{"id":"https://openalex.org/W2123031400","doi":"https://doi.org/10.1145/1504176.1504196","title":"Solving dense linear systems on platforms with multiple hardware accelerators","display_name":"Solving dense linear systems on platforms with multiple hardware accelerators","publication_year":2009,"publication_date":"2009-02-14","ids":{"openalex":"https://openalex.org/W2123031400","doi":"https://doi.org/10.1145/1504176.1504196","mag":"2123031400"},"language":"en","primary_location":{"id":"doi:10.1145/1504176.1504196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1504176.1504196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGPLAN symposium on Principles and practice of parallel programming","raw_type":"proceedings-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/A5086284706","display_name":"Gregorio Quintana\u2010Ort\u00ed","orcid":"https://orcid.org/0000-0002-7912-7826"},"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":"Gregorio Quintana-Ort\u00ed","raw_affiliation_strings":["Universidad Jaime I, Castellon, Spain","Universidad Jaime I, Castellon, Spain#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Jaime I, Castellon, Spain","institution_ids":["https://openalex.org/I10902133"]},{"raw_affiliation_string":"Universidad Jaime I, Castellon, Spain#TAB#","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 D. Igual","raw_affiliation_strings":["Universidad Jaime I, Castellon, Spain","Universidad Jaime I, Castellon, Spain#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Jaime I, Castellon, Spain","institution_ids":["https://openalex.org/I10902133"]},{"raw_affiliation_string":"Universidad Jaime I, Castellon, Spain#TAB#","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"middle","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-Ort\u00ed","raw_affiliation_strings":["Universidad Jaime I, Castellon, Spain","Universidad Jaime I, Castellon, Spain#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Jaime I, Castellon, Spain","institution_ids":["https://openalex.org/I10902133"]},{"raw_affiliation_string":"Universidad Jaime I, Castellon, Spain#TAB#","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061722569","display_name":"Robert A. Geijn","orcid":"https://orcid.org/0009-0004-6434-8492"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert A. van de Geijn","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA","The University of Texas At Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas At Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.4043,"has_fulltext":false,"cited_by_count":104,"citation_normalized_percentile":{"value":0.99034822,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9991000294685364,"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":0.8202731609344482},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.774060070514679},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.6863478422164917},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6167859435081482},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.5670946836471558},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.5466915965080261},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.5339606404304504},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4984438419342041},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.4752095639705658},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.42094939947128296},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14714965224266052},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09210565686225891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202731609344482},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.774060070514679},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.6863478422164917},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6167859435081482},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.5670946836471558},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.5466915965080261},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.5339606404304504},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4984438419342041},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.4752095639705658},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.42094939947128296},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14714965224266052},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09210565686225891},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1504176.1504196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1504176.1504196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGPLAN symposium on Principles and practice of parallel programming","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.140.2509","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.140.2509","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/PPoPP2009_submitted.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.476.2747","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.476.2747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.rice.edu/~vs3/PDF/ppopp.09/p121-quintana-orti.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W54170965","https://openalex.org/W1518917853","https://openalex.org/W1536607540","https://openalex.org/W1541148880","https://openalex.org/W1555915743","https://openalex.org/W1568272005","https://openalex.org/W1748452786","https://openalex.org/W1947869163","https://openalex.org/W1973305402","https://openalex.org/W1988425770","https://openalex.org/W1990262300","https://openalex.org/W1992067978","https://openalex.org/W1993879252","https://openalex.org/W2002257715","https://openalex.org/W2005900526","https://openalex.org/W2016358047","https://openalex.org/W2038339443","https://openalex.org/W2038469228","https://openalex.org/W2044997049","https://openalex.org/W2047656763","https://openalex.org/W2063186542","https://openalex.org/W2095597068","https://openalex.org/W2099281741","https://openalex.org/W2105528986","https://openalex.org/W2109098465","https://openalex.org/W2121082877","https://openalex.org/W2124480634","https://openalex.org/W2124661136","https://openalex.org/W2136570295","https://openalex.org/W2136834900","https://openalex.org/W2151994818","https://openalex.org/W2152786407","https://openalex.org/W2159559515","https://openalex.org/W2159998508","https://openalex.org/W2166737459","https://openalex.org/W2187691968","https://openalex.org/W2896073125","https://openalex.org/W4205585823","https://openalex.org/W4253246067","https://openalex.org/W4255761504","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2120385681","https://openalex.org/W2022113063","https://openalex.org/W1974923383","https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W2085105049","https://openalex.org/W2592417500","https://openalex.org/W1939907483","https://openalex.org/W2056079253","https://openalex.org/W2929736795"],"abstract_inverted_index":{"In":[0,32,85],"a":[1,18,51,57,76,81,141],"previous":[2],"PPoPP":[3],"paper":[4,34],"we":[5,35,87,175],"showed":[6],"how":[7],"the":[8,13,43,90,109,116,135,166,170,179],"FLAME":[9,91],"methodology,":[10],"combined":[11],"with":[12,69,153],"SuperMatrix":[14,117],"runtime":[15,118],"system,":[16],"yields":[17],"simple":[19],"yet":[20],"powerful":[21],"solution":[22],"for":[23,46,165,188],"programming":[24,92],"dense":[25],"linear":[26],"algebra":[27],"operations":[28],"on":[29,140,184],"multicore":[30,58],"platforms.":[31],"this":[33,40,47,95,185],"provide":[36],"further":[37],"evidence":[38],"that":[39,89,100],"approach":[41],"solves":[42],"programmability":[44],"problem":[45],"domain":[48],"by":[49],"targeting":[50],"more":[52,78],"complex":[53],"architecture,":[54],"composed":[55],"of":[56,80,125],"processor":[59],"and":[60,161,169],"multiple":[61],"hardware":[62],"accelerators":[63],"(GPUs,":[64],"Cell":[65],"B.E.,":[66],"etc.),":[67],"each":[68],"its":[70],"own":[71],"local":[72],"memory,":[73],"resulting":[74],"in":[75,130],"platform":[77,152],"reminiscent":[79],"heterogeneous":[82],"distributed-memory":[83],"system.":[84],"particular,":[86],"show":[88],"model":[93],"accommodates":[94],"new":[96,186],"situation":[97],"effortlessly":[98],"so":[99],"no":[101],"significant":[102],"change":[103],"needs":[104],"to":[105,108,133,147,177],"be":[106,178],"made":[107],"codebase.":[110],"All":[111],"complexity":[112],"is":[113],"hidden":[114],"inside":[115],"scheduling":[119],"mechanism,":[120],"which":[121,174],"incorporates":[122],"software":[123],"implementations":[124],"standard":[126],"cache/memory":[127],"coherence":[128],"techniques":[129],"computer":[131],"architecture":[132,187],"improve":[134],"performance.":[136],"Our":[137],"experimental":[138],"evaluation":[139],"Intel":[142],"Xeon":[143],"8-core":[144],"host":[145],"linked":[146],"an":[148],"NVIDIA":[149],"Tesla":[150],"S870":[151],"four":[154],"GPUs":[155],"delivers":[156],"peak":[157],"performances":[158],"around":[159],"550":[160],"450":[162],"(single-precision)":[163],"GFLOPS":[164],"matrix-matrix":[167],"product":[168],"Cholesky":[171],"factorization,":[172],"respectively,":[173],"believe":[176],"best":[180],"performance":[181],"numbers":[182],"posted":[183],"such":[189],"operations.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":17},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":21}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
