{"id":"https://openalex.org/W2996519492","doi":"https://doi.org/10.1145/3368474.3368483","title":"Accuracy Improvement of Memory System Simulation for Modern Shared Memory Processor","display_name":"Accuracy Improvement of Memory System Simulation for Modern Shared Memory Processor","publication_year":2019,"publication_date":"2019-12-17","ids":{"openalex":"https://openalex.org/W2996519492","doi":"https://doi.org/10.1145/3368474.3368483","mag":"2996519492"},"language":"en","primary_location":{"id":"doi:10.1145/3368474.3368483","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368474.3368483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102814672","display_name":"Yuetsu Kodama","orcid":"https://orcid.org/0000-0001-5787-0363"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuetsu Kodama","raw_affiliation_strings":["RIKEN Center for Computational Science(R-CCS)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science(R-CCS)","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085261318","display_name":"Tetsuya Odajima","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tetsuya Odajima","raw_affiliation_strings":["R-CCS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"R-CCS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041588974","display_name":"Akira Asato","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159607","display_name":"Fujitsu (China)","ror":"https://ror.org/04w4yzw62","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159607"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Akira Asato","raw_affiliation_strings":["Fujitsu Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Limited","institution_ids":["https://openalex.org/I4210159607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040254066","display_name":"Mitsuhisa Sato","orcid":"https://orcid.org/0000-0003-0543-7116"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mitsuhisa Sato","raw_affiliation_strings":["R-CCS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"R-CCS","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8628,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.70389214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"142","last_page":"149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9979000091552734,"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":0.9979000091552734,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9728000164031982,"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/computer-science","display_name":"Computer science","score":0.8748043775558472},{"id":"https://openalex.org/keywords/computer-architecture-simulator","display_name":"Computer architecture simulator","score":0.6165528297424316},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5766791105270386},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5616924166679382},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5452829003334045},{"id":"https://openalex.org/keywords/instructions-per-cycle","display_name":"Instructions per cycle","score":0.5363155007362366},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5179063677787781},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5063372850418091},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4523426592350006},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.422183096408844},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4188340902328491},{"id":"https://openalex.org/keywords/out-of-order-execution","display_name":"Out-of-order execution","score":0.4165419042110443},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3439905047416687},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.3120008111000061},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.25433117151260376},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18337073922157288}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8748043775558472},{"id":"https://openalex.org/C201203610","wikidata":"https://www.wikidata.org/wiki/Q5157524","display_name":"Computer architecture simulator","level":2,"score":0.6165528297424316},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5766791105270386},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5616924166679382},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5452829003334045},{"id":"https://openalex.org/C156972235","wikidata":"https://www.wikidata.org/wiki/Q1443434","display_name":"Instructions per cycle","level":3,"score":0.5363155007362366},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5179063677787781},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5063372850418091},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4523426592350006},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.422183096408844},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4188340902328491},{"id":"https://openalex.org/C1793878","wikidata":"https://www.wikidata.org/wiki/Q1153762","display_name":"Out-of-order execution","level":2,"score":0.4165419042110443},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3439905047416687},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.3120008111000061},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.25433117151260376},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18337073922157288},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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":1,"locations":[{"id":"doi:10.1145/3368474.3368483","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368474.3368483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2613264175","https://openalex.org/W2899187877","https://openalex.org/W2938324068","https://openalex.org/W3123542955"],"related_works":["https://openalex.org/W2366807055","https://openalex.org/W2112394217","https://openalex.org/W4311294724","https://openalex.org/W3092369023","https://openalex.org/W2075747496","https://openalex.org/W2000547159","https://openalex.org/W4236831773","https://openalex.org/W2122760055","https://openalex.org/W2055341571","https://openalex.org/W1964950829"],"abstract_inverted_index":{"For":[0],"the":[1,24,33,53,75,91,97,101,107,115,118,135,160,163,182,185,194,203,206,217],"purpose":[2],"of":[3,36,56,68,79,100,117,124,138,162,165,175,184,202,209,219,227],"developing":[4],"applications":[5],"for":[6,200],"supercomputer":[7],"Fugaku":[8,38,126,144,177],"at":[9],"an":[10],"early":[11],"stage,":[12],"RIKEN":[13,108],"has":[14],"developed":[15],"a":[16,37,80,125,143,176],"processor":[17,26,145,178],"simulator.":[18],"This":[19],"simulator":[20,27,167],"is":[21,83,196],"based":[22],"on":[23,142],"general-purpose":[25],"gem5.":[28],"It":[29],"does":[30],"not":[31,89],"simulate":[32,86],"actual":[34],"hardware":[35],"processor.":[39,127],"However,":[40],"we":[41,110,131,158],"believe":[42],"that":[43,123,148,174,193],"sufficient":[44],"simulation":[45],"accuracy":[46,61,88,147,171],"can":[47],"be":[48],"obtained":[49],"since":[50],"it":[51,82,190],"simulates":[52],"instruction":[54,92],"pipeline":[55],"out-of-order":[57,69],"execution":[58,77,93,136,208],"with":[59,63,87,146,173,230],"cycle-level":[60],"along":[62],"performing":[64],"detailed":[65],"parameter":[66],"tuning":[67],"resources.":[70],"In":[71,128,155,181,205],"order":[72],"to":[73,85,113,122,133,216],"estimate":[74,134],"accurate":[76],"time":[78,99],"program,":[81],"necessary":[84],"only":[90],"time,":[94],"but":[95],"also":[96],"access":[98],"cache":[102,119],"memory":[103,120,228],"hierarchy.":[104],"Therefore,":[105],"in":[106],"simulator,":[109,130],"expanded":[111],"gem5":[112],"match":[114],"performance":[116,214],"hierarchy":[121],"this":[129,156,166],"aim":[132],"cycles":[137],"one":[139],"node":[140],"application":[141,153],"enables":[149],"relative":[150],"evaluation":[151,183],"and":[152,168,223],"tuning.":[154],"paper,":[157],"show":[159],"details":[161],"implementation":[164],"verify":[169],"its":[170],"compared":[172],"test":[179],"chip.":[180],"total":[186],"46":[187],"kernel":[188],"benchmarks,":[189],"was":[191,221],"confirmed":[192],"difference":[195],"13%":[197],"or":[198],"less":[199],"85%":[201],"kernels.":[204],"multithreaded":[207],"Stream":[210],"Triad":[211],"benchmark,":[212],"scalable":[213],"according":[215],"number":[218],"threads":[220],"confirmed,":[222],"achieved":[224],"over":[225],"80%":[226],"throughput":[229],"enough":[231],"accuracy.":[232]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}