{"id":"https://openalex.org/W2318393100","doi":"https://doi.org/10.1177/1094342015607950","title":"High-performance conjugate gradient performance improvement on the K computer","display_name":"High-performance conjugate gradient performance improvement on the K computer","publication_year":2015,"publication_date":"2015-10-11","ids":{"openalex":"https://openalex.org/W2318393100","doi":"https://doi.org/10.1177/1094342015607950","mag":"2318393100"},"language":"en","primary_location":{"id":"doi:10.1177/1094342015607950","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015607950","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","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/A5111957081","display_name":"Kiyoshi Kumahata","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165842","display_name":"RIKEN Center for Advanced Photonics","ror":"https://ror.org/05vmjks78","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210165842"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kiyoshi Kumahata","raw_affiliation_strings":["Software Development Team, Operations and Computer Technologies Division, RIKEN AICS, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Development Team, Operations and Computer Technologies Division, RIKEN AICS, Japan","institution_ids":["https://openalex.org/I4210165842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047106505","display_name":"Kazuo Minami","orcid":"https://orcid.org/0000-0002-9689-7953"},"institutions":[{"id":"https://openalex.org/I4210165842","display_name":"RIKEN Center for Advanced Photonics","ror":"https://ror.org/05vmjks78","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210165842"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuo Minami","raw_affiliation_strings":["Software Development Team, Operations and Computer Technologies Division, RIKEN AICS, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Development Team, Operations and Computer Technologies Division, RIKEN AICS, Japan","institution_ids":["https://openalex.org/I4210165842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035025604","display_name":"Naoya Maruyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naoya Maruyama","raw_affiliation_strings":["HPC Programming Framework Research Team, RIKEN AICS, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HPC Programming Framework Research Team, RIKEN AICS, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111957081"],"corresponding_institution_ids":["https://openalex.org/I4210165842"],"apc_list":null,"apc_paid":null,"fwci":2.635,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.90309207,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"30","issue":"1","first_page":"55","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987999796867371,"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"}},"topics":[{"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9958999752998352,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.8226022720336914},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7746596336364746},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7629960179328918},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7080615758895874},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6200913190841675},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.5376997590065002},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.5113314986228943},{"id":"https://openalex.org/keywords/multigrid-method","display_name":"Multigrid method","score":0.5059275031089783},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4952799379825592},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48943892121315},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4783191978931427},{"id":"https://openalex.org/keywords/biconjugate-gradient-method","display_name":"Biconjugate gradient method","score":0.43943747878074646},{"id":"https://openalex.org/keywords/conjugate-residual-method","display_name":"Conjugate residual method","score":0.40066301822662354},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3911515474319458},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32133376598358154},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.18856915831565857},{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.13999876379966736},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13170605897903442},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.11672523617744446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08040103316307068}],"concepts":[{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.8226022720336914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746596336364746},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7629960179328918},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7080615758895874},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6200913190841675},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.5376997590065002},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.5113314986228943},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.5059275031089783},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4952799379825592},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48943892121315},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4783191978931427},{"id":"https://openalex.org/C89408827","wikidata":"https://www.wikidata.org/wiki/Q855169","display_name":"Biconjugate gradient method","level":5,"score":0.43943747878074646},{"id":"https://openalex.org/C91394653","wikidata":"https://www.wikidata.org/wiki/Q5161159","display_name":"Conjugate residual method","level":4,"score":0.40066301822662354},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3911515474319458},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32133376598358154},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.18856915831565857},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.13999876379966736},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13170605897903442},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.11672523617744446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08040103316307068},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342015607950","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015607950","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W105754624","https://openalex.org/W821177523","https://openalex.org/W1966827540","https://openalex.org/W1999472284","https://openalex.org/W2002555321","https://openalex.org/W2009196736","https://openalex.org/W2049644498","https://openalex.org/W2073791002","https://openalex.org/W2076988681","https://openalex.org/W2111784516","https://openalex.org/W2169631286","https://openalex.org/W2397741840","https://openalex.org/W2435668395","https://openalex.org/W2587647010","https://openalex.org/W4252353527"],"related_works":["https://openalex.org/W1848849174","https://openalex.org/W3159557833","https://openalex.org/W2073922269","https://openalex.org/W4362580740","https://openalex.org/W177599668","https://openalex.org/W3108840043","https://openalex.org/W3010456047","https://openalex.org/W3159907817","https://openalex.org/W2067153720","https://openalex.org/W2129625121"],"abstract_inverted_index":{"The":[0,26,50],"high-performance":[1],"conjugate":[2,40,60],"gradient":[3,41,61],"(HPCG)":[4],"is":[5,63],"new":[6],"benchmark":[7],"software":[8],"for":[9,79],"supercomputers":[10],"that":[11],"provides":[12],"a":[13,45,53,58,76,132,134],"more":[14],"realistic":[15],"performance":[16,104,111,127],"metric":[17],"than":[18,106],"existing":[19],"benchmarks,":[20],"such":[21],"as":[22],"the":[23,29,39,80,88,139],"LINPACK":[24],"benchmark.":[25],"HPCG":[27,135],"measures":[28],"speed":[30],"of":[31,52],"solving":[32],"symmetric":[33,47],"sparse":[34,54],"linear":[35,55],"system":[36,56],"equations":[37],"using":[38],"method":[42,62,78],"preconditioned":[43,59],"by":[44],"multigrid":[46],"Gauss\u2013Seidel":[48],"smoother.":[49],"combination":[51],"and":[57,69,117,128],"widely":[64],"used":[65],"in":[66],"many":[67],"scientific":[68],"engineering":[70],"computer":[71,141],"applications.":[72],"This":[73],"study":[74],"introduces":[75],"tuning":[77,98],"K":[81,89,140],"computer.":[82],"According":[83],"to":[84,123],"weak-scaling":[85],"measurements":[86],"on":[87,101,114],"computer,":[90],"it":[91],"has":[92],"good":[93],"parallel":[94,107],"scalability.":[95],"Therefore,":[96,120],"our":[97],"strategy":[99],"focuses":[100],"single":[102],"CPU":[103,110],"rather":[105],"performance.":[108],"Single":[109],"strongly":[112],"depends":[113],"memory":[115],"throughput":[116],"multicore":[118],"utilization.":[119],"we":[121],"attempt":[122],"improve":[124],"memory/cache":[125],"access":[126],"multithreading":[129],"efficiency.":[130],"As":[131],"result,":[133],"score":[136],"obtained":[137],"with":[138],"achieved":[142],"second":[143],"place":[144],"at":[145],"SC\u201914.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}