{"id":"https://openalex.org/W2147394477","doi":"https://doi.org/10.1177/1094342013492446","title":"Analysis and optimization of gyrokinetic toroidal simulations on homogenous and heterogenous platforms","display_name":"Analysis and optimization of gyrokinetic toroidal simulations on homogenous and heterogenous platforms","publication_year":2013,"publication_date":"2013-07-18","ids":{"openalex":"https://openalex.org/W2147394477","doi":"https://doi.org/10.1177/1094342013492446","mag":"2147394477"},"language":"en","primary_location":{"id":"doi:10.1177/1094342013492446","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342013492446","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/1407202","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062016419","display_name":"Khaled Z. Ibrahim","orcid":"https://orcid.org/0009-0004-5362-3612"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Khaled Z Ibrahim","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057403059","display_name":"Kamesh Madduri","orcid":"https://orcid.org/0000-0003-4344-0957"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kamesh Madduri","raw_affiliation_strings":["The Pennsylvania State University, University Park, USA","The Pennsylvania State University , University Park , USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park , USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102746800","display_name":"Samuel Williams","orcid":"https://orcid.org/0000-0002-8327-5717"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Williams","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047478622","display_name":"Bei Wang","orcid":"https://orcid.org/0000-0003-4942-9652"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bei Wang","raw_affiliation_strings":["Princeton Institute of Computational Science and Engineering, Princeton University, USA"],"affiliations":[{"raw_affiliation_string":"Princeton Institute of Computational Science and Engineering, Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078217605","display_name":"S. Ethier","orcid":"https://orcid.org/0000-0002-2666-8733"},"institutions":[{"id":"https://openalex.org/I2799567181","display_name":"Princeton Plasma Physics Laboratory","ror":"https://ror.org/03vn1ts68","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I20089843","https://openalex.org/I2799567181","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephane Ethier","raw_affiliation_strings":["Princeton Plasma Physics Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Princeton Plasma Physics Laboratory, USA","institution_ids":["https://openalex.org/I2799567181"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113842004","display_name":"Leonid Oliker","orcid":"https://orcid.org/0000-0002-7923-2896"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonid Oliker","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, USA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5062016419"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":4.6646,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.94535569,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"27","issue":"4","first_page":"454","last_page":"473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10346","display_name":"Magnetic confinement fusion research","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10346","display_name":"Magnetic confinement fusion research","score":1.0,"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/T11367","display_name":"Particle accelerators and beam dynamics","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/T10384","display_name":"Laser-Plasma Interactions and Diagnostics","score":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8159258961677551},{"id":"https://openalex.org/keywords/microturbulence","display_name":"Microturbulence","score":0.7770158052444458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7697970867156982},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6283788681030273},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5919909477233887},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5849645137786865},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.5778003931045532},{"id":"https://openalex.org/keywords/toroid","display_name":"Toroid","score":0.5660405158996582},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5336927175521851},{"id":"https://openalex.org/keywords/fortran","display_name":"Fortran","score":0.5180752277374268},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.47793343663215637},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.41072165966033936},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.37926432490348816},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.22141364216804504},{"id":"https://openalex.org/keywords/plasma","display_name":"Plasma","score":0.19525563716888428},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1200571358203888},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06451436877250671}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8159258961677551},{"id":"https://openalex.org/C2776259265","wikidata":"https://www.wikidata.org/wiki/Q3269040","display_name":"Microturbulence","level":3,"score":0.7770158052444458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7697970867156982},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6283788681030273},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5919909477233887},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5849645137786865},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.5778003931045532},{"id":"https://openalex.org/C15001198","wikidata":"https://www.wikidata.org/wiki/Q3241394","display_name":"Toroid","level":3,"score":0.5660405158996582},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5336927175521851},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.5180752277374268},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.47793343663215637},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.41072165966033936},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.37926432490348816},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.22141364216804504},{"id":"https://openalex.org/C82706917","wikidata":"https://www.wikidata.org/wiki/Q10251","display_name":"Plasma","level":2,"score":0.19525563716888428},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1200571358203888},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06451436877250671},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"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/C150846664","wikidata":"https://www.wikidata.org/wiki/Q7602306","display_name":"Stars","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1177/1094342013492446","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342013492446","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:escholarship.org/ark:/13030/qt48w9z3w5","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/48w9z3w5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of High Performance Computing Applications, vol 27, iss 4","raw_type":"article"},{"id":"pmh:oai:osti.gov:1407202","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1407202","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:qt48w9z3w5","is_oa":false,"landing_page_url":"http://www.escholarship.org/uc/item/48w9z3w5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ibrahim, KZ; Madduri, K; Williams, S; Wang, B; Ethier, S; &amp; Oliker, L. (2013). Analysis and optimization of gyrokinetic toroidal simulations on homogenous and heterogenous platforms. International Journal of High Performance Computing Applications, 27(4), 454 - 473. doi: 10.1177/1094342013492446. Lawrence Berkeley National Laboratory: Lawrence Berkeley National Laboratory. Retrieved from: http://www.escholarship.org/uc/item/48w9z3w5","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:osti.gov:1407202","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1407202","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W98259598","https://openalex.org/W1562752809","https://openalex.org/W1672666614","https://openalex.org/W1972955025","https://openalex.org/W1975138713","https://openalex.org/W1996633787","https://openalex.org/W2002774347","https://openalex.org/W2019980488","https://openalex.org/W2021119996","https://openalex.org/W2021665366","https://openalex.org/W2028869067","https://openalex.org/W2029390018","https://openalex.org/W2056385753","https://openalex.org/W2057053526","https://openalex.org/W2062898146","https://openalex.org/W2063225694","https://openalex.org/W2072423127","https://openalex.org/W2076441288","https://openalex.org/W2085548535","https://openalex.org/W2110835813","https://openalex.org/W2113453009","https://openalex.org/W2116685589","https://openalex.org/W2137985407","https://openalex.org/W2144607581","https://openalex.org/W2151359168","https://openalex.org/W2157877452","https://openalex.org/W2615050003","https://openalex.org/W3150827651"],"related_works":["https://openalex.org/W126146189","https://openalex.org/W3087399931","https://openalex.org/W1445273741","https://openalex.org/W1985658314","https://openalex.org/W2243234941","https://openalex.org/W2589012642","https://openalex.org/W3094339781","https://openalex.org/W2147394477","https://openalex.org/W3170387719","https://openalex.org/W3104815003"],"abstract_inverted_index":{"The":[0],"Gyrokinetic":[1],"Toroidal":[2],"Code":[3],"(GTC)":[4],"uses":[5,55],"the":[6,24,68],"particle-in-cell":[7],"method":[8],"to":[9,22,36,63,79],"efficiently":[10,78],"simulate":[11],"plasma":[12],"microturbulence.":[13],"This":[14],"work":[15],"presents":[16],"novel":[17],"analysis":[18,35],"and":[19,45,58,76],"optimization":[20],"techniques":[21],"enhance":[23],"performance":[25],"of":[26,53,81,83],"GTC":[27,54],"on":[28,43,72],"large-scale":[29],"machines.":[30],"We":[31],"introduce":[32],"cell":[33],"access":[34],"better":[37],"manage":[38],"locality":[39],"vs.":[40],"synchronization":[41],"tradeoffs":[42],"CPU":[44],"GPU-based":[46],"architectures.":[47],"Our":[48],"optimized":[49],"hybrid":[50],"parallel":[51,74],"implementation":[52],"MPI,":[56],"OpenMP,":[57],"NVIDIA":[59],"CUDA,":[60],"achieves":[61],"up":[62],"a":[64],"2\u00d7":[65],"speedup":[66],"over":[67],"reference":[69],"Fortran":[70],"version":[71],"multiple":[73],"systems,":[75],"scales":[77],"tens":[80],"thousands":[82],"cores.":[84]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
