{"id":"https://openalex.org/W2979838629","doi":"https://doi.org/10.1145/3352460.3358283","title":"Boosting the Performance of CNN Accelerators with Dynamic Fine-Grained Channel Gating","display_name":"Boosting the Performance of CNN Accelerators with Dynamic Fine-Grained Channel Gating","publication_year":2019,"publication_date":"2019-10-11","ids":{"openalex":"https://openalex.org/W2979838629","doi":"https://doi.org/10.1145/3352460.3358283","mag":"2979838629"},"language":"en","primary_location":{"id":"doi:10.1145/3352460.3358283","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3352460.3358283","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3352460.3358283","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual IEEE/ACM International Symposium on Microarchitecture","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/10.1145/3352460.3358283","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025545085","display_name":"Weizhe Hua","orcid":"https://orcid.org/0000-0002-5231-9799"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weizhe Hua","raw_affiliation_strings":["Cornell University, Ithaca, NY"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049853160","display_name":"Yuan Zhou","orcid":"https://orcid.org/0000-0002-9198-6586"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Zhou","raw_affiliation_strings":["Cornell University, Ithaca, NY"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041869459","display_name":"Christopher De","orcid":"https://orcid.org/0000-0002-3610-2696"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher De Sa","raw_affiliation_strings":["Cornell University, Ithaca, NY"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037210004","display_name":"Zhiru Zhang","orcid":"https://orcid.org/0000-0002-0778-0308"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiru Zhang","raw_affiliation_strings":["Cornell University, Ithaca, NY"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024329178","display_name":"G. Edward Suh","orcid":"https://orcid.org/0000-0001-6409-9888"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Edward Suh","raw_affiliation_strings":["Cornell University, Ithaca, NY"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025545085"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":3.8823,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.94952473,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"139","last_page":"150"},"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/T11307","display_name":"Domain Adaptation and Few-Shot 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.823816180229187},{"id":"https://openalex.org/keywords/gating","display_name":"Gating","score":0.8182481527328491},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.778617262840271},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6776044368743896},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6383545398712158},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5836303234100342},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5412527918815613},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5214521288871765},{"id":"https://openalex.org/keywords/power-gating","display_name":"Power gating","score":0.4223910868167877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3358790874481201},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.28093165159225464},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07051342725753784},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06956583261489868}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.823816180229187},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.8182481527328491},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.778617262840271},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6776044368743896},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6383545398712158},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5836303234100342},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5412527918815613},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5214521288871765},{"id":"https://openalex.org/C2780700455","wikidata":"https://www.wikidata.org/wiki/Q7236515","display_name":"Power gating","level":4,"score":0.4223910868167877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3358790874481201},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.28093165159225464},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07051342725753784},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06956583261489868},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C42407357","wikidata":"https://www.wikidata.org/wiki/Q521","display_name":"Physiology","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C172385210","wikidata":"https://www.wikidata.org/wiki/Q5339","display_name":"Transistor","level":3,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3352460.3358283","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3352460.3358283","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3352460.3358283","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3352460.3358283","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3352460.3358283","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3352460.3358283","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2543051913","display_name":null,"funder_award_id":"1453378, 1618275","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6277332594","display_name":"STARSS: Small: Automatic Synthesis of Verifiably Secure Hardware Accelerators","funder_award_id":"1618275","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7766285678","display_name":null,"funder_award_id":"1453378","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"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320314786","display_name":"Xilinx","ror":"https://ror.org/01rb7bk56"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2979838629.pdf","grobid_xml":"https://content.openalex.org/works/W2979838629.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1665214252","https://openalex.org/W1821462560","https://openalex.org/W1836465849","https://openalex.org/W2094756095","https://openalex.org/W2117539524","https://openalex.org/W2155893237","https://openalex.org/W2162639668","https://openalex.org/W2186615578","https://openalex.org/W2194775991","https://openalex.org/W2276486856","https://openalex.org/W2279098554","https://openalex.org/W2419597278","https://openalex.org/W2513554817","https://openalex.org/W2515385951","https://openalex.org/W2516141709","https://openalex.org/W2516430887","https://openalex.org/W2562731582","https://openalex.org/W2585560244","https://openalex.org/W2585774018","https://openalex.org/W2625457103","https://openalex.org/W2724359148","https://openalex.org/W2737121650","https://openalex.org/W2748428003","https://openalex.org/W2752037867","https://openalex.org/W2759777444","https://openalex.org/W2760063890","https://openalex.org/W2771159931","https://openalex.org/W2786771851","https://openalex.org/W2883542588","https://openalex.org/W2884071170","https://openalex.org/W2891967877","https://openalex.org/W2896006880","https://openalex.org/W2904607988","https://openalex.org/W2949117887","https://openalex.org/W2950656546","https://openalex.org/W2952682304","https://openalex.org/W2963125010","https://openalex.org/W2963367920","https://openalex.org/W2964299589","https://openalex.org/W3104393472","https://openalex.org/W3105314253","https://openalex.org/W3118608800","https://openalex.org/W4232665025","https://openalex.org/W4245199738","https://openalex.org/W4251575795","https://openalex.org/W4289441319","https://openalex.org/W6638523607","https://openalex.org/W6687483927","https://openalex.org/W6726275242","https://openalex.org/W6743912273","https://openalex.org/W6753357821","https://openalex.org/W6910690987"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2913534066","https://openalex.org/W2970375204","https://openalex.org/W2259094912","https://openalex.org/W2371329481"],"abstract_inverted_index":{"This":[0,140],"paper":[1,141],"proposes":[2],"a":[3,51,91,128,134,151,157,162],"new":[4],"fine-grained":[5],"dynamic":[6,25,80,193],"pruning":[7],"technique":[8],"for":[9,55,164,176],"CNN":[10,39,158],"inference,":[11,76],"named":[12],"channel":[13,28,77,102,145,197],"gating,":[14],"and":[15,48,89,132,138,160],"presents":[16],"an":[17,171],"accelerator":[18,169],"architecture":[19],"that":[20,41,117,144,186],"can":[21,121,147,189],"effectively":[22,190],"exploit":[23,191],"the":[24,31,34,45,57,105,118,179,187,192],"sparsity.":[26],"Intuitively,":[27],"gating":[29,78,103,106,146],"identifies":[30],"regions":[32],"in":[33,59,90],"feature":[35],"map":[36],"of":[37,53,154,174],"each":[38,84],"layer":[40],"contribute":[42],"less":[43,61],"to":[44,75,83,156],"classification":[46],"result":[47],"turns":[49],"off":[50],"subset":[52],"channels":[54],"computing":[56],"activations":[58],"these":[60],"important":[62],"regions.":[63],"Unlike":[64],"static":[65],"network":[66],"pruning,":[67],"which":[68],"removes":[69],"redundant":[70],"weights":[71,110],"or":[72],"neurons":[73],"prior":[74],"exploits":[79],"sparsity":[81,194],"specific":[82],"input":[85],"at":[86],"run":[87],"time":[88],"structured":[92],"manner.":[93],"To":[94],"maximize":[95],"compute":[96],"savings":[97],"while":[98],"minimizing":[99],"accuracy":[100,130],"loss,":[101,131],"learns":[104],"thresholds":[107],"together":[108],"with":[109,127,150],"automatically":[111],"through":[112],"training.":[113],"Experimental":[114],"results":[115],"show":[116],"proposed":[119],"approach":[120],"significantly":[122],"speed":[123],"up":[124],"state-of-the-art":[125],"networks":[126],"marginal":[129],"enable":[133],"trade-off":[135],"between":[136],"performance":[137],"accuracy.":[139],"also":[142],"shows":[143,170],"be":[148],"supported":[149],"small":[152],"set":[153],"extensions":[155],"accelerator,":[159],"implements":[161],"prototype":[163],"quantized":[165],"ResNet-18":[166],"models.":[167],"The":[168],"average":[172],"speedup":[173],"2.3\u00d7":[175],"ImageNet":[177],"when":[178],"theoretical":[180],"FLOP":[181],"reduction":[182],"is":[183],"2.8\u00d7,":[184],"indicating":[185],"hardware":[188],"exposed":[195],"by":[196],"gating.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}