{"id":"https://openalex.org/W2580907809","doi":"https://doi.org/10.1145/3026937.3026940","title":"Batched Gauss-Jordan Elimination for Block-Jacobi Preconditioner Generation on GPUs","display_name":"Batched Gauss-Jordan Elimination for Block-Jacobi Preconditioner Generation on GPUs","publication_year":2017,"publication_date":"2017-01-27","ids":{"openalex":"https://openalex.org/W2580907809","doi":"https://doi.org/10.1145/3026937.3026940","mag":"2580907809"},"language":"en","primary_location":{"id":"doi:10.1145/3026937.3026940","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3026937.3026940","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3026940&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3026940&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Hartwig Anzt","raw_affiliation_strings":["Innovative Computing Lab, University of Tennessee, Knoxville, Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"Innovative Computing Lab, University of Tennessee, Knoxville, Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]},{"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"]},{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["Innovative Computing Lab, University of Tennessee, Knoxville, Tennessee, USA; Oak Ridge National Laboratory, USA; School of Computer Science, University of Manchester, United Kingdom","Innovative Computing Lab, University of Tennessee, Knoxville, Tennessee, USA","Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Innovative Computing Lab, University of Tennessee, Knoxville, Tennessee, USA; Oak Ridge National Laboratory, USA; School of Computer Science, University of Manchester, United Kingdom","institution_ids":["https://openalex.org/I75027704","https://openalex.org/I28407311","https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Innovative Computing Lab, University of Tennessee, Knoxville, Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017361033","display_name":"Goran Flegar","orcid":"https://orcid.org/0000-0002-4154-0420"},"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":"Goran Flegar","raw_affiliation_strings":["Depto. Ingenier\u00eda y Ciencia de Computadores, Universidad Jaume I, Castell\u00f3n, Spain"],"affiliations":[{"raw_affiliation_string":"Depto. Ingenier\u00eda y Ciencia de Computadores, Universidad Jaume I, Castell\u00f3n, 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-Ort\u00ed","raw_affiliation_strings":["Depto. Ingenier\u00eda y Ciencia de Computadores, Universidad Jaume I, Castell\u00f3n, Spain"],"affiliations":[{"raw_affiliation_string":"Depto. Ingenier\u00eda y Ciencia de Computadores, Universidad Jaume I, Castell\u00f3n, Spain","institution_ids":["https://openalex.org/I10902133"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012133869"],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":3.7704,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.94012945,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9997000098228455,"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":0.9997000098228455,"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/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"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/preconditioner","display_name":"Preconditioner","score":0.8345469236373901},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8332580924034119},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6783215403556824},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6547811031341553},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.651751697063446},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.6256961226463318},{"id":"https://openalex.org/keywords/gaussian-elimination","display_name":"Gaussian elimination","score":0.5591151714324951},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.5527341961860657},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5421709418296814},{"id":"https://openalex.org/keywords/jacobi-method","display_name":"Jacobi method","score":0.5212339162826538},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.48030799627304077},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4177553057670593},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2731977701187134},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.25562596321105957},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.23074859380722046},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.21712753176689148},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2079460322856903},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.1276198923587799},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.06918266415596008},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06582194566726685}],"concepts":[{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.8345469236373901},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8332580924034119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6783215403556824},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6547811031341553},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.651751697063446},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6256961226463318},{"id":"https://openalex.org/C126312332","wikidata":"https://www.wikidata.org/wiki/Q2658","display_name":"Gaussian elimination","level":3,"score":0.5591151714324951},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.5527341961860657},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5421709418296814},{"id":"https://openalex.org/C67923128","wikidata":"https://www.wikidata.org/wiki/Q1481893","display_name":"Jacobi method","level":2,"score":0.5212339162826538},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.48030799627304077},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4177553057670593},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2731977701187134},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.25562596321105957},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.23074859380722046},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.21712753176689148},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2079460322856903},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.1276198923587799},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.06918266415596008},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06582194566726685},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3026937.3026940","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3026937.3026940","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3026940&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3026937.3026940","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3026937.3026940","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3026940&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1065316766","display_name":null,"funder_award_id":"Award","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5372185796","display_name":null,"funder_award_id":"DE-SC-0010042","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7702789587","display_name":null,"funder_award_id":"TIN2014-53495-R","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2580907809.pdf","grobid_xml":"https://content.openalex.org/works/W2580907809.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1975847068","https://openalex.org/W2022819055","https://openalex.org/W2095258827","https://openalex.org/W2101196233","https://openalex.org/W2118060959","https://openalex.org/W2138215414","https://openalex.org/W2340850905","https://openalex.org/W2346297479","https://openalex.org/W2406344247","https://openalex.org/W2410272182","https://openalex.org/W2501119265","https://openalex.org/W2519968131","https://openalex.org/W2566696892","https://openalex.org/W2596951540","https://openalex.org/W2798909945","https://openalex.org/W4252552527","https://openalex.org/W6750968397","https://openalex.org/W7053100431"],"related_works":["https://openalex.org/W2983282793","https://openalex.org/W1973046741","https://openalex.org/W2029041499","https://openalex.org/W2127641858","https://openalex.org/W68723791","https://openalex.org/W2148966361","https://openalex.org/W2160144917","https://openalex.org/W2147974772","https://openalex.org/W4251891679","https://openalex.org/W2061198804"],"abstract_inverted_index":{"In":[0,57],"this":[1],"paper,":[2],"we":[3,30,59],"design":[4],"and":[5,47,62],"evaluate":[6],"a":[7,32],"routine":[8],"for":[9,38],"the":[10,24,27,49,54,70],"efficient":[11],"generation":[12],"of":[13,26],"block-Jacobi":[14,71],"preconditioners":[15],"on":[16],"graphics":[17,28],"processing":[18],"units":[19],"(GPUs).":[20],"Concretely,":[21],"to":[22,66],"exploit":[23],"architecture":[25],"accelerator,":[29],"develop":[31],"batched":[33],"Gauss-Jordan":[34],"elimination":[35],"CUDA":[36,64],"kernel":[37],"matrix":[39],"inversion":[40,51],"that":[41],"embeds":[42],"an":[43],"implicit":[44],"pivoting":[45],"technique":[46],"handles":[48],"entire":[50],"process":[52],"in":[53],"GPU":[55],"registers.":[56],"addition,":[58],"integrate":[60],"extraction":[61],"insertion":[63],"kernels":[65],"rapidly":[67],"set":[68],"up":[69],"preconditioner.":[72]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":4}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}
