{"id":"https://openalex.org/W3114243583","doi":"https://doi.org/10.1109/hpec43674.2020.9286162","title":"A Scalable Architecture for CNN Accelerators Leveraging High-Performance Memories","display_name":"A Scalable Architecture for CNN Accelerators Leveraging High-Performance Memories","publication_year":2020,"publication_date":"2020-09-22","ids":{"openalex":"https://openalex.org/W3114243583","doi":"https://doi.org/10.1109/hpec43674.2020.9286162","mag":"3114243583"},"language":"en","primary_location":{"id":"doi:10.1109/hpec43674.2020.9286162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5061417904","display_name":"Maarten Hattink","orcid":"https://orcid.org/0000-0001-7032-2839"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Maarten Hattink","raw_affiliation_strings":["Department of Electrical Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079644832","display_name":"Giuseppe Di Guglielmo","orcid":"https://orcid.org/0000-0002-5749-1432"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Giuseppe Di Guglielmo","raw_affiliation_strings":["Columbia University in the City of New York, New York, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University in the City of New York, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009992367","display_name":"Luca P. Carloni","orcid":"https://orcid.org/0000-0001-5600-8931"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luca P. Carloni","raw_affiliation_strings":["Columbia University in the City of New York, New York, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University in the City of New York, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081695392","display_name":"Keren Bergman","orcid":"https://orcid.org/0000-0001-8580-1728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keren Bergman","raw_affiliation_strings":["Department of Electrical Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061417904"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2055,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52984481,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9991000294685364,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9975000023841858,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9958999752998352,"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":0.8329520225524902},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.6922883987426758},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.666824221611023},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6655977964401245},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.6468383073806763},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.613344669342041},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.6130926609039307},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.566394031047821},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4941706955432892},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4756217300891876},{"id":"https://openalex.org/keywords/memory-architecture","display_name":"Memory architecture","score":0.42448630928993225},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.42292726039886475},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.30806541442871094},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.29228371381759644},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.19164779782295227},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16039761900901794},{"id":"https://openalex.org/keywords/memory-controller","display_name":"Memory controller","score":0.15763425827026367},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11650076508522034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8329520225524902},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.6922883987426758},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.666824221611023},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6655977964401245},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.6468383073806763},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.613344669342041},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.6130926609039307},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.566394031047821},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4941706955432892},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4756217300891876},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.42448630928993225},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.42292726039886475},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.30806541442871094},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.29228371381759644},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.19164779782295227},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16039761900901794},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.15763425827026367},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11650076508522034},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec43674.2020.9286162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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","display_name":"Affordable and clean energy","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G8943761781","display_name":null,"funder_award_id":"A#: 1764000","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G966577757","display_name":null,"funder_award_id":"DE-SC0017182","funder_id":"https://openalex.org/F4320309030","funder_display_name":"Small Business Innovation Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309030","display_name":"Small Business Innovation Research","ror":"https://ror.org/015t55b95"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1487564550","https://openalex.org/W1686810756","https://openalex.org/W1926668751","https://openalex.org/W2094756095","https://openalex.org/W2172654076","https://openalex.org/W2296236528","https://openalex.org/W2626616508","https://openalex.org/W2761085955","https://openalex.org/W2776940252","https://openalex.org/W2786106922","https://openalex.org/W2806397907","https://openalex.org/W2963568120","https://openalex.org/W3036715599","https://openalex.org/W3104714893"],"related_works":["https://openalex.org/W4293430534","https://openalex.org/W2342813629","https://openalex.org/W3150934690","https://openalex.org/W2335743642","https://openalex.org/W4297812927","https://openalex.org/W2800412005","https://openalex.org/W1976244802","https://openalex.org/W1992487929","https://openalex.org/W2083934844","https://openalex.org/W2800626838"],"abstract_inverted_index":{"As":[0],"FPGA-based":[1],"accelerators":[2,56],"become":[3],"ubiquitous":[4],"and":[5,37,43,63],"more":[6],"powerful,":[7],"the":[8,68,95],"demand":[9],"for":[10,52],"integration":[11],"with":[12],"High-Performance":[13],"Memory":[14],"(HPM)":[15],"grows.":[16],"Although":[17],"HPMs":[18],"offer":[19],"a":[20,49],"much":[21],"greater":[22],"bandwidth":[23,39],"than":[24],"standard":[25],"DDR4":[26],"DRAM,":[27],"they":[28],"introduce":[29],"new":[30],"design":[31],"challenges":[32,62],"such":[33],"as":[34],"increased":[35],"latency":[36],"higher":[38],"mismatch":[40],"between":[41],"memory":[42,97],"FPGA":[44],"cores.":[45],"This":[46],"paper":[47],"presents":[48],"scalable":[50],"architecture":[51,88],"convolutional":[53],"neural":[54],"network":[55],"conceived":[57],"specifically":[58],"to":[59,93],"address":[60],"these":[61],"make":[64],"full":[65],"use":[66],"of":[67,86],"memory's":[69],"high":[70],"bandwidth.":[71,98],"The":[72,83],"accelerator,":[73],"which":[74],"was":[75],"designed":[76],"using":[77],"high-level":[78],"synthesis,":[79],"is":[80],"highly":[81],"configurable.":[82],"intrinsic":[84],"parallelism":[85],"its":[87],"allows":[89],"near-perfect":[90],"scaling":[91],"up":[92],"saturating":[94],"available":[96]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}