{"id":"https://openalex.org/W2154874153","doi":"https://doi.org/10.1109/ipdps.2009.5160940","title":"Fast development of dense linear algebra codes on graphics processors","display_name":"Fast development of dense linear algebra codes on graphics processors","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2154874153","doi":"https://doi.org/10.1109/ipdps.2009.5160940","mag":"2154874153"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2009.5160940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5160940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel & Distributed Processing","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/A5056024850","display_name":"M. Jesus Zafont","orcid":null},"institutions":[{"id":"https://openalex.org/I10902133","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11","country_code":"ES","type":"education","lineage":["https://openalex.org/I10902133"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"M. Jesus Zafont","raw_affiliation_strings":["Departamento de Ingenier\u00eda y Ciencia de los Computadores, Universidad Jaume I, Castellon, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Ingenier\u00eda y Ciencia de los Computadores, Universidad Jaume I, Castellon, Spain","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034172411","display_name":"Alberto F. Mart\u0131\u0301n","orcid":"https://orcid.org/0000-0001-5751-4561"},"institutions":[{"id":"https://openalex.org/I10902133","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11","country_code":"ES","type":"education","lineage":["https://openalex.org/I10902133"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alberto Martin","raw_affiliation_strings":["Departamento de Ingenier\u00eda y Ciencia de los Computadores, Universidad Jaume I, Castellon, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Ingenier\u00eda y Ciencia de los Computadores, Universidad Jaume I, Castellon, Spain","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075880248","display_name":"Francisco D. Igual","orcid":"https://orcid.org/0000-0003-4480-9517"},"institutions":[{"id":"https://openalex.org/I10902133","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11","country_code":"ES","type":"education","lineage":["https://openalex.org/I10902133"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Francisco Igual","raw_affiliation_strings":["Departamento de Ingenier\u00eda y Ciencia de los Computadores, Universidad Jaume I, Castellon, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Ingenier\u00eda y Ciencia de los Computadores, Universidad Jaume I, Castellon, Spain","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012806004","display_name":"Enrique S. Quintana\u2013Ort\u0301\u0131","orcid":"https://orcid.org/0000-0002-5454-165X"},"institutions":[{"id":"https://openalex.org/I10902133","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11","country_code":"ES","type":"education","lineage":["https://openalex.org/I10902133"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Enrique S. Quintana-Orti","raw_affiliation_strings":["Departamento de Ingenier\u00eda y Ciencia de los Computadores, Universidad Jaume I, Castellon, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Ingenier\u00eda y Ciencia de los Computadores, Universidad Jaume I, Castellon, Spain","institution_ids":["https://openalex.org/I10902133"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I10902133"],"apc_list":null,"apc_paid":null,"fwci":0.5487,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64630793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"68","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T12303","display_name":"Tensor decomposition and applications","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8231867551803589},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.8078381419181824},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.7902733087539673},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6467007994651794},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.6092703342437744},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5895213484764099},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5190216302871704},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4729968011379242},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.425651878118515},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.414631724357605},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.329621821641922},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13652154803276062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8231867551803589},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.8078381419181824},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.7902733087539673},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6467007994651794},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6092703342437744},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5895213484764099},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5190216302871704},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4729968011379242},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.425651878118515},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.414631724357605},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.329621821641922},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13652154803276062},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2009.5160940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5160940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel & Distributed Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.142.4728","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.142.4728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/users/flame/pubs/hips.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1568272005","https://openalex.org/W1586776267","https://openalex.org/W1589918049","https://openalex.org/W1973305402","https://openalex.org/W2019592888","https://openalex.org/W2105528986","https://openalex.org/W2109098465","https://openalex.org/W2149822470","https://openalex.org/W4229666556","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2403987929","https://openalex.org/W2039814159","https://openalex.org/W2374847384","https://openalex.org/W2063512590","https://openalex.org/W160834089","https://openalex.org/W2112488134","https://openalex.org/W2988894191","https://openalex.org/W2132919497","https://openalex.org/W3208993877","https://openalex.org/W2137144623"],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2,97],"application":[3],"programming":[4,10],"interface":[5],"(API)":[6],"for":[7],"the":[8,14,25,34,40,44,49,60,83,106],"C":[9],"language":[11],"that":[12],"facilitates":[13],"development":[15],"of":[16,33,43,70,79],"dense":[17,80],"linear":[18,81],"algebra":[19],"algorithms":[20],"on":[21,31,96],"graphics":[22],"processors":[23],"applying":[24],"FLAME":[26],"methodology.":[27],"The":[28,66],"interface,":[29],"built":[30],"top":[32],"NVIDIA":[35,98],"CUBLAS":[36],"library,":[37],"implements":[38],"all":[39,93],"computational":[41],"functionality":[42],"FLAME/C":[45],"interface.":[46],"In":[47],"addition,":[48],"API":[50],"includes":[51],"data":[52],"transference":[53],"routines":[54],"to":[55],"explicitly":[56],"handle":[57],"communication":[58],"between":[59],"CPU":[61,107],"and":[62,68,91],"GPU":[63],"memory":[64],"spaces.":[65],"flexibility":[67],"simplicity-of-use":[69],"this":[71,87],"tool":[72],"are":[73],"illustrated":[74],"using":[75],"a":[76],"complex":[77],"operation":[78],"algebra:":[82],"Cholesky":[84],"factorization.":[85],"For":[86],"operation,":[88],"we":[89],"implement":[90],"evaluate":[92],"existing":[94],"variants":[95],"G80":[99],"processor,":[100],"attaining":[101],"speedups":[102],"7times":[103],"compared":[104],"with":[105],"implementations.":[108]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}