{"id":"https://openalex.org/W2047614366","doi":"https://doi.org/10.1117/12.850538","title":"CULA: hybrid GPU accelerated linear algebra routines","display_name":"CULA: hybrid GPU accelerated linear algebra routines","publication_year":2010,"publication_date":"2010-04-22","ids":{"openalex":"https://openalex.org/W2047614366","doi":"https://doi.org/10.1117/12.850538","mag":"2047614366"},"language":"en","primary_location":{"id":"doi:10.1117/12.850538","doi":"https://doi.org/10.1117/12.850538","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.850538","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPIE Proceedings","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5044670292","display_name":"John R. Humphrey","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210112520","display_name":"EM Photonics (United States)","ror":"https://ror.org/01scb6a48","country_code":"US","type":"company","lineage":["https://openalex.org/I4210112520"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Humphrey","raw_affiliation_strings":["EM Photonics, Inc. (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EM Photonics, Inc. (United States)","institution_ids":["https://openalex.org/I4210112520"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039737560","display_name":"Daniel K. Price","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210112520","display_name":"EM Photonics (United States)","ror":"https://ror.org/01scb6a48","country_code":"US","type":"company","lineage":["https://openalex.org/I4210112520"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel K. Price","raw_affiliation_strings":["EM Photonics, Inc. (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EM Photonics, Inc. (United States)","institution_ids":["https://openalex.org/I4210112520"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005304347","display_name":"Kyle E. Spagnoli","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210112520","display_name":"EM Photonics (United States)","ror":"https://ror.org/01scb6a48","country_code":"US","type":"company","lineage":["https://openalex.org/I4210112520"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle E. Spagnoli","raw_affiliation_strings":["EM Photonics, Inc. (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EM Photonics, Inc. (United States)","institution_ids":["https://openalex.org/I4210112520"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063193673","display_name":"Aaron L. Paolini","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210112520","display_name":"EM Photonics (United States)","ror":"https://ror.org/01scb6a48","country_code":"US","type":"company","lineage":["https://openalex.org/I4210112520"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron L. Paolini","raw_affiliation_strings":["EM Photonics, Inc. (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EM Photonics, Inc. (United States)","institution_ids":["https://openalex.org/I4210112520"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027175476","display_name":"Eric J. Kelmelis","orcid":"https://orcid.org/0000-0002-7651-891X","observed_orcids":["https://orcid.org/0000-0002-7651-891X"]},"institutions":[{"id":"https://openalex.org/I4210112520","display_name":"EM Photonics (United States)","ror":"https://ror.org/01scb6a48","country_code":"US","type":"company","lineage":["https://openalex.org/I4210112520"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric J. Kelmelis","raw_affiliation_strings":["EM Photonics, Inc. (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EM Photonics, Inc. (United States)","institution_ids":["https://openalex.org/I4210112520"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210112520"],"apc_list":null,"apc_paid":null,"fwci":9.7055,"has_fulltext":false,"cited_by_count":148,"citation_normalized_percentile":{"value":0.98897838,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"7705","issue":null,"first_page":"770502","last_page":"770502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9765999913215637,"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":0.9765999913215637,"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":0.021700000390410423,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/gpu-acceleration","display_name":"GPU acceleration","score":0.9020000100135803},{"id":"https://openalex.org/keywords/linear-algebra-routines","display_name":"linear algebra routines","score":0.7269999980926514},{"id":"https://openalex.org/keywords/hybrid-cpu-gpu-computing","display_name":"CPU-GPU hybrid computing","score":0.902999997138977},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8759999871253967},{"id":"https://openalex.org/keywords/nvidia-gpus","display_name":"NVIDIA GPUs","score":0.800000011920929},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.9490000009536743},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"singular value decomposition","score":0.9919999837875366},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":1.0},{"id":"https://openalex.org/keywords/least-squares","display_name":"least squares","score":0.7540000081062317},{"id":"https://openalex.org/keywords/linear-systems-of-equations","display_name":"systems of linear equations","score":0.7749999761581421},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"parallel computing","score":0.7110000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8107585310935974},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.583936870098114},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42187952995300293},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.40286189317703247},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1117/12.850538","doi":"https://doi.org/10.1117/12.850538","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.850538","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPIE Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.456.478","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.456.478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.culatools.com/wp-content/uploads/2011/02/SPIE2010-CULA1.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1863336885","https://openalex.org/W2033964700","https://openalex.org/W2063186542","https://openalex.org/W2911830835"],"related_works":["https://openalex.org/W2484319592","https://openalex.org/W1967989368","https://openalex.org/W1004371317","https://openalex.org/W7098091127","https://openalex.org/W1658975261","https://openalex.org/W7096066604","https://openalex.org/W2169851036","https://openalex.org/W176243545","https://openalex.org/W111941793","https://openalex.org/W4407741229"],"abstract_inverted_index":{"The":[0,94],"modern":[1],"graphics":[2],"processing":[3,54,160],"unit":[4],"(GPU)":[5],"found":[6],"in":[7,162],"many":[8,174],"standard":[9],"personal":[10],"computers":[11],"is":[12,61,177],"a":[13,25,29,49,64,159],"highly":[14],"parallel":[15],"math\r\nprocessor":[16],"capable":[17],"of":[18,56,67,113],"nearly":[19],"1":[20],"TFLOPS":[21],"peak":[22],"throughput":[23],"at":[24,142],"cost":[26],"similar":[27],"to":[28,116,128,170,183],"high-end":[30],"CPU":[31,165],"and":[32,82,91,111,131,146,166],"an":[33],"excellent\r\nFLOPS/watt":[34],"ratio.":[35],"High-level":[36],"linear":[37,68,123],"algebra":[38,69,124],"operations":[39,115],"are":[40],"computationally":[41],"intense,":[42],"often":[43],"requiring":[44,108],"O(N3)":[45],"operations\r\nand":[46],"would":[47],"seem":[48],"natural":[50],"fit":[51],"for":[52],"the":[53,57,129,137,164,185],"power":[55],"GPU.":[58],"Our":[59,153],"work":[60,154,168,186],"on":[62,102,136],"CULA,":[63],"GPU":[65,130,167],"accelerated\r\nimplementation":[66],"routines.":[70],"We":[71],"present":[72],"results":[73],"from":[74,122],"factorizations":[75],"such":[76],"as":[77],"LU":[78],"decomposition,":[79],"singular\r\nvalue":[80],"decomposition":[81,84],"QR":[83],"along":[85],"with":[86],"applications":[87],"like":[88],"system":[89],"solution":[90],"least":[92],"squares.":[93],"GPU\r\nexecution":[95],"model":[96],"featured":[97],"by":[98,179],"NVIDIA":[99],"GPUs":[100],"based":[101],"CUDA":[103],"demands":[104],"very":[105],"strong":[106],"parallelism,":[107],"between":[109],"hundreds":[110],"thousands":[112],"simultaneous":[114],"achieve":[117],"high":[118],"performance.":[119],"Some":[120],"constructs":[121],"map":[125,133],"extremely":[126],"well":[127,141],"others":[132],"poorly.":[134],"CPUs,":[135],"other":[138],"hand,":[139],"do":[140,184],"smaller":[143],"order":[144],"parallelism":[145],"perform":[147],"acceptably":[148],"during":[149],"low-parallelism":[150],"code":[151],"segments.":[152],"addresses":[155],"this":[156,176],"via":[157],"hybrid":[158],"model,":[161],"which":[163],"simultaneously":[169],"produce":[171],"results.":[172],"In":[173],"cases,":[175],"accomplished":[178],"allowing":[180],"each":[181],"platform":[182],"it":[187],"performs":[188],"most":[189],"naturally.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":23},{"year":2014,"cited_by_count":29},{"year":2013,"cited_by_count":23},{"year":2012,"cited_by_count":21}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}