{"id":"https://openalex.org/W4416749977","doi":"https://doi.org/10.1109/lca.2025.3637756","title":"CODA: A Computation-Driven Paradigm for Sparse DNN Acceleration","display_name":"CODA: A Computation-Driven Paradigm for Sparse DNN Acceleration","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4416749977","doi":"https://doi.org/10.1109/lca.2025.3637756"},"language":null,"primary_location":{"id":"doi:10.1109/lca.2025.3637756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2025.3637756","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","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/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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanhuan Liu","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101630070","display_name":"Wenming Li","orcid":"https://orcid.org/0000-0003-4069-2251"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenming Li","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014918710","display_name":"Kunming Zhang","orcid":"https://orcid.org/0000-0001-7088-8154"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunming Zhang","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086221754","display_name":"Tianyu Liu","orcid":"https://orcid.org/0000-0003-3905-6936"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Liu","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023098180","display_name":"Xiaochun Ye","orcid":"https://orcid.org/0000-0003-4598-1685"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochun Ye","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101472673","display_name":"Xuejun An","orcid":"https://orcid.org/0009-0005-0494-6332"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuejun An","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103111619"],"corresponding_institution_ids":["https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39677619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"2","first_page":"381","last_page":"384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.4797999858856201,"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":0.4797999858856201,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.13650000095367432,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.1339000016450882,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/dataflow","display_name":"Dataflow","score":0.8402000069618225},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7067999839782715},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6398000121116638},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5425999760627747},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.48080000281333923},{"id":"https://openalex.org/keywords/serialization","display_name":"Serialization","score":0.4417000114917755},{"id":"https://openalex.org/keywords/coda","display_name":"Coda","score":0.43470001220703125},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4189000129699707},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.3901999890804291},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.3869999945163727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8756999969482422},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8402000069618225},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7067999839782715},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6398000121116638},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.557699978351593},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5425999760627747},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C3962253","wikidata":"https://www.wikidata.org/wiki/Q852466","display_name":"Coda","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4189000129699707},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38830000162124634},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C67212190","wikidata":"https://www.wikidata.org/wiki/Q104851","display_name":"Firmware","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36739999055862427},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36500000953674316},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.29260000586509705},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C134066672","wikidata":"https://www.wikidata.org/wiki/Q1424639","display_name":"Payload (computing)","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2025.3637756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2025.3637756","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G919011926","display_name":null,"funder_award_id":"L234078","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2606722458","https://openalex.org/W2963163009","https://openalex.org/W3040024858","https://openalex.org/W4312910656","https://openalex.org/W4318540786","https://openalex.org/W4327930477","https://openalex.org/W4360831848","https://openalex.org/W4401212175","https://openalex.org/W4401895034"],"related_works":[],"abstract_inverted_index":{"The":[0],"spatial":[1],"dataflow":[2],"paradigm,":[3],"while":[4],"effective":[5],"for":[6,36,191],"dense":[7],"workloads,":[8],"collapses":[9],"on":[10],"unstructured":[11],"sparsity,":[12],"manifesting":[13],"as":[14],"a":[15,19,62,93,112,177,186],"profound":[16],"Twin":[17,144],"Crisis:":[18],"high":[20],"Latency":[21],"Overhead":[22],"(termed":[23],"the":[24,75,100,106,135,143,158],"<italic":[25,43,107,136],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[26,44,60,65,96,108,115,137,166,171,179],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Latency":[27,109],"Crisis</i>)":[28],"driven":[29],"by":[30,48,73],"slow,":[31],"dominant":[32],"offline":[33],"software":[34],"preprocessing":[35,101],"data":[37],"reordering":[38],"and":[39,41,133,155,176],"formatting,":[40],"an":[42],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Inefficiency":[45,138],"Crisis</i>":[46],"characterized":[47],"massive":[49],"pipeline":[50],"stalls":[51,132],"that":[52,68],"leave":[53],"hardware":[54,94],"underutilized.":[55],"This":[56],"paper":[57],"introduces":[58],"<bold":[59,64,95,114,165,170,178],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">CODA</b>,":[61],"novel":[63],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">computation-driven</b>":[66],"architecture":[67],"challenges":[69],"this":[70,85],"data-centric":[71],"model":[72],"shifting":[74],"focus":[76],"from":[77],"\u201cscheduling":[78],"data\u201d":[79],"to":[80,127,164],"\u201cdiscovering":[81],"work.\u201d":[82],"CODA":[83,146],"materializes":[84],"new":[86,188],"paradigm":[87],"through":[88],"two":[89],"core":[90],"innovations.":[91],"First,":[92],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Work":[97],"Tokenizer</b>":[98],"eliminates":[99],"bottleneck":[102],"on-the-fly,":[103],"directly":[104,141],"resolving":[105,142],"Crisis</i>.":[110,139],"Second,":[111],"scalable":[113],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Dynamic":[116],"Execution":[117],"Core</b>":[118],"performs":[119],"asynchronous,":[120],"pull-based":[121],"dispatch":[122],"of":[123],"computable":[124],"work":[125],"packets":[126],"idle":[128],"resources,":[129],"which":[130],"eradicates":[131],"solves":[134],"By":[140],"Crisis,":[145],"demonstrates":[147],"superior":[148],"performance":[149],"over":[150],"state-of-the-art":[151],"accelerators":[152],"like":[153],"Mentor":[154],"Hirac.":[156],"On":[157],"BERT-BASE":[159],"benchmark,":[160],"it":[161],"achieves":[162],"up":[163],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3.95\u00d7</b>":[167],"higher":[168],"speed,":[169],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3.4\u00d7</b>":[172],"greater":[173],"energy":[174],"efficiency,":[175],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3.1\u00d7</b>":[180],"reduction":[181],"in":[182],"end-to-end":[183],"latency,":[184],"establishing":[185],"necessary":[187],"architectural":[189],"blueprint":[190],"sparse":[192],"acceleration.":[193]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}