{"id":"https://openalex.org/W3126995771","doi":"https://doi.org/10.14529/jsfi200401","title":"Effects of Using a Memory Stalled Core for Handling MPI Communication Overlapping in the SOR Solver on SX-ACE and SX-Aurora TSUBASA","display_name":"Effects of Using a Memory Stalled Core for Handling MPI Communication Overlapping in the SOR Solver on SX-ACE and SX-Aurora TSUBASA","publication_year":2020,"publication_date":"2020-12-01","ids":{"openalex":"https://openalex.org/W3126995771","doi":"https://doi.org/10.14529/jsfi200401","mag":"3126995771"},"language":"en","primary_location":{"id":"doi:10.14529/jsfi200401","is_oa":true,"landing_page_url":"https://doi.org/10.14529/jsfi200401","pdf_url":"https://superfri.org/index.php/superfri/article/download/318/375","source":{"id":"https://openalex.org/S4210177204","display_name":"Supercomputing Frontiers and Innovations","issn_l":"2313-8734","issn":["2313-8734","2409-6008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310312680","host_organization_name":"Publishing center of the South Ural State University","host_organization_lineage":["https://openalex.org/P4310312680"],"host_organization_lineage_names":["Publishing center of the South Ural State University"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Supercomputing Frontiers and Innovations","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://superfri.org/index.php/superfri/article/download/318/375","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101062490","display_name":"Takashi Soga","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Takashi Soga","raw_affiliation_strings":["NEC Solution Innovators, Ltd"],"affiliations":[{"raw_affiliation_string":"NEC Solution Innovators, Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113218531","display_name":"Kenta Yamaguchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenta Yamaguchi","raw_affiliation_strings":["NEC Solution Innovators, Ltd"],"affiliations":[{"raw_affiliation_string":"NEC Solution Innovators, Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067790256","display_name":"Raghunandan Mathur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raghunandan Mathur","raw_affiliation_strings":["NEC Corporation"],"affiliations":[{"raw_affiliation_string":"NEC Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088236477","display_name":"Osamu Watanabe","orcid":"https://orcid.org/0000-0003-0284-7566"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Osamu Watanabe","raw_affiliation_strings":["NEC Corporation"],"affiliations":[{"raw_affiliation_string":"NEC Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032678092","display_name":"Akihiro Musa","orcid":"https://orcid.org/0000-0002-2161-658X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akihiro Musa","raw_affiliation_strings":["NEC Corporation"],"affiliations":[{"raw_affiliation_string":"NEC Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033954091","display_name":"Ryusuke Egawa","orcid":"https://orcid.org/0000-0001-8966-867X"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryusuke Egawa","raw_affiliation_strings":["Tohoku University"],"affiliations":[{"raw_affiliation_string":"Tohoku University","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007893254","display_name":"Hiroaki Kobayashi","orcid":"https://orcid.org/0000-0002-3350-1413"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroaki Kobayashi","raw_affiliation_strings":["Tohoku University"],"affiliations":[{"raw_affiliation_string":"Tohoku University","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101062490"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.2317634,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"7","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9990000128746033,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9990000128746033,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987999796867371,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9977999925613403,"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/supercomputer","display_name":"Supercomputer","score":0.8405429124832153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7833704948425293},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7109331488609314},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5795828104019165},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.5702345967292786},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5193318128585815},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5163663625717163},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4997739791870117},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4914053678512573},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.49091988801956177},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.48771342635154724},{"id":"https://openalex.org/keywords/idle","display_name":"Idle","score":0.4633975327014923},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.4562349319458008},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44005870819091797},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2224770188331604},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11452361941337585}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8405429124832153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833704948425293},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7109331488609314},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5795828104019165},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.5702345967292786},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5193318128585815},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5163663625717163},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4997739791870117},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4914053678512573},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.49091988801956177},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.48771342635154724},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.4633975327014923},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.4562349319458008},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44005870819091797},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2224770188331604},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11452361941337585},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14529/jsfi200401","is_oa":true,"landing_page_url":"https://doi.org/10.14529/jsfi200401","pdf_url":"https://superfri.org/index.php/superfri/article/download/318/375","source":{"id":"https://openalex.org/S4210177204","display_name":"Supercomputing Frontiers and Innovations","issn_l":"2313-8734","issn":["2313-8734","2409-6008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310312680","host_organization_name":"Publishing center of the South Ural State University","host_organization_lineage":["https://openalex.org/P4310312680"],"host_organization_lineage_names":["Publishing center of the South Ural State University"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Supercomputing Frontiers and Innovations","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.14529/jsfi200401","is_oa":true,"landing_page_url":"https://doi.org/10.14529/jsfi200401","pdf_url":"https://superfri.org/index.php/superfri/article/download/318/375","source":{"id":"https://openalex.org/S4210177204","display_name":"Supercomputing Frontiers and Innovations","issn_l":"2313-8734","issn":["2313-8734","2409-6008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310312680","host_organization_name":"Publishing center of the South Ural State University","host_organization_lineage":["https://openalex.org/P4310312680"],"host_organization_lineage_names":["Publishing center of the South Ural State University"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Supercomputing Frontiers and Innovations","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3126995771.pdf","grobid_xml":"https://content.openalex.org/works/W3126995771.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2066912925","https://openalex.org/W2092481329","https://openalex.org/W2111519549","https://openalex.org/W2147128853","https://openalex.org/W2156261073","https://openalex.org/W2552332896","https://openalex.org/W2760678483","https://openalex.org/W2792838682","https://openalex.org/W2886969169","https://openalex.org/W2888975747","https://openalex.org/W2902045097","https://openalex.org/W2950331044","https://openalex.org/W4229929217","https://openalex.org/W4287901611"],"related_works":["https://openalex.org/W2124048060","https://openalex.org/W4386915331","https://openalex.org/W2378910916","https://openalex.org/W2116006827","https://openalex.org/W2361929291","https://openalex.org/W2086666199","https://openalex.org/W2366325093","https://openalex.org/W2498758832","https://openalex.org/W2133825528","https://openalex.org/W2154020360"],"abstract_inverted_index":{"Modern":[0],"high-performance":[1],"computing":[2],"(HPC)":[3],"systems":[4],"consist":[5],"of":[6,10,31,44,54,122,140],"a":[7,22,59,64],"large":[8],"number":[9,43],"nodes":[11],"featuring":[12],"multi-core":[13],"processors.":[14],"Many":[15],"computational":[16],"fluid":[17],"dynamics":[18],"(CFD)":[19],"codes":[20],"utilize":[21],"Message":[23],"Passing":[24],"Interface":[25],"(MPI)":[26],"to":[27,73,78],"exploit":[28],"the":[29,36,42,55,69,74,83,87,102,118,125,132,138,141],"potential":[30],"such":[32],"systems.":[33],"In":[34,48],"general,":[35],"MPI":[37,45,119],"communication":[38,66,85,88,120],"costs":[39],"increase":[40],"as":[41,63],"processes":[46],"increases.":[47],"this":[49,114],"paper,":[50],"we":[51],"discuss":[52],"performance":[53,75,110,139],"code":[56,115],"in":[57],"which":[58],"core":[60,67,70],"is":[61,146],"used":[62],"dedicated":[65,84],"when":[68],"cannot":[71],"contribute":[72],"improvement":[76],"due":[77],"memory-bandwidth":[79],"limitations.":[80],"By":[81],"using":[82],"core,":[86],"operations":[89],"are":[90],"overlapped":[91],"with":[92],"computation":[93,99],"operations,":[94],"thus":[95],"enabling":[96],"highly":[97],"efficient":[98],"by":[100,148],"exploiting":[101],"limited":[103],"memory":[104],"bandwidth":[105],"and":[106,129,137,152],"idle":[107],"cores.":[108],"The":[109],"evaluation":[111],"shows":[112],"that":[113],"can":[116],"hide":[117],"times":[121],"90%":[123],"on":[124,131,150,154],"supercomputer":[126,133],"SX-ACE":[127,151],"system":[128],"80%":[130],"SX-Aurora":[134,155],"TSUBASA":[135],"system,":[136],"successive":[142],"over-relaxation":[143],"(SOR)":[144],"method":[145],"improved":[147],"32%":[149],"20%":[153],"TSUBASA.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-02-15T00:00:00"}
