{"id":"https://openalex.org/W2104110430","doi":"https://doi.org/10.1145/2063384.2063394","title":"Parallel reduction to condensed forms for symmetric eigenvalue problems using aggregated fine-grained and memory-aware kernels","display_name":"Parallel reduction to condensed forms for symmetric eigenvalue problems using aggregated fine-grained and memory-aware kernels","publication_year":2011,"publication_date":"2011-11-08","ids":{"openalex":"https://openalex.org/W2104110430","doi":"https://doi.org/10.1145/2063384.2063394","mag":"2104110430"},"language":"en","primary_location":{"id":"doi:10.1145/2063384.2063394","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063384.2063394","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/A5101964224","display_name":"Azzam Haidar","orcid":"https://orcid.org/0000-0002-3177-2084"},"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":"Azzam Haidar","raw_affiliation_strings":["University of Tennessee, Knoxville, TN","University of Tennessee, 1122 Volunteer Blvd, Knoxville, TN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, TN","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee, 1122 Volunteer Blvd, Knoxville, TN","institution_ids":["https://openalex.org/I75027704"]}]},{"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":["KAUST Supercomputing Laboratory, Thuwal, Saudi Arabia","[KAUST Supercomputing Laboratory, Thuwal, Saudi Arabia]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAUST Supercomputing Laboratory, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"[KAUST Supercomputing Laboratory, Thuwal, Saudi Arabia]","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"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":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee, Knoxville, TN","University of Tennessee, 1122 Volunteer Blvd, Knoxville, TN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, TN","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee, 1122 Volunteer Blvd, Knoxville, TN","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.996999979019165,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9851999878883362,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/tridiagonal-matrix","display_name":"Tridiagonal matrix","score":0.7682414650917053},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.7481191158294678},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.719667911529541},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6917790174484253},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.5652009844779968},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5518659353256226},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5439517498016357},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5268815159797668},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.525759756565094},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5013527870178223},{"id":"https://openalex.org/keywords/tile","display_name":"Tile","score":0.4999268054962158},{"id":"https://openalex.org/keywords/symmetric-matrix","display_name":"Symmetric matrix","score":0.4305819869041443},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3826214075088501},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33190807700157166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1731416881084442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08839264512062073}],"concepts":[{"id":"https://openalex.org/C51647924","wikidata":"https://www.wikidata.org/wiki/Q1755277","display_name":"Tridiagonal matrix","level":3,"score":0.7682414650917053},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.7481191158294678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.719667911529541},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6917790174484253},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.5652009844779968},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5518659353256226},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5439517498016357},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5268815159797668},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.525759756565094},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5013527870178223},{"id":"https://openalex.org/C2780728851","wikidata":"https://www.wikidata.org/wiki/Q468402","display_name":"Tile","level":2,"score":0.4999268054962158},{"id":"https://openalex.org/C54848796","wikidata":"https://www.wikidata.org/wiki/Q339011","display_name":"Symmetric matrix","level":3,"score":0.4305819869041443},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3826214075088501},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33190807700157166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1731416881084442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08839264512062073},{"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2063384.2063394","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063384.2063394","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:10.1.1.228.4556","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.4556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.netlib.org/utk/people/JackDongarra/PAPERS/lawn254.pdf","raw_type":"text"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/575751","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/575751","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":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W94439627","https://openalex.org/W1570906644","https://openalex.org/W1576347883","https://openalex.org/W1842923156","https://openalex.org/W1991973947","https://openalex.org/W2016358047","https://openalex.org/W2025400771","https://openalex.org/W2030167104","https://openalex.org/W2050090934","https://openalex.org/W2069146503","https://openalex.org/W2080986154","https://openalex.org/W2081114193","https://openalex.org/W2095597068","https://openalex.org/W2102181290","https://openalex.org/W2105524676","https://openalex.org/W2107410315","https://openalex.org/W2108417208","https://openalex.org/W2119522963","https://openalex.org/W2124480634","https://openalex.org/W2136570295","https://openalex.org/W2145960411","https://openalex.org/W2164895445","https://openalex.org/W2168612748","https://openalex.org/W2561675875","https://openalex.org/W2798909945","https://openalex.org/W4229666556","https://openalex.org/W4237414616","https://openalex.org/W4248198501","https://openalex.org/W4320800818","https://openalex.org/W6638753708"],"related_works":["https://openalex.org/W2060901997","https://openalex.org/W2079120751","https://openalex.org/W2038377282","https://openalex.org/W2039525487","https://openalex.org/W1968185752","https://openalex.org/W2076299227","https://openalex.org/W2385136209","https://openalex.org/W2018718799","https://openalex.org/W2059940384","https://openalex.org/W2369254890"],"abstract_inverted_index":{"This":[0],"paper":[1,110],"introduces":[2],"a":[3,8,32,65,149],"novel":[4],"implementation":[5,114],"in":[6,97,108,116],"reducing":[7],"symmetric":[9,22,43],"dense":[10],"matrix":[11,38,150],"to":[12,42,47,118,126],"tridiagonal":[13,105],"form,":[14],"which":[15,68],"is":[16,39,111],"the":[17,29,36,48,82,94,104,127],"preprocessing":[18],"step":[19],"toward":[20],"solving":[21],"eigenvalue":[23],"problems.":[24],"Based":[25],"on":[26,138],"tile":[27,37],"algorithms,":[28],"reduction":[30,106],"follows":[31],"two-stage":[33],"approach,":[34],"where":[35],"first":[40],"reduced":[41],"band":[44],"form":[45],"prior":[46],"final":[49],"condensed":[50],"structure.":[51],"The":[52,101],"challenging":[53],"trade-off":[54],"between":[55],"algorithmic":[56],"performance":[57,102],"and":[58,73,120,133],"task":[59],"granularity":[60],"has":[61],"been":[62],"tackled":[63],"through":[64],"grouping":[66],"technique,":[67],"consists":[69],"of":[70,152],"aggregating":[71],"fine-grained":[72],"memory-aware":[74],"computational":[75],"tasks":[76,96],"during":[77],"both":[78],"stages,":[79],"while":[80],"sustaining":[81],"application's":[83],"overall":[84],"high":[85],"performance.":[86],"A":[87],"dynamic":[88],"runtime":[89],"environment":[90],"system":[91,147],"then":[92],"schedules":[93],"different":[95],"an":[98,139],"out-of-order":[99],"fashion.":[100],"for":[103],"reported":[107],"this":[109],"unprecedented.":[112],"Our":[113],"results":[115],"up":[117],"50-fold":[119],"12-fold":[121],"improvement":[122],"(130":[123],"Gflop/s)":[124],"compared":[125],"equivalent":[128],"routines":[129],"from":[130],"LAPACK":[131],"V3.2":[132],"Intel":[134],"MKL":[135],"V10.3,":[136],"respectively,":[137],"eight":[140],"socket":[141],"hexa-core":[142],"AMD":[143],"Opteron":[144],"multicore":[145],"shared-memory":[146],"with":[148],"size":[151],"24000":[153],"x":[154],"24000.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}