{"id":"https://openalex.org/W3036221207","doi":"https://doi.org/10.23919/date48585.2020.9116511","title":"Sparsity-Aware Caches to Accelerate Deep Neural Networks","display_name":"Sparsity-Aware Caches to Accelerate Deep Neural Networks","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3036221207","doi":"https://doi.org/10.23919/date48585.2020.9116511","mag":"3036221207"},"language":"en","primary_location":{"id":"doi:10.23919/date48585.2020.9116511","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date48585.2020.9116511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Design, Automation & Test in Europe Conference & Exhibition (DATE)","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/A5101608355","display_name":"Vinod Ganesan","orcid":"https://orcid.org/0000-0002-0875-9893"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Vinod Ganesan","raw_affiliation_strings":["Department of Computer Science and Engineering, IIT Madras, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIT Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021284824","display_name":"Sanchari Sen","orcid":"https://orcid.org/0000-0003-0080-2882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanchari Sen","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101614266","display_name":"Pratyush Kumar","orcid":"https://orcid.org/0000-0002-8732-0183"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pratyush Kumar","raw_affiliation_strings":["Department of Computer Science and Engineering, IIT Madras, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIT Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007490713","display_name":"Neel Gala","orcid":"https://orcid.org/0000-0001-8611-6511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neel Gala","raw_affiliation_strings":["InCore Semiconductors Pvt. Ltd"],"affiliations":[{"raw_affiliation_string":"InCore Semiconductors Pvt. Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010004459","display_name":"V. Kamakoti","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kamakoti Veezhinathan","raw_affiliation_strings":["Department of Computer Science and Engineering, IIT Madras, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIT Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065766721","display_name":"Anand Raghunathan","orcid":"https://orcid.org/0000-0002-4624-564X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anand Raghunathan","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101608355"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":0.9241,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71733449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"85","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9987999796867371,"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":0.8842930197715759},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7978500127792358},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4976220428943634},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.48451656103134155},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4607786536216736},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.4599415957927704},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.4361986517906189},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.42284369468688965},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.4143002927303314},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.37740689516067505},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.360609769821167},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2545925974845886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8842930197715759},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7978500127792358},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4976220428943634},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.48451656103134155},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4607786536216736},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.4599415957927704},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.4361986517906189},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.42284369468688965},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.4143002927303314},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.37740689516067505},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.360609769821167},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2545925974845886},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date48585.2020.9116511","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date48585.2020.9116511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1598866093","https://openalex.org/W1935978687","https://openalex.org/W1957436476","https://openalex.org/W1963881655","https://openalex.org/W1976494130","https://openalex.org/W2020517863","https://openalex.org/W2030922317","https://openalex.org/W2062143991","https://openalex.org/W2116674125","https://openalex.org/W2119144962","https://openalex.org/W2132153846","https://openalex.org/W2134633067","https://openalex.org/W2151811992","https://openalex.org/W2154614859","https://openalex.org/W2155366133","https://openalex.org/W2155893237","https://openalex.org/W2162752393","https://openalex.org/W2168113051","https://openalex.org/W2237415205","https://openalex.org/W2293587938","https://openalex.org/W2331783522","https://openalex.org/W2606722458","https://openalex.org/W2612445135","https://openalex.org/W2612832886","https://openalex.org/W2626991402","https://openalex.org/W2657126969","https://openalex.org/W2931743911","https://openalex.org/W2950094539","https://openalex.org/W2963674932","https://openalex.org/W2964080840","https://openalex.org/W2964299589","https://openalex.org/W4234059337","https://openalex.org/W4239813889","https://openalex.org/W4242495425","https://openalex.org/W4297775537","https://openalex.org/W6635810480","https://openalex.org/W6640289440","https://openalex.org/W6640860923","https://openalex.org/W6677580257","https://openalex.org/W6682843658","https://openalex.org/W6702085493","https://openalex.org/W6737664043","https://openalex.org/W6746512655","https://openalex.org/W6764076272"],"related_works":["https://openalex.org/W2133489088","https://openalex.org/W2363769136","https://openalex.org/W2404820046","https://openalex.org/W2012518269","https://openalex.org/W2086718556","https://openalex.org/W2146079099","https://openalex.org/W2109715593","https://openalex.org/W1965891727","https://openalex.org/W57688818","https://openalex.org/W1860107648"],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"have":[4],"transformed":[5],"the":[6,13,42,81,99,114,166,172,197,209],"field":[7],"of":[8,46,102,109,116],"artificial":[9],"intelligence":[10,30],"and":[11,38,176,184,187,194,230],"represent":[12],"state-of-the-art":[14,205],"in":[15,24,31,55,149,216,223,234],"many":[16],"machine":[17],"learning":[18],"tasks.":[19],"There":[20],"is":[21],"considerable":[22],"interest":[23],"using":[25],"DNNs":[26,47,77,206],"to":[27,52,60,72,78,98,139,191,196,220,236],"realize":[28],"edge":[29],"highly":[32],"resource-constrained":[33],"devices":[34,68],"such":[35],"as":[36],"wearables":[37],"IoT":[39],"sensors.":[40],"Unfortunately,":[41],"high":[43],"computational":[44],"requirements":[45],"pose":[48],"a":[49,106,128,133,150,181,237],"serious":[50],"challenge":[51,93],"their":[53],"deployment":[54],"these":[56,67],"systems.":[57],"Moreover,":[58],"due":[59],"tight":[61],"cost":[62],"(and":[63],"hence,":[64],"area)":[65],"constraints,":[66],"are":[69],"often":[70],"unable":[71],"accommodate":[73],"hardware":[74],"accelerators,":[75],"requiring":[76],"execute":[79],"on":[80,132,203],"General":[82],"Purpose":[83],"Processor":[84],"(GPP)":[85],"cores":[86],"that":[87,104,126],"they":[88],"contain.":[89],"We":[90,119,200],"address":[91,156],"this":[92],"through":[94],"lightweight":[95],"micro-architectural":[96],"extensions":[97],"memory":[100],"hierarchy":[101],"GPPs":[103],"exploit":[105],"key":[107],"attribute":[108],"DNNs,":[110],"viz.":[111],"sparsity,":[112],"or":[113],"prevalence":[115],"zero":[117],"values.":[118],"propose":[120],"SparseCache,":[121],"an":[122],"enhanced":[123],"cache":[124,130,143,162,168],"architecture":[125],"utilizes":[127,180],"null":[129,198],"based":[131],"Ternary":[134],"Content":[135],"Addressable":[136],"Memory":[137],"(TCAM)":[138],"compactly":[140],"store":[141],"zero-valued":[142,161],"lines,":[144,163],"while":[145],"storing":[146,155],"non-zero":[147],"lines":[148],"conventional":[151],"data":[152],"cache.":[153,199],"By":[154],"rather":[157],"than":[158],"values":[159],"for":[160],"SparseCache":[164,179,202,212],"increases":[165],"effective":[167],"capacity,":[169],"thereby":[170],"reducing":[171],"overall":[173],"miss":[174],"rate":[175],"execution":[177,224],"time.":[178],"Zero":[182],"Detector":[183],"Approximator":[185],"(ZDA)":[186],"Address":[188],"Merger":[189],"(AM)":[190],"perform":[192],"reads":[193],"writes":[195],"evaluate":[201],"four":[204],"programmed":[207],"with":[208,226],"Caffe":[210],"framework.":[211],"achieves":[213],"5-28%":[214],"reduction":[215,222],"miss-rate,":[217],"which":[218],"translates":[219],"5-21%":[221],"time,":[225],"only":[227],"0.1%":[228],"area":[229],"3.8%":[231],"power":[232],"overhead":[233],"comparison":[235],"low-end":[238],"Intel":[239],"Atom":[240],"Z-series":[241],"processor.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}