{"id":"https://openalex.org/W3007444108","doi":"https://doi.org/10.1145/3373087.3375302","title":"Reuse Kernels or Activations?","display_name":"Reuse Kernels or Activations?","publication_year":2020,"publication_date":"2020-02-23","ids":{"openalex":"https://openalex.org/W3007444108","doi":"https://doi.org/10.1145/3373087.3375302","mag":"3007444108"},"language":"en","primary_location":{"id":"doi:10.1145/3373087.3375302","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3373087.3375302","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3373087.3375302","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3373087.3375302","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101472380","display_name":"Yue Niu","orcid":"https://orcid.org/0000-0002-1663-2921"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yue Niu","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042560222","display_name":"Rajgopal Kannan","orcid":"https://orcid.org/0000-0001-8736-3012"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajgopal Kannan","raw_affiliation_strings":["US Army Research Lab-West, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"US Army Research Lab-West, Los Angeles, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002594174","display_name":"Ajitesh Srivastava","orcid":"https://orcid.org/0000-0002-8706-5717"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ajitesh Srivastava","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033166029","display_name":"Viktor K. Prasanna","orcid":"https://orcid.org/0000-0002-1609-8589"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viktor Prasanna","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101472380"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":1.1777,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.80816218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"266","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9990000128746033,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9973000288009644,"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":0.8600194454193115},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5942891240119934},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5771851539611816},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5480327010154724},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5330385565757751},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5051780343055725},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4768965244293213},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.46467405557632446},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4639994502067566},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4342302680015564},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4280732274055481},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4188995659351349},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4176003336906433},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38692498207092285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16327649354934692},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12784355878829956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8600194454193115},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5942891240119934},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5771851539611816},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5480327010154724},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5330385565757751},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5051780343055725},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4768965244293213},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.46467405557632446},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4639994502067566},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4342302680015564},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4280732274055481},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4188995659351349},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4176003336906433},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38692498207092285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16327649354934692},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12784355878829956},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3373087.3375302","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3373087.3375302","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3373087.3375302","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"}],"best_oa_location":{"id":"doi:10.1145/3373087.3375302","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3373087.3375302","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3373087.3375302","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4294909562","display_name":null,"funder_award_id":"CNS-1643351","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7205111918","display_name":null,"funder_award_id":"1643351","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8587235517","display_name":"SPX: Collaborative Research: FASTLEAP: FPGA based compact Deep Learning Platform","funder_award_id":"1919117","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8669643791","display_name":null,"funder_award_id":"CCF-1919117","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3007444108.pdf","grobid_xml":"https://content.openalex.org/works/W3007444108.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1841592590","https://openalex.org/W1849277567","https://openalex.org/W1902934009","https://openalex.org/W1903029394","https://openalex.org/W2097117768","https://openalex.org/W2163605009","https://openalex.org/W2164278908","https://openalex.org/W2194775991","https://openalex.org/W2276486856","https://openalex.org/W2286365479","https://openalex.org/W2340076492","https://openalex.org/W2513140567","https://openalex.org/W2584616277","https://openalex.org/W2613718673","https://openalex.org/W2614143469","https://openalex.org/W2625954420","https://openalex.org/W2766304518","https://openalex.org/W2792503273","https://openalex.org/W2798170643","https://openalex.org/W2798724095","https://openalex.org/W2963122961","https://openalex.org/W2963363373","https://openalex.org/W2964233199","https://openalex.org/W2964299589","https://openalex.org/W2969284583","https://openalex.org/W2982037701","https://openalex.org/W3104263540","https://openalex.org/W4292363360","https://openalex.org/W4387007199"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W2907307640"],"abstract_inverted_index":{"Spectral-domain":[0],"CNNs":[1,12],"have":[2],"been":[3],"shown":[4],"to":[5,74,117,128,159,171],"be":[6],"more":[7],"efficient":[8],"than":[9],"traditional":[10],"spatial":[11],"in":[13,114],"terms":[14],"of":[15,96,135,165,176],"reducing":[16],"computation":[17],"complexity.":[18],"However":[19],"they":[20],"come":[21],"with":[22,155],"a":[23,33,46,71,81,107,124,144],"'kernel":[24],"explosion'":[25],"problem":[26],"that,":[27],"even":[28],"after":[29],"compression":[30,55],"(pruning),":[31],"imposes":[32],"high":[34],"memory":[35,133],"burden":[36],"and":[37,56,79,100,139,161],"off-chip":[38,119],"bandwidth":[39],"requirement":[40],"for":[41,62,109,168],"kernel":[42],"access.":[43],"This":[44],"creates":[45],"performance":[47,77],"gap":[48,78],"between":[49],"the":[50,93,131,172],"potential":[51],"acceleration":[52],"offered":[53],"by":[54,153],"actual":[57],"FPGA":[58,146],"implementation":[59],"performance,":[60],"especially":[61],"low-latency":[63],"CNN":[64,86],"inference.":[65],"In":[66],"this":[67,76],"paper,":[68],"we":[69,91,122],"develop":[70,106],"principled":[72],"approach":[73],"overcoming":[75],"designing":[80],"low-latency,":[82],"low-bandwidth,":[83],"spectral":[84],"sparse":[85,97,137],"accelerator":[87],"on":[88],"FPGAs.":[89],"First,":[90],"analyze":[92],"bandwidth-storage":[94],"tradeoff":[95],"convolutional":[98],"layers":[99,116],"locate":[101],"communication":[102],"bottlenecks.":[103],"We":[104],"then":[105],"dataflow":[108],"flexibly":[110],"optimizing":[111],"data":[112,151],"reuse":[113],"different":[115],"minimize":[118,140],"communication.":[120],"Finally,":[121],"propose":[123],"novel":[125],"scheduling":[126],"algorithm":[127],"optimally":[129],"schedule":[130],"on-chip":[132],"access":[134],"multiple":[136],"kernels":[138],"read":[141],"conflicts.":[142],"On":[143],"state-of-the-art":[145,174],"platform,":[147],"our":[148],"design":[149],"reduces":[150],"transfers":[152],"42%":[154],"DSP":[156],"utilization":[157],"up":[158],"90%":[160],"achieves":[162],"inference":[163],"latency":[164,175],"9":[166],"ms":[167],"VGG16,":[169],"compared":[170],"baseline":[173],"68":[177],"ms.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}