{"id":"https://openalex.org/W4403598877","doi":"https://doi.org/10.1109/tc.2024.3483632","title":"Bit-Sparsity Aware Acceleration With Compact CSD Code on Generic Matrix Multiplication","display_name":"Bit-Sparsity Aware Acceleration With Compact CSD Code on Generic Matrix Multiplication","publication_year":2024,"publication_date":"2024-10-21","ids":{"openalex":"https://openalex.org/W4403598877","doi":"https://doi.org/10.1109/tc.2024.3483632"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2024.3483632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3483632","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-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/A5101705740","display_name":"Zixuan Zhu","orcid":"https://orcid.org/0009-0000-2925-7975"},"institutions":[{"id":"https://openalex.org/I4210111959","display_name":"Shanghai Advanced Research Institute","ror":"https://ror.org/02br7py06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210111959"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Zhu","raw_affiliation_strings":["Shanghai Advanced Research Institute, Chinese Academy of Science, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-2925-7975","affiliations":[{"raw_affiliation_string":"Shanghai Advanced Research Institute, Chinese Academy of Science, Shanghai, China","institution_ids":["https://openalex.org/I4210111959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036387111","display_name":"Xiaolong Zhou","orcid":"https://orcid.org/0000-0003-0732-5169"},"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":"Xiaolong Zhou","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chundong Wang","orcid":"https://orcid.org/0000-0001-9069-2650"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chundong Wang","raw_affiliation_strings":["ShanghaiTech University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9069-2650","affiliations":[{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739638","display_name":"Tian Li","orcid":"https://orcid.org/0000-0001-7810-7711"},"institutions":[{"id":"https://openalex.org/I4210111959","display_name":"Shanghai Advanced Research Institute","ror":"https://ror.org/02br7py06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210111959"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Tian","raw_affiliation_strings":["Shanghai Advanced Research Institute, Chinese Academy of Science, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Advanced Research Institute, Chinese Academy of Science, Shanghai, China","institution_ids":["https://openalex.org/I4210111959"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zunkai Huang","orcid":"https://orcid.org/0000-0001-7501-8959"},"institutions":[{"id":"https://openalex.org/I4210111959","display_name":"Shanghai Advanced Research Institute","ror":"https://ror.org/02br7py06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210111959"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zunkai Huang","raw_affiliation_strings":["Shanghai Advanced Research Institute, Chinese Academy of Science, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7501-8959","affiliations":[{"raw_affiliation_string":"Shanghai Advanced Research Institute, Chinese Academy of Science, Shanghai, China","institution_ids":["https://openalex.org/I4210111959"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yongxin Zhu","orcid":"https://orcid.org/0000-0002-1813-1792"},"institutions":[{"id":"https://openalex.org/I4210111959","display_name":"Shanghai Advanced Research Institute","ror":"https://ror.org/02br7py06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210111959"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxin Zhu","raw_affiliation_strings":["Shanghai Advanced Research Institute, Chinese Academy of Science, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1813-1792","affiliations":[{"raw_affiliation_string":"Shanghai Advanced Research Institute, Chinese Academy of Science, Shanghai, China","institution_ids":["https://openalex.org/I4210111959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8523,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75431069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"74","issue":"2","first_page":"414","last_page":"426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9678000211715698,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9678000211715698,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9488000273704529,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9452000260353088,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6669995784759521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6387580037117004},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.6371919512748718},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6137776970863342},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.573612630367279},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.5308566689491272},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5148965120315552},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5143747925758362},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41780704259872437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33867090940475464},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1427198350429535},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12618166208267212},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.10062241554260254},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.07608357071876526}],"concepts":[{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6669995784759521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6387580037117004},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.6371919512748718},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6137776970863342},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.573612630367279},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.5308566689491272},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5148965120315552},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5143747925758362},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41780704259872437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33867090940475464},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1427198350429535},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12618166208267212},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.10062241554260254},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.07608357071876526},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2024.3483632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3483632","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G8997430418","display_name":null,"funder_award_id":"2023YFB2807001","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1856156113","https://openalex.org/W2143266288","https://openalex.org/W2153415113","https://openalex.org/W2172082768","https://openalex.org/W2194775991","https://openalex.org/W2417429787","https://openalex.org/W2521617467","https://openalex.org/W2541839172","https://openalex.org/W2931118404","https://openalex.org/W2962874694","https://openalex.org/W2982083293","https://openalex.org/W3134524932","https://openalex.org/W3160017297","https://openalex.org/W3207265322","https://openalex.org/W4221149185","https://openalex.org/W4307566804","https://openalex.org/W4308413540","https://openalex.org/W4385245566","https://openalex.org/W4386106780","https://openalex.org/W4387789741","https://openalex.org/W4389665191","https://openalex.org/W4390874575","https://openalex.org/W4403757510","https://openalex.org/W6684191040","https://openalex.org/W6763456558","https://openalex.org/W6810081322","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W2057797376","https://openalex.org/W2090319426","https://openalex.org/W752783541","https://openalex.org/W2506252583","https://openalex.org/W1506547947","https://openalex.org/W2048249848","https://openalex.org/W2067758538","https://openalex.org/W2995605830"],"abstract_inverted_index":{"The":[0],"ever-increasing":[1],"demand":[2],"for":[3,104,160],"matrix":[4,76],"multiplication":[5],"in":[6,39,56,156],"artificial":[7],"intelligence":[8],"(AI)":[9],"and":[10,24,37,48,108,117,133,140,158,163,179],"generic":[11,58,75],"computing":[12,18,59,191],"emphasizes":[13],"the":[14,110,124],"necessity":[15],"of":[16,126],"efficient":[17],"power":[19],"accommodating":[20],"both":[21,115,138,161],"floating-point":[22],"(FP)":[23],"quantized":[25],"integer":[26],"(QINT).":[27],"While":[28],"state-of-the-art":[29,168],"bit-sparsity-aware":[30],"acceleration":[31],"techniques":[32],"have":[33],"demonstrated":[34],"impressive":[35],"performance":[36,157],"efficiency":[38,159,183],"neural":[40],"networks":[41],"through":[42],"software-driven":[43],"methods":[44],"such":[45],"as":[46],"pruning":[47],"quantization,":[49],"these":[50],"approaches":[51],"are":[52,144],"not":[53],"always":[54],"feasible":[55],"typical":[57],"scenarios.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"propose":[65],"Bit-Cigma,":[66],"a":[67,99],"hardware-centric":[68],"architecture":[69],"that":[70],"leverages":[71],"bit-sparsity":[72],"to":[73,112,167],"accelerate":[74],"multiplication.":[77],"Bit-Cigma":[78,142,170],"features":[79],"(1)":[80],"CCSD":[81,121],"encoding,":[82],"an":[83],"optimized":[84],"on-chip":[85],"sparsification":[86],"technique":[87,103],"based":[88],"on":[89],"canonical":[90],"signed":[91],"digit":[92],"(CSD)":[93],"representation;":[94],"(2)":[95],"segmented":[96,134],"dot":[97,135],"product,":[98],"multi-stage":[100],"exponent":[101],"matching":[102],"long":[105],"FP":[106,116,162],"vectors;":[107],"(3)":[109],"versatility":[111],"efficiently":[113],"process":[114],"QINT":[118,164],"data":[119,187],"types.":[120],"encoding":[122,128],"halves":[123],"cost":[125],"CSD":[127],"while":[129,188],"achieving":[130],"optimal":[131],"bit-sparsity,":[132],"product":[136],"improves":[137],"accuracy":[139],"throughput.":[141],"cores":[143],"implemented":[145],"using":[146],"65":[147],"nm":[148],"technology":[149],"at":[150],"1":[151],"GHz,":[152],"demonstrating":[153],"substantial":[154],"gains":[155],"configurations.":[165],"Compared":[166],"Bitlet,":[169],"achieves":[171],"3.2<inline-formula><tex-math":[172],"notation=\"LaTeX\">$\\boldsymbol{\\times}$</tex-math></inline-formula>":[173,176,181],"performance,":[174],"6.1<inline-formula><tex-math":[175],"area":[177],"efficiency,":[178],"15.3<inline-formula><tex-math":[180],"energy":[182],"when":[184],"processing":[185],"FP32":[186],"ensuring":[189],"zero":[190],"error.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}
