{"id":"https://openalex.org/W2010763423","doi":"https://doi.org/10.1109/hpec.2014.7040951","title":"Performance and energy limits of a processor-integrated FFT accelerator","display_name":"Performance and energy limits of a processor-integrated FFT accelerator","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2010763423","doi":"https://doi.org/10.1109/hpec.2014.7040951","mag":"2010763423"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2014.7040951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2014.7040951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5088801059","display_name":"Tung Thanh-Hoang","orcid":null},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tung Thanh-Hoang","raw_affiliation_strings":["Department of Computer Science, University of Chicago, Chicago, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Chicago, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048335169","display_name":"Amirali Shambayati","orcid":null},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amirali Shambayati","raw_affiliation_strings":["Department of Computer Science, University of Chicago, Chicago, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Chicago, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048337173","display_name":"Calvin Deutschbein","orcid":"https://orcid.org/0000-0003-1354-7200"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Calvin Deutschbein","raw_affiliation_strings":["Department of Computer Science, University of Chicago, Chicago, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Chicago, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080833704","display_name":"Henry Hoffmann","orcid":"https://orcid.org/0000-0003-0816-8150"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henry Hoffmann","raw_affiliation_strings":["Department of Computer Science, University of Chicago, Chicago, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Chicago, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085538238","display_name":"Andrew A. Chien","orcid":"https://orcid.org/0000-0002-1204-206X"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew A. Chien","raw_affiliation_strings":["Argonne National Laboratory, Chicago, Illinois, USA","Department of Computer Science, University of Chicago, Chicago, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Department of Computer Science, University of Chicago, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5088801059"],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":1.8389,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84752528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"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":0.9997000098228455,"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":0.9997000098228455,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9984999895095825,"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.8479690551757812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7014313340187073},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.6200351715087891},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4702932834625244},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4664181172847748},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.4646313786506653},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.43424737453460693},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.416110634803772},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13424885272979736},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12762054800987244},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10987567901611328},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09418407082557678}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.8479690551757812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7014313340187073},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.6200351715087891},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4702932834625244},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4664181172847748},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.4646313786506653},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.43424737453460693},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.416110634803772},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13424885272979736},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12762054800987244},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10987567901611328},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09418407082557678}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2014.7040951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2014.7040951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8999999761581421,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338113","display_name":"Accelerated Innovation Research Initiative Turning Top Science and Ideas into High-Impact Values","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1526092740","https://openalex.org/W1577565190","https://openalex.org/W1980745435","https://openalex.org/W1981220134","https://openalex.org/W1999340092","https://openalex.org/W2006312753","https://openalex.org/W2013435193","https://openalex.org/W2017813686","https://openalex.org/W2019183874","https://openalex.org/W2025787141","https://openalex.org/W2047532956","https://openalex.org/W2059405679","https://openalex.org/W2061171222","https://openalex.org/W2064867263","https://openalex.org/W2071208935","https://openalex.org/W2093545354","https://openalex.org/W2098335003","https://openalex.org/W2100799944","https://openalex.org/W2104176873","https://openalex.org/W2105853930","https://openalex.org/W2108872752","https://openalex.org/W2111755292","https://openalex.org/W2121602084","https://openalex.org/W2124694698","https://openalex.org/W2131413854","https://openalex.org/W2135440536","https://openalex.org/W2138146350","https://openalex.org/W2153331583","https://openalex.org/W2157406439","https://openalex.org/W2162639668","https://openalex.org/W2168847677","https://openalex.org/W2171568334","https://openalex.org/W2474451066","https://openalex.org/W2542693654","https://openalex.org/W2551489658","https://openalex.org/W3139689176","https://openalex.org/W3145269652","https://openalex.org/W4236433846","https://openalex.org/W6634780314","https://openalex.org/W6651700774","https://openalex.org/W6655113037","https://openalex.org/W6675701887","https://openalex.org/W6679823348","https://openalex.org/W6720847907"],"related_works":["https://openalex.org/W4327521644","https://openalex.org/W2978884468","https://openalex.org/W3132558499","https://openalex.org/W2168413811","https://openalex.org/W2005846134","https://openalex.org/W2369237035","https://openalex.org/W2948041274","https://openalex.org/W2165986314","https://openalex.org/W4226515754","https://openalex.org/W2087878472"],"abstract_inverted_index":{"Accelerators":[0],"have":[1],"long":[2],"been":[3],"used":[4],"to":[5],"improve":[6],"the":[7,25,61,132,173,186],"performance":[8,33,62,83,108],"and":[9,34,39,59,63,151,156,170,196],"energy":[10,35,64,94,125,136,147,171,193],"efficiency":[11,36,65,126,148],"of":[12,27,93,162],"embedded":[13],"signal":[14],"processing":[15],"systems":[16],"relying":[17],"on":[18],"Fast":[19],"Fourier":[20],"Transforms":[21],"(FFTs).":[22],"We":[23],"explore":[24],"benefits":[26],"processor-integrated":[28,77],"FFT":[29,51,78,98,144],"accelerators,":[30],"characterizing":[31],"their":[32],"for":[37,66,84,149,172,194],"current":[38],"future":[40],"memory":[41,107,134,202],"architectures.":[42],"First,":[43],"we":[44,113],"consider":[45],"designs":[46],"that":[47,74,124],"deeply":[48],"integrate":[49],"an":[50],"accelerator":[52,79,99,187],"into":[53],"a":[54,67,75,85,110,163,182],"simple":[55],"5-stage":[56],"RISC":[57],"pipeline":[58],"evaluate":[60,114],"32":[68],"nm":[69],"process.":[70],"Our":[71,121],"results":[72,122],"indicate":[73,123],"64-point":[76,97],"alone":[80],"can":[81,128,177],"increase":[82,185],"4K/32k-point":[86],"1D-FFT":[87],"by":[88,137],"7/4-fold":[89],"respectively.":[90,158],"In":[91],"term":[92],"efficiency,":[95],"our":[96,143],"increases":[100,154],"it":[101],"at":[102,189],"least":[103,190],"4-fold.":[104],"Second,":[105],"since":[106],"is":[109],"critical":[111],"constraint,":[112],"system":[115],"configuration":[116],"with":[117,142,160],"3D-stacked":[118,133,201],"DRAM":[119],"systems.":[120],"bottlenecks":[127],"be":[129,178],"alleviated,":[130],"as":[131],"reduces":[135],"nearly":[138],"14-fold.":[139],"When":[140],"combined":[141],"accelerator,":[145],"overall":[146],"4k":[150],"32k-point":[152],"FFTs":[153],"86-fold":[155],"70-fold":[157],"Prospectively,":[159],"addition":[161],"data":[164,174],"layout":[165],"transformation":[166],"engine,":[167],"cycle":[168],"count":[169],"transpose":[175],"phase":[176],"reduced":[179],"10x.":[180],"Such":[181],"step":[183],"would":[184],"benefit":[188],"10-fold":[191],"in":[192,200],"DDR3":[195],"more":[197],"than":[198],"100-fold":[199],"system.":[203]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}