{"id":"https://openalex.org/W3207265322","doi":"https://doi.org/10.1145/3466752.3480123","title":"Distilling Bit-level Sparsity Parallelism for General Purpose Deep Learning Acceleration","display_name":"Distilling Bit-level Sparsity Parallelism for General Purpose Deep Learning Acceleration","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3207265322","doi":"https://doi.org/10.1145/3466752.3480123","mag":"3207265322"},"language":"en","primary_location":{"id":"doi:10.1145/3466752.3480123","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3466752.3480123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture","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/A5014244388","display_name":"Hang L\u00fc","orcid":"https://orcid.org/0000-0001-6233-3538"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hang Lu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038647640","display_name":"Liang Chang","orcid":"https://orcid.org/0000-0002-6685-5576"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Chang","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398932","display_name":"Chenglong Li","orcid":"https://orcid.org/0000-0002-7233-2739"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705740","display_name":"Zixuan Zhu","orcid":"https://orcid.org/0009-0000-2925-7975"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Zhu","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109513441","display_name":"Shengjian Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengjian Lu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103111619","display_name":"Yanhuan Liu","orcid":"https://orcid.org/0009-0003-7151-6549"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhuan Liu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101985755","display_name":"Mingzhe Zhang","orcid":"https://orcid.org/0000-0002-6440-7550"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingzhe Zhang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5014244388"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":2.7119,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.91977231,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"963","last_page":"976"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9966999888420105,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9908000230789185,"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":0.8468539714813232},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.733124315738678},{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.6445229649543762},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.620603621006012},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5995801687240601},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5929104089736938},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5307177305221558},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49417784810066223},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4901350438594818},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.46802574396133423},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4332966208457947},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4306981861591339},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34300315380096436},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3325296640396118},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.26338231563568115},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2617378234863281},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2136915624141693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8468539714813232},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.733124315738678},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.6445229649543762},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.620603621006012},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5995801687240601},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5929104089736938},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5307177305221558},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49417784810066223},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4901350438594818},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.46802574396133423},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4332966208457947},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4306981861591339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34300315380096436},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3325296640396118},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.26338231563568115},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2617378234863281},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2136915624141693},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3466752.3480123","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3466752.3480123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1191365092","https://openalex.org/W2117539524","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2442974303","https://openalex.org/W2541839172","https://openalex.org/W2625457103","https://openalex.org/W2769654144","https://openalex.org/W2819476901","https://openalex.org/W2895531329","https://openalex.org/W2931118404","https://openalex.org/W2945146780","https://openalex.org/W2979439447","https://openalex.org/W2979590285","https://openalex.org/W2998470761","https://openalex.org/W3014447010","https://openalex.org/W3036405789","https://openalex.org/W3102015846","https://openalex.org/W3102659484","https://openalex.org/W3104962140","https://openalex.org/W4230315356","https://openalex.org/W4245536296","https://openalex.org/W4245551996","https://openalex.org/W4252829690","https://openalex.org/W4253550658","https://openalex.org/W4255556797","https://openalex.org/W4299412296","https://openalex.org/W6600291067"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2532502681","https://openalex.org/W2586397364","https://openalex.org/W4319952061","https://openalex.org/W4280636456","https://openalex.org/W4388913998","https://openalex.org/W4310584535","https://openalex.org/W4295935044","https://openalex.org/W4307927141","https://openalex.org/W3159906349"],"abstract_inverted_index":{"Along":[0],"with":[1],"the":[2,9,17,33,42,52,57,61,104],"rapid":[3],"evolution":[4],"of":[5],"deep":[6,100],"neural":[7],"networks,":[8],"ever-increasing":[10],"complexity":[11],"imposes":[12],"formidable":[13],"computation":[14],"intensity":[15],"to":[16,39,59,82,109,126,147],"hardware":[18],"accelerator.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23],"propose":[24],"a":[25,72],"novel":[26],"computing":[27],"philosophy":[28],"called":[29,37],"\u201cbit":[30],"interleaving\u201d":[31],"and":[32,78,93,140,150,161],"associate":[34],"accelerator":[35],"design":[36],"\u201cBitlet\u201d":[38],"maximally":[40],"exploit":[41],"bit-level":[43],"sparsity.":[44],"Apart":[45],"from":[46,80,144],"existing":[47],"bit-serial/parallel":[48],"accelerators,":[49],"Bitlet":[50,64,87],"leverages":[51],"abundant":[53],"\u201csparsity":[54],"parallelism\u201d":[55],"in":[56],"parameters":[58],"enforce":[60],"inference":[62,92],"acceleration.":[63],"is":[65],"versatile":[66],"by":[67,159],"supporting":[68],"diverse":[69],"precisions":[70],"on":[71,97],"single":[73],"platform,":[74],"including":[75],"floating-point":[76],"32":[77],"fixed-point":[79,135],"1b":[81],"24b.":[83],"The":[84],"versatility":[85],"enables":[86],"feasible":[88],"for":[89,117],"both":[90],"efficient":[91],"training.":[94],"Empirical":[95],"studies":[96],"12":[98],"domain-specific":[99],"learning":[101],"applications":[102],"highlight":[103],"following":[105],"results:":[106],"(1)":[107],"up":[108,125],"81":[110],"\u00d7":[111,113,128,130],"/21":[112],"energy":[114],"efficiency":[115],"improvement":[116],"training/inference":[118],"over":[119,133],"recent":[120],"high":[121],"performance":[122],"GPUs;":[123],"(2)":[124],"15":[127],"/8":[129],"higher":[131],"speedup/efficiency":[132],"state-of-the-art":[134],"accelerators;":[136],"(3)":[137],"1.5mm2":[138],"area":[139],"scalable":[141],"power":[142],"consumption":[143],"570mW":[145],"(float32)":[146],"432mW":[148],"(16b)":[149],"365mW":[151],"(8b)":[152],"@28nm":[153],"TSMC;":[154],"(4)":[155],"highly":[156],"configurable":[157],"justified":[158],"ablation":[160],"sensitivity":[162],"studies.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}