{"id":"https://openalex.org/W2620167579","doi":null,"title":"Prospects for scalable 3D FFTs on heterogeneous exascale systems","display_name":"Prospects for scalable 3D FFTs on heterogeneous exascale systems","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2620167579","mag":"2620167579"},"language":"en","primary_location":{"id":"mag:2620167579","doi":null,"is_oa":false,"landing_page_url":"http://mcclanahoochie.com/blog/wp-content/uploads/2011/01/fft-sc11.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W2620167579"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"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/A5018427481","display_name":"Chris McClanahan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris McClanahan","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061648378","display_name":"Kent Czechowski","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kent Czechowski","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015530126","display_name":"Casey Battaglino","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Casey Battaglino","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027876225","display_name":"Kartik P. Iyer","orcid":"https://orcid.org/0000-0001-7071-9211","observed_orcids":["https://orcid.org/0000-0001-7071-9211"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kartik P. Iyer","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":"https://orcid.org/0000-0001-7071-9211","affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005975375","display_name":"P. K. Yeung","orcid":"https://orcid.org/0000-0002-6278-6032","observed_orcids":["https://orcid.org/0000-0002-6278-6032"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. K. Yeung","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":"https://orcid.org/0000-0002-6278-6032","affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016738770","display_name":"Richard W. Vuduc","orcid":"https://orcid.org/0000-0003-2178-138X","observed_orcids":["https://orcid.org/0000-0003-2178-138X"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Vuduc","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.835,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.86924624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0006000000284984708,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.00039999998989515007,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/3d-fast-fourier-transform","display_name":"3D fast Fourier transform","score":0.8809999823570251},{"id":"https://openalex.org/keywords/exascale-computing","display_name":"exascale computing","score":0.8489999771118164},{"id":"https://openalex.org/keywords/gpu-computing","display_name":"GPU computing","score":0.777999997138977},{"id":"https://openalex.org/keywords/heterogeneous-computing","display_name":"heterogeneous computing","score":0.6819999814033508},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.7609999775886536},{"id":"https://openalex.org/keywords/analytical-performance-model","display_name":"analytical performance model","score":0.8500000238418579},{"id":"https://openalex.org/keywords/inter-node-communication","display_name":"inter-node communication","score":0.7549999952316284},{"id":"https://openalex.org/keywords/intra-node-communication","display_name":"intra-node communication","score":0.9950000047683716},{"id":"https://openalex.org/keywords/all-to-all-communication","display_name":"all-to-all communication","score":0.8510000109672546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8397272825241089},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.835442304611206},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8342528343200684},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6493490934371948},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.6288268566131592},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5288021564483643},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4979119300842285},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4567706286907196},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.44895023107528687},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43277284502983093},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42599111795425415},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3499329090118408},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.28181928396224976},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1680019497871399},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.1494135558605194},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13353699445724487},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0879894495010376},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2620167579","doi":null,"is_oa":false,"landing_page_url":"http://mcclanahoochie.com/blog/wp-content/uploads/2011/01/fft-sc11.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W31232120","https://openalex.org/W268624065","https://openalex.org/W1497413785","https://openalex.org/W1509342228","https://openalex.org/W1550054107","https://openalex.org/W1589759851","https://openalex.org/W1966416130","https://openalex.org/W1967802285","https://openalex.org/W1980759071","https://openalex.org/W1995333355","https://openalex.org/W2000584869","https://openalex.org/W2009516879","https://openalex.org/W2024639384","https://openalex.org/W2032484463","https://openalex.org/W2038454316","https://openalex.org/W2045579177","https://openalex.org/W2095875205","https://openalex.org/W2102182691","https://openalex.org/W2105524676","https://openalex.org/W2107483876","https://openalex.org/W2108600626","https://openalex.org/W2108896526","https://openalex.org/W2109707129","https://openalex.org/W2113691861","https://openalex.org/W2114927422","https://openalex.org/W2131413854","https://openalex.org/W2135401856","https://openalex.org/W2138690674","https://openalex.org/W2142265837","https://openalex.org/W2146451305","https://openalex.org/W2151434489","https://openalex.org/W2162186524","https://openalex.org/W2164566630","https://openalex.org/W2188838890","https://openalex.org/W2275977038","https://openalex.org/W2508628598","https://openalex.org/W2515346046","https://openalex.org/W2717654573","https://openalex.org/W3120389717"],"related_works":["https://openalex.org/W2140980608","https://openalex.org/W4210691403","https://openalex.org/W1995333355","https://openalex.org/W2171120359","https://openalex.org/W3162971815","https://openalex.org/W1996178571","https://openalex.org/W7096292184","https://openalex.org/W7095209670","https://openalex.org/W3036255981"],"abstract_inverted_index":{"We":[0,29,62,90],"consider":[1],"the":[2,64,82,97,124],"problem":[3],"of":[4,19,66,81,99,126],"implementing":[5],"scalable":[6],"threedimensional":[7],"fast":[8],"Fourier":[9],"transforms":[10],"with":[11],"an":[12,137],"eye":[13],"toward":[14],"future":[15],"exascale":[16],"systems":[17],"comprised":[18],"graphics":[20],"co-processor":[21],"(GPUs)":[22],"or":[23],"other":[24],"similarly":[25],"high-density":[26],"compute":[27],"units.":[28],"describe":[30],"a":[31,38,111],"new":[32],"software":[33,68],"implementation;":[34],"derive":[35],"and":[36,43,58,69],"calibrate":[37],"suitable":[39],"analytical":[40,93],"performance":[41],"model;":[42],"use":[44,91],"this":[45],"model":[46,94],"to":[47,95,122],"make":[48],"predictions":[49],"about":[50],"potential":[51],"outcomes":[52],"at":[53,85],"exascale,":[54],"based":[55],"on":[56,72],"current":[57],"likely":[59],"technology":[60],"trends.":[61],"evaluate":[63],"scalability":[65],"our":[67,92],"instantiate":[70],"models":[71],"real":[73],"systems,":[74],"including":[75],"64":[76],"nodes":[77],"(192":[78],"NVIDIA\u201cFermi\u201d":[79],"GPUs)":[80],"Keeneland":[83],"system":[84],"Oak":[86],"Ridge":[87],"National":[88],"Laboratory.":[89],"quantify":[96],"impact":[98],"both":[100],"interand":[101],"intra-node":[102,132],"communication":[103,119,133],"that":[104,115,134],"impede":[105],"further":[106],"scalability.":[107],"Among":[108],"various":[109],"observations,":[110],"key":[112],"prediction":[113],"is":[114,120,130],"although":[116],"inter-node":[117],"all-to-all":[118],"expected":[121],"be":[123],"bottleneck":[125],"distributed":[127],"FFTs,":[128],"it":[129],"actually":[131],"may":[135],"play":[136],"even":[138],"more":[139],"critical":[140],"role.":[141]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2017-06-05T00:00:00"}