{"id":"https://openalex.org/W4316252407","doi":"https://doi.org/10.1145/3547276.3548521","title":"A Software/Hardware Co-design Local Irregular Sparsity Method for Accelerating CNNs on FPGA","display_name":"A Software/Hardware Co-design Local Irregular Sparsity Method for Accelerating CNNs on FPGA","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4316252407","doi":"https://doi.org/10.1145/3547276.3548521"},"language":"en","primary_location":{"id":"doi:10.1145/3547276.3548521","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3547276.3548521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 51st International Conference on Parallel Processing","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/A5007368731","display_name":"Jiangwei Shang","orcid":"https://orcid.org/0000-0002-2720-2273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangwei Shang","raw_affiliation_strings":["Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393410","display_name":"Zhan Zhang","orcid":"https://orcid.org/0000-0001-7419-4272"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Zhang","raw_affiliation_strings":["Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101979710","display_name":"Chuanyou Li","orcid":"https://orcid.org/0000-0002-8725-6417"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanyou Li","raw_affiliation_strings":["Southeast University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342309","display_name":"Kun Zhang","orcid":"https://orcid.org/0000-0002-0738-9958"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Zhang","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101811550","display_name":"Lei Qian","orcid":"https://orcid.org/0000-0003-3580-9566"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Qian","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100411959","display_name":"Hongwei Liu","orcid":"https://orcid.org/0000-0002-9215-7173"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Liu","raw_affiliation_strings":["Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1015,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42090874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T12676","display_name":"Machine Learning and ELM","score":0.9980999827384949,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/speedup","display_name":"Speedup","score":0.9567399024963379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8148584365844727},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.76789391040802},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7226673364639282},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7024694681167603},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6170099377632141},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6038610935211182},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5851427912712097},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4788922369480133},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4592997133731842},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.45858025550842285},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3790775537490845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32126885652542114},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2801443636417389}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.9567399024963379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148584365844727},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.76789391040802},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7226673364639282},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7024694681167603},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6170099377632141},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6038610935211182},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5851427912712097},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4788922369480133},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4592997133731842},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45858025550842285},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3790775537490845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32126885652542114},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2801443636417389},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3547276.3548521","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3547276.3548521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G2544296921","display_name":null,"funder_award_id":"61902063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2119144962","https://openalex.org/W2533598788","https://openalex.org/W2559655401","https://openalex.org/W2616014673","https://openalex.org/W2625457103","https://openalex.org/W2751366252","https://openalex.org/W2792503273","https://openalex.org/W2904902077","https://openalex.org/W2949619037","https://openalex.org/W2949650786","https://openalex.org/W2963000224","https://openalex.org/W2963037989","https://openalex.org/W2963363373","https://openalex.org/W2964233199","https://openalex.org/W2999533992","https://openalex.org/W3005712428","https://openalex.org/W3009383973","https://openalex.org/W3038838661","https://openalex.org/W3085447111","https://openalex.org/W3093982621","https://openalex.org/W3104393472","https://openalex.org/W4297813615","https://openalex.org/W4310895557","https://openalex.org/W6640289440","https://openalex.org/W6725543821"],"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/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W3046370962"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"have":[4,56,90],"been":[5,57],"widely":[6],"used":[7],"in":[8,115],"different":[9],"areas.":[10],"The":[11,154],"success":[12],"of":[13,20,66],"CNNs":[14,26,61],"comes":[15],"with":[16,172],"a":[17,91,110,123,141,165,173],"huge":[18],"amount":[19],"parameters":[21,67,108],"and":[22,24,68,80,88,151],"computations,":[23],"nowaday":[25],"still":[27],"keep":[28,103],"moving":[29],"toward":[30],"larger":[31,34],"structures.":[32],"Although":[33],"structures":[35],"often":[36],"bring":[37,128],"about":[38],"better":[39],"inference":[40,48],"accuracy,":[41],"the":[42,47,64,95,98,107,136,169],"increasing":[43],"size":[44],"also":[45],"slows":[46],"speed":[49],"down.":[50],"Recently,":[51],"various":[52],"parameter":[53],"sparsity":[54,71,83,100,131],"methods":[55,72,84,101,171],"proposed":[58],"to":[59,127,147],"accelerate":[60],"by":[62,105],"reducing":[63],"number":[65],"computations.":[69],"Existing":[70],"could":[73,102],"be":[74],"classified":[75],"into":[76,132],"two":[77],"categories:":[78],"unstructured":[79],"structured.":[81],"Unstructured":[82],"easily":[85],"cause":[86],"irregularity":[87],"thus":[89],"suboptimal":[92],"speedup.":[93,153],"On":[94],"other":[96],"hand,":[97],"structured":[99],"regularity":[104],"pruning":[106],"following":[109],"certain":[111],"pattern":[112],"but":[113],"result":[114],"low":[116],"sparsity.":[117],"In":[118],"this":[119],"paper,":[120],"we":[121,139],"propose":[122],"software/hardware":[124,160],"co-design":[125,161],"approach":[126],"local":[129,137],"irregular":[130],"CNNs.":[133],"Benefiting":[134],"from":[135],"irregularity,":[138],"design":[140],"row-wise":[142],"computing":[143],"engine,":[144],"RConv":[145],"Engine,":[146],"achieve":[148,164],"workload":[149],"balance":[150],"remarkable":[152],"experimental":[155],"results":[156],"show":[157],"that":[158],"our":[159],"method":[162],"can":[163],"10.9x":[166],"speedup":[167],"than":[168],"state-of-the-art":[170],"negligible":[174],"accuracy":[175],"loss.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}