{"id":"https://openalex.org/W4225859329","doi":"https://doi.org/10.1177/10943420221100262","title":"Matrix-free approaches for GPU acceleration of a high-order finite element hydrodynamics application using MFEM, Umpire, and RAJA","display_name":"Matrix-free approaches for GPU acceleration of a high-order finite element hydrodynamics application using MFEM, Umpire, and RAJA","publication_year":2022,"publication_date":"2022-05-25","ids":{"openalex":"https://openalex.org/W4225859329","doi":"https://doi.org/10.1177/10943420221100262"},"language":"en","primary_location":{"id":"doi:10.1177/10943420221100262","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420221100262","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":"preprint","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/A5056456280","display_name":"Arturo Vargas","orcid":"https://orcid.org/0000-0002-2576-9671"},"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":true,"raw_author_name":"Arturo Vargas","raw_affiliation_strings":["Weapons and Complex Integration, Lawrence Livermore National Laboratory, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Weapons and Complex Integration, Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087585256","display_name":"Thomas Stitt","orcid":"https://orcid.org/0000-0002-7068-2073"},"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":"Thomas M Stitt","raw_affiliation_strings":["Weapons and Complex Integration, Lawrence Livermore National Laboratory, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Weapons and Complex Integration, Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029194242","display_name":"Kenneth M. Weiss","orcid":"https://orcid.org/0000-0002-2528-9993"},"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":"Kenneth Weiss","raw_affiliation_strings":["Weapons and Complex Integration, Lawrence Livermore National Laboratory, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Weapons and Complex Integration, Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056525853","display_name":"Vladimir Tomov","orcid":"https://orcid.org/0000-0002-1846-6816"},"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":"Vladimir Z Tomov","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":"middle","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"]}]},{"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/A5081558023","display_name":"Robert N. Rieben","orcid":"https://orcid.org/0000-0003-3526-0649"},"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":"Robert N Rieben","raw_affiliation_strings":["Weapons and Complex Integration, Lawrence Livermore National Laboratory, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Weapons and Complex Integration, Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5056456280"],"corresponding_institution_ids":["https://openalex.org/I1282311441"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04072645,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"4","first_page":"492","last_page":"509"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.996999979019165,"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":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7198363542556763},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.6965917944908142},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6091915965080261},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5696904063224792},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5393092632293701},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5150877833366394},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.49280479550361633},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.48927590250968933},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4853135943412781},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4714568257331848},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.45329445600509644},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.41072720289230347},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2849043011665344},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18493330478668213},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13778889179229736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7198363542556763},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.6965917944908142},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6091915965080261},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5696904063224792},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5393092632293701},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5150877833366394},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.49280479550361633},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.48927590250968933},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4853135943412781},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4714568257331848},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.45329445600509644},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.41072720289230347},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2849043011665344},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18493330478668213},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13778889179229736},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/10943420221100262","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420221100262","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1995775829","https://openalex.org/W2046585015","https://openalex.org/W2067673417","https://openalex.org/W2110143814","https://openalex.org/W2111389017","https://openalex.org/W2133567334","https://openalex.org/W2281558607","https://openalex.org/W2327087277","https://openalex.org/W2460432330","https://openalex.org/W2783853321","https://openalex.org/W2884066481","https://openalex.org/W2996807164","https://openalex.org/W3003487218","https://openalex.org/W3018086455","https://openalex.org/W3020915295","https://openalex.org/W3040786754","https://openalex.org/W3108083020","https://openalex.org/W3171139128","https://openalex.org/W3195293013","https://openalex.org/W4253074238","https://openalex.org/W6884641258"],"related_works":["https://openalex.org/W320786","https://openalex.org/W564427","https://openalex.org/W401528","https://openalex.org/W1014487","https://openalex.org/W2584135","https://openalex.org/W4810477","https://openalex.org/W2936016","https://openalex.org/W2764298","https://openalex.org/W17610788","https://openalex.org/W15896789"],"abstract_inverted_index":{"With":[0],"the":[1,37],"introduction":[2],"of":[3,100,118],"advanced":[4],"heterogeneous":[5],"computing":[6],"architectures":[7],"based":[8],"on":[9,36,103,111],"GPU":[10],"accelerators,":[11],"large-scale":[12],"production":[13],"codes":[14],"have":[15,121],"had":[16],"to":[17,33,48,80,125],"rethink":[18],"their":[19],"numerical":[20],"algorithms":[21,84],"and":[22,27,52,55,85,114,135],"incorporate":[23],"new":[24,76,83,86],"programming":[25],"models":[26],"memory":[28],"management":[29],"strategies":[30],"in":[31,63,90],"order":[32],"run":[34],"efficiently":[35],"latest":[38],"supercomputers.":[39],"In":[40],"this":[41],"work":[42],"we":[43,108],"discuss":[44],"our":[45,119],"co-design":[46],"strategy":[47],"address":[49],"these":[50],"challenges":[51],"achieve":[53],"performance":[54],"portability":[56],"with":[57],"MARBL,":[58],"a":[59,72,91,98],"next-generation":[60],"multi-physics":[61],"code":[62,95],"development":[64],"at":[65],"Lawrence":[66],"Livermore":[67],"National":[68],"Laboratory.":[69],"We":[70],"present":[71],"two-fold":[73],"approach,":[74],"wherein":[75],"hardware":[77],"is":[78],"used":[79],"motivate":[81],"both":[82],"abstraction":[87],"layers,":[88],"resulting":[89],"single":[92],"source":[93],"application":[94],"suitable":[96],"for":[97],"variety":[99],"platforms.":[101],"Focusing":[102],"MARBL\u2019s":[104],"ALE":[105],"hydrodynamics":[106],"package,":[107],"demonstrate":[109],"scalability":[110],"different":[112],"platforms":[113],"highlight":[115],"that":[116],"many":[117],"innovations":[120],"been":[122],"contributed":[123],"back":[124],"open-source":[126],"software":[127],"libraries,":[128],"such":[129],"as":[130],"MFEM":[131],"(finite":[132],"element":[133],"algorithms)":[134],"RAJA":[136],"(kernel":[137],"abstractions).":[138]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-05-05T00:00:00"}