{"id":"https://openalex.org/W4210691403","doi":"https://doi.org/10.1109/sc.2012.100","title":"Scalable multi-GPU 3-D FFT for TSUBAME 2.0 Supercomputer","display_name":"Scalable multi-GPU 3-D FFT for TSUBAME 2.0 Supercomputer","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W4210691403","doi":"https://doi.org/10.1109/sc.2012.100"},"language":"en","primary_location":{"id":"doi:10.1109/sc.2012.100","doi":"https://doi.org/10.1109/sc.2012.100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc.2012.100","pdf_url":null,"source":{"id":"https://openalex.org/S4363608557","display_name":"International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","issn_l":"2167-4337","issn":["2167-4337"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W4210691403"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5006972521","display_name":"Akira Nukada","orcid":"https://orcid.org/0000-0001-7959-6975","observed_orcids":["https://orcid.org/0000-0001-7959-6975"]},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698","https://openalex.org/I4400009020"]},{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210086780"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Nukada","raw_affiliation_strings":["Tokyo Inst. of Technol., Tokyo, Japan","Japan Science and Technology Agency, Japan","Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Inst. of Technol., Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Japan Science and Technology Agency, Japan","institution_ids":["https://openalex.org/I4210086780"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025610878","display_name":"Kento Sato","orcid":"https://orcid.org/0000-0001-7850-2121","observed_orcids":["https://orcid.org/0000-0001-7850-2121"]},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698","https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kento Sato","raw_affiliation_strings":["Tokyo Inst. of Technol., Tokyo, Japan","Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Inst. of Technol., Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103252086","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-2126-2926","observed_orcids":["https://orcid.org/0000-0003-2126-2926"]},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698","https://openalex.org/I4400009020"]},{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210086780"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Matsuoka","raw_affiliation_strings":["Tokyo Inst. of Technol., Tokyo, Japan","Japan Science and Technology Agency, Japan","National Institute of Informatics (NII), Japan","Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Inst. of Technol., Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Japan Science and Technology Agency, Japan","institution_ids":["https://openalex.org/I4210086780"]},{"raw_affiliation_string":"National Institute of Informatics (NII), Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7698,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.63773742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980000257492065,"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":0.9980000257492065,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.000699999975040555,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/multi-gpu-computing","display_name":"multi-GPU computing","score":0.9200000166893005},{"id":"https://openalex.org/keywords/all-to-all-communication","display_name":"all-to-all communication","score":0.8140000104904175},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.9049999713897705},{"id":"https://openalex.org/keywords/strong-scaling","display_name":"strong scaling","score":0.5899999737739563},{"id":"https://openalex.org/keywords/auto-tuning","display_name":"auto-tuning","score":0.9139999747276306},{"id":"https://openalex.org/keywords/gpu-scheduling","display_name":"GPU scheduling","score":0.5230000019073486},{"id":"https://openalex.org/keywords/mpi","display_name":"MPI","score":0.34700000286102295},{"id":"https://openalex.org/keywords/double-precision","display_name":"double precision","score":0.5320000052452087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8829596042633057},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8580352663993835},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.820027768611908},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7724646329879761},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7262997627258301},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6990985870361328},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.601853609085083},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4663027822971344},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.44710782170295715},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.43880587816238403},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21270179748535156},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.083009272813797},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/sc.2012.100","doi":"https://doi.org/10.1109/sc.2012.100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc.2012.100","pdf_url":null,"source":{"id":"https://openalex.org/S4363608557","display_name":"International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","issn_l":"2167-4337","issn":["2167-4337"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0004061646","doi":null,"is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100652472","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of 2012 ACM/IEEE International Conference for High Performance, Networking, Storage, and Analysis (SC\u201912)","raw_type":"conference paper"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50199536","doi":null,"is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100652472","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5125938736","display_name":"Fault Tolerant Infrastructure Toward Billion of Parallelization and Exa-scale Supercomputer","funder_award_id":"23220003","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W31232120","https://openalex.org/W1483804831","https://openalex.org/W1967802285","https://openalex.org/W1995333355","https://openalex.org/W2015352249","https://openalex.org/W2032484463","https://openalex.org/W2045629276","https://openalex.org/W2061171222","https://openalex.org/W2071739952","https://openalex.org/W2107483876","https://openalex.org/W2133712572","https://openalex.org/W2134572726","https://openalex.org/W2155503253","https://openalex.org/W2158261096","https://openalex.org/W2171249995","https://openalex.org/W2334899772","https://openalex.org/W2481321346","https://openalex.org/W2620167579","https://openalex.org/W2717654573","https://openalex.org/W3145767355","https://openalex.org/W3147878143","https://openalex.org/W4252970023","https://openalex.org/W6601238768","https://openalex.org/W6628534940","https://openalex.org/W6654554885","https://openalex.org/W6679962583"],"related_works":["https://openalex.org/W4386000644","https://openalex.org/W4280528130","https://openalex.org/W2071739952","https://openalex.org/W4289827962","https://openalex.org/W2620167579","https://openalex.org/W4212854452","https://openalex.org/W2272797324","https://openalex.org/W2171120359","https://openalex.org/W4416004243","https://openalex.org/W2767764218"],"abstract_inverted_index":{"For":[0],"scalable":[1],"3-D":[2],"FFT":[3],"computation":[4],"using":[5,99],"multiple":[6],"GPUs,":[7],"efficient":[8],"all-to-all":[9,43],"communication":[10],"between":[11,45],"GPUs":[12],"is":[13],"the":[14,54],"most":[15],"important":[16],"factor":[17],"in":[18,42,108],"good":[19,88,94],"performance.":[20],"Implementations":[21],"with":[22],"point-to-point":[23],"MPI":[24],"library":[25],"functions":[26],"and":[27,67,78],"CUDA":[28],"memory":[29],"copy":[30],"APIs":[31],"typically":[32],"exhibit":[33],"very":[34,87],"large":[35],"overheads":[36],"especially":[37],"for":[38],"small":[39],"message":[40],"sizes":[41],"communications":[44],"many":[46],"nodes.":[47],"We":[48],"propose":[49],"several":[50],"schemes":[51],"to":[52,63,75,97],"minimize":[53],"overheads,":[55],"including":[56],"employment":[57],"of":[58,61,102],"lower-level":[59],"API":[60],"InfiniBand":[62],"effectively":[64],"overlap":[65],"intra-":[66],"inter-node":[68],"communication,":[69],"as":[70,72,91,93],"well":[71,92],"auto-tuning":[73],"strategies":[74],"control":[76],"scheduling":[77],"determine":[79],"rail":[80],"assignments.":[81],"As":[82],"a":[83],"result":[84],"we":[85],"achieve":[86],"strong":[89],"scalability":[90],"performance,":[95],"up":[96],"4.8TFLOPS":[98],"256":[100],"nodes":[101],"TSUBAME":[103],"2.0":[104],"Supercomputer":[105],"(768":[106],"GPUs)":[107],"double":[109],"precision.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-02-08T00:00:00"}