{"id":"https://openalex.org/W4387007199","doi":"https://doi.org/10.1145/3603165.3607390","title":"Caffeine: Towards Uniformed Representation and Acceleration for Deep Convolutional Neural Networks","display_name":"Caffeine: Towards Uniformed Representation and Acceleration for Deep Convolutional Neural Networks","publication_year":2023,"publication_date":"2023-07-28","ids":{"openalex":"https://openalex.org/W4387007199","doi":"https://doi.org/10.1145/3603165.3607390"},"language":"en","primary_location":{"id":"doi:10.1145/3603165.3607390","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3603165.3607390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Turing Award Celebration Conference - China 2023","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/A5100374175","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0003-2762-2726"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiaotong university, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiaotong university, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089719475","display_name":"Guangyu Sun","orcid":"https://orcid.org/0000-0002-7315-6589"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyu Sun","raw_affiliation_strings":["School of Integrated Circuits, Peking University, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065889904","display_name":"Zhenman Fang","orcid":"https://orcid.org/0000-0003-0603-9697"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhenman Fang","raw_affiliation_strings":["School of Engineering Science, Simon Fraser University, Canada"],"affiliations":[{"raw_affiliation_string":"School of Engineering Science, Simon Fraser University, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063866156","display_name":"Peipei Zhou","orcid":"https://orcid.org/0000-0002-0493-1844"},"institutions":[{"id":"https://openalex.org/I4210124474","display_name":"Swanson Center","ror":"https://ror.org/0362zrb32","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210124474"]},{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peipei Zhou","raw_affiliation_strings":["Swanson School of Engineering, University of Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Swanson School of Engineering, University of Pittsburgh, United States","institution_ids":["https://openalex.org/I4210124474","https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016776689","display_name":"Jason Cong","orcid":"https://orcid.org/0000-0003-2887-6963"},"institutions":[{"id":"https://openalex.org/I4210140243","display_name":"Samueli Institute","ror":"https://ror.org/03teef091","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210140243"]},{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Cong","raw_affiliation_strings":["Samueli School Of Engineering, University of California, Los Angeles, United States"],"affiliations":[{"raw_affiliation_string":"Samueli School Of Engineering, University of California, Los Angeles, United States","institution_ids":["https://openalex.org/I4210140243","https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100374175"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.7218,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.86922577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9936000108718872,"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":0.9923999905586243,"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":0.8081834316253662},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7802943587303162},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.7566379308700562},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.706157386302948},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6690508723258972},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5795254111289978},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5400832891464233},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5219442248344421},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.48349955677986145},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4697701632976532},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.4607219994068146},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4558407962322235},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43167638778686523},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.4234570860862732},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4173593819141388},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3276832103729248},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3254849910736084},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17199018597602844},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0768156349658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8081834316253662},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7802943587303162},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.7566379308700562},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.706157386302948},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6690508723258972},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5795254111289978},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5400832891464233},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5219442248344421},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.48349955677986145},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4697701632976532},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.4607219994068146},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4558407962322235},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43167638778686523},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.4234570860862732},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4173593819141388},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3276832103729248},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3254849910736084},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17199018597602844},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0768156349658966},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3603165.3607390","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3603165.3607390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Turing Award Celebration Conference - China 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8600000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2094756095","https://openalex.org/W2096645269","https://openalex.org/W2102605133","https://openalex.org/W2145287260","https://openalex.org/W2294282016","https://openalex.org/W4212788319"],"related_works":["https://openalex.org/W2213533160","https://openalex.org/W2467043670","https://openalex.org/W4252450863","https://openalex.org/W2022867993","https://openalex.org/W2085105049","https://openalex.org/W3203561460","https://openalex.org/W3009624197","https://openalex.org/W4251138667","https://openalex.org/W2682544458","https://openalex.org/W1969709731"],"abstract_inverted_index":{"With":[0],"the":[1,28,33,36,43,64,71,96,142],"recent":[2],"advancement":[3],"of":[4,32,42,106],"multilayer":[5],"convolutional":[6],"neural":[7],"networks":[8],"(CNN),":[9],"deep":[10,99],"learning":[11,100],"has":[12],"achieved":[13],"amazing":[14],"success":[15],"in":[16,20],"many":[17],"areas,":[18],"especially":[19],"visual":[21],"content":[22],"understanding":[23],"and":[24,30,52,57,83,88,113,124,127,137],"classification.":[25],"To":[26],"improve":[27],"performance":[29,105,126],"energy-efficiency":[31,140],"computation-demanding":[34],"CNN,":[35],"FPGA-based":[37,85],"acceleration":[38],"emerges":[39],"as":[40],"one":[41],"most":[44],"attractive":[45],"alternatives.":[46],"In":[47],"this":[48],"paper":[49],"we":[50],"design":[51,78],"implement":[53],"Caffeine,":[54],"a":[55,77,103,133],"hardware":[56,87],"software":[58,90,98],"co-designed":[59],"library":[60],"to":[61,122],"efficiently":[62],"accelerate":[63],"entire":[65],"CNN":[66],"on":[67,70,109,116,132],"FPGAs.":[68],"Based":[69],"portable":[72],"high-level":[73],"synthesis,":[74],"Caffeine":[75,94],"provides":[76],"automation":[79],"flow":[80],"that":[81],"optimizes":[82],"generates":[84],"AI":[86],"runtime":[89],"codes.":[91],"We":[92],"integrate":[93],"into":[95],"industry-standard":[97],"framework.Caffeine":[101],"achieves":[102],"peak":[104],"365":[107],"GOPS":[108,115],"Xilinx":[110],"KU060":[111],"FPGA":[112],"636":[114],"Virtex7":[117],"690t":[118],"FPGA,":[119],"showing":[120],"up":[121],"7.3x":[123],"43.5x":[125],"energy":[128],"gains":[129],"over":[130,141],"Caffe":[131],"12-core":[134],"Xeon":[135],"server,":[136],"1.5x":[138],"better":[139],"GPU.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}