{"id":"https://openalex.org/W3160244283","doi":"https://doi.org/10.1109/isqed51717.2021.9424301","title":"HardCompress: A Novel Hardware-based Low-power Compression Scheme for DNN Accelerators","display_name":"HardCompress: A Novel Hardware-based Low-power Compression Scheme for DNN Accelerators","publication_year":2021,"publication_date":"2021-04-07","ids":{"openalex":"https://openalex.org/W3160244283","doi":"https://doi.org/10.1109/isqed51717.2021.9424301","mag":"3160244283"},"language":"en","primary_location":{"id":"doi:10.1109/isqed51717.2021.9424301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isqed51717.2021.9424301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 22nd International Symposium on Quality Electronic Design (ISQED)","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/A5070147631","display_name":"A. Arunachalam","orcid":"https://orcid.org/0000-0002-0750-0484"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayush Arunachalam","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066094401","display_name":"Shamik Kundu","orcid":"https://orcid.org/0000-0002-5992-8554"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shamik Kundu","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066464351","display_name":"Arnab Raha","orcid":"https://orcid.org/0000-0002-8848-1069"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnab Raha","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083178603","display_name":"Suvadeep Banerjee","orcid":"https://orcid.org/0000-0001-5188-1651"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suvadeep Banerjee","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113724917","display_name":"Suriyaprakash Natarajan","orcid":"https://orcid.org/0000-0002-5499-4341"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suriyaprakash Natarajan","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066320524","display_name":"Kanad Basu","orcid":"https://orcid.org/0000-0002-6431-7512"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kanad Basu","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"457","last_page":"462"},"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":0.9979000091552734,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9973000288009644,"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/computer-science","display_name":"Computer science","score":0.8167436122894287},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.705708384513855},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7035815119743347},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.5535861253738403},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5193856358528137},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.508965253829956},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5042070150375366},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4792882800102234},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.46376749873161316},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4595123827457428},{"id":"https://openalex.org/keywords/inference-engine","display_name":"Inference engine","score":0.4569038450717926},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4475003778934479},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.43181443214416504},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4151725172996521},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35057228803634644},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.33734169602394104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2759988307952881},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.16325682401657104},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14664536714553833},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09672361612319946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8167436122894287},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.705708384513855},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7035815119743347},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.5535861253738403},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5193856358528137},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.508965253829956},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5042070150375366},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4792882800102234},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.46376749873161316},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4595123827457428},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.4569038450717926},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4475003778934479},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.43181443214416504},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4151725172996521},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35057228803634644},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.33734169602394104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2759988307952881},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.16325682401657104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14664536714553833},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09672361612319946},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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:10.1109/isqed51717.2021.9424301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isqed51717.2021.9424301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 22nd International Symposium on Quality Electronic Design (ISQED)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2108481929","https://openalex.org/W2108598243","https://openalex.org/W2119144962","https://openalex.org/W2147267708","https://openalex.org/W2161651385","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2399535694","https://openalex.org/W2515531880","https://openalex.org/W2535375934","https://openalex.org/W2604319603","https://openalex.org/W2606722458","https://openalex.org/W2770370002","https://openalex.org/W2944349874","https://openalex.org/W2945065183","https://openalex.org/W2963122961","https://openalex.org/W2964299589","https://openalex.org/W2979535540","https://openalex.org/W2982479999","https://openalex.org/W3024621361","https://openalex.org/W6677580257","https://openalex.org/W6745848107"],"related_works":["https://openalex.org/W4285144618","https://openalex.org/W3166492421","https://openalex.org/W4285104150","https://openalex.org/W4295943704","https://openalex.org/W4389319487","https://openalex.org/W3208617247","https://openalex.org/W4380681266","https://openalex.org/W3046471834","https://openalex.org/W3210256422","https://openalex.org/W3128751578"],"abstract_inverted_index":{"The":[0,92,121],"ever-increasing":[1],"computing":[2],"requirements":[3],"of":[4,13,21,55,79,99,105,123,161],"Deep":[5],"Neural":[6],"Networks":[7],"(DNNs)":[8],"have":[9],"accentuated":[10],"the":[11,48,60,77,83,106,119,172],"deployment":[12],"such":[14,31],"networks":[15,132],"on":[16,129,134,141,154],"hardware":[17,114],"accelerators.":[18,91],"Inference":[19],"execution":[20],"large":[22,138,155],"DNNs":[23,139],"often":[24],"manifests":[25],"as":[26,63],"an":[27],"energy":[28,50],"bottleneck":[29],"in":[30,36,52,59,65,118,152,168,171],"accelerators,":[32],"especially":[33],"when":[34],"used":[35],"resource-constrained":[37],"Internet-of-Things":[38],"(IoT)":[39],"edge":[40],"devices.":[41],"This":[42],"can":[43],"be":[44],"primarily":[45],"attributed":[46],"to":[47,76,88,164],"massive":[49],"incurred":[51],"accessing":[53],"millions":[54],"trained":[56,133,140],"parameters":[57],"stored":[58],"on-chip":[61],"memory,":[62],"demonstrated":[64],"existing":[66],"research.":[67],"To":[68],"address":[69],"this":[70],"challenge,":[71],"we":[72],"propose":[73],"HardCompress,":[74,148],"which,":[75],"best":[78],"our":[80,124],"knowledge,":[81],"is":[82,127],"first":[84],"compression":[85,104,160],"solution":[86],"pertaining":[87],"commercial":[89],"DNN":[90,175],"three-step":[93],"approach":[94,126],"involves":[95],"hardware-based":[96],"post-quantization":[97],"trimming":[98],"weights,":[100],"followed":[101],"by":[102,111],"dictionary-based":[103],"weights":[107],"and":[108,137],"subsequent":[109],"decompression":[110],"a":[112,158],"low-power":[113],"engine":[115],"during":[116],"inference":[117],"accelerator.":[120,176],"efficiency":[122],"proposed":[125],"evaluated":[128],"both":[130],"lightweight":[131],"MNIST":[135],"dataset":[136],"ImageNet":[142],"dataset.":[143],"Our":[144],"results":[145],"demonstrate":[146],"that":[147],"without":[149],"any":[150],"loss":[151],"accuracy":[153],"DNNs,":[156],"furnishes":[157],"maximum":[159],"99.27%,":[162],"equivalent":[163],"137":[165],"*":[166],"reduction":[167],"memory":[169],"footprint":[170],"systolic":[173],"array-based":[174]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}