{"id":"https://openalex.org/W4206990365","doi":"https://doi.org/10.1109/hipc53243.2021.00029","title":"The 16,384-node Parallelism of 3D-CNN Training on An Arm CPU based Supercomputer","display_name":"The 16,384-node Parallelism of 3D-CNN Training on An Arm CPU based Supercomputer","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W4206990365","doi":"https://doi.org/10.1109/hipc53243.2021.00029"},"language":"en","primary_location":{"id":"doi:10.1109/hipc53243.2021.00029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc53243.2021.00029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 28th International Conference on High Performance Computing, Data, and Analytics (HiPC)","raw_type":"proceedings-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/A5041051226","display_name":"Akihiro Tabuchi","orcid":"https://orcid.org/0009-0009-3931-3817"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Akihiro Tabuchi","raw_affiliation_strings":["Fujitsu Limited, Kawasaki, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102314855","display_name":"Koichi Shirahata","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Shirahata","raw_affiliation_strings":["Fujitsu Limited, Kawasaki, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110948623","display_name":"Masafumi Yamazaki","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masafumi Yamazaki","raw_affiliation_strings":["Fujitsu Limited, Kawasaki, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089627100","display_name":"Akihiko Kasagi","orcid":"https://orcid.org/0000-0002-5793-335X"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiko Kasagi","raw_affiliation_strings":["Fujitsu Limited, Kawasaki, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081391958","display_name":"Takumi Honda","orcid":"https://orcid.org/0000-0002-1572-4533"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takumi Honda","raw_affiliation_strings":["Fujitsu Limited, Kawasaki, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105459197","display_name":"Kouji Kurihara","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kouji Kurihara","raw_affiliation_strings":["Fujitsu Limited, Kawasaki, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041721902","display_name":"Kentaro Kawakami","orcid":"https://orcid.org/0000-0002-3248-1190"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kentaro Kawakami","raw_affiliation_strings":["Fujitsu Limited, Kawasaki, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034919372","display_name":"Tsuguchika Tabaru","orcid":"https://orcid.org/0000-0001-6568-1968"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsuguchika Tabaru","raw_affiliation_strings":["Fujitsu Limited, Kawasaki, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041548002","display_name":"Naoto Fukumoto","orcid":"https://orcid.org/0000-0003-2103-881X"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoto Fukumoto","raw_affiliation_strings":["Fujitsu Limited, Kawasaki, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022767887","display_name":"Akiyoshi Kuroda","orcid":"https://orcid.org/0000-0002-3249-5592"},"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":"Akiyoshi Kuroda","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Hyogo, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Hyogo, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016173926","display_name":"Takaaki Fukai","orcid":"https://orcid.org/0000-0003-4216-4807"},"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":"Takaaki Fukai","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Hyogo, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Hyogo, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025610878","display_name":"Kento Sato","orcid":"https://orcid.org/0000-0001-7850-2121"},"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":"Kento Sato","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Hyogo, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Hyogo, Japan","institution_ids":["https://openalex.org/I4210129730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5041051226"],"corresponding_institution_ids":["https://openalex.org/I2252096349"],"apc_list":null,"apc_paid":null,"fwci":0.1921,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51638889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"21","issue":null,"first_page":"152","last_page":"161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8613827228546143},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.816261887550354},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.7823225855827332},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7483607530593872},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.520747184753418},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.4832811653614044},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.43444186449050903},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4264463782310486},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4182937741279602},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2958984971046448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8613827228546143},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.816261887550354},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.7823225855827332},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7483607530593872},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.520747184753418},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4832811653614044},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.43444186449050903},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4264463782310486},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4182937741279602},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2958984971046448},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipc53243.2021.00029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc53243.2021.00029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 28th International Conference on High Performance Computing, Data, and Analytics (HiPC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2049644498","https://openalex.org/W2066310479","https://openalex.org/W2168231600","https://openalex.org/W2464708700","https://openalex.org/W2481380994","https://openalex.org/W2618530766","https://openalex.org/W2622263826","https://openalex.org/W2757910899","https://openalex.org/W2805245388","https://openalex.org/W2886189612","https://openalex.org/W2898825203","https://openalex.org/W2926655273","https://openalex.org/W2952046647","https://openalex.org/W2962780982","https://openalex.org/W2963351145","https://openalex.org/W2972291421","https://openalex.org/W3037847693","https://openalex.org/W3113588636","https://openalex.org/W3132277775","https://openalex.org/W3208855587","https://openalex.org/W4239823607","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4294641903","https://openalex.org/W4301239768","https://openalex.org/W6684859321","https://openalex.org/W6748645090","https://openalex.org/W6753584990","https://openalex.org/W6756332123","https://openalex.org/W6756379755","https://openalex.org/W6769627184","https://openalex.org/W6777096940"],"related_works":["https://openalex.org/W1855765675","https://openalex.org/W3046859795","https://openalex.org/W1505902692","https://openalex.org/W111037196","https://openalex.org/W2950520577","https://openalex.org/W1501159154","https://openalex.org/W1554644772","https://openalex.org/W2003935582","https://openalex.org/W2494130044","https://openalex.org/W3170887803"],"abstract_inverted_index":{"As":[0],"the":[1,109,119,136,148],"computational":[2],"cost":[3],"and":[4,28,93,98,104,117,131],"datasets":[5],"available":[6],"for":[7,20,31,48,71,80],"deep":[8],"neural":[9],"network":[10,83],"training":[11,23,52,101,120],"continue":[12],"to":[13,112],"increase,":[14],"there":[15],"is":[16,135],"a":[17,49,54,68,113],"significant":[18],"demand":[19],"fast":[21],"distributed":[22],"on":[24,53],"supercomputers.":[25],"However,":[26],"porting":[27],"tuning":[29,45],"applications":[30],"new":[32,55],"advanced":[33],"supercomputers":[34],"requires":[35],"tremendous":[36],"amount":[37],"of":[38,128,139],"development":[39],"efforts.":[40],"Therefore,":[41],"we":[42],"present":[43],"software":[44],"best":[46],"practice":[47],"3D-CNN":[50,115],"model":[51,105],"Arm":[56],"CPU":[57],"based":[58],"supercomputer,":[59],"Fugaku.":[60],"We":[61,107],"(i)":[62],"tune":[63,86],"computation":[64],"in":[65,102,121,143,147],"DL":[66],"by":[67,88],"JIT":[69],"translator":[70],"aarch64,":[72],"(ii)":[73],"optimize":[74],"collective":[75],"communication":[76],"such":[77],"as":[78],"Allreduce":[79],"6D":[81],"mesh/torus":[82],"topology,":[84],"(iii)":[85],"I/O":[87],"data":[89,94,103],"staging":[90],"with":[91,96],"compression":[92],"loader":[95],"caching,":[97],"(iv)":[99],"parallelize":[100],"parallelism.":[106],"apply":[108],"proposed":[110],"methods":[111],"CosmoFlow":[114],"model,":[116],"achieve":[118],"30":[122],"minutes":[123],"using":[124],"16,384":[125],"nodes":[126],"consisting":[127],"4096":[129],"data-":[130],"4":[132],"model-parallelism.":[133],"This":[134],"fastest":[137],"result":[138],"any":[140],"CPU-based":[141],"systems":[142],"MLPerf":[144],"HPC":[145],"v0.7":[146],"world.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
