{"id":"https://openalex.org/W2964194679","doi":"https://doi.org/10.1109/asap.2017.7995252","title":"CATERPILLAR: Coarse Grain Reconfigurable Architecture for accelerating the training of Deep Neural Networks","display_name":"CATERPILLAR: Coarse Grain Reconfigurable Architecture for accelerating the training of Deep Neural Networks","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2964194679","doi":"https://doi.org/10.1109/asap.2017.7995252","mag":"2964194679"},"language":"en","primary_location":{"id":"doi:10.1109/asap.2017.7995252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2017.7995252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 28th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","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/A5017943466","display_name":"Yuan-Fang Li","orcid":"https://orcid.org/0000-0003-4651-2821"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuanfang Li","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006068818","display_name":"Ardavan Pedram","orcid":"https://orcid.org/0000-0002-6348-6701"},"institutions":[{"id":"https://openalex.org/I4401726927","display_name":"Cerebras Systems (United States)","ror":"https://ror.org/040zz8080","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726927"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Ardavan Pedram","raw_affiliation_strings":["Cerebras Systems"],"affiliations":[{"raw_affiliation_string":"Cerebras Systems","institution_ids":["https://openalex.org/I4401726927"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017943466"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.2743,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88346847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"49","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9980999827384949,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.7724816799163818},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7424510717391968},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6561861634254456},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5801315903663635},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5128641128540039},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5030454993247986},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4794313311576843},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.45581525564193726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4440917372703552},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.4416189193725586},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4398728311061859},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40559035539627075},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.401419460773468},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3483877182006836},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1479254961013794},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14055362343788147}],"concepts":[{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.7724816799163818},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7424510717391968},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6561861634254456},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5801315903663635},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5128641128540039},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5030454993247986},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4794313311576843},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.45581525564193726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4440917372703552},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.4416189193725586},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4398728311061859},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40559035539627075},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.401419460773468},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3483877182006836},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1479254961013794},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14055362343788147},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asap.2017.7995252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2017.7995252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 28th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","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":0.9100000262260437}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W589810062","https://openalex.org/W1686810756","https://openalex.org/W1818493870","https://openalex.org/W1841592590","https://openalex.org/W1907710939","https://openalex.org/W1980697457","https://openalex.org/W2016369813","https://openalex.org/W2056882228","https://openalex.org/W2072566913","https://openalex.org/W2072730350","https://openalex.org/W2087402357","https://openalex.org/W2100987062","https://openalex.org/W2108020882","https://openalex.org/W2116424792","https://openalex.org/W2132424367","https://openalex.org/W2138243089","https://openalex.org/W2153387583","https://openalex.org/W2163605009","https://openalex.org/W2168231600","https://openalex.org/W2170796499","https://openalex.org/W2269491305","https://openalex.org/W2285660444","https://openalex.org/W2507556850","https://openalex.org/W2604319603","https://openalex.org/W2606722458","https://openalex.org/W2766736793","https://openalex.org/W2949405272","https://openalex.org/W2950656546","https://openalex.org/W2963374099","https://openalex.org/W2964115671","https://openalex.org/W2964333985","https://openalex.org/W3106213055","https://openalex.org/W3137284226","https://openalex.org/W4293404878","https://openalex.org/W4297661238","https://openalex.org/W6607333740","https://openalex.org/W6617522502","https://openalex.org/W6638335665","https://openalex.org/W6638783484","https://openalex.org/W6680402377","https://openalex.org/W6682934876","https://openalex.org/W6684191040","https://openalex.org/W6684859321","https://openalex.org/W6764273044"],"related_works":["https://openalex.org/W4315697128","https://openalex.org/W3102845713","https://openalex.org/W2971502891","https://openalex.org/W3205506801","https://openalex.org/W4287755480","https://openalex.org/W3131497135","https://openalex.org/W2785875001","https://openalex.org/W4292794827","https://openalex.org/W4224939635","https://openalex.org/W4285818394"],"abstract_inverted_index":{"Accelerating":[0],"the":[1,17,20],"inference":[2],"of":[3,22,38,50,120,151],"a":[4,8,148],"trained":[5],"DNN":[6],"is":[7,27,108],"well":[9],"studied":[10],"subject.":[11],"In":[12],"this":[13],"paper":[14,44],"we":[15],"switch":[16],"focus":[18],"to":[19,53],"training":[21,25,64,82,129,143],"DNNs.":[23,65],"The":[24],"phase":[26],"compute":[28],"intensive,":[29],"demands":[30],"complicated":[31],"data":[32,39],"communication,":[33],"and":[34,41,59,88,133,157],"contains":[35],"multiple":[36],"levels":[37],"dependencies":[40],"parallelism.":[42],"This":[43],"presents":[45],"an":[46,70],"algorithm/architecture":[47],"space":[48],"exploration":[49],"efficient":[51],"accelerators":[52],"achieve":[54],"better":[55],"network":[56],"convergence":[57],"rates":[58],"higher":[60,109],"energy":[61],"efficiency":[62],"for":[63,75,105,127,140],"We":[66],"further":[67],"demonstrate":[68],"that":[69,97],"architecture":[71],"with":[72],"hierarchical":[73],"support":[74],"collective":[76],"communication":[77],"semantics":[78],"provides":[79],"flexibility":[80],"in":[81],"various":[83],"networks":[84,99,107,132,146],"performing":[85],"both":[86],"stochastic":[87],"batched":[89,111],"gradient":[90],"descent":[91],"based":[92],"techniques.":[93],"Our":[94],"results":[95],"suggest":[96],"smaller":[98],"favor":[100],"non-batched":[101],"techniques":[102],"while":[103],"performance":[104,118],"larger":[106,145],"using":[110,147],"operations.":[112],"At":[113],"45nm":[114],"technology,":[115],"CATERPILLAR":[116],"achieves":[117],"efficiencies":[119],"177":[121],"GFLOPS/W":[122,135],"at":[123,136],"over":[124,137],"80%":[125],"utilization":[126,139],"SGD":[128],"on":[130,144],"small":[131],"211":[134],"90%":[138],"pipelined":[141],"SGD/CP":[142],"total":[149],"area":[150],"103.2":[152],"mm":[153,159],"<sup":[154,160],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[155,161],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[156,162],"178.9":[158],"respectively.":[163]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}