{"id":"https://openalex.org/W3081137248","doi":"https://doi.org/10.1145/3404555.3404626","title":"A High Energy-Efficiency Inference Accelerator Exploiting Sparse CNNs","display_name":"A High Energy-Efficiency Inference Accelerator Exploiting Sparse CNNs","publication_year":2020,"publication_date":"2020-04-23","ids":{"openalex":"https://openalex.org/W3081137248","doi":"https://doi.org/10.1145/3404555.3404626","mag":"3081137248"},"language":"en","primary_location":{"id":"doi:10.1145/3404555.3404626","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404555.3404626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","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/A5081265309","display_name":"Ning Li","orcid":"https://orcid.org/0000-0002-4534-9009"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5081265309"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.08802178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"534","last_page":"541"},"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":0.9993000030517578,"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/T12676","display_name":"Machine Learning and ELM","score":0.9983000159263611,"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":0.8489031195640564},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7214901447296143},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6946080327033997},{"id":"https://openalex.org/keywords/stratix","display_name":"Stratix","score":0.6235799193382263},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6000350117683411},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.586353063583374},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5804184675216675},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5686162710189819},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5078907608985901},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.46769237518310547},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.4483538568019867},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4295922517776489},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4279037117958069},{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.4174182713031769},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.41486042737960815},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3672698438167572},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24391740560531616},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2352408468723297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22025543451309204},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.1907981038093567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8489031195640564},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7214901447296143},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6946080327033997},{"id":"https://openalex.org/C2776277307","wikidata":"https://www.wikidata.org/wiki/Q22074755","display_name":"Stratix","level":3,"score":0.6235799193382263},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6000350117683411},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.586353063583374},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5804184675216675},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5686162710189819},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5078907608985901},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.46769237518310547},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.4483538568019867},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4295922517776489},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4279037117958069},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.4174182713031769},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.41486042737960815},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3672698438167572},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24391740560531616},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2352408468723297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22025543451309204},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1907981038093567},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3404555.3404626","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404555.3404626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2094756095","https://openalex.org/W2194775991","https://openalex.org/W2419597278","https://openalex.org/W2513419314","https://openalex.org/W2516141709","https://openalex.org/W2565851976","https://openalex.org/W2584311934","https://openalex.org/W2585774018","https://openalex.org/W2621285457","https://openalex.org/W2952682304","https://openalex.org/W3118608800","https://openalex.org/W4211095909","https://openalex.org/W4255534610","https://openalex.org/W4299994276"],"related_works":["https://openalex.org/W2556282987","https://openalex.org/W1533508804","https://openalex.org/W2050923821","https://openalex.org/W4200457651","https://openalex.org/W2518118925","https://openalex.org/W2155444381","https://openalex.org/W2106942255","https://openalex.org/W2891818448","https://openalex.org/W2765235648","https://openalex.org/W2155374825"],"abstract_inverted_index":{"The":[0,121],"significantly":[1],"growing":[2],"computation":[3,81],"and":[4,39,136],"memory":[5],"demands":[6],"have":[7],"become":[8],"a":[9,52,103],"bottleneck":[10],"for":[11,36,79,134],"the":[12,29,84,98,116],"application":[13],"of":[14,86,118],"convolutional":[15],"neural":[16],"networks":[17],"(CNNs).":[18],"Model":[19],"compression":[20],"is":[21,93,112],"an":[22],"efficient":[23],"method":[24],"to":[25,66,82,95,114],"accelerate":[26],"CNNs.":[27],"However,":[28],"commonly":[30],"designed":[31,94],"architectures":[32],"are":[33],"not":[34],"suitable":[35],"compressed":[37],"models":[38],"waste":[40],"large":[41],"computational":[42],"resources":[43],"on":[44,57],"zero":[45],"operands.":[46],"In":[47],"this":[48],"work,":[49],"we":[50],"propose":[51],"flexible":[53],"CNNs":[54],"inference":[55],"accelerator":[56,71,126],"FPGA":[58],"utilizing":[59],"uniform":[60],"sparsity":[61],"introduced":[62],"by":[63],"pattern":[64],"pruning":[65],"achieve":[67,128],"high":[68],"performance.":[69],"Our":[70],"architecture":[72],"exploits":[73],"different":[74],"input":[75],"&":[76],"output":[77],"parallelism":[78],"sparse":[80],"maximize":[83],"utilization":[85],"computing":[87],"arrays.":[88],"A":[89],"dynamically":[90],"adjustable":[91],"mechanism":[92],"deal":[96],"with":[97,108],"unbalanced":[99],"workload.":[100],"What's":[101],"more,":[102],"novel":[104],"data":[105],"buffering":[106],"structure":[107],"slightly":[109],"rearranged":[110],"sequences":[111],"applied":[113],"address":[115],"challenge":[117],"access":[119],"conflict.":[120],"experiments":[122],"show":[123],"that":[124],"our":[125],"can":[127],"316.4":[129],"GOP/s":[130,133],"~":[131],"343.5":[132],"VGG-16":[135],"ResNet-50.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}