{"id":"https://openalex.org/W2949674260","doi":"https://doi.org/10.1109/vlsi-dat.2019.8741855","title":"Customization of a Deep Learning Accelerator","display_name":"Customization of a Deep Learning Accelerator","publication_year":2019,"publication_date":"2019-04-01","ids":{"openalex":"https://openalex.org/W2949674260","doi":"https://doi.org/10.1109/vlsi-dat.2019.8741855","mag":"2949674260"},"language":"en","primary_location":{"id":"doi:10.1109/vlsi-dat.2019.8741855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vlsi-dat.2019.8741855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)","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/A5109189574","display_name":"Shien-Chun Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148468","display_name":"Industrial Technology Research Institute","ror":"https://ror.org/05szzwt63","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I4210148468"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Shien-Chun Luo","raw_affiliation_strings":["Industrial Technology Research Institute, Taiwan"],"affiliations":[{"raw_affiliation_string":"Industrial Technology Research Institute, Taiwan","institution_ids":["https://openalex.org/I4210148468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5109189574"],"corresponding_institution_ids":["https://openalex.org/I4210148468"],"apc_list":null,"apc_paid":null,"fwci":0.6073,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71724303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8030081987380981},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6946262121200562},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6469894647598267},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5673081874847412},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5089826583862305},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.46238675713539124},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4549618661403656},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.43399155139923096},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4054698944091797},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.33234304189682007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3254619240760803},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14112979173660278},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.11206862330436707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8030081987380981},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6946262121200562},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6469894647598267},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5673081874847412},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5089826583862305},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.46238675713539124},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4549618661403656},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.43399155139923096},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4054698944091797},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.33234304189682007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3254619240760803},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14112979173660278},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.11206862330436707},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vlsi-dat.2019.8741855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vlsi-dat.2019.8741855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2002555321","https://openalex.org/W2097117768","https://openalex.org/W2194775991","https://openalex.org/W2612445135","https://openalex.org/W2618530766","https://openalex.org/W2811130204","https://openalex.org/W2949650786","https://openalex.org/W2963037989","https://openalex.org/W3037463632","https://openalex.org/W4297775537"],"related_works":["https://openalex.org/W2109940557","https://openalex.org/W2466832359","https://openalex.org/W2111241003","https://openalex.org/W4391210591","https://openalex.org/W1582019636","https://openalex.org/W1967938402","https://openalex.org/W2386041993","https://openalex.org/W1608572506","https://openalex.org/W2518118925","https://openalex.org/W3159273459"],"abstract_inverted_index":{"Deep-learning":[0],"algorithms":[1],"require":[2],"large":[3],"and":[4,7,48,103,144],"parallel":[5,16],"multiplication":[6],"accumulation":[8],"(MAC),":[9],"which":[10,53,100],"fits":[11],"hardware":[12,64,98],"accelerators":[13,87],"consist":[14],"of":[15,58,68,85,112,152],"processing":[17],"elements":[18],"(PEs)":[19],"to":[20,29,43,63,78,89,95,139],"speed":[21],"up.":[22],"As":[23],"the":[24,35,39,45,49,59,66,75,81,86,91,96,130],"PE":[25],"number":[26],"increases,":[27],"how":[28],"distribute":[30],"data":[31,50],"in":[32],"time":[33],"becomes":[34],"key":[36],"problem.":[37],"Improving":[38],"accelerator":[40,122],"performance":[41],"needs":[42,88],"balance":[44],"computation":[46],"power":[47],"communication":[51],"bandwidth,":[52],"forms":[54],"a":[55],"roofline":[56,76],"model":[57,133,135],"throughput.":[60],"In":[61],"addition":[62],"setup,":[65,99],"combination":[67],"neural":[69,92],"network":[70,93,158],"operators,":[71],"layers,":[72],"also":[73],"causes":[74],"curve":[77],"shift.":[79],"Optimizing":[80],"performance,":[82],"power,":[83],"cost":[84],"link":[90],"models":[94],"physical":[97],"indicates":[101],"custom":[102,113],"model-specific":[104],"are":[105,147],"essential.":[106],"This":[107],"presentation":[108],"introduces":[109],"an":[110,126,150],"example":[111],"deep-learning":[114,121],"accelerating":[115],"system":[116],"developed":[117],"from":[118,132],"open-source":[119],"NVIDIA":[120],"(DLA).":[123],"We":[124],"supplement":[125],"environment":[127],"for":[128],"developing":[129],"system,":[131],"quantization,":[134],"compilation,":[136],"test":[137,145],"generation,":[138],"driving":[140],"tools.":[141],"FPGA":[142],"prototypes":[143],"chips":[146],"designed,":[148],"running":[149],"application":[151],"object":[153],"detection,":[154],"offering":[155],"70%":[156],"MAC":[157],"utilization.":[159]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}