{"id":"https://openalex.org/W2944305421","doi":"https://doi.org/10.1109/tpds.2020.3010016","title":"K-Athena: A Performance Portable Structured Grid Finite Volume Magnetohydrodynamics Code","display_name":"K-Athena: A Performance Portable Structured Grid Finite Volume Magnetohydrodynamics Code","publication_year":2020,"publication_date":"2020-07-17","ids":{"openalex":"https://openalex.org/W2944305421","doi":"https://doi.org/10.1109/tpds.2020.3010016","mag":"2944305421"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2020.3010016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.3010016","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.04341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045259714","display_name":"Philipp Grete","orcid":"https://orcid.org/0000-0003-3555-9886"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Philipp Grete","raw_affiliation_strings":["Department of Physics and Astronomy, Michigan State University, East Lansing, MI, USA","#N#Department of Physics and Astronomy, Michigan State University, East Lansing MI, USA"],"raw_orcid":"https://orcid.org/0000-0003-3555-9886","affiliations":[{"raw_affiliation_string":"Department of Physics and Astronomy, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"#N#Department of Physics and Astronomy, Michigan State University, East Lansing MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Forrest W. Glines","orcid":"https://orcid.org/0000-0002-2786-0348"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Forrest W. Glines","raw_affiliation_strings":["Department of Physics and Astronomy, Michigan State University, East Lansing, MI, USA","#N#Department of Physics and Astronomy, Michigan State University, East Lansing MI, USA"],"raw_orcid":"https://orcid.org/0000-0002-2786-0348","affiliations":[{"raw_affiliation_string":"Department of Physics and Astronomy, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"#N#Department of Physics and Astronomy, Michigan State University, East Lansing MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":null,"display_name":"Brian W. O'Shea","orcid":"https://orcid.org/0000-0002-6837-8195"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian W. O'Shea","raw_affiliation_strings":["Department of Physics and Astronomy, Michigan State University, East Lansing, MI, USA","#N#Department of Physics and Astronomy, Michigan State University, East Lansing MI, USA"],"raw_orcid":"https://orcid.org/0000-0002-6837-8195","affiliations":[{"raw_affiliation_string":"Department of Physics and Astronomy, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"#N#Department of Physics and Astronomy, Michigan State University, East Lansing MI, USA","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045259714"],"corresponding_institution_ids":["https://openalex.org/I87216513"],"apc_list":null,"apc_paid":null,"fwci":0.4714,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56407726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"32","issue":"1","first_page":"85","last_page":"97"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9957000017166138,"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":0.8221815824508667},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.6912938356399536},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6685848832130432},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.6236432790756226},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5421934127807617},{"id":"https://openalex.org/keywords/exascale-computing","display_name":"Exascale computing","score":0.5002272129058838},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.4477095305919647},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44143033027648926},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4366138279438019},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.4293648898601532},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4162765443325043},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31042689085006714},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13279256224632263}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8221815824508667},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.6912938356399536},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6685848832130432},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.6236432790756226},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5421934127807617},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.5002272129058838},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.4477095305919647},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44143033027648926},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4366138279438019},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.4293648898601532},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4162765443325043},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31042689085006714},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13279256224632263},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tpds.2020.3010016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.3010016","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:arXiv.org:1905.04341","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.04341","pdf_url":"https://arxiv.org/pdf/1905.04341","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"mag:2944305421","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1905.04341","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1905.04341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.04341","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.04341","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.04341","pdf_url":"https://arxiv.org/pdf/1905.04341","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G5411477494","display_name":null,"funder_award_id":"SMD-16-7720","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"},{"id":"https://openalex.org/G5429065745","display_name":null,"funder_award_id":"NNX15AP39G","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"}],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2944305421.pdf","grobid_xml":"https://content.openalex.org/works/W2944305421.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W842872497","https://openalex.org/W1948589040","https://openalex.org/W1984222112","https://openalex.org/W1988888548","https://openalex.org/W2002555321","https://openalex.org/W2022916138","https://openalex.org/W2036551003","https://openalex.org/W2040469410","https://openalex.org/W2078794610","https://openalex.org/W2079577430","https://openalex.org/W2095954861","https://openalex.org/W2100315046","https://openalex.org/W2116091257","https://openalex.org/W2133695315","https://openalex.org/W2473671032","https://openalex.org/W2523918178","https://openalex.org/W2589502104","https://openalex.org/W2607112060","https://openalex.org/W2607256436","https://openalex.org/W2729736213","https://openalex.org/W2743401659","https://openalex.org/W2754695535","https://openalex.org/W2796649226","https://openalex.org/W2798136584","https://openalex.org/W2891830569","https://openalex.org/W2920798074","https://openalex.org/W2953482774","https://openalex.org/W2996073524","https://openalex.org/W2998644365","https://openalex.org/W3025571086","https://openalex.org/W3106178351","https://openalex.org/W4243474409","https://openalex.org/W4248722156","https://openalex.org/W4300715235","https://openalex.org/W6727472278","https://openalex.org/W6750448596","https://openalex.org/W6760272376"],"related_works":["https://openalex.org/W3043057203","https://openalex.org/W2898519564","https://openalex.org/W2508073476","https://openalex.org/W3199844424","https://openalex.org/W1577137152","https://openalex.org/W2913776273","https://openalex.org/W2593792346","https://openalex.org/W2755294164","https://openalex.org/W2294903947","https://openalex.org/W2628042908","https://openalex.org/W3170632927","https://openalex.org/W2529731748","https://openalex.org/W2583971833","https://openalex.org/W1998641004","https://openalex.org/W2963971706","https://openalex.org/W2769155990","https://openalex.org/W2338293335","https://openalex.org/W2461669091","https://openalex.org/W2181329641","https://openalex.org/W2916956826"],"abstract_inverted_index":{"Large":[0],"scale":[1],"simulations":[2,69],"are":[3],"a":[4,41,57,74,105,116,148,165,193],"key":[5],"pillar":[6],"of":[7,40,118,169],"modern":[8],"research":[9,190],"and":[10,80,93,115,163,179],"require":[11],"ever-increasing":[12],"computational":[13],"resources.":[14],"Different":[15],"novel":[16],"manycore":[17],"architectures":[18,72],"have":[19],"emerged":[20],"in":[21,183],"recent":[22],"years":[23],"on":[24,70,104,120,126],"the":[25,28,154,175,180,202],"way":[26],"towards":[27],"exascale":[29,203],"era.":[30,204],"Performance":[31],"portability":[32,167],"is":[33,157,206],"required":[34],"to":[35,66,122,129,196],"prevent":[36],"repeated":[37],"non-trivial":[38],"refactoring":[39],"code":[42],"for":[43,83,109,201],"different":[44,84],"architectures.":[45],"We":[46,77],"combine":[47],"ATHENA++,":[48],"an":[49],"existing":[50],"magnetohydrodynamics":[51],"(MHD)":[52],"CPU":[53,131],"code,":[54],"with":[55,192],"KOKKOS,":[56],"performance":[58,156,166],"portable":[59],"on-node":[60],"parallel":[61,145],"programming":[62],"paradigm,":[63],"into":[64],"K-ATHENA":[65,96,205],"allow":[67],"efficient":[68],"multiple":[71],"using":[73],"single":[75,106],"codebase.":[76],"present":[78,174],"profiling":[79],"scaling":[81],"results":[82],"platforms":[85],"including":[86],"Intel":[87,90],"Skylake":[88],"CPUs,":[89],"Xeon":[91],"Phis,":[92],"NVIDIA":[94],"GPUs.":[95],"achieves":[97],">":[98],"10":[99,136],"<sup":[100,137],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[101,138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">8</sup>":[102],"cell-updates/s":[103,141],"V100":[107],"GPU":[108],"second-order":[110],"double":[111],"precision":[112],"MHD":[113],"calculations,":[114],"speedup":[117],"30":[119],"up":[121],"24":[123],"576":[124],"GPUs":[125],"Summit":[127],"(compared":[128],"172,032":[130],"cores),":[132],"reaching":[133],"1:94":[134],"\u00d7":[135],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">12</sup>":[139],"total":[140],"at":[142,208],"76":[143],"percent":[144],"efficiency.":[146],"Using":[147],"roofline":[149],"analysis":[150],"we":[151,173],"demonstrate":[152],"that":[153],"overall":[155],"currently":[158],"limited":[159],"by":[160],"DRAM":[161],"bandwidth":[162],"calculate":[164],"metric":[168],"62.8":[170],"percent.":[171],"Finally,":[172],"implementation":[176],"strategies":[177],"used":[178],"challenges":[181],"encountered":[182],"maximizing":[184],"performance.":[185],"This":[186],"will":[187],"provide":[188],"other":[189],"groups":[191],"straightforward":[194],"approach":[195],"prepare":[197],"their":[198],"own":[199],"codes":[200],"available":[207],"https://gitlab.com/pgrete/kathena.":[209]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}