{"id":"https://openalex.org/W4409716921","doi":"https://doi.org/10.1016/j.jocs.2025.102590","title":"Accelerating Particle-in-Cell Monte Carlo simulations with MPI, OpenMP/OpenACC and Asynchronous Multi-GPU Programming","display_name":"Accelerating Particle-in-Cell Monte Carlo simulations with MPI, OpenMP/OpenACC and Asynchronous Multi-GPU Programming","publication_year":2025,"publication_date":"2025-04-23","ids":{"openalex":"https://openalex.org/W4409716921","doi":"https://doi.org/10.1016/j.jocs.2025.102590"},"language":"en","primary_location":{"id":"doi:10.1016/j.jocs.2025.102590","doi":"https://doi.org/10.1016/j.jocs.2025.102590","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jocs.2025.102590","pdf_url":null,"source":{"id":"https://openalex.org/S192071280","display_name":"Journal of Computational Science","issn_l":"1877-7503","issn":["1877-7503","1877-7511"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-d","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Science","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.jocs.2025.102590","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054224006","display_name":"Jeremy J. Williams","orcid":"https://orcid.org/0000-0003-2095-3063","observed_orcids":["https://orcid.org/0000-0003-2095-3063"]},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Jeremy J. Williams","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-2095-3063","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053322052","display_name":"Felix Liu","orcid":"https://orcid.org/0000-0001-6865-9379","observed_orcids":["https://orcid.org/0000-0001-6865-9379","https://orcid.org/0000-0001-8288-2817"]},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Felix Liu","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114537008","display_name":"Jordy Trilaksono","orcid":"https://orcid.org/0009-0000-3910-8615","observed_orcids":["https://orcid.org/0009-0000-3910-8615"]},"institutions":[{"id":"https://openalex.org/I4210139716","display_name":"Max Planck Institute for Plasma Physics","ror":"https://ror.org/03taest98","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210139716"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jordy Trilaksono","raw_affiliation_strings":["Max Planck Institute for Plasma Physics, Garching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Plasma Physics, Garching, Germany","institution_ids":["https://openalex.org/I4210139716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018416241","display_name":"David Tskhakaya","orcid":"https://orcid.org/0000-0002-4229-0961","observed_orcids":["https://orcid.org/0000-0002-4229-0961"]},"institutions":[{"id":"https://openalex.org/I4210111736","display_name":"Czech Academy of Sciences, Institute of Plasma Physics","ror":"https://ror.org/01h494015","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210111736"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"David Tskhakaya","raw_affiliation_strings":["Institute of Plasma Physics of the CAS, Prague, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Plasma Physics of the CAS, Prague, Czech Republic","institution_ids":["https://openalex.org/I4210111736"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044388885","display_name":"S. Costea","orcid":"https://orcid.org/0000-0003-0594-0555","observed_orcids":["https://orcid.org/0000-0003-0594-0555"]},"institutions":[{"id":"https://openalex.org/I153976015","display_name":"University of Ljubljana","ror":"https://ror.org/05njb9z20","country_code":"SI","type":"education","lineage":["https://openalex.org/I153976015"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Stefan Costea","raw_affiliation_strings":["LECAD Laboratory, University of Ljubljana, Ljubljana, Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LECAD Laboratory, University of Ljubljana, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I153976015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045617542","display_name":"L. Kos","orcid":"https://orcid.org/0000-0002-1790-7093","observed_orcids":["https://orcid.org/0000-0002-1790-7093"]},"institutions":[{"id":"https://openalex.org/I153976015","display_name":"University of Ljubljana","ror":"https://ror.org/05njb9z20","country_code":"SI","type":"education","lineage":["https://openalex.org/I153976015"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Leon Kos","raw_affiliation_strings":["LECAD Laboratory, University of Ljubljana, Ljubljana, Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LECAD Laboratory, University of Ljubljana, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I153976015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074539607","display_name":"A. Podoln\u00edk","orcid":"https://orcid.org/0000-0003-1237-8812","observed_orcids":["https://orcid.org/0000-0003-1237-8812"]},"institutions":[{"id":"https://openalex.org/I4210111736","display_name":"Czech Academy of Sciences, Institute of Plasma Physics","ror":"https://ror.org/01h494015","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210111736"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ales Podolnik","raw_affiliation_strings":["Institute of Plasma Physics of the CAS, Prague, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Plasma Physics of the CAS, Prague, Czech Republic","institution_ids":["https://openalex.org/I4210111736"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038147894","display_name":"Jakub Hrom\u00e1dka","orcid":"https://orcid.org/0000-0003-2708-7049","observed_orcids":["https://orcid.org/0000-0003-2708-7049"]},"institutions":[{"id":"https://openalex.org/I4210111736","display_name":"Czech Academy of Sciences, Institute of Plasma Physics","ror":"https://ror.org/01h494015","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210111736"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jakub Hromadka","raw_affiliation_strings":["Institute of Plasma Physics of the CAS, Prague, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Plasma Physics of the CAS, Prague, Czech Republic","institution_ids":["https://openalex.org/I4210111736"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035946652","display_name":"Pratibha Raghupati Hegde","orcid":"https://orcid.org/0000-0002-6059-8249","observed_orcids":["https://orcid.org/0000-0002-6059-8249"]},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Pratibha Hegde","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082933794","display_name":"Marta Garc\u00eda-Gasulla","orcid":"https://orcid.org/0000-0003-3682-9905","observed_orcids":["https://orcid.org/0000-0003-3682-9905"]},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Marta Garcia-Gasulla","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114537007","display_name":"Valentin Seitz","orcid":"https://orcid.org/0009-0009-8618-2688","observed_orcids":["https://orcid.org/0009-0009-8618-2688"]},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Valentin Seitz","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077188645","display_name":"F. Jenko","orcid":"https://orcid.org/0000-0001-6686-1469","observed_orcids":["https://orcid.org/0000-0001-6686-1469"]},"institutions":[{"id":"https://openalex.org/I4210139716","display_name":"Max Planck Institute for Plasma Physics","ror":"https://ror.org/03taest98","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210139716"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank Jenko","raw_affiliation_strings":["Max Planck Institute for Plasma Physics, Garching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Plasma Physics, Garching, Germany","institution_ids":["https://openalex.org/I4210139716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011376663","display_name":"Erwin Laure","orcid":"https://orcid.org/0000-0002-9901-9857","observed_orcids":["https://orcid.org/0000-0002-9901-9857"]},"institutions":[{"id":"https://openalex.org/I4210132734","display_name":"Max Planck Computing and Data Facility","ror":"https://ror.org/03e21z229","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210132734","https://openalex.org/I4210139716"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Erwin Laure","raw_affiliation_strings":["Max Planck Computing and Data Facility, Garching and Greifswald, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Computing and Data Facility, Garching and Greifswald, Germany","institution_ids":["https://openalex.org/I4210132734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085178088","display_name":"Stefano Markidis","orcid":"https://orcid.org/0000-0003-0639-0639","observed_orcids":["https://orcid.org/0000-0003-0639-0639"]},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Stefano Markidis","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5054224006"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":{"value":3560,"currency":"USD","value_usd":3560},"apc_paid":{"value":3560,"currency":"USD","value_usd":3560},"fwci":4.944,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.95582777,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"88","issue":null,"first_page":"102590","last_page":"102590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9970999956130981,"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":0.9970999956130981,"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/T10346","display_name":"Magnetic confinement fusion research","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.00039999998989515007,"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/particle-in-cell-monte-carlo-simulation","display_name":"particle-in-cell/Monte Carlo simulation","score":0.871999979019165},{"id":"https://openalex.org/keywords/plasma-simulation","display_name":"plasma simulation","score":0.6389999985694885},{"id":"https://openalex.org/keywords/tokamak-divertor","display_name":"tokamak divertor","score":0.8640000224113464},{"id":"https://openalex.org/keywords/plasma-material-interaction","display_name":"plasma-material interaction","score":0.8130000233650208},{"id":"https://openalex.org/keywords/hybrid-parallelization","display_name":"hybrid parallelism","score":0.9210000038146973},{"id":"https://openalex.org/keywords/mpi","display_name":"MPI","score":0.824999988079071},{"id":"https://openalex.org/keywords/openmp","display_name":"OpenMP","score":0.9580000042915344},{"id":"https://openalex.org/keywords/openacc","display_name":"OpenACC","score":0.996999979019165},{"id":"https://openalex.org/keywords/gpu-acceleration","display_name":"GPU acceleration","score":0.593999981880188},{"id":"https://openalex.org/keywords/parallel-efficiency","display_name":"parallel efficiency","score":0.6370000243186951},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.5899999737739563},{"id":"https://openalex.org/keywords/exascale-computing","display_name":"exascale computing","score":0.7630000114440918},{"id":"https://openalex.org/keywords/eurohpc","display_name":"EuroHPC","score":0.9190000295639038}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7090393900871277},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7036986351013184},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6912297010421753},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.6719918847084045},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5165661573410034},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4831663966178894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07892122864723206},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.jocs.2025.102590","doi":"https://doi.org/10.1016/j.jocs.2025.102590","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jocs.2025.102590","pdf_url":null,"source":{"id":"https://openalex.org/S192071280","display_name":"Journal of Computational Science","issn_l":"1877-7503","issn":["1877-7503","1877-7511"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-d","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Science","raw_type":"journal-article"},{"id":"doi:10.48550/arxiv.2404.10270","doi":"https://doi.org/10.48550/arxiv.2404.10270","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2404.10270","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-journal"}],"best_oa_location":{"id":"doi:10.1016/j.jocs.2025.102590","doi":"https://doi.org/10.1016/j.jocs.2025.102590","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jocs.2025.102590","pdf_url":null,"source":{"id":"https://openalex.org/S192071280","display_name":"Journal of Computational Science","issn_l":"1877-7503","issn":["1877-7503","1877-7511"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-d","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Science","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Affordable and clean energy","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/7"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2343504260","display_name":null,"funder_award_id":"101093261","funder_id":"https://openalex.org/F1100377486","funder_display_name":"European High Performance Computing Joint Undertaking"},{"id":"https://openalex.org/G8869864247","display_name":"NAISS","funder_award_id":"2022-06725","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F1100377486","display_name":"European High Performance Computing Joint Undertaking","ror":"https://ror.org/04dvh0v63"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322509","display_name":"Kungliga Tekniska H\u00f6gskolan","ror":"https://ror.org/026vcq606"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W791316411","https://openalex.org/W1950036567","https://openalex.org/W1973202568","https://openalex.org/W2016636268","https://openalex.org/W2023574796","https://openalex.org/W2054025053","https://openalex.org/W2073793879","https://openalex.org/W2108801243","https://openalex.org/W2109241917","https://openalex.org/W2176890627","https://openalex.org/W2249637006","https://openalex.org/W2528966197","https://openalex.org/W2546716216","https://openalex.org/W2576489192","https://openalex.org/W2623839724","https://openalex.org/W2759484396","https://openalex.org/W2762756599","https://openalex.org/W2763388378","https://openalex.org/W3048511720","https://openalex.org/W3165978538","https://openalex.org/W3207432783","https://openalex.org/W3210646446","https://openalex.org/W4230519234","https://openalex.org/W4244412182","https://openalex.org/W4245962127","https://openalex.org/W4293211604","https://openalex.org/W4313546848","https://openalex.org/W4320061944","https://openalex.org/W4367664915","https://openalex.org/W4376502341","https://openalex.org/W4384343946","https://openalex.org/W4386106809","https://openalex.org/W4387353410","https://openalex.org/W4387919466","https://openalex.org/W4400267437","https://openalex.org/W4401862050","https://openalex.org/W4403368752","https://openalex.org/W4404099840","https://openalex.org/W6649274955","https://openalex.org/W6864332055","https://openalex.org/W6869584066"],"related_works":["https://openalex.org/W4399354997","https://openalex.org/W2005148983","https://openalex.org/W2012954338","https://openalex.org/W2096672917","https://openalex.org/W2392023973","https://openalex.org/W3189307731","https://openalex.org/W1428699136","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1998560227"],"abstract_inverted_index":{"As":[0,192],"fusion":[1,12,395],"energy":[2,396],"devices":[3],"advance,":[4],"plasma":[5,328],"simulations":[6,18],"play":[7],"a":[8,103,113,130,152,162,421],"critical":[9],"role":[10],"in":[11,40,133,205,282,292],"reactor":[13],"design.":[14],"Particle-in-Cell":[15],"Monte":[16],"Carlo":[17],"are":[19,383],"essential":[20],"for":[21,46,188,326],"modeling":[22],"plasma-material":[23],"interactions":[24],"and":[25,44,48,61,75,78,145,220,236,264,307,313,332,340,360,379,415],"analyzing":[26],"power":[27],"load":[28],"distributions":[29],"on":[30,64,102,245],"tokamak":[31],"divertors.":[32],"Previous":[33],"work":[34,409],"(Williams,":[35],"2024)":[36],"introduced":[37],"hybrid":[38],"parallelization":[39],"BIT1":[41,193,387,411],"using":[42,72],"MPI":[43,58,92,124,345,441],"OpenMP/OpenACC":[45,414],"shared-memory":[47],"multicore":[49,110],"CPU":[50],"processing.":[51],"In":[52],"this":[53],"extended":[54],"work,":[55],"we":[56,321],"integrate":[57],"with":[59,68,81,151,169,349,358,412],"OpenMP":[60,69,95,144,178,199,226,355,368,447,465],"OpenACC,":[62],"focusing":[63],"asynchronous":[65,179,200,227,269,279,296,304,351,416,457],"multi-GPU":[66,201,228,270,280,297,352,417,458],"programming":[67,372],"Target":[70,356],"Tasks":[71,357],"the":[73,82,108,118,134,139,170,249,268,276,287,369,475],"\u201cnowait\u201d":[74,359],"\u201cdepend\u201d":[76,361],"clauses,":[77],"OpenACC":[79,109,126,146,182,204,237,432,443,462],"Parallel":[80],"\u201casync(n)\u201d":[83,171],"clause.":[84],"Our":[85],"results":[86,459],"show":[87,460],"significant":[88],"performance":[89,175,302,375,472],"improvements:":[90],"16":[91,425],"ranks":[93,346],"plus":[94],"threads":[96],"reduced":[97,148],"simulation":[98,149],"runtime":[99,428],"by":[100,429,435],"53%":[101],"petascale":[104,422],"EuroHPC":[105,164,423],"supercomputer,":[106,143,165],"while":[107,431],"implementation":[111,289,353],"achieved":[112],"58%":[114],"reduction":[115,154],"compared":[116],"to":[117,122,196,213,262,344,388,403,439,451],"MPI-only":[119],"version.":[120,251],"Scaling":[121,438],"64":[123,440],"ranks,":[125,442],"outperformed":[127,203],"OpenMP,":[128],"achieving":[129,229,238,404],"24%":[131],"improvement":[132],"particle":[135],"mover":[136],"function.":[137],"On":[138,420],"HPE":[140],"Cray":[141],"EX":[142],"consistently":[147],"times,":[150],"37%":[153],"at":[155,183],"100":[156],"nodes.":[157],"Results":[158],"from":[159],"MareNostrum":[160,246,398,455],"5,":[161,247],"pre-exascale":[163],"highlight":[166],"OpenACC\u2019s":[167],"effectiveness,":[168],"configuration":[172],"delivering":[173],"notable":[174],"gains.":[176],"However,":[177,267],"configurations":[180,202],"outperform":[181],"larger":[184],"node":[185,254],"counts,":[186,255],"particularly":[187],"extreme":[189],"scaling":[190],"runs.":[191],"scales":[194],"asynchronously":[195],"128":[197],"GPUs,":[198,215],"runtime,":[206],"demonstrating":[207,275],"superior":[208],"scalability,":[209],"which":[210],"continues":[211],"up":[212,450],"400":[214,452],"further":[216],"improving":[217],"runtime.":[218],"Speedup":[219],"parallel":[221],"efficiency":[222,325],"(PE)":[223],"studies":[224],"reveal":[225],"an":[230,239],"8.77":[231],"\u00d7":[232,241],"speedup":[233,242],"(54.81%":[234],"PE)":[235,244],"8.14":[240],"(50.87%":[243],"surpassing":[248],"CPU-only":[250,288],"At":[252],"higher":[253],"PE":[256],"declined":[257],"across":[258],"all":[259],"implementations":[260],"due":[261],"communication":[263],"synchronization":[265],"costs.":[266],"versions":[271],"maintained":[272],"better":[273,300,449],"PE,":[274],"benefits":[277],"of":[278],"execution":[281],"reducing":[283],"scalability":[284],"bottlenecks.":[285],"While":[286],"is":[290],"faster":[291],"some":[293],"cases,":[294],"OpenMP\u2019s":[295,350,471],"approach":[298],"delivers":[299],"GPU":[301,342,381],"through":[303],"data":[305,311,338],"transfer":[306],"task":[308],"dependencies,":[309],"ensuring":[310],"consistency":[312],"avoiding":[314],"race":[315],"conditions.":[316],"Using":[317],"NVIDIA":[318],"Nsight":[319],"tools,":[320],"confirmed":[322],"BIT1\u2019s":[323],"overall":[324],"large-scale":[327],"simulations,":[329],"leveraging":[330],"current":[331],"future":[333],"exascale":[334,405,478],"supercomputing":[335,392],"infrastructures.":[336],"Asynchronous":[337],"transfers":[339],"dedicated":[341],"assignments":[343],"enhance":[347],"performance,":[348],"utilizing":[354],"clauses":[362],"outperforming":[363],"other":[364],"configurations.":[365],"This":[366,385,408],"makes":[367],"preferred":[370],"application":[371],"interface":[373],"when":[374],"portability,":[376],"high":[377],"throughput,":[378],"efficient":[380],"utilization":[382],"critical.":[384],"enables":[386],"fully":[389],"exploit":[390],"modern":[391],"architectures,":[393],"advancing":[394],"research.":[397],"5":[399,456],"brings":[400],"us":[401],"closer":[402],"performance.":[406],"\u2022":[407,419,437,454,467],"accelerates":[410],"MPI,":[413],"programming.":[418],"system,":[424],"MPI+OpenMP":[426],"cuts":[427,433],"53%,":[430],"it":[434],"58%.":[436],"performed":[444],"well":[445],"however,":[446],"scaled":[448],"GPUs.":[453],"that":[461],"excels,":[463],"but":[464],"prevails.":[466],"Profiling":[468],"tools":[469],"confirm":[470],"portability":[473],"as":[474],"path":[476],"toward":[477],"capability.":[479]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}
