{"id":"https://openalex.org/W2900082550","doi":"https://doi.org/10.1145/3240765.3240856","title":"TGPA","display_name":"TGPA","publication_year":2018,"publication_date":"2018-11-05","ids":{"openalex":"https://openalex.org/W2900082550","doi":"https://doi.org/10.1145/3240765.3240856","mag":"2900082550"},"language":"en","primary_location":{"id":"doi:10.1145/3240765.3240856","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240765.3240856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Computer-Aided Design","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102904614","display_name":"Xuechao Wei","orcid":"https://orcid.org/0000-0002-0996-2260"},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Xuechao Wei","raw_affiliation_strings":["Peking University, China and Falcon Computing Solutions, Inc","Center for Energy-efficient Computing and Applications, School of EECS, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, China and Falcon Computing Solutions, Inc","institution_ids":["https://openalex.org/I111483173"]},{"raw_affiliation_string":"Center for Energy-efficient Computing and Applications, School of EECS, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"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":"Yun Liang","raw_affiliation_strings":["Peking University, China","Center for Energy-efficient Computing and Applications, School of EECS, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Center for Energy-efficient Computing and Applications, School of EECS, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663885","display_name":"Xiuhong Li","orcid":"https://orcid.org/0000-0002-5327-0907"},"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":"Xiuhong Li","raw_affiliation_strings":["Peking University, China","Center for Energy-efficient Computing and Applications, School of EECS, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Center for Energy-efficient Computing and Applications, School of EECS, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008633310","display_name":"Cody Hao Yu","orcid":"https://orcid.org/0000-0002-9298-6254"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210113436","display_name":"SC Solutions (United States)","ror":"https://ror.org/01x5py295","country_code":"US","type":"company","lineage":["https://openalex.org/I4210113436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cody Hao Yu","raw_affiliation_strings":["University of California and Falcon Computing Solutions, Inc","Computer Science Department, University of California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California and Falcon Computing Solutions, Inc","institution_ids":["https://openalex.org/I4210113436"]},{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364062","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0001-9428-9340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Falcon Computing Solutions, Inc","Palcon Computing Solutions, Inc., Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Falcon Computing Solutions, Inc","institution_ids":[]},{"raw_affiliation_string":"Palcon Computing Solutions, Inc., Los Angeles, CA, USA","institution_ids":[]}]},{"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/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Jason Cong","raw_affiliation_strings":["Peking University, China and University of California and Falcon Computing Solutions, Inc","Center for Energy-efficient Computing and Applications, School of EECS, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, China and University of California and Falcon Computing Solutions, Inc","institution_ids":["https://openalex.org/I111483173"]},{"raw_affiliation_string":"Center for Energy-efficient Computing and Applications, School of EECS, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9980999827384949,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.849081814289093},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6968473196029663},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6044231057167053},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5799141526222229},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5440470576286316},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5384078025817871},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5252551436424255},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4767281115055084},{"id":"https://openalex.org/keywords/high-level-synthesis","display_name":"High-level synthesis","score":0.469188928604126},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4499194025993347},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4479224979877472},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.44787412881851196},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.44015246629714966},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4397597908973694},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.4157710075378418},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.41115567088127136},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3504292070865631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1394539177417755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.849081814289093},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6968473196029663},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6044231057167053},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5799141526222229},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5440470576286316},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5384078025817871},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5252551436424255},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4767281115055084},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.469188928604126},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4499194025993347},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4479224979877472},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44787412881851196},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.44015246629714966},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4397597908973694},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.4157710075378418},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.41115567088127136},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3504292070865631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1394539177417755},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3240765.3240856","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240765.3240856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Computer-Aided Design","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2094756095","https://openalex.org/W2097117768","https://openalex.org/W2194775991","https://openalex.org/W2466675884","https://openalex.org/W2475840367","https://openalex.org/W2503158931","https://openalex.org/W2513568085","https://openalex.org/W2520083297","https://openalex.org/W2525740295","https://openalex.org/W2565125333","https://openalex.org/W2565305208","https://openalex.org/W2574797063","https://openalex.org/W2584311934","https://openalex.org/W2585774018","https://openalex.org/W2606722458","https://openalex.org/W2618530766","https://openalex.org/W2625954420","https://openalex.org/W2626616508","https://openalex.org/W2627042741","https://openalex.org/W2727238169","https://openalex.org/W2729080111","https://openalex.org/W2756829667","https://openalex.org/W2809121165","https://openalex.org/W3001659479","https://openalex.org/W3102169921","https://openalex.org/W3148529197","https://openalex.org/W4249932213"],"related_works":["https://openalex.org/W4281926497","https://openalex.org/W2269990635","https://openalex.org/W2108242004","https://openalex.org/W4312985392","https://openalex.org/W2042762783","https://openalex.org/W4283730710","https://openalex.org/W4281784598","https://openalex.org/W4313484792","https://openalex.org/W4282568311","https://openalex.org/W4295935044"],"abstract_inverted_index":{"FPGAs":[0],"are":[1,136],"more":[2,4],"and":[3,175],"widely":[5],"used":[6],"as":[7],"reconfigurable":[8],"hardware":[9],"accelerators":[10,67,135],"for":[11,69,84,108,162],"applications":[12],"leveraging":[13],"convolutional":[14],"neural":[15],"networks":[16],"(CNNs)":[17],"in":[18],"recent":[19],"years.":[20],"Previous":[21],"designs":[22,63,81,161],"normally":[23],"adopt":[24],"a":[25,34,61,115,126],"uniform":[26],"accelerator":[27],"architecture":[28,102],"that":[29,159],"processes":[30],"all":[31],"layers":[32,71],"of":[33,57,89,122],"given":[35],"CNN":[36,111,164],"model":[37],"one":[38],"after":[39],"another.":[40],"This":[41],"homogeneous":[42,173],"design":[43,117],"methodology":[44],"usually":[45],"has":[46],"dynamic":[47],"resource":[48,154],"underutilization":[49],"issue":[50],"due":[51],"to":[52,74,142,151,168],"the":[53],"tensor":[54],"shape":[55],"diversity":[56],"different":[58,70,94,139,163],"layers.":[59],"As":[60],"result,":[62],"equipped":[64],"with":[65],"heterogeneous":[66,80,116,132],"specific":[68],"were":[72],"proposed":[73],"resolve":[75],"this":[76,97],"issue.":[77],"However,":[78],"existing":[79],"sacrifice":[82],"latency":[83,110,177],"throughput":[85],"by":[86],"concurrent":[87],"execution":[88,121],"multiple":[90,123,131],"input":[91,128],"images":[92],"on":[93,130],"accelerators.":[95,133],"In":[96],"paper,":[98],"we":[99],"propose":[100],"an":[101],"named":[103],"Tile-Grained":[104],"Pipeline":[105],"Architecture":[106],"(TGPA)":[107],"low":[109],"inference.":[112],"TGPA":[113,160],"adopts":[114],"which":[118],"supports":[119],"pipelining":[120],"tiles":[124],"within":[125],"single":[127],"image":[129],"The":[134],"partitioned":[137],"onto":[138],"FPGA":[140],"dies":[141],"guarantee":[143],"high":[144],"frequency.":[145],"A":[146],"partition":[147],"strategy":[148],"is":[149],"designd":[150],"maximize":[152],"on-chip":[153],"utilization.":[155],"Experiment":[156],"results":[157],"show":[158],"models":[165],"achieve":[166],"up":[167],"40%":[169],"performance":[170],"improvement":[171],"than":[172],"designs,":[174],"3X":[176],"reduction":[178],"over":[179],"state-of-the-art":[180],"designs.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":13}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2018-11-16T00:00:00"}