{"id":"https://openalex.org/W2557985372","doi":"https://doi.org/10.1109/tpds.2016.2633349","title":"Optimization of Fusion Kernels on Accelerators with Indirect or Strided Memory Access Patterns","display_name":"Optimization of Fusion Kernels on Accelerators with Indirect or Strided Memory Access Patterns","publication_year":2016,"publication_date":"2016-11-29","ids":{"openalex":"https://openalex.org/W2557985372","doi":"https://doi.org/10.1109/tpds.2016.2633349","mag":"2557985372"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2016.2633349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2633349","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":"article","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/A5036953994","display_name":"Yuuichi Asahi","orcid":"https://orcid.org/0000-0002-9997-1274"},"institutions":[{"id":"https://openalex.org/I117197279","display_name":"Japan Atomic Energy Agency","ror":"https://ror.org/05nf86y53","country_code":"JP","type":"funder","lineage":["https://openalex.org/I117197279"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuuichi Asahi","raw_affiliation_strings":["Japan Atomic Energy Agency, Kashiwa, Chiba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Atomic Energy Agency, Kashiwa, Chiba, Japan","institution_ids":["https://openalex.org/I117197279"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Latu","raw_affiliation_strings":["CEA Cadarache, IRFM, Saint-Paul-lez-Durance, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CEA Cadarache, IRFM, Saint-Paul-lez-Durance, France","institution_ids":["https://openalex.org/I4210110641","https://openalex.org/I2738703131"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088222852","display_name":"Takuya Ina","orcid":"https://orcid.org/0000-0002-3989-5011"},"institutions":[{"id":"https://openalex.org/I117197279","display_name":"Japan Atomic Energy Agency","ror":"https://ror.org/05nf86y53","country_code":"JP","type":"funder","lineage":["https://openalex.org/I117197279"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Ina","raw_affiliation_strings":["Japan Atomic Energy Agency, Kashiwa, Chiba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Atomic Energy Agency, Kashiwa, Chiba, Japan","institution_ids":["https://openalex.org/I117197279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017412373","display_name":"Yasuhiro Idomura","orcid":"https://orcid.org/0000-0002-2829-0498"},"institutions":[{"id":"https://openalex.org/I117197279","display_name":"Japan Atomic Energy Agency","ror":"https://ror.org/05nf86y53","country_code":"JP","type":"funder","lineage":["https://openalex.org/I117197279"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuhiro Idomura","raw_affiliation_strings":["Japan Atomic Energy Agency, Kashiwa, Chiba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Atomic Energy Agency, Kashiwa, Chiba, Japan","institution_ids":["https://openalex.org/I117197279"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Virginie Grandgirard","raw_affiliation_strings":["CEA Cadarache, IRFM, Saint-Paul-lez-Durance, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CEA Cadarache, IRFM, Saint-Paul-lez-Durance, France","institution_ids":["https://openalex.org/I4210110641","https://openalex.org/I2738703131"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009377621","display_name":"X. Garbet","orcid":"https://orcid.org/0000-0001-5730-1259"},"institutions":[{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"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":"Xavier Garbet","raw_affiliation_strings":["CEA Cadarache, IRFM, Saint-Paul-lez-Durance, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CEA Cadarache, IRFM, Saint-Paul-lez-Durance, France","institution_ids":["https://openalex.org/I4210110641","https://openalex.org/I2738703131"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5036953994"],"corresponding_institution_ids":["https://openalex.org/I117197279"],"apc_list":null,"apc_paid":null,"fwci":2.9712,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92628133,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"28","issue":"7","first_page":"1974","last_page":"1988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10346","display_name":"Magnetic confinement fusion research","score":0.9997000098228455,"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":0.9997000098228455,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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/T11367","display_name":"Particle accelerators and beam dynamics","score":0.9610999822616577,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.813075065612793},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8054031729698181},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.7108545303344727},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.6517422199249268},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5553216934204102},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.48677611351013184},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4568397104740143},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.42341890931129456},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4159987270832062},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3792805075645447},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.2507905662059784},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10252085328102112},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.095120370388031}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.813075065612793},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8054031729698181},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.7108545303344727},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.6517422199249268},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5553216934204102},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.48677611351013184},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4568397104740143},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.42341890931129456},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4159987270832062},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3792805075645447},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.2507905662059784},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10252085328102112},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.095120370388031},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2016.2633349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2633349","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309911","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20"},{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1506424797","https://openalex.org/W1562841074","https://openalex.org/W1594498663","https://openalex.org/W1677252112","https://openalex.org/W1703498004","https://openalex.org/W1907157228","https://openalex.org/W1979413470","https://openalex.org/W1985880774","https://openalex.org/W2002555321","https://openalex.org/W2009893040","https://openalex.org/W2011804442","https://openalex.org/W2013196286","https://openalex.org/W2036895361","https://openalex.org/W2041317506","https://openalex.org/W2042690107","https://openalex.org/W2049161806","https://openalex.org/W2067081242","https://openalex.org/W2086617698","https://openalex.org/W2104597668","https://openalex.org/W2107069653","https://openalex.org/W2126256127","https://openalex.org/W2127073620","https://openalex.org/W2138030864","https://openalex.org/W2154078685","https://openalex.org/W2159497832","https://openalex.org/W2170258208","https://openalex.org/W2294357336","https://openalex.org/W2312126115","https://openalex.org/W2484886375","https://openalex.org/W2765650784","https://openalex.org/W2963636689","https://openalex.org/W3098749344","https://openalex.org/W3152199537","https://openalex.org/W4229929217","https://openalex.org/W6630360801","https://openalex.org/W6633715354","https://openalex.org/W6635425727","https://openalex.org/W6646582756","https://openalex.org/W6722291136","https://openalex.org/W7008672335"],"related_works":["https://openalex.org/W2213533160","https://openalex.org/W4252450863","https://openalex.org/W2467043670","https://openalex.org/W2085105049","https://openalex.org/W2269110805","https://openalex.org/W3203561460","https://openalex.org/W3009624197","https://openalex.org/W4251138667","https://openalex.org/W2682544458","https://openalex.org/W2105221648"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"optimization":[3],"for":[4,89,166,178],"high-dimensional":[5],"stencil":[6],"computations":[7],"on":[8,58,111,162,174,189],"accelerators":[9,67],"involving":[10],"complex":[11],"memory":[12,32,37,48,63,91,118,126,151],"access":[13,33,38,49,64],"patterns,":[14,34],"which":[15],"appear":[16],"in":[17,39,50,128],"five":[18],"dimensional":[19],"fusion":[20],"plasma":[21],"turbulence":[22],"codes,":[23],"GYSELA":[24,40],"and":[25,45,71,105,170],"GT5D.":[26],"They":[27],"include":[28],"different":[29],"types":[30],"of":[31,61,80,82,123,134,139,143,150,159,171],"the":[35,46,59,62,78,97,116,121,124,129,140,144,148,167,179,185],"indirect":[36,125],"with":[41,52,182],"a":[42,53],"Semi-Lagrangian":[43,130,168],"scheme":[44,146,169,181],"strided":[47],"GT5D":[51],"Finite-Difference":[54,145],"scheme.":[55,131],"We":[56],"focus":[57],"affinity":[60],"patterns":[65],"to":[66,184],"such":[68],"as":[69],"GPGPUs":[70],"Xeon":[72,112,163,175],"Phi":[73,164,176],"coprocessors.":[74],"On":[75,114],"both":[76],"devices,":[77],"Array":[79,83],"Structure":[81],"(AoSoA)":[84],"data":[85,107],"layout":[86],"is":[87,94,109],"preferable":[88],"contiguous":[90],"accesses.":[92,152],"It":[93],"shown":[95],"that":[96],"effective":[98],"local":[99],"cache":[100],"usage":[101,119],"by":[102,136],"improving":[103],"spatial":[104],"temporal":[106],"locality":[108],"critical":[110],"Phi.":[113],"GPGPU,":[115],"texture":[117],"improves":[120],"performance":[122],"accesses":[127],"The":[132],"reuse":[133],"registers":[135],"taking":[137],"account":[138],"physical":[141],"symmetry":[142],"reduces":[147],"amount":[149],"Through":[153],"these":[154],"optimizations,":[155],"we":[156],"achieve":[157],"acceleration":[158],"3.9":[160],"(8.1)":[161],"(GPGPU)":[165,177],"1.4":[172],"(3.9)":[173],"Finite-Different":[180],"respect":[183],"fully":[186],"optimized":[187],"codes":[188],"Sandy":[190],"Bridge.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}