{"id":"https://openalex.org/W2410272182","doi":"https://doi.org/10.1109/tpds.2015.2481890","title":"Implementation and Tuning of Batched Cholesky Factorization and Solve for NVIDIA GPUs","display_name":"Implementation and Tuning of Batched Cholesky Factorization and Solve for NVIDIA GPUs","publication_year":2015,"publication_date":"2015-09-24","ids":{"openalex":"https://openalex.org/W2410272182","doi":"https://doi.org/10.1109/tpds.2015.2481890","mag":"2410272182"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2015.2481890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2015.2481890","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.manchester.ac.uk/ws/files/47908959/imple_tuning_batch.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070456582","display_name":"Jakub Kurzak","orcid":"https://orcid.org/0000-0002-9697-0145"},"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":"Jakub Kurzak","raw_affiliation_strings":["Electrical Engineering and Computer Science, University of Tennessee, 1122 Volunteer Blvd, Ste 413 Claxton, Knoxville, Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, University of Tennessee, 1122 Volunteer Blvd, Ste 413 Claxton, Knoxville, Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012133869","display_name":"Hartwig Anzt","orcid":"https://orcid.org/0000-0003-2177-952X"},"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":"Hartwig Anzt","raw_affiliation_strings":["Electrical Engineering and Computer Science, University of Tennessee, Knoxville, Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, University of Tennessee, Knoxville, Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104910026","display_name":"Mark Gates","orcid":"https://orcid.org/0000-0003-2996-1641"},"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":"Mark Gates","raw_affiliation_strings":["Electrical Engineering and Computer Science, University of Tennessee, Knoxville, Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, University of Tennessee, Knoxville, Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"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":["Electrical Engineering and Computer Science, University of Tennessee, Knoxville, Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, University of Tennessee, Knoxville, Tennessee","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":7.4191,"has_fulltext":true,"cited_by_count":48,"citation_normalized_percentile":{"value":0.97772255,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"27","issue":"7","first_page":"2036","last_page":"2048"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9959999918937683,"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":0.9959999918937683,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9627000093460083,"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":0.9621999859809875,"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/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.9711507558822632},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7628988027572632},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6624655723571777},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.6007404327392578},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.5565363168716431},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5519188046455383},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.537194550037384},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4734577536582947},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.4515945613384247},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4378066062927246},{"id":"https://openalex.org/keywords/incomplete-cholesky-factorization","display_name":"Incomplete Cholesky factorization","score":0.42899876832962036},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.4261016845703125},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.382037878036499},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2875237464904785},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13442689180374146}],"concepts":[{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.9711507558822632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628988027572632},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6624655723571777},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.6007404327392578},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.5565363168716431},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5519188046455383},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.537194550037384},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4734577536582947},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.4515945613384247},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4378066062927246},{"id":"https://openalex.org/C44363057","wikidata":"https://www.wikidata.org/wiki/Q6015160","display_name":"Incomplete Cholesky factorization","level":4,"score":0.42899876832962036},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.4261016845703125},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.382037878036499},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2875237464904785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13442689180374146},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpds.2015.2481890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2015.2481890","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/f81e1266-b82a-4be6-884b-8e63a5a49a18","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/f81e1266-b82a-4be6-884b-8e63a5a49a18","pdf_url":"https://pure.manchester.ac.uk/ws/files/47908959/imple_tuning_batch.pdf","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Kurzak, J, Anzt, H, Gates, M & Dongarra, J 2016, 'Implementation and Tuning of Batched Cholesky Factorization and Solve for NVIDIA GPUs', IEEE Transactions on Parallel and Distributed Systems, vol. 27, no. 7, 7275187, pp. 2036-2048. https://doi.org/10.1109/TPDS.2015.2481890","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.atira.dk:publications/f81e1266-b82a-4be6-884b-8e63a5a49a18","is_oa":true,"landing_page_url":null,"pdf_url":"https://www.research.manchester.ac.uk/portal/en/publications/implementation-and-tuning-of-batched-cholesky-factorization-and-solve-for-nvidia-gpus(f81e1266-b82a-4be6-884b-8e63a5a49a18).html","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/f81e1266-b82a-4be6-884b-8e63a5a49a18","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/f81e1266-b82a-4be6-884b-8e63a5a49a18","pdf_url":"https://pure.manchester.ac.uk/ws/files/47908959/imple_tuning_batch.pdf","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Kurzak, J, Anzt, H, Gates, M & Dongarra, J 2016, 'Implementation and Tuning of Batched Cholesky Factorization and Solve for NVIDIA GPUs', IEEE Transactions on Parallel and Distributed Systems, vol. 27, no. 7, 7275187, pp. 2036-2048. https://doi.org/10.1109/TPDS.2015.2481890","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1351316705","display_name":null,"funder_award_id":"DE-SC0010042","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4979348124","display_name":"SHF: Small: Bench-testing Environment for Automated Software Tuning (BEAST)","funder_award_id":"1320603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7594707981","display_name":null,"funder_award_id":"#DE-SC0010042","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2410272182.pdf","grobid_xml":"https://content.openalex.org/works/W2410272182.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1737435842","https://openalex.org/W1978642402","https://openalex.org/W1985691044","https://openalex.org/W1997033059","https://openalex.org/W2006682733","https://openalex.org/W2063509315","https://openalex.org/W2090698642","https://openalex.org/W2101409192","https://openalex.org/W2127906479","https://openalex.org/W2138215414","https://openalex.org/W2155942156","https://openalex.org/W2162525251","https://openalex.org/W2167182394","https://openalex.org/W2169150754","https://openalex.org/W2208934446","https://openalex.org/W2502925949","https://openalex.org/W2605732856","https://openalex.org/W4229666556","https://openalex.org/W6736403352"],"related_works":["https://openalex.org/W1987177655","https://openalex.org/W1520628408","https://openalex.org/W1582269492","https://openalex.org/W2135765421","https://openalex.org/W54819768","https://openalex.org/W2087421046","https://openalex.org/W2084136662","https://openalex.org/W2074550915","https://openalex.org/W4288072583","https://openalex.org/W2025829250"],"abstract_inverted_index":{"Many":[0],"problems":[1],"in":[2,53,146,175],"engineering":[3],"and":[4,38,44,76,85,88,134,153],"scientific":[5],"computing":[6],"require":[7],"the":[8,42,45,54,60,63,74,79,82,86,94,102,106,122,142],"solution":[9,95],"of":[10,14,17,36,65,78,96,98,101,124,131,151],"a":[11,125],"large":[12],"number":[13],"small":[15],"systems":[16,64,100],"linear":[18,99],"equations.":[19],"Due":[20,120],"to":[21,116,121,159],"their":[22],"high":[23],"processing":[24],"power,":[25],"Graphics":[26],"Processing":[27],"Units":[28],"became":[29],"an":[30],"attractive":[31],"target":[32],"for":[33,81,139],"this":[34,147],"class":[35],"problems,":[37],"routines":[39,156],"based":[40],"on":[41,109],"LU":[43,133],"QR":[46,136],"factorization":[47,84,145],"have":[48],"been":[49],"provided":[50],"by":[51,114,118],"NVIDIA":[52],"cuBLAS":[55,126,132,135,161],"library.":[56],"This":[57],"work":[58],"addresses":[59],"situation":[61],"where":[62,105],"equations":[66],"are":[67,137,157,168],"symmetric":[68],"positive":[69],"definite.":[70],"The":[71],"paper":[72],"describes":[73],"implementation":[75],"tuning":[77],"kernels":[80],"Cholesky":[83,127,144],"forward":[87,152],"backward":[89,154],"substitution.":[90],"Targeted":[91],"workloads":[92],"involve":[93],"thousands":[97],"same":[103],"size,":[104],"focus":[107],"is":[108,173],"matrix":[110],"dimensions":[111],"from":[112],"5":[113,115],"100":[117],"100.":[119],"lack":[123],"factorization,":[128],"execution":[129],"rates":[130,150],"used":[138],"comparison":[140],"against":[141,164],"proposed":[143],"work.":[148],"Execution":[149],"substitution":[155],"compared":[158],"equivalent":[160],"routines.":[162],"Comparisons":[163],"optimized":[165],"multicore":[166],"implementations":[167],"also":[169],"presented.":[170],"Superior":[171],"performance":[172],"reached":[174],"all":[176],"cases.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}