{"id":"https://openalex.org/W4416798425","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249175","title":"Efficient Sparse Matrix Acceleration for Deep Learning via Two-Step Bitmap Tensor Architecture","display_name":"Efficient Sparse Matrix Acceleration for Deep Learning via Two-Step Bitmap Tensor Architecture","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798425","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249175"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5112832494","display_name":"Jia-Hong Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["SG","TW"],"is_corresponding":false,"raw_author_name":"Jia-Hong Weng","raw_affiliation_strings":["Institutes of Microelectronics, National Cheng Kung University,Tainan City,Taiwan,701401"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institutes of Microelectronics, National Cheng Kung University,Tainan City,Taiwan,701401","institution_ids":["https://openalex.org/I91807558","https://openalex.org/I4210090209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104176657","display_name":"Yuan-Jin Lin","orcid":"https://orcid.org/0009-0004-2429-4143"},"institutions":[{"id":"https://openalex.org/I4210120917","display_name":"Taiwan Semiconductor Manufacturing Company (Taiwan)","ror":"https://ror.org/02wx79d08","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210120917"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Jin Lin","raw_affiliation_strings":["National Cheng Kung University,Program on Semiconductor Manufacturing Technology, Academy of Innovative Semiconductor and Sustainable Manufacturing,Tainan City,Taiwan,701401"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Program on Semiconductor Manufacturing Technology, Academy of Innovative Semiconductor and Sustainable Manufacturing,Tainan City,Taiwan,701401","institution_ids":["https://openalex.org/I4210120917"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wan-Hsun Tsai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["SG","TW"],"is_corresponding":false,"raw_author_name":"Wan-Hsun Tsai","raw_affiliation_strings":["Institutes of Microelectronics, National Cheng Kung University,Tainan City,Taiwan,701401"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institutes of Microelectronics, National Cheng Kung University,Tainan City,Taiwan,701401","institution_ids":["https://openalex.org/I91807558","https://openalex.org/I4210090209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101620888","display_name":"Yujie Yang","orcid":"https://orcid.org/0000-0001-7222-0019"},"institutions":[{"id":"https://openalex.org/I4210120917","display_name":"Taiwan Semiconductor Manufacturing Company (Taiwan)","ror":"https://ror.org/02wx79d08","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210120917"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Jie Yang","raw_affiliation_strings":["National Cheng Kung University,Program on Semiconductor Manufacturing Technology, Academy of Innovative Semiconductor and Sustainable Manufacturing,Tainan City,Taiwan,701401"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Program on Semiconductor Manufacturing Technology, Academy of Innovative Semiconductor and Sustainable Manufacturing,Tainan City,Taiwan,701401","institution_ids":["https://openalex.org/I4210120917"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103325381","display_name":"Wei\u2010Chen Tu","orcid":"https://orcid.org/0000-0003-1134-5859"},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["SG","TW"],"is_corresponding":false,"raw_author_name":"Wei-Chen Tu","raw_affiliation_strings":["Institutes of Microelectronics, National Cheng Kung University,Tainan City,Taiwan,701401"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institutes of Microelectronics, National Cheng Kung University,Tainan City,Taiwan,701401","institution_ids":["https://openalex.org/I91807558","https://openalex.org/I4210090209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30913749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1297","last_page":"1300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.3474999964237213,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.3474999964237213,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.09059999883174896,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.07720000296831131,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6439999938011169},{"id":"https://openalex.org/keywords/bitmap","display_name":"Bitmap","score":0.6111000180244446},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5960999727249146},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5839999914169312},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5328999757766724},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5062999725341797},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.475600004196167},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4634000062942505},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4287000000476837},{"id":"https://openalex.org/keywords/interfacing","display_name":"Interfacing","score":0.426800012588501},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41429999470710754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.814300000667572},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6439999938011169},{"id":"https://openalex.org/C3115412","wikidata":"https://www.wikidata.org/wiki/Q1194708","display_name":"Bitmap","level":2,"score":0.6111000180244446},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5960999727249146},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5839999914169312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5638999938964844},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5328999757766724},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C2776303644","wikidata":"https://www.wikidata.org/wiki/Q1020499","display_name":"Interfacing","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3619999885559082},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3596000075340271},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3084000051021576},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.27869999408721924},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C65232700","wikidata":"https://www.wikidata.org/wiki/Q5656403","display_name":"Hardware architecture","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C2781003394","wikidata":"https://www.wikidata.org/wiki/Q737372","display_name":"Alphanumeric","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26499998569488525}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":10,"referenced_works":["https://openalex.org/W2604319603","https://openalex.org/W2953915593","https://openalex.org/W3016735325","https://openalex.org/W3162542754","https://openalex.org/W4378804782","https://openalex.org/W4379115862","https://openalex.org/W4399424818","https://openalex.org/W4401041682","https://openalex.org/W4403447496","https://openalex.org/W4406157245"],"related_works":[],"abstract_inverted_index":{"As":[0],"deep":[1,159],"learning":[2,160],"models":[3],"continue":[4],"to":[5,97,134],"scale":[6],"in":[7,19,158],"complexity,":[8],"their":[9],"computational,":[10],"memory,":[11],"and":[12,25,61,72,94,100,119,137,148],"energy":[13],"demands":[14],"become":[15],"increasingly":[16],"burdensome,":[17],"especially":[18],"applications":[20],"such":[21],"as":[22],"computer":[23],"vision":[24],"natural":[26],"language":[27],"processing.":[28],"To":[29,75],"address":[30],"these":[31],"challenges,":[32],"this":[33,77],"paper":[34],"proposes":[35],"a":[36,81],"novel":[37],"two-step":[38],"bitmap":[39],"compression":[40],"method":[41],"tailored":[42],"for":[43,85,154],"column-balanced,":[44],"block-wise":[45],"pruned":[46],"convolutional":[47],"neural":[48],"networks.":[49],"The":[50,102],"proposed":[51,152],"scheme":[52],"effectively":[53],"encodes":[54],"both":[55],"structured":[56],"sparsity":[57,63],"introduced":[58],"by":[59,65,116,122,140],"pruning":[60],"irregular":[62],"induced":[64],"activation":[66],"functions,":[67],"thereby":[68],"reducing":[69],"memory":[70],"overhead":[71],"data":[73,111,129],"movement.":[74],"support":[76],"format,":[78],"we":[79],"design":[80],"dedicated":[82],"hardware":[83],"accelerator":[84],"bidirectional":[86],"sparse":[87,156],"matrix":[88],"multiplication,":[89],"leveraging":[90],"the":[91,146,151],"Gustavson":[92],"dataflow":[93],"preprocessing":[95],"modules":[96],"maximize":[98],"throughput":[99],"efficiency.":[101],"system":[103],"demonstrates":[104],"significant":[105],"improvements:":[106],"at":[107,125],"50":[108,117],"%":[109,118,127,136],"sparsity,":[110,128],"transfer":[112,130],"time":[113,121,131,139],"is":[114,132],"reduced":[115,133],"computation":[120,138],"80":[123],"%;":[124],"75":[126],"25":[135],"85":[141],"%.":[142],"These":[143],"results":[144],"validate":[145],"effectiveness":[147],"scalability":[149],"of":[150],"solution":[153],"accelerating":[155],"inference":[157],"applications.":[161]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}