{"id":"https://openalex.org/W4416429564","doi":"https://doi.org/10.1109/iccad66269.2025.11240738","title":"SPIMA: Scalable and Cost-Efficient Sparse Matrix Multiplication via Processing in DRAM Array","display_name":"SPIMA: Scalable and Cost-Efficient Sparse Matrix Multiplication via Processing in DRAM Array","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W4416429564","doi":"https://doi.org/10.1109/iccad66269.2025.11240738"},"language":null,"primary_location":{"id":"doi:10.1109/iccad66269.2025.11240738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240738","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/A5120368060","display_name":"Tairali Assylbekov","orcid":null},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Tairali Assylbekov","raw_affiliation_strings":["Ulsan National Institute of Science and Technology (UNIST),Department of Electrical Engineering,Ulsan,Korea"],"affiliations":[{"raw_affiliation_string":"Ulsan National Institute of Science and Technology (UNIST),Department of Electrical Engineering,Ulsan,Korea","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102938734","display_name":"Minsang Yu","orcid":"https://orcid.org/0000-0002-2515-1601"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsang Yu","raw_affiliation_strings":["Ulsan National Institute of Science and Technology (UNIST),Department of Electrical Engineering,Ulsan,Korea"],"affiliations":[{"raw_affiliation_string":"Ulsan National Institute of Science and Technology (UNIST),Department of Electrical Engineering,Ulsan,Korea","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359860","display_name":"Jaewoo Park","orcid":"https://orcid.org/0000-0002-6477-9813"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewoo Park","raw_affiliation_strings":["Ulsan National Institute of Science and Technology (UNIST),Department of Computer Science and Engineering,Ulsan,Korea"],"affiliations":[{"raw_affiliation_string":"Ulsan National Institute of Science and Technology (UNIST),Department of Computer Science and Engineering,Ulsan,Korea","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049499414","display_name":"Min\u2010Gon Kim","orcid":"https://orcid.org/0000-0002-3525-0048"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mingon Kim","raw_affiliation_strings":["Ulsan National Institute of Science and Technology (UNIST),Department of Computer Science and Engineering,Ulsan,Korea"],"affiliations":[{"raw_affiliation_string":"Ulsan National Institute of Science and Technology (UNIST),Department of Computer Science and Engineering,Ulsan,Korea","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111262396","display_name":"Seungsu Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungsu Kim","raw_affiliation_strings":["Ulsan National Institute of Science and Technology (UNIST),Department of Electrical Engineering,Ulsan,Korea"],"affiliations":[{"raw_affiliation_string":"Ulsan National Institute of Science and Technology (UNIST),Department of Electrical Engineering,Ulsan,Korea","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100780257","display_name":"Jongeun Lee","orcid":"https://orcid.org/0000-0003-1523-2974"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongeun Lee","raw_affiliation_strings":["Ulsan National Institute of Science and Technology (UNIST),Department of Electrical Engineering,Ulsan,Korea"],"affiliations":[{"raw_affiliation_string":"Ulsan National Institute of Science and Technology (UNIST),Department of Electrical Engineering,Ulsan,Korea","institution_ids":["https://openalex.org/I48566637"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5120368060"],"corresponding_institution_ids":["https://openalex.org/I48566637"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41070859,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9447000026702881,"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":0.9447000026702881,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.011099999770522118,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.010200000368058681,"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/dram","display_name":"Dram","score":0.683899998664856},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.632099986076355},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5942000150680542},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5827999711036682},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4997999966144562},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4819999933242798},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4733999967575073},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.43939998745918274},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.4009000062942505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8238000273704529},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7421000003814697},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.683899998664856},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.632099986076355},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5942000150680542},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5827999711036682},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4997999966144562},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4819999933242798},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4733999967575073},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.4009000062942505},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3312999904155731},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.31859999895095825},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3093999922275543},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C134757568","wikidata":"https://www.wikidata.org/wiki/Q274089","display_name":"Heap (data structure)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C161824985","wikidata":"https://www.wikidata.org/wiki/Q919509","display_name":"Vector processor","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad66269.2025.11240738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240738","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2029924454","https://openalex.org/W2034102265","https://openalex.org/W2035080386","https://openalex.org/W2069277577","https://openalex.org/W2084990336","https://openalex.org/W2116341502","https://openalex.org/W2119609467","https://openalex.org/W2572767837","https://openalex.org/W2725159389","https://openalex.org/W2794952988","https://openalex.org/W2997945685","https://openalex.org/W3002603762","https://openalex.org/W3006586535","https://openalex.org/W3016542674","https://openalex.org/W3016735325","https://openalex.org/W3016832937","https://openalex.org/W3100710793","https://openalex.org/W3103168911","https://openalex.org/W3134274954","https://openalex.org/W3146763006","https://openalex.org/W3158831985","https://openalex.org/W3198975860","https://openalex.org/W4221001402","https://openalex.org/W4229370543","https://openalex.org/W4239366869","https://openalex.org/W4241140669","https://openalex.org/W4285121610","https://openalex.org/W4285335127","https://openalex.org/W4312678586","https://openalex.org/W4318540786","https://openalex.org/W4378804782","https://openalex.org/W4386765257","https://openalex.org/W4389500318","https://openalex.org/W4393145487","https://openalex.org/W4393407040"],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"matrix":[1,134],"multiplication":[2],"(SpMM)":[3],"is":[4],"a":[5,10,38,51,57,65,97],"critical":[6],"kernel":[7],"used":[8],"in":[9,131],"wide":[11],"range":[12],"of":[13,46,111,133],"applications,":[14],"but":[15],"irregular":[16],"memory":[17,21],"access":[18],"patterns":[19],"and":[20,32,73,77,100,127,136,147],"bandwidth":[22],"bottleneck":[23],"as":[24,26],"well":[25],"load":[27],"imbalance":[28],"make":[29],"the":[30,43,109,140],"efficient":[31],"scalable":[33],"processing":[34],"on":[35,56,144],"parallel":[36],"architectures":[37],"significant":[39],"challenge.":[40],"Motivated":[41],"by":[42],"memory-bound":[44],"nature":[45],"SpMM":[47,53],"computation,":[48],"we":[49,149],"propose":[50],"cost-effective":[52],"accelerator":[54],"based":[55],"DRAM":[58,95],"processing-in-memory":[59],"(PIM)":[60],"approach.":[61],"Our":[62,85,115],"design":[63],"introduces":[64],"novel":[66,113],"dataflow":[67,126],"to":[68,107],"exploit":[69],"high":[70],"bank-level":[71],"parallelism":[72],"reuse":[74],"both":[75],"input":[76,91],"output":[78,98],"data":[79],"even":[80],"for":[81,93],"highly":[82,160],"sparse":[83,120,161],"matrices.":[84,162],"proposed":[86,125],"architecture,":[87],"SPIMA,":[88],"features":[89],"multiple":[90],"buffers":[92],"scheduling":[94],"access,":[96],"buffer":[99],"vector":[101],"register":[102],"files":[103],"working":[104],"holistically,":[105],"co-designed":[106],"maximize":[108],"performance":[110,158],"our":[112,124,152],"dataflow.":[114],"experimental":[116],"results":[117],"using":[118],"various":[119],"matrices":[121],"demonstrate":[122],"that":[123,151],"architecture":[128,154],"are":[129],"robust":[130],"terms":[132],"size":[135],"sparsity.":[137],"Compared":[138],"with":[139,159],"state-of-the-art":[141],"accelerators":[142],"implemented":[143],"PIM,":[145],"ASIC,":[146],"FPGA,":[148],"estimate":[150],"PIM":[153],"can":[155],"yield":[156],"competitive":[157]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-20T00:00:00"}