{"id":"https://openalex.org/W4379013997","doi":"https://doi.org/10.1177/10943420231175462","title":"End-to-end GPU acceleration of low-order-refined preconditioning for high-order finite element discretizations","display_name":"End-to-end GPU acceleration of low-order-refined preconditioning for high-order finite element discretizations","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4379013997","doi":"https://doi.org/10.1177/10943420231175462"},"language":"en","primary_location":{"id":"doi:10.1177/10943420231175462","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420231175462","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1975987","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030630927","display_name":"Will Pazner","orcid":"https://orcid.org/0000-0003-4885-2934"},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]},{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Will Pazner","raw_affiliation_strings":["Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, Livermore, CA, USA","Fariborz Maseeh Department of Mathematics and Statistics, Portland State University, Portland, OR, USA"],"affiliations":[{"raw_affiliation_string":"Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Fariborz Maseeh Department of Mathematics and Statistics, Portland State University, Portland, OR, USA","institution_ids":["https://openalex.org/I126345244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003911272","display_name":"Tzanio Kolev","orcid":"https://orcid.org/0000-0002-2810-3090"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tzanio Kolev","raw_affiliation_strings":["Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050967111","display_name":"Jean\u2010Sylvain Camier","orcid":"https://orcid.org/0000-0003-2421-1999"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean-Sylvain Camier","raw_affiliation_strings":["Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030630927"],"corresponding_institution_ids":["https://openalex.org/I126345244","https://openalex.org/I1282311441"],"apc_list":null,"apc_paid":null,"fwci":1.5014,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78563099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"37","issue":"5","first_page":"578","last_page":"599"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9973999857902527,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9955000281333923,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.7052446603775024},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.6291384100914001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5296342968940735},{"id":"https://openalex.org/keywords/preconditioner","display_name":"Preconditioner","score":0.5255730748176575},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4833037853240967},{"id":"https://openalex.org/keywords/discontinuous-galerkin-method","display_name":"Discontinuous Galerkin method","score":0.4781668782234192},{"id":"https://openalex.org/keywords/degree-of-a-polynomial","display_name":"Degree of a polynomial","score":0.4528329372406006},{"id":"https://openalex.org/keywords/multigrid-method","display_name":"Multigrid method","score":0.42585915327072144},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40811389684677124},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.39482492208480835},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35734695196151733},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3496897518634796},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32632094621658325},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.3048824071884155},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.17574822902679443},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.140164315700531},{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.1086529791355133},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09226235747337341}],"concepts":[{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.7052446603775024},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.6291384100914001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5296342968940735},{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.5255730748176575},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4833037853240967},{"id":"https://openalex.org/C92244383","wikidata":"https://www.wikidata.org/wiki/Q428273","display_name":"Discontinuous Galerkin method","level":3,"score":0.4781668782234192},{"id":"https://openalex.org/C25878781","wikidata":"https://www.wikidata.org/wiki/Q1473607","display_name":"Degree of a polynomial","level":3,"score":0.4528329372406006},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.42585915327072144},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40811389684677124},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.39482492208480835},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35734695196151733},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3496897518634796},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32632094621658325},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.3048824071884155},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.17574822902679443},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.140164315700531},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.1086529791355133},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09226235747337341},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1177/10943420231175462","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420231175462","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:pdxscholar.library.pdx.edu:mth_fac-1388","is_oa":false,"landing_page_url":"https://pdxscholar.library.pdx.edu/mth_fac/384","pdf_url":null,"source":{"id":"https://openalex.org/S4377196300","display_name":"PDXScholar  (Portland State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126345244","host_organization_name":"Portland State University","host_organization_lineage":["https://openalex.org/I126345244"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mathematics and Statistics Faculty Publications and Presentations","raw_type":"text"},{"id":"pmh:oai:osti.gov:1975987","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1975987","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:osti.gov:2281467","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2281467","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1975987","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1975987","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1319584452","display_name":null,"funder_award_id":"Exascale Computing Project (17-SC-20-SC)","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6353535777","display_name":null,"funder_award_id":"LDRD 20-ERD-002","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W152258552","https://openalex.org/W1525132831","https://openalex.org/W1845641575","https://openalex.org/W1862644536","https://openalex.org/W1980005758","https://openalex.org/W1982005385","https://openalex.org/W1984334096","https://openalex.org/W1985144286","https://openalex.org/W1985263109","https://openalex.org/W2005047411","https://openalex.org/W2010804587","https://openalex.org/W2013242019","https://openalex.org/W2039789965","https://openalex.org/W2069736604","https://openalex.org/W2071483785","https://openalex.org/W2073389244","https://openalex.org/W2075896209","https://openalex.org/W2075993982","https://openalex.org/W2088917948","https://openalex.org/W2093842590","https://openalex.org/W2138696267","https://openalex.org/W2501406482","https://openalex.org/W2592996154","https://openalex.org/W2597480328","https://openalex.org/W2767520933","https://openalex.org/W2943869808","https://openalex.org/W2963269877","https://openalex.org/W2969466890","https://openalex.org/W2982610918","https://openalex.org/W2989169576","https://openalex.org/W3016268593","https://openalex.org/W3018086455","https://openalex.org/W3040786754","https://openalex.org/W3091293834","https://openalex.org/W3122714673","https://openalex.org/W3167826856","https://openalex.org/W3179468891","https://openalex.org/W3181886927","https://openalex.org/W3199141021","https://openalex.org/W3204468590","https://openalex.org/W3215122111","https://openalex.org/W4210857846","https://openalex.org/W4251219752","https://openalex.org/W4293427763"],"related_works":["https://openalex.org/W4389317411","https://openalex.org/W1492522302","https://openalex.org/W2120298265","https://openalex.org/W2096454229","https://openalex.org/W2042199958","https://openalex.org/W2103149966","https://openalex.org/W2177482563","https://openalex.org/W2016008514","https://openalex.org/W2464766188","https://openalex.org/W2167521757"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3],"present":[4],"algorithms":[5],"and":[6,40,79,89,135,138,151,159,173],"implementations":[7],"for":[8,27,33,65,92],"the":[9,28,48,117,120,129,136,143,154,174,177,189],"end-to-end":[10],"GPU":[11,121],"acceleration":[12],"of":[13,17,30,50,72,76,119,126,128,142,153,176,188],"matrix-free":[14],"low-order-refined":[15],"preconditioning":[16],"high-order":[18,34],"finite":[19,84,190],"element":[20,85,191],"problems.":[21],"The":[22,43,70,123,147],"methods":[23,144],"described":[24],"here":[25],"allow":[26],"construction":[29,49],"effective":[31],"preconditioners":[32,44,178],"problems":[35,86,165],"with":[36],"optimal":[37],"memory":[38],"usage":[39],"computational":[41],"complexity.":[42],"are":[45,74,112,171],"based":[46],"on":[47,56,157,164,179],"a":[51,57,98,180],"spectrally":[52],"equivalent":[53],"low-order":[54],"discretization":[55],"refined":[58,168],"mesh,":[59],"which":[60],"is":[61,103,133,145,161,195],"then":[62],"amenable":[63],"to,":[64],"example,":[66],"algebraic":[67],"multigrid":[68],"preconditioning.":[69],"constants":[71],"equivalence":[73],"independent":[75],"mesh":[77],"size":[78],"polynomial":[80],"degree.":[81],"For":[82],"vector":[83],"in":[87],"H(curl)":[88],"H(div)":[90],"(e.g.,":[91],"electromagnetic":[93],"or":[94],"radiation":[95],"diffusion":[96,183],"problems),":[97],"specially":[99],"constructed":[100],"interpolation\u2013histopolation":[101],"basis":[102],"used":[104],"to":[105,115],"ensure":[106],"fast":[107],"convergence.":[108],"Detailed":[109],"performance":[110],"studies":[111],"carried":[113],"out":[114],"analyze":[116],"efficiency":[118],"algorithms.":[122],"kernel":[124],"throughput":[125],"each":[127],"main":[130],"algorithmic":[131,155],"components":[132,156],"measured,":[134],"strong":[137],"weak":[139],"parallel":[140],"scalability":[141],"demonstrated.":[146],"different":[148],"relative":[149],"weighting":[150],"significance":[152],"GPUs":[158],"CPUs":[160],"discussed.":[162],"Results":[163],"involving":[166],"adaptively":[167],"nonconforming":[169],"meshes":[170],"shown,":[172],"use":[175],"large-scale":[181],"magnetic":[182],"problem":[184],"using":[185],"all":[186],"spaces":[187],"de":[192],"Rham":[193],"complex":[194],"illustrated.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
