{"id":"https://openalex.org/W4308090254","doi":"https://doi.org/10.1109/hpec55821.2022.9926377","title":"A High-performance Deployment Framework for Pipelined CNN Accelerators with Flexible DSE Strategy","display_name":"A High-performance Deployment Framework for Pipelined CNN Accelerators with Flexible DSE Strategy","publication_year":2022,"publication_date":"2022-09-19","ids":{"openalex":"https://openalex.org/W4308090254","doi":"https://doi.org/10.1109/hpec55821.2022.9926377"},"language":"en","primary_location":{"id":"doi:10.1109/hpec55821.2022.9926377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec55821.2022.9926377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5008878143","display_name":"Conghui Luo","orcid":"https://orcid.org/0000-0002-0525-1840"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Conghui Luo","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University,Guangzhou,China","School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048231607","display_name":"Wenjin Huang","orcid":"https://orcid.org/0000-0002-8861-4263"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjin Huang","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University,Guangzhou,China","School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022560782","display_name":"Dehao Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dehao Xiang","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University,Guangzhou,China","School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046290441","display_name":"Yihua Huang","orcid":"https://orcid.org/0000-0001-5910-5972"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihua Huang","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University,Guangzhou,China","School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008878143"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1019792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9994000196456909,"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":0.9994000196456909,"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":0.9947999715805054,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8308571577072144},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6789966225624084},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5356919765472412},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.479398250579834},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4495696425437927},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.4199678301811218},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4125673770904541},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3807888627052307},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34188392758369446},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3305990695953369},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.18819659948349},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14180994033813477},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12858688831329346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8308571577072144},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6789966225624084},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5356919765472412},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.479398250579834},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4495696425437927},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.4199678301811218},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4125673770904541},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3807888627052307},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34188392758369446},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3305990695953369},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.18819659948349},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14180994033813477},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12858688831329346}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec55821.2022.9926377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec55821.2022.9926377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE High Performance Extreme Computing Conference (HPEC)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W2384410913","https://openalex.org/W1967938402","https://openalex.org/W2386041993","https://openalex.org/W1608572506"],"abstract_inverted_index":{"The":[0,74],"pipelined":[1,34],"DCNN(Deep":[2],"Convolutional":[3],"Neural":[4],"Networks)":[5],"accelerator":[6,35],"can":[7,82,103,144],"effectively":[8],"take":[9],"advantage":[10],"of":[11,28,65,69,106,155],"the":[12,25,33,41,49,63,79,99,113,151],"inter-layer":[13],"parallelism,":[14],"so":[15],"it":[16],"is":[17,60,126,137],"widely":[18],"used,":[19],"e.g.,":[20],"video":[21],"stream":[22],"processing.":[23],"But":[24],"large":[26],"amount":[27],"intermediate":[29],"results":[30,76],"generated":[31],"in":[32,140],"imposes":[36],"a":[37,53,66],"considerable":[38],"burden":[39],"on":[40,45,92,109],"on-chip":[42],"storage":[43,51],"resources":[44,108],"FPGAs.":[46],"To":[47],"ease":[48],"overburden":[50],"demand,":[52],"storage-optimized":[54],"design":[55],"space":[56],"exploration":[57],"(DSE)":[58],"method":[59],"proposed":[61,139],"at":[62],"cost":[64],"slight":[67],"drop":[68],"computing":[70,133,152],"resource":[71,100,134,153],"utilization":[72,90,115,135],"ratio.":[73],"experimental":[75],"show":[77],"that":[78,125],"DSE":[80],"strategy":[81,102],"achieve":[83,145],"98.49%":[84],"and":[85,94],"98.00%":[86],"CE":[87,114],"(Computation":[88],"Engines)":[89],"ratio":[91,116,136],"VGG16":[93],"ResNet101,":[95],"respectively.":[96],"In":[97],"addition,":[98],"optimization":[101],"save":[104],"27.84%":[105],"BRAM":[107],"VGG":[110],"16,":[111],"while":[112],"dropped":[117],"by":[118,149],"only":[119],"3.04%.":[120],"An":[121],"automated":[122],"deployment":[123],"framework":[124],"adaptable":[127],"to":[128],"different":[129],"networks":[130],"with":[131],"high":[132],"also":[138],"this":[141],"paper,":[142],"which":[143],"workload":[146],"balancing":[147],"automatically":[148],"optimizing":[150],"allocation":[154],"each":[156],"layer.":[157]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}