{"id":"https://openalex.org/W2953672018","doi":"https://doi.org/10.1007/978-3-030-22734-0_20","title":"Development of Element-by-Element Kernel Algorithms in Unstructured Implicit Low-Order Finite-Element Earthquake Simulation for Many-Core Wide-SIMD CPUs","display_name":"Development of Element-by-Element Kernel Algorithms in Unstructured Implicit Low-Order Finite-Element Earthquake Simulation for Many-Core Wide-SIMD CPUs","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2953672018","doi":"https://doi.org/10.1007/978-3-030-22734-0_20","mag":"2953672018"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-22734-0_20","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"book-chapter","type_crossref":"book-chapter","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/A5101402257","display_name":"Kohei Fujita","orcid":"https://orcid.org/0000-0003-2911-0222"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I4210120963","display_name":"Association for the Development of Earthquake Prediction","ror":"https://ror.org/02akdcs48","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210120963"]},{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kohei Fujita","raw_affiliation_strings":["Center for Computational Science, RIKEN, Kobe, Japan","Earthquake Research Institute and Department of Civil Engineering, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Earthquake Research Institute and Department of Civil Engineering, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974","https://openalex.org/I4210120963"]},{"raw_affiliation_string":"Center for Computational Science, RIKEN, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073314426","display_name":"Masashi Horikoshi","orcid":null},"institutions":[],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Horikoshi","raw_affiliation_strings":["Core and Visual Computing Group, Intel K.K, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Core and Visual Computing Group, Intel K.K, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102274309","display_name":"Tsuyoshi Ichimura","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I4210120963","display_name":"Association for the Development of Earthquake Prediction","ror":"https://ror.org/02akdcs48","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210120963"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsuyoshi Ichimura","raw_affiliation_strings":["Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan","Center for Computational Science, RIKEN, Kobe, Japan","Earthquake Research Institute and Department of Civil Engineering, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Computational Science, RIKEN, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]},{"raw_affiliation_string":"Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Earthquake Research Institute and Department of Civil Engineering, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210120963","https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075276415","display_name":"Larry Meadows","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Larry Meadows","raw_affiliation_strings":["Data Center Group, Intel Corporation, Hillsboro, USA"],"affiliations":[{"raw_affiliation_string":"Data Center Group, Intel Corporation, Hillsboro, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109365632","display_name":"Kengo Nakajima","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kengo Nakajima","raw_affiliation_strings":["Center for Computational Science, RIKEN, Kobe, Japan","Information Technology Center, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Computational Science, RIKEN, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]},{"raw_affiliation_string":"Information Technology Center, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010899083","display_name":"Muneo Hori","orcid":"https://orcid.org/0000-0002-0642-6753"},"institutions":[{"id":"https://openalex.org/I1315852903","display_name":"Japan Agency for Marine-Earth Science and Technology","ror":"https://ror.org/059qg2m13","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1315852903"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Muneo Hori","raw_affiliation_strings":["Japan Agency for Marine-Earth Science and Technology, Yokosuka, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Agency for Marine-Earth Science and Technology, Yokosuka, Japan","institution_ids":["https://openalex.org/I1315852903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020079438","display_name":"Lalith Wijerathne","orcid":"https://orcid.org/0000-0001-6334-4802"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]},{"id":"https://openalex.org/I4210120963","display_name":"Association for the Development of Earthquake Prediction","ror":"https://ror.org/02akdcs48","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210120963"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lalith Maddegedara","raw_affiliation_strings":["Center for Computational Science, RIKEN, Kobe, Japan","Earthquake Research Institute and Department of Civil Engineering, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Computational Science, RIKEN, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]},{"raw_affiliation_string":"Earthquake Research Institute and Department of Civil Engineering, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210120963","https://openalex.org/I74801974"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101402257"],"corresponding_institution_ids":["https://openalex.org/I74801974","https://openalex.org/I4210120963","https://openalex.org/I4210129730"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392,"provenance":"doaj"},"apc_paid":null,"fwci":0.677,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.560199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":62,"max":70},"biblio":{"volume":null,"issue":null,"first_page":"267","last_page":"280"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Performance Optimization","score":0.9988,"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 Performance Optimization","score":0.9988,"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/T10792","display_name":"Matrix Algorithms and Iterative Methods","score":0.9946,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11522","display_name":"Design and Optimization of Field-Programmable Gate Arrays and Application-Specific Integrated Circuits","score":0.9929,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/simd","display_name":"SIMD","score":0.85351324},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7934153},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.7295642},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6850018},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.6238514},{"id":"https://openalex.org/keywords/multicore-architectures","display_name":"Multicore Architectures","score":0.55813},{"id":"https://openalex.org/keywords/high-performance-computing","display_name":"High-Performance Computing","score":0.530669},{"id":"https://openalex.org/keywords/heterogeneous-computing","display_name":"Heterogeneous Computing","score":0.527172},{"id":"https://openalex.org/keywords/gpu-computing","display_name":"GPU Computing","score":0.519722},{"id":"https://openalex.org/keywords/performance-optimization","display_name":"Performance Optimization","score":0.509339}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.85351324},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7934153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76381326},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7593607},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.7295642},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6850018},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.6238514},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.5767168},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.42235482},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.41630113},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3248645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08584231},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.08020073},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.071733475},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06907046},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-22734-0_20","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.84,"display_name":"Sustainable cities and communities"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":13,"referenced_works":["https://openalex.org/W1509169340","https://openalex.org/W2032576830","https://openalex.org/W2036502262","https://openalex.org/W2070232376","https://openalex.org/W2073168606","https://openalex.org/W2079118382","https://openalex.org/W2083279262","https://openalex.org/W2475636809","https://openalex.org/W2562913534","https://openalex.org/W2567451879","https://openalex.org/W2751354592","https://openalex.org/W2886097661","https://openalex.org/W2978256392"],"related_works":["https://openalex.org/W947442053","https://openalex.org/W2929736795","https://openalex.org/W2739740241","https://openalex.org/W2526069705","https://openalex.org/W2475524688","https://openalex.org/W2099629705","https://openalex.org/W2085105049","https://openalex.org/W2056079253","https://openalex.org/W2022113063","https://openalex.org/W1974923383"],"abstract_inverted_index":{"Acceleration":[0],"of":[1,67,99,108],"the":[2,19,93,100,113],"Element-by-Element":[3],"(EBE)":[4],"kernel":[5,21,62,95],"in":[6,13],"matrix-vector":[7],"products":[8],"is":[9,22,117],"essential":[10],"for":[11,48],"high-performance":[12],"unstructured":[14],"implicit":[15],"finite-element":[16,102,115],"applications.":[17],"However,":[18],"EBE":[20,61],"not":[23],"straightforward":[24],"to":[25,30,43,89],"attain":[26],"high":[27,49],"performance":[28,50],"due":[29],"random":[31],"data":[32,35,46],"access":[33],"with":[34,55],"recurrence.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"develop":[41],"methods":[42],"circumvent":[44],"these":[45],"races":[47],"on":[51,70,104],"many-core":[52],"CPU":[53],"architectures":[54],"wide":[56],"SIMD":[57],"units.":[58],"The":[59],"developed":[60,114],"attains":[63],"16.3%":[64],"and":[65,78,96],"20.9%":[66],"FP32":[68],"peak":[69],"Intel":[71,79],"Xeon":[72,81],"Phi":[73],"Knights":[74],"Landing":[75],"based":[76,84],"Oakforest-PACS":[77],"Skylake":[80],"Gold":[82],"processor":[83],"system,":[85],"respectively.":[86],"This":[87],"leads":[88],"2.88-fold":[90],"speedup":[91,98],"over":[92],"baseline":[94],"2.03-fold":[97],"whole":[101],"application":[103,116],"Oakforest-PACS.":[105],"An":[106],"example":[107],"urban":[109],"earthquake":[110],"simulation":[111],"using":[112],"shown.":[118]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2953672018","counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2024-10-15T11:28:02.754590","created_date":"2019-07-12"}
