{"id":"https://openalex.org/W2897016567","doi":"https://doi.org/10.1109/cahpc.2018.8645933","title":"Scaling and Optimizing the Gysela Code on a Cluster of Many-Core Processors","display_name":"Scaling and Optimizing the Gysela Code on a Cluster of Many-Core Processors","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2897016567","doi":"https://doi.org/10.1109/cahpc.2018.8645933","mag":"2897016567"},"language":"en","primary_location":{"id":"doi:10.1109/cahpc.2018.8645933","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cahpc.2018.8645933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.inria.fr/hal-01719208","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059558666","display_name":"Guillaume Latu","orcid":"https://orcid.org/0009-0001-7274-1305"},"institutions":[{"id":"https://openalex.org/I4210110641","display_name":"CEA Cadarache","ror":"https://ror.org/01rs1gy10","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I4210110641"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Guillaume Latu","raw_affiliation_strings":["CEA, IRFM, St-Paul-lez-Durance"],"affiliations":[{"raw_affiliation_string":"CEA, IRFM, St-Paul-lez-Durance","institution_ids":["https://openalex.org/I4210110641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036953994","display_name":"Yuuichi Asahi","orcid":"https://orcid.org/0000-0002-9997-1274"},"institutions":[{"id":"https://openalex.org/I4210108322","display_name":"National Institute for Fusion Science","ror":"https://ror.org/01t3wyv61","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I199525922","https://openalex.org/I4210108322"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuuichi Asahi","raw_affiliation_strings":["QST Rokkasho Fusion Institute, Aomori, Japan"],"affiliations":[{"raw_affiliation_string":"QST Rokkasho Fusion Institute, Aomori, Japan","institution_ids":["https://openalex.org/I4210108322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073645491","display_name":"Julien Bigot","orcid":"https://orcid.org/0000-0002-0015-4304"},"institutions":[{"id":"https://openalex.org/I4210125654","display_name":"Maison de la Simulation","ror":"https://ror.org/03jv6w209","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I195731000","https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210113668","https://openalex.org/I4210125654","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Julien Bigot","raw_affiliation_strings":["CEA, Maison de la Simulation, Gif-sur-Yvette"],"affiliations":[{"raw_affiliation_string":"CEA, Maison de la Simulation, Gif-sur-Yvette","institution_ids":["https://openalex.org/I4210125654"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066682900","display_name":"T. Feh\u00e9r","orcid":"https://orcid.org/0000-0003-2095-4349"},"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":"Tamas Feher","raw_affiliation_strings":["Max Planck Institute for Plasma Physics, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Plasma Physics, Garching, Germany","institution_ids":["https://openalex.org/I4210139716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078757204","display_name":"V. Grandgirard","orcid":"https://orcid.org/0000-0001-7821-9107"},"institutions":[{"id":"https://openalex.org/I4210110641","display_name":"CEA Cadarache","ror":"https://ror.org/01rs1gy10","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I4210110641"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Virginie Grandgirard","raw_affiliation_strings":["CEA, IRFM, St-Paul-lez-Durance"],"affiliations":[{"raw_affiliation_string":"CEA, IRFM, St-Paul-lez-Durance","institution_ids":["https://openalex.org/I4210110641"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059558666"],"corresponding_institution_ids":["https://openalex.org/I4210110641"],"apc_list":null,"apc_paid":null,"fwci":0.5862,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72560099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"466","last_page":"473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991999864578247,"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":0.9991999864578247,"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/T10346","display_name":"Magnetic confinement fusion research","score":0.9991000294685364,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8248913288116455},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.797834038734436},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7336097359657288},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.7248653173446655},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7135980725288391},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.7018787264823914},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6569966077804565},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.557332456111908},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5475368499755859},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.49662357568740845},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.48424074053764343},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.46933379769325256},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43628591299057007},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13419172167778015},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13182365894317627},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.11225727200508118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8248913288116455},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.797834038734436},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7336097359657288},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.7248653173446655},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7135980725288391},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.7018787264823914},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6569966077804565},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.557332456111908},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5475368499755859},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.49662357568740845},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.48424074053764343},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.46933379769325256},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43628591299057007},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13419172167778015},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13182365894317627},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.11225727200508118},{"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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/cahpc.2018.8645933","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cahpc.2018.8645933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01719208v1","is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-01719208","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/hal-01719208","raw_type":"\\ninfo:eu-repo/semantics/preprint\\n"},{"id":"pmh:oai:HAL:hal-01719208v2","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01719208","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE","raw_type":"Conference papers"},{"id":"pmh:oai:escidoc.org:escidoc:2637586","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0001-FE20-D","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/lecture"},{"id":"pmh:oai:pure.mpg.de:item_3048424","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0003-686C-0","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01719208v1","is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-01719208","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/hal-01719208","raw_type":"\\ninfo:eu-repo/semantics/preprint\\n"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.41999998688697815}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334323","display_name":"Euratom Research and Training Programme","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1767549604","https://openalex.org/W1985880774","https://openalex.org/W2294357336","https://openalex.org/W2484414518","https://openalex.org/W2744170517","https://openalex.org/W2963570079","https://openalex.org/W6637988584"],"related_works":["https://openalex.org/W2740999212","https://openalex.org/W1939907483","https://openalex.org/W2188971969","https://openalex.org/W2035419609","https://openalex.org/W2056079253","https://openalex.org/W2912502764","https://openalex.org/W1994052277","https://openalex.org/W1766386015","https://openalex.org/W2024554511","https://openalex.org/W2895895456"],"abstract_inverted_index":{"The":[0],"current":[1],"generation":[2],"of":[3,39,47,76,86,118],"the":[4,30,40,44,55],"Xeon":[5],"Phi":[6],"Knights":[7],"Landing":[8],"(KNL)":[9],"processor":[10],"provides":[11],"a":[12,65,95,106,116,132,140,147],"highly":[13],"multi-threaded":[14],"environment":[15],"on":[16,35,120,125,139],"which":[17],"regular":[18],"programming":[19],"models":[20],"such":[21],"as":[22],"MPIjopenMP":[23],"can":[24],"be":[25],"used.":[26],"Many":[27],"factors":[28],"impact":[29],"performance":[31],"achieved":[32],"by":[33,103],"applications":[34],"these":[36],"devices:":[37],"one":[38,52,87],"key":[41],"points":[42],"is":[43,54],"efficient":[45],"exploitation":[46],"SIMD":[48],"vector":[49],"units,":[50],"and":[51,123],"another":[53],"memory":[56],"access":[57],"pattern.":[58],"Works":[59],"have":[60,79,100,136],"been":[61,80,101,137],"conducted":[62],"to":[63,91,105,114,131,152],"adapt":[64],"plasma":[66],"turbulence":[67],"application,":[68],"namely":[69],"Gysela,":[70],"for":[71],"this":[72],"architecture.":[73],"A":[74],"set":[75],"different":[77],"techniques":[78],"used:":[81],"standard":[82],"vectorization":[83],"techniques,":[84],"auto-tuning":[85],"computation":[88],"kernel,":[89],"switching":[90],"high-order":[92],"scheme.":[93],"As":[94],"result,":[96],"KNL":[97],"execution":[98],"times":[99],"reduced":[102],"up":[104,130],"factor":[107],"3.":[108],"This":[109],"effort":[110],"has":[111],"also":[112],"permitted":[113],"gain":[115],"speedup":[117],"2x":[119],"Broadwell":[121],"architecture":[122],"3x":[124],"Skylake.":[126],"Nice":[127],"scalability":[128],"curves":[129],"few":[133],"thousands":[134],"cores":[135],"obtained":[138],"strong":[141],"scaling":[142],"experiment.":[143],"Incremental":[144],"work":[145],"meant":[146],"large":[148],"payoff":[149],"without":[150],"resorting":[151],"using":[153],"low-level":[154],"intrinsics.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
