{"id":"https://openalex.org/W4416429900","doi":"https://doi.org/10.1109/iccad66269.2025.11240912","title":"ScanNow: A Scan Window-Based Sparse Matrix Multiplication Accelerator Design","display_name":"ScanNow: A Scan Window-Based Sparse Matrix Multiplication Accelerator Design","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W4416429900","doi":"https://doi.org/10.1109/iccad66269.2025.11240912"},"language":"en","primary_location":{"id":"doi:10.1109/iccad66269.2025.11240912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","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/A5033576366","display_name":"Chunming Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Chaofang Ma","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007348638","display_name":"Lin Jiang","orcid":"https://orcid.org/0000-0003-3085-9847"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Lin Jiang","raw_affiliation_strings":["Northeastern University"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455077","display_name":"Zeyu Li","orcid":"https://orcid.org/0009-0001-5704-7817"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zeyu Li","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037594554","display_name":"Hanwei Fan","orcid":"https://orcid.org/0000-0002-1177-2108"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hanwei Fan","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014749523","display_name":"Maolin Wang","orcid":"https://orcid.org/0000-0001-7449-9834"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Maolin Wang","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013248987","display_name":"Jiang Xu","orcid":"https://orcid.org/0000-0001-9089-7752"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang Xu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (GZ)"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (GZ)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100441532","display_name":"Wei Zhang","orcid":"https://orcid.org/0009-0006-2358-299X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5033576366"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41495804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8709999918937683,"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":0.8709999918937683,"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":0.03539999946951866,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.016699999570846558,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6274999976158142},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5335999727249146},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5325999855995178},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5321999788284302},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5302000045776367},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5198000073432922},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5065000057220459},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4925999939441681},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.47690001130104065},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.46709999442100525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7867000102996826},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6274999976158142},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5335999727249146},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5325999855995178},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5321999788284302},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5302000045776367},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5198000073432922},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5065000057220459},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.47690001130104065},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46709999442100525},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4645000100135803},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4357999861240387},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4284999966621399},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42730000615119934},{"id":"https://openalex.org/C37724790","wikidata":"https://www.wikidata.org/wiki/Q210813","display_name":"Direct memory access","level":3,"score":0.42010000348091125},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.3903999924659729},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3750999867916107},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3662000000476837},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C118021083","wikidata":"https://www.wikidata.org/wiki/Q610398","display_name":"System on a chip","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2838999927043915},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2793000042438507},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C206274596","wikidata":"https://www.wikidata.org/wiki/Q1063837","display_name":"Programmable logic device","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.2615000009536743},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccad66269.2025.11240912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-168966","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-168966","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1665157575","https://openalex.org/W2035080386","https://openalex.org/W2039189705","https://openalex.org/W2089437293","https://openalex.org/W2096169320","https://openalex.org/W2285660444","https://openalex.org/W2574229471","https://openalex.org/W2725159389","https://openalex.org/W2794952988","https://openalex.org/W2979310060","https://openalex.org/W3004525272","https://openalex.org/W3012561096","https://openalex.org/W3016542674","https://openalex.org/W3016832937","https://openalex.org/W3040646053","https://openalex.org/W3103168911","https://openalex.org/W3155922894","https://openalex.org/W3184606595","https://openalex.org/W3205727737","https://openalex.org/W4230094279","https://openalex.org/W4309620166","https://openalex.org/W4318540786","https://openalex.org/W4381050447","https://openalex.org/W4389046642","https://openalex.org/W4390946831","https://openalex.org/W4391591405","https://openalex.org/W4395106386","https://openalex.org/W4401090539"],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"matrix-matrix":[1],"multiplication":[2],"(SpMM)":[3],"is":[4,140],"a":[5,29,76,85,129,163],"prevailing":[6],"kernel":[7],"in":[8,25],"scientific":[9],"and":[10,112,116,137,148],"artificial":[11],"intelligence":[12],"applications.":[13],"However,":[14],"the":[15,38,45,66,70,94,144,171],"irregular":[16,96],"memory":[17,97,135],"access":[18,98],"behaviors":[19,99],"caused":[20],"by":[21,100],"diverse":[22,55],"sparse":[23,126],"patterns":[24],"SpMM":[26,56,79,167],"lead":[27],"to":[28,53,59,92,124,142,170],"significant":[30],"performance":[31],"bottleneck":[32],"for":[33,40,120],"traditional":[34],"computing":[35],"platforms,":[36],"driving":[37],"demand":[39],"dedicated":[41],"hardware":[42,47,131,173],"accelerators.":[43],"Unfortunately,":[44],"existing":[46],"accelerators":[48],"are":[49],"not":[50],"flexible":[51],"enough":[52],"handle":[54],"workloads":[57,168],"due":[58],"their":[60],"rigid":[61],"task":[62,88,108,145],"dispatch":[63,89,109,146],"schemes,":[64],"limiting":[65],"overall":[67],"performance.To":[68],"address":[69],"challenge,":[71],"this":[72],"paper":[73],"introduces":[74],"ScanNow,":[75],"scan":[77,86],"window-based":[78,87],"accelerator":[80],"design.":[81],"ScanNow":[82,155],"first":[83],"presents":[84],"scheme":[90,110,147],"designed":[91],"minimize":[93],"time-consuming":[95],"exploiting":[101],"potential":[102],"data":[103,118],"reuse":[104,119],"opportunities.":[105],"The":[106],"proposed":[107,141],"effectively":[111],"dynamically":[113],"balances":[114],"input":[115],"output":[117],"row-wise":[121],"dataflow":[122],"according":[123],"real-time":[125],"patterns.":[127],"Moreover,":[128],"tailored":[130],"architecture,":[132],"featuring":[133],"multiple":[134],"components":[136],"customized":[138],"schedulers,":[139],"accommodate":[143],"improve":[149],"computation":[150],"parallelism.":[151],"Experiments":[152],"demonstrate":[153],"that":[154],"achieves":[156],"an":[157],"average":[158],"speedup":[159],"of":[160,166],"1.67x":[161],"across":[162],"wide":[164],"range":[165],"compared":[169],"state-of-the-art":[172],"accelerator.":[174]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-20T00:00:00"}
