{"id":"https://openalex.org/W4411725439","doi":"https://doi.org/10.1109/iscas56072.2025.11043315","title":"FlexAcc: Accelerating Batch Normalization through GPU-FPGA Integration","display_name":"FlexAcc: Accelerating Batch Normalization through GPU-FPGA Integration","publication_year":2025,"publication_date":"2025-05-25","ids":{"openalex":"https://openalex.org/W4411725439","doi":"https://doi.org/10.1109/iscas56072.2025.11043315"},"language":"en","primary_location":{"id":"doi:10.1109/iscas56072.2025.11043315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas56072.2025.11043315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5051373012","display_name":"Haishuai Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haishuai Zhang","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications,Nanjing,China,210023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications,Nanjing,China,210023","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380123","display_name":"Zhihao Li","orcid":"https://orcid.org/0000-0002-6149-0627"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Li","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications,Nanjing,China,210023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications,Nanjing,China,210023","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101631836","display_name":"Pengyang Li","orcid":"https://orcid.org/0000-0003-2105-2128"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyang Li","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications,Nanjing,China,210023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications,Nanjing,China,210023","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032326552","display_name":"Xuehuai Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuehuai Shi","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications,Nanjing,China,210023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications,Nanjing,China,210023","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048584559","display_name":"Xiaobai Chen","orcid":"https://orcid.org/0000-0003-1166-6927"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobai Chen","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications,Nanjing,China,210023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications,Nanjing,China,210023","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082725592","display_name":"Jieming Yin","orcid":"https://orcid.org/0009-0008-2878-1853"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieming Yin","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications,Nanjing,China,210023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications,Nanjing,China,210023","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9470000267028809,"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"}},"topics":[{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9470000267028809,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9269000291824341,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9259999990463257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7846192717552185},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7387205958366394},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6820182204246521},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4760860502719879},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.46296098828315735},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4113022983074188},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.332790732383728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32064783573150635},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.21330052614212036}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7846192717552185},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387205958366394},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6820182204246521},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4760860502719879},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.46296098828315735},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4113022983074188},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.332790732383728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32064783573150635},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.21330052614212036},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas56072.2025.11043315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas56072.2025.11043315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2570343428","https://openalex.org/W2587914027","https://openalex.org/W2900316824","https://openalex.org/W2949619037","https://openalex.org/W2951771281","https://openalex.org/W2997828269","https://openalex.org/W3004766715","https://openalex.org/W3102510044","https://openalex.org/W3132745255","https://openalex.org/W3157174059","https://openalex.org/W4385080160"],"related_works":["https://openalex.org/W4399354997","https://openalex.org/W2005148983","https://openalex.org/W2012954338","https://openalex.org/W2096672917","https://openalex.org/W2392023973","https://openalex.org/W3189307731","https://openalex.org/W1428699136","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1998560227"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"are":[3],"fundamental":[4],"to":[5,24,47,51,67],"deep":[6,84],"learning,":[7],"especially":[8],"in":[9],"computer":[10],"vision.":[11],"However,":[12],"their":[13],"computational":[14],"demands,":[15],"particularly":[16],"during":[17],"batch":[18],"normalization,":[19],"create":[20],"significant":[21],"inefficiencies":[22],"due":[23],"excessive":[25],"data":[26,54],"movement":[27,55],"between":[28,78],"memory":[29],"and":[30,45,56,80],"processing":[31],"units.":[32],"To":[33],"address":[34],"this,":[35],"we":[36],"propose":[37],"FlexAcc,":[38],"a":[39],"novel":[40],"architecture":[41],"that":[42],"integrates":[43],"GPUs":[44],"FPGAs":[46],"offload":[48],"BN":[49],"computations":[50],"FPGAs,":[52],"reducing":[53],"improving":[57],"hardware":[58],"utilization.":[59],"FlexAcc":[60],"accelerates":[61],"end-to-end":[62],"training":[63],"performance":[64,76],"by":[65],"up":[66],"1.1\u00d7":[68],"across":[69],"various":[70],"models.":[71],"This":[72],"approach":[73],"bridges":[74],"the":[75],"gap":[77],"convolutional":[79],"non-convolutional":[81],"layers,":[82],"advancing":[83],"learning":[85],"model":[86],"deployment.":[87]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}