{"id":"https://openalex.org/W2162186524","doi":"https://doi.org/10.1145/1654059.1654083","title":"A 32x32x32, spatially distributed 3D FFT in four microseconds on Anton","display_name":"A 32x32x32, spatially distributed 3D FFT in four microseconds on Anton","publication_year":2009,"publication_date":"2009-11-14","ids":{"openalex":"https://openalex.org/W2162186524","doi":"https://doi.org/10.1145/1654059.1654083","mag":"2162186524"},"language":"en","primary_location":{"id":"doi:10.1145/1654059.1654083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1654059.1654083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","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/A5035427716","display_name":"Cliff Young","orcid":"https://orcid.org/0000-0003-2172-1651"},"institutions":[{"id":"https://openalex.org/I2799548008","display_name":"D. E. Shaw Research","ror":"https://ror.org/02s04h872","country_code":"US","type":"company","lineage":["https://openalex.org/I2799548008"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cliff Young","raw_affiliation_strings":["D. E. Shaw Research, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D. E. Shaw Research, New York, NY","institution_ids":["https://openalex.org/I2799548008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084619335","display_name":"Joseph A. Bank","orcid":null},"institutions":[{"id":"https://openalex.org/I2799548008","display_name":"D. E. Shaw Research","ror":"https://ror.org/02s04h872","country_code":"US","type":"company","lineage":["https://openalex.org/I2799548008"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph A. Bank","raw_affiliation_strings":["D. E. Shaw Research, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D. E. Shaw Research, New York, NY","institution_ids":["https://openalex.org/I2799548008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061322136","display_name":"Ron O. Dror","orcid":"https://orcid.org/0000-0002-6418-2793"},"institutions":[{"id":"https://openalex.org/I2799548008","display_name":"D. E. Shaw Research","ror":"https://ror.org/02s04h872","country_code":"US","type":"company","lineage":["https://openalex.org/I2799548008"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron O. Dror","raw_affiliation_strings":["D. E. Shaw Research, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D. E. Shaw Research, New York, NY","institution_ids":["https://openalex.org/I2799548008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112225904","display_name":"J.P. Grossman","orcid":null},"institutions":[{"id":"https://openalex.org/I2799548008","display_name":"D. E. Shaw Research","ror":"https://ror.org/02s04h872","country_code":"US","type":"company","lineage":["https://openalex.org/I2799548008"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. P. Grossman","raw_affiliation_strings":["D. E. Shaw Research, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D. E. Shaw Research, New York, NY","institution_ids":["https://openalex.org/I2799548008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030397130","display_name":"John K. Salmon","orcid":null},"institutions":[{"id":"https://openalex.org/I2799548008","display_name":"D. E. Shaw Research","ror":"https://ror.org/02s04h872","country_code":"US","type":"company","lineage":["https://openalex.org/I2799548008"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John K. Salmon","raw_affiliation_strings":["D. E. Shaw Research, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D. E. Shaw Research, New York, NY","institution_ids":["https://openalex.org/I2799548008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074305095","display_name":"David E. Shaw","orcid":"https://orcid.org/0000-0001-8265-5761"},"institutions":[{"id":"https://openalex.org/I2799548008","display_name":"D. E. Shaw Research","ror":"https://ror.org/02s04h872","country_code":"US","type":"company","lineage":["https://openalex.org/I2799548008"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David E. Shaw","raw_affiliation_strings":["D. E. Shaw Research, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D. E. Shaw Research, New York, NY","institution_ids":["https://openalex.org/I2799548008"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2799548008"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9973000288009644,"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/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.8551709651947021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8114978075027466},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6920977830886841},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5586667656898499},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5574844479560852},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.48720163106918335},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32208728790283203},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15513479709625244},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08037182688713074}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.8551709651947021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8114978075027466},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6920977830886841},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5586667656898499},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5574844479560852},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.48720163106918335},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32208728790283203},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15513479709625244},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08037182688713074}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1654059.1654083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1654059.1654083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1833612708","https://openalex.org/W2000584869","https://openalex.org/W2052977106","https://openalex.org/W2061171222","https://openalex.org/W2086889049","https://openalex.org/W2102182691","https://openalex.org/W2114927422","https://openalex.org/W2115451770","https://openalex.org/W2117639210","https://openalex.org/W2117897850","https://openalex.org/W2124099550","https://openalex.org/W2153228625","https://openalex.org/W2163491234"],"related_works":["https://openalex.org/W1774183074","https://openalex.org/W2057488824","https://openalex.org/W2334687145","https://openalex.org/W2178011914","https://openalex.org/W4235962491","https://openalex.org/W2061778832","https://openalex.org/W1513001507","https://openalex.org/W2257153718","https://openalex.org/W3134702077","https://openalex.org/W2167527468"],"abstract_inverted_index":{"Anton,":[0],"a":[1,11,18,25,49,119],"massively":[2],"parallel":[3],"special-purpose":[4],"machine":[5],"for":[6,87,115],"molecular":[7,116],"dynamics":[8,117],"simulations,":[9,118],"performs":[10],"32x32x32":[12],"FFT":[13,20,37,46],"in":[14,21,80,130],"3.7":[15],"microseconds":[16,23],"and":[17,54,85,90,125],"64x64x64":[19],"13.3":[22],"on":[24,142],"configuration":[26],"with":[27],"512":[28],"nodes---an":[29],"order":[30],"of":[31,39,52,74,83,106,121,140],"magnitude":[32],"faster":[33],"than":[34],"all":[35],"other":[36],"implementations":[38],"which":[40],"we":[41],"are":[42],"aware.":[43],"Achieving":[44],"this":[45,131],"performance":[47],"requires":[48],"coordinated":[50],"combination":[51],"computation":[53,97],"communication":[55,66],"techniques":[56,128],"that":[57,101],"leverage":[58],"Anton's":[59,65,95],"underlying":[60],"hardware":[61,123],"mechanisms.":[62],"Most":[63],"significantly,":[64],"subsystem":[67],"provides":[68],"over":[69],"300":[70],"gigabits":[71],"per":[72,76],"second":[73],"bandwidth":[75],"node,":[77],"message":[78],"latency":[79],"the":[81,103,122,138],"hundreds":[82],"nanoseconds,":[84],"support":[86,102],"word-level":[88],"writes":[89],"single-ended":[91],"communication.":[92],"In":[93],"addition,":[94],"general-purpose":[96,143],"system":[98],"incorporates":[99],"primitives":[100,124],"efficient":[104],"parallelization":[105],"small":[107],"1D":[108],"FFTs.":[109],"Although":[110],"Anton":[111],"was":[112],"designed":[113],"specifically":[114],"number":[120],"software":[126],"implementation":[127],"described":[129],"paper":[132],"may":[133],"also":[134],"be":[135],"applicable":[136],"to":[137],"acceleration":[139],"FFTs":[141],"high-performance":[144],"machines.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
