{"id":"https://openalex.org/W2998655561","doi":"https://doi.org/10.1109/iccad45719.2019.8942122","title":"FastWave: Accelerating Autoregressive Convolutional Neural Networks on FPGA","display_name":"FastWave: Accelerating Autoregressive Convolutional Neural Networks on FPGA","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2998655561","doi":"https://doi.org/10.1109/iccad45719.2019.8942122","mag":"2998655561"},"language":"en","primary_location":{"id":"doi:10.1109/iccad45719.2019.8942122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad45719.2019.8942122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.04971","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015232966","display_name":"Shehzeen Hussain","orcid":"https://orcid.org/0000-0003-4693-2113"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shehzeen Hussain","raw_affiliation_strings":["UC San Diego Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"UC San Diego Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052706169","display_name":"Mojan Javaheripi","orcid":"https://orcid.org/0000-0003-4062-8807"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mojan Javaheripi","raw_affiliation_strings":["UC San Diego Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"UC San Diego Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030710635","display_name":"Paarth Neekhara","orcid":"https://orcid.org/0009-0002-8598-0353"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paarth Neekhara","raw_affiliation_strings":["UC San Diego Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"UC San Diego Department of Computer Science","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000231774","display_name":"Ryan Kastner","orcid":"https://orcid.org/0000-0001-9062-5570"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Kastner","raw_affiliation_strings":["UC San Diego Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"UC San Diego Department of Computer Science","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019931011","display_name":"Farinaz Koushanfar","orcid":"https://orcid.org/0000-0003-0798-3794"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farinaz Koushanfar","raw_affiliation_strings":["UC San Diego Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"UC San Diego Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5015232966"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":2.4567,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91882572,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9947999715805054,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8498891592025757},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6930776834487915},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6627581119537354},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6604682207107544},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5379474759101868},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5315002799034119},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5188461542129517},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.42030495405197144},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4125511944293976},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.4121777415275574},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34757453203201294},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3228651285171509},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2913753390312195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2772354185581207},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2691642642021179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8498891592025757},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6930776834487915},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6627581119537354},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6604682207107544},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5379474759101868},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5315002799034119},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5188461542129517},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.42030495405197144},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4125511944293976},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.4121777415275574},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34757453203201294},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3228651285171509},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2913753390312195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2772354185581207},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2691642642021179},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccad45719.2019.8942122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad45719.2019.8942122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.04971","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.04971","pdf_url":"https://arxiv.org/pdf/2002.04971","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.04971","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.04971","pdf_url":"https://arxiv.org/pdf/2002.04971","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1492347181","https://openalex.org/W1560013842","https://openalex.org/W1583837637","https://openalex.org/W1674799117","https://openalex.org/W1902041153","https://openalex.org/W2094756095","https://openalex.org/W2272300165","https://openalex.org/W2294282016","https://openalex.org/W2412782625","https://openalex.org/W2519091744","https://openalex.org/W2529096783","https://openalex.org/W2540404261","https://openalex.org/W2559246505","https://openalex.org/W2562773490","https://openalex.org/W2585720638","https://openalex.org/W2588448445","https://openalex.org/W2612690371","https://openalex.org/W2725615981","https://openalex.org/W2747161606","https://openalex.org/W2749651610","https://openalex.org/W2767052532","https://openalex.org/W2792764867","https://openalex.org/W2806476189","https://openalex.org/W2889329491","https://openalex.org/W2963266252","https://openalex.org/W2963600562","https://openalex.org/W2963840672","https://openalex.org/W2964243274","https://openalex.org/W4242577057","https://openalex.org/W4297699616","https://openalex.org/W4298642009","https://openalex.org/W4301368689","https://openalex.org/W6693859313","https://openalex.org/W6734716764","https://openalex.org/W6765987481"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W4200391368","https://openalex.org/W2355315220","https://openalex.org/W2210979487","https://openalex.org/W3150905897","https://openalex.org/W4327525404","https://openalex.org/W4313341326"],"abstract_inverted_index":{"Autoregressive":[0],"convolutional":[1,86],"neural":[2,20,87],"networks":[3],"(CNNs)":[4],"have":[5],"been":[6],"widely":[7],"exploited":[8],"for":[9,40,84,126,136,151],"sequence":[10,41],"generation":[11,49,171,180],"tasks":[12],"such":[13],"as":[14],"audio":[15,48,69],"synthesis,":[16],"language":[17],"modeling":[18],"and":[19,89,104,116,148,177],"machine":[21],"translation.":[22],"WaveNet":[23,44,156],"is":[24,38,55],"a":[25,60,71,106,121],"deep":[26],"autoregressive":[27,85],"CNN":[28],"composed":[29],"of":[30,34,68,109],"several":[31],"stacked":[32],"layers":[33],"dilated":[35],"convolution":[36],"that":[37,130,163],"used":[39],"generation.":[42],"While":[43],"produces":[45],"state-of-the":[46],"art":[47],"results,":[50],"the":[51,79,91,97,144,159],"naive":[52],"inference":[53,99],"implementation":[54,176],"quite":[56],"slow;":[57],"it":[58],"takes":[59],"few":[61],"minutes":[62],"to":[63,174],"generate":[64],"just":[65],"one":[66],"second":[67],"on":[70,158],"high-end":[72],"GPU.":[73],"In":[74],"this":[75],"work,":[76],"we":[77],"develop":[78],"first":[80],"accelerator":[81],"platform":[82],"FastWave":[83],"networks,":[88],"address":[90],"associated":[92],"design":[93,96,157],"challenges.":[94],"We":[95],"Fast-Wavenet":[98],"model":[100,119],"in":[101],"Vivado":[102],"HLS":[103],"perform":[105],"wide":[107],"range":[108],"optimizations":[110],"including":[111],"fixed-point":[112],"implementation,":[113],"array":[114],"partitioning":[115],"pipelining.":[117],"Our":[118,140,154],"uses":[120,164],"fully":[122],"parameterized":[123],"parallel":[124],"architecture":[125],"fast":[127],"matrix-vector":[128],"multiplication":[129],"enables":[131],"per-layer":[132],"customized":[133],"latency":[134],"fine-tuning":[135],"further":[137],"throughput":[138,147],"improvement.":[139],"experiments":[141],"comparatively":[142],"assess":[143],"tradeoff":[145],"between":[146],"resource":[149],"utilization":[150],"various":[152],"optimizations.":[153],"best":[155],"Xilinx":[160],"XCVU13P":[161],"FPGA":[162],"only":[165],"on-chip":[166],"memory,":[167],"achieves":[168],"66\u00d7":[169],"faster":[170,179],"speed":[172,181],"compared":[173],"CPU":[175],"11\u00d7":[178],"than":[182],"GPU":[183],"implementation.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":9}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}