{"id":"https://openalex.org/W4411725637","doi":"https://doi.org/10.1109/iscas56072.2025.11044026","title":"SSMA: A Memory-Efficient Accelerator for State Space Model in the Mamba","display_name":"SSMA: A Memory-Efficient Accelerator for State Space Model in the Mamba","publication_year":2025,"publication_date":"2025-05-25","ids":{"openalex":"https://openalex.org/W4411725637","doi":"https://doi.org/10.1109/iscas56072.2025.11044026"},"language":"en","primary_location":{"id":"doi:10.1109/iscas56072.2025.11044026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas56072.2025.11044026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102515657","display_name":"Qiwei Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiwei Dong","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347369","display_name":"Siyu Zhang","orcid":"https://orcid.org/0000-0001-5531-8655"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Zhang","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100696999","display_name":"Zhongfeng Wang","orcid":"https://orcid.org/0000-0002-7227-4786"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongfeng Wang","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":5.019,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95229176,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.314300000667572,"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"}},"topics":[{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.314300000667572,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.626128613948822},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4735628366470337},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4455627501010895},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2735310196876526},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09982150793075562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.626128613948822},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4735628366470337},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4455627501010895},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2735310196876526},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09982150793075562}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas56072.2025.11044026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas56072.2025.11044026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2795915628","https://openalex.org/W2906043559","https://openalex.org/W2910396952","https://openalex.org/W3004421177","https://openalex.org/W3027324516","https://openalex.org/W3094502228","https://openalex.org/W3138516171","https://openalex.org/W4360770950","https://openalex.org/W4360832001","https://openalex.org/W4385187240","https://openalex.org/W4387789586","https://openalex.org/W4393141090","https://openalex.org/W4402904179","https://openalex.org/W4403727496","https://openalex.org/W4403842425"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Mamba":[0],"has":[1],"exhibited":[2],"great":[3],"potential":[4],"across":[5],"various":[6],"tasks,":[7],"achieving":[8],"the":[9,23,60,82,106,123,143,148],"powerful":[10],"capability":[11],"of":[12,26],"long-sequence":[13],"modeling":[14],"with":[15,147],"linear":[16],"complexity.":[17],"Selective":[18,63,88],"State":[19],"Space":[20],"Models":[21],"(SSMs),":[22],"core":[24],"component":[25],"Mamba,":[27],"possess":[28],"unique":[29],"computational":[30],"flow":[31],"and":[32,45,75,84,110,117,136],"massive":[33],"memory":[34,115],"requirements,":[35],"which":[36],"pose":[37],"new":[38],"challenges":[39],"for":[40],"deployment":[41],"on":[42,127],"edge":[43],"devices":[44],"are":[46],"difficult":[47],"to":[48,79,98,133],"be":[49],"efficiently":[50,80],"supported":[51],"by":[52,103],"existing":[53],"deep":[54],"learning":[55],"accelerators.":[56],"Therefore,":[57],"we":[58,69,91],"develop":[59],"first":[61],"memory-efficient":[62],"SSM":[64,111],"Accelerator,":[65],"namely":[66],"SSMA.":[67],"Specifically,":[68],"design":[70],"a":[71,93],"reconfigurable":[72],"hardware":[73],"architecture":[74],"low-complexity":[76],"nonlinear":[77],"units":[78],"execute":[81],"rearranged":[83],"fused":[85],"operations":[86],"in":[87],"SSM.":[89],"Moreover,":[90],"introduce":[92],"novel":[94],"tile-stationary":[95],"recurrent":[96],"dataflow":[97],"achieve":[99],"on-chip":[100],"layer":[101],"fusion":[102],"recurrently":[104],"updating":[105],"tiled":[107],"latent":[108],"state":[109],"parameters,":[112],"dramatically":[113],"decreasing":[114],"usage":[116],"access.":[118],"Experimental":[119],"results":[120],"show":[121],"that":[122],"proposed":[124],"SSMA,":[125],"evaluated":[126],"Xilinx":[128],"ZCU102":[129],"FPGA,":[130],"achieves":[131],"up":[132],"3.33\u00d7":[134],"speedup":[135],"41.8":[137],"\u00d7":[138],"higher":[139],"energy":[140],"efficiency":[141],"than":[142],"optimized":[144],"GPU":[145],"implementation":[146],"same":[149],"setting.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}