{"id":"https://openalex.org/W2990001850","doi":"https://doi.org/10.1145/3373087.3375389","title":"FeCaffe: FPGA-enabled Caffe with OpenCL for Deep Learning Training and Inference on Intel Stratix 10","display_name":"FeCaffe: FPGA-enabled Caffe with OpenCL for Deep Learning Training and Inference on Intel Stratix 10","publication_year":2020,"publication_date":"2020-02-23","ids":{"openalex":"https://openalex.org/W2990001850","doi":"https://doi.org/10.1145/3373087.3375389","mag":"2990001850"},"language":"en","primary_location":{"id":"doi:10.1145/3373087.3375389","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373087.3375389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.08905","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ke He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke He","raw_affiliation_strings":["Intel IoTG VMC PRC, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel IoTG VMC PRC, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bo Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Intel Flex Services, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Flex Services, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Intel IoTG VMC PRC, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel IoTG VMC PRC, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Andrew Ling","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Ling","raw_affiliation_strings":["Intel PSG, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel PSG, Toronto, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Dian Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dian Gu","raw_affiliation_strings":["Intel IoTG VMC PRC, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel IoTG VMC PRC, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5744,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.67156888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"314","last_page":"314"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9987999796867371,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9955999851226807,"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/deep-learning","display_name":"Deep learning","score":0.819599986076355},{"id":"https://openalex.org/keywords/stratix","display_name":"Stratix","score":0.7621999979019165},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6211000084877014},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5684999823570251},{"id":"https://openalex.org/keywords/reusability","display_name":"Reusability","score":0.49549999833106995},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4691999852657318},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.41819998621940613},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3833000063896179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.83160001039505},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.819599986076355},{"id":"https://openalex.org/C2776277307","wikidata":"https://www.wikidata.org/wiki/Q22074755","display_name":"Stratix","level":3,"score":0.7621999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6588000059127808},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6211000084877014},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.620199978351593},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5684999823570251},{"id":"https://openalex.org/C137981799","wikidata":"https://www.wikidata.org/wiki/Q1369184","display_name":"Reusability","level":3,"score":0.49549999833106995},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4458000063896179},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3887999951839447},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3596000075340271},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C65232700","wikidata":"https://www.wikidata.org/wiki/Q5656403","display_name":"Hardware architecture","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2727999985218048},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3373087.3375389","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373087.3375389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.08905","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.08905","pdf_url":"https://arxiv.org/pdf/1911.08905","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:1911.08905","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.08905","pdf_url":"https://arxiv.org/pdf/1911.08905","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning":[1,47,151],"has":[2],"becoming":[3],"increasingly":[4],"more":[5,161],"popular":[6,14,90],"in":[7,16,98],"recent":[8],"years,":[9],"and":[10,24,32,68,95,116,137,147,163,166,172,180],"there":[11],"are":[12],"many":[13],"frameworks":[15,28,44],"the":[17,51,60,74,127],"market":[18],"accordingly,":[19],"such":[20],"as":[21],"Caffe,":[22,64,75],"TensorFlow":[23],"Pytorch.":[25],"All":[26],"these":[27,43],"natively":[29],"support":[30,41,80,131,160],"CPUs":[31],"GPGPUs.":[33],"However,":[34],"FPGAs":[35],"still":[36],"cannot":[37],"provide":[38,86],"a":[39,65],"comprehensive":[40],"by":[42],"for":[45,50,135,149,178,183],"deep":[46,150],"development,":[48],"especially":[49],"training":[52,82,136,164],"phase.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,85],"firstly":[58],"propose":[59],"FeCaffe,":[61,94],"i.e.":[62],"FPGA-enabled":[63],"hierarchical":[66],"software":[67],"hardware":[69],"design":[70,144],"methodology":[71],"based":[72],"on":[73],"to":[76,79,154],"enable":[77],"FPGA":[78,106],"CNN":[81,91],"features.":[83],"Moreover,":[84],"some":[87,102],"benchmarks":[88],"of":[89,143],"networks":[92],"with":[93,140],"further":[96],"analysis":[97],"details":[99],"accordingly.":[100],"Finally,":[101],"optimization":[103],"directions":[104],"including":[105],"kernel":[107],"design,":[108],"system":[109],"pipeline,":[110],"network":[111,162],"architecture,":[112],"user":[113],"case":[114],"application":[115],"heterogeneous":[117],"platform":[118],"levels,":[119],"have":[120],"been":[121],"proposed":[122,128],"gradually.":[123],"The":[124],"result":[125],"demonstrates":[126],"FeCaffe":[129],"can":[130,159,169],"almost":[132],"full":[133],"features":[134],"inference":[138],"respectively":[139,182],"high":[141],"degree":[142],"flexibility,":[145],"expansibility":[146],"reusability":[148],"development.":[152],"Compared":[153],"prior":[155],"studies,":[156],"our":[157],"architecture":[158],"settings":[165],"current":[167],"configuration":[168],"achieve":[170],"6.4x":[171],"8.4x":[173],"average":[174],"execution":[175],"time":[176],"improvement":[177],"forward":[179],"backward":[181],"LeNet.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2019-12-05T00:00:00"}