract_inverted_index":{"The":[0,113],"demand":[1],"for":[2,24],"dense":[3,48,64],"matrix":[4,28,49],"computation":[5,53],"in":[6,146],"large":[7],"scale":[8],"and":[9,65,98,108],"complex":[10,60],"simulations":[11],"is":[12,22,34,58,74],"increasing;":[13],"however,":[14],"the":[15,44,52,70,136,141,147,155],"memory":[16,45],"capacity":[17],"of":[18,47,54,63,143,154],"current":[19],"computer":[20],"system":[21],"insufficient":[23],"such":[25,128],"simulations.":[26],"Hierarchical":[27],"method":[29,40],"(":[30],"$$\\mathcal":[31,55,71,79],"{H}$$":[32,56,72,80],"-matrices)":[33],"attracting":[35],"attention":[36],"as":[37],"a":[38,87,131],"computational":[39],"that":[41,62,153],"can":[42,121],"reduce":[43],"requirements":[46],"computations.":[50],"However,":[51],"-matrices":[57,73],"more":[59],"than":[61],"sparse":[66],"matrices;":[67],"thus,":[68],"accelerating":[69],"required.":[75],"We":[76,93],"focus":[77],"on":[78,86],"-matrix":[81],"-":[82],"vector":[83],"multiplication":[84],"(HMVM)":[85],"single":[88,132],"NVIDIA":[89],"Tesla":[90],"P100":[91],"GPU.":[92],"implement":[94],"five":[95],"GPU":[96,133,158],"kernels":[97,129],"compare":[99],"execution":[100],"times":[101],"among":[102],"various":[103],"processors":[104],"(the":[105],"Broadwell-EP,":[106],"Skylake-SP,":[107],"Knights":[109],"Landing)":[110],"by":[111],"OpenMP.":[112],"results":[114],"show":[115],"that,":[116],"although":[117],"an":[118],"HMVM":[119],"kernel":[120,134],"compute":[122],"many":[123],"small":[124],"GEMV":[125],"kernels,":[126],"merging":[127],"to":[130,152],"was":[135,150],"most":[137],"effective":[138],"implementation.":[139],"Moreover,":[140],"performance":[142],"BATCHED":[144],"BLAS":[145],"MAGMA":[148],"library":[149],"comparable":[151],"manually":[156],"tuned":[157],"kernel.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}
