{"id":"https://openalex.org/W2130748128","doi":"https://doi.org/10.1137/10079906x","title":"Accelerating the Explicitly Restarted Arnoldi Method with GPUs Using an Autotuned Matrix Vector Product","display_name":"Accelerating the Explicitly Restarted Arnoldi Method with GPUs Using an Autotuned Matrix Vector Product","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2130748128","doi":"https://doi.org/10.1137/10079906x","mag":"2130748128"},"language":"en","primary_location":{"id":"doi:10.1137/10079906x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/10079906x","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":"article","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/A5051842697","display_name":"J\u00e9r\u00f4me Dubois","orcid":"https://orcid.org/0009-0001-1872-5603"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"J\u00e9r\u00f4me Dubois","raw_affiliation_strings":["jerome.dubois@cea.fr#TAB#"],"affiliations":[{"raw_affiliation_string":"jerome.dubois@cea.fr#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112345142","display_name":"Christophe Calvin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christophe Calvin","raw_affiliation_strings":["christophe.calvin@cea.fr#TAB#"],"affiliations":[{"raw_affiliation_string":"christophe.calvin@cea.fr#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108528905","display_name":"Serge G. Petiton","orcid":"https://orcid.org/0000-0002-8423-3682"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Serge Petiton","raw_affiliation_strings":["serge.petiton@lifl.fr#TAB#"],"affiliations":[{"raw_affiliation_string":"serge.petiton@lifl.fr#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051842697"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9766,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.77225169,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"33","issue":"5","first_page":"3010","last_page":"3019"},"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/T10591","display_name":"Theoretical and Computational Physics","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/3104","display_name":"Condensed Matter Physics"},"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/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9735000133514404,"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/speedup","display_name":"Speedup","score":0.9151583909988403},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7499228715896606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7115783095359802},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6681784391403198},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6345214247703552},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6050904989242554},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5698926448822021},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5630021095275879},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5291346311569214},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.47551992535591125},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4735923111438751},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4263794422149658},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.12300899624824524},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.10916519165039062},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0917673110961914}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.9151583909988403},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7499228715896606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7115783095359802},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6681784391403198},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6345214247703552},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6050904989242554},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5698926448822021},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5630021095275879},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5291346311569214},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.47551992535591125},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4735923111438751},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4263794422149658},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.12300899624824524},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.10916519165039062},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0917673110961914},{"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1137/10079906x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/10079906x","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:HAL:hal-01704337v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01704337","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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, 2011, 33 (5), pp.3010 - 3019. ⟨10.1137/10079906X⟩","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1976097264","https://openalex.org/W2000335122","https://openalex.org/W2044809217","https://openalex.org/W2088943630","https://openalex.org/W2147542748","https://openalex.org/W2149381887"],"related_works":["https://openalex.org/W2119534391","https://openalex.org/W2023770367","https://openalex.org/W2503137108","https://openalex.org/W1966576946","https://openalex.org/W2020279179","https://openalex.org/W2765743988","https://openalex.org/W2062253548","https://openalex.org/W2393490604","https://openalex.org/W2393707426","https://openalex.org/W2229844714"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,15,41,62,137,151,160,168],"parallelized":[4],"hybrid":[5],"single-vector":[6],"Arnoldi":[7,33,46,87],"algorithm":[8],"for":[9],"computing":[10],"approximations":[11],"to":[12,29,39,142,156,162,172,175],"eigenpairs":[13],"of":[14,24,44,79,94,140,154,170],"nonsymmetric":[16],"matrix.":[17],"We":[18],"are":[19,112],"interested":[20],"in":[21,61],"the":[22,32,45,70,80,86,92,95,147,176],"use":[23,51],"accelerators":[25],"and":[26,65,97,110,117,127,150,166],"multicore":[27,53,164],"units":[28,59],"speed":[30],"up":[31],"process.":[34],"The":[35,106],"main":[36],"goal":[37],"is":[38,74,104],"propose":[40],"parallel":[42],"version":[43],"solver,":[47],"which":[48],"can":[49],"efficiently":[50],"multiple":[52,56,122],"processors":[54],"or":[55],"graphics":[57],"processing":[58],"(GPUs)":[60],"mixed":[63],"coarse":[64],"fine":[66],"grain":[67],"fashion.":[68],"In":[69],"proposed":[71],"algorithms,":[72],"this":[73,163],"achieved":[75],"by":[76],"an":[77],"autotuning":[78],"matrix":[81],"vector":[82],"product":[83],"before":[84],"starting":[85],"eigensolver":[88],"as":[89,91],"well":[90],"reorganization":[93],"data":[96],"global":[98],"communications":[99],"so":[100],"that":[101],"communication":[102],"time":[103],"reduced.":[105],"execution":[107],"time,":[108],"performance,":[109],"scalability":[111],"assessed":[113],"with":[114],"well-known":[115],"dense":[116],"sparse":[118],"test":[119],"matrices":[120],"on":[121],"Nehalems,":[123],"GT200":[124],"NVidia":[125],"Tesla,":[126],"next":[128],"generation":[129],"Fermi":[130],"Tesla.":[131],"With":[132],"one":[133],"processor,":[134],"we":[135],"see":[136],"performance":[138],"speedup":[139,153,169],"2":[141,155],"3x":[143],"when":[144,158],"using":[145],"all":[146],"physical":[148],"cores,":[149],"total":[152],"8x":[157],"adding":[159],"GPU":[161],"unit,":[165],"hence":[167],"4":[171],"24x":[173],"compared":[174],"sequential":[177],"solver.":[178]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}