{"id":"https://openalex.org/W995198334","doi":"https://doi.org/10.1145/2894747","title":"A High Performance QDWH-SVD Solver Using Hardware Accelerators","display_name":"A High Performance QDWH-SVD Solver Using Hardware Accelerators","publication_year":2016,"publication_date":"2016-08-13","ids":{"openalex":"https://openalex.org/W995198334","doi":"https://doi.org/10.1145/2894747","mag":"995198334"},"language":"en","primary_location":{"id":"doi:10.1145/2894747","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2894747","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10754/348632","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064027099","display_name":"Dalal Sukkari","orcid":"https://orcid.org/0000-0002-4228-4211"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Dalal Sukkari","raw_affiliation_strings":["Extreme Computing Research Center, KAUST, Thuwal Jeddah, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, KAUST, Thuwal Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017526753","display_name":"Hatem Ltaief","orcid":"https://orcid.org/0000-0002-6897-1095"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Hatem Ltaief","raw_affiliation_strings":["Extreme Computing Research Center, KAUST, Thuwal Jeddah, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, KAUST, Thuwal Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021283893","display_name":"David E. Keyes","orcid":"https://orcid.org/0000-0002-4052-7224"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"David Keyes","raw_affiliation_strings":["Extreme Computing Research Center, KAUST, Thuwal Jeddah, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, KAUST, Thuwal Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":3.5118,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.92705149,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"43","issue":"1","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998000264167786,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9962999820709229,"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/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.995199978351593,"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/singular-value-decomposition","display_name":"Singular value decomposition","score":0.8984272480010986},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.7812989950180054},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.750135600566864},{"id":"https://openalex.org/keywords/singular-value","display_name":"Singular value","score":0.727935791015625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5997108817100525},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5771076679229736},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5533410310745239},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4761536121368408},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4545511305332184},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4423788785934448},{"id":"https://openalex.org/keywords/eigendecomposition-of-a-matrix","display_name":"Eigendecomposition of a matrix","score":0.428352952003479},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4219967722892761},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.30683082342147827},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2755833864212036}],"concepts":[{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.8984272480010986},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.7812989950180054},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.750135600566864},{"id":"https://openalex.org/C109282560","wikidata":"https://www.wikidata.org/wiki/Q4166054","display_name":"Singular value","level":3,"score":0.727935791015625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5997108817100525},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5771076679229736},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5533410310745239},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4761536121368408},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4545511305332184},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4423788785934448},{"id":"https://openalex.org/C169756996","wikidata":"https://www.wikidata.org/wiki/Q194919","display_name":"Eigendecomposition of a matrix","level":3,"score":0.428352952003479},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4219967722892761},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.30683082342147827},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2755833864212036},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2894747","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2894747","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/348632","is_oa":true,"landing_page_url":"http://hdl.handle.net/10754/348632","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Technical Report"}],"best_oa_location":{"id":"pmh:oai:repository.kaust.edu.sa:10754/348632","is_oa":true,"landing_page_url":"http://hdl.handle.net/10754/348632","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Technical Report"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W154771833","https://openalex.org/W1229772349","https://openalex.org/W1576347883","https://openalex.org/W1958574493","https://openalex.org/W1964629279","https://openalex.org/W1987255606","https://openalex.org/W1991973947","https://openalex.org/W1997301958","https://openalex.org/W2016279572","https://openalex.org/W2016606481","https://openalex.org/W2039937805","https://openalex.org/W2052799831","https://openalex.org/W2057069782","https://openalex.org/W2059076129","https://openalex.org/W2077166865","https://openalex.org/W2078841894","https://openalex.org/W2083246623","https://openalex.org/W2102181290","https://openalex.org/W2104110430","https://openalex.org/W2105524676","https://openalex.org/W2107410315","https://openalex.org/W2119522963","https://openalex.org/W2140064412","https://openalex.org/W2156779053","https://openalex.org/W2169378749","https://openalex.org/W2397480569","https://openalex.org/W2946724226","https://openalex.org/W3154152825","https://openalex.org/W4237384699"],"related_works":["https://openalex.org/W4365788292","https://openalex.org/W1976060951","https://openalex.org/W3013553788","https://openalex.org/W2083748498","https://openalex.org/W995198334","https://openalex.org/W2049453722","https://openalex.org/W2484275557","https://openalex.org/W1892994333","https://openalex.org/W1976542806","https://openalex.org/W2462387008"],"abstract_inverted_index":{"This":[0],"article":[1],"describes":[2],"a":[3],"new":[4,123],"high":[5,124],"performance":[6,125],"implementation":[7,126,175],"of":[8,50,62,97,169,176],"the":[9,46,51,55,59,63,69,73,79,84,94,98,117,142,189],"QR-based":[10],"Dynamically":[11],"Weighted":[12],"Halley":[13],"Singular":[14],"Value":[15],"Decomposition":[16],"(QDWH-SVD)":[17],"solver":[18,120],"on":[19,127,178],"multicore":[20],"architecture":[21],"enhanced":[22],"with":[23],"multiple":[24],"GPUs.":[25],"The":[26,171],"standard":[27,118],"QDWH-SVD":[28,99,159,177],"algorithm":[29],"was":[30],"introduced":[31],"by":[32,162,166],"Nakatsukasa":[33],"and":[34,39,72,77,149],"Higham":[35],"(SIAM":[36],"SISC,":[37],"2013)":[38],"combines":[40],"three":[41],"successive":[42],"computational":[43],"stages:":[44],"(1)":[45],"polar":[47,65],"decomposition":[48],"calculation":[49],"original":[52],"matrix":[53,138],"using":[54],"QDWH":[56],"algorithm,":[57,121],"(2)":[58],"symmetric":[60],"eigendecomposition":[61],"resulting":[64],"factor":[66],"to":[67,82,105,116,133,141,185],"obtain":[68],"singular":[70,75,87,113,155,172],"values":[71,156],"right":[74],"vectors,":[76],"(3)":[78],"matrix-matrix":[80],"multiplication":[81],"get":[83],"associated":[85],"left":[86],"vectors.":[88],"A":[89],"comprehensive":[90],"test":[91],"suite":[92],"highlights":[93],"numerical":[95],"robustness":[96],"solver.":[100],"Although":[101],"it":[102],"performs":[103],"up":[104,132,184],"two":[106],"times":[107],"more":[108,164],"flops":[109,165],"when":[110,153],"computing":[111],"all":[112],"vectors":[114],"compared":[115,140],"SVD":[119],"our":[122],"single":[128,179],"GPU":[129,180],"results":[130],"in":[131],"4\u00d7":[134],"improvements":[135],"for":[136],"asymptotic":[137],"sizes,":[139],"equivalent":[143,192],"routines":[144],"from":[145],"existing":[146,191],"state-of-the-art":[147],"open-source":[148],"commercial":[150],"libraries.":[151],"However,":[152],"only":[154,174],"are":[157],"needed,":[158],"is":[160],"penalized":[161],"performing":[163],"an":[167],"order":[168],"magnitude.":[170],"value":[173],"can":[181],"still":[182],"run":[183],"18%":[186],"faster":[187],"than":[188],"best":[190],"routines.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
