{"id":"https://openalex.org/W4414153888","doi":"https://doi.org/10.1109/lca.2025.3609283","title":"A Quantitative Analysis of Mamba-2-Based Large Language Model: Study of State Space Duality","display_name":"A Quantitative Analysis of Mamba-2-Based Large Language Model: Study of State Space Duality","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4414153888","doi":"https://doi.org/10.1109/lca.2025.3609283"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2025.3609283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2025.3609283","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/A5032340064","display_name":"Gi-Yong Yang","orcid":"https://orcid.org/0009-0006-4204-5081"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Gyeongrok Yang","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001799808","display_name":"Jaeha Min","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeha Min","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102418138","display_name":"In Ha Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"In-Jun Jung","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100447377","display_name":"Joo-Young Kim","orcid":"https://orcid.org/0000-0003-1099-1496"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joo-Young Kim","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032340064"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36135153,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"2","first_page":"309","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.14059999585151672,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.14059999585151672,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/duality","display_name":"Duality (order theory)","score":0.6869000196456909},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5746999979019165},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5715000033378601},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5475999712944031},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5460000038146973},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.53329998254776},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5077999830245972},{"id":"https://openalex.org/keywords/quantitative-analysis","display_name":"Quantitative analysis (chemistry)","score":0.4449000060558319}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562999725341797},{"id":"https://openalex.org/C2778023678","wikidata":"https://www.wikidata.org/wiki/Q554403","display_name":"Duality (order theory)","level":2,"score":0.6869000196456909},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5746999979019165},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5715000033378601},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5460000038146973},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.53329998254776},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5217000246047974},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5077999830245972},{"id":"https://openalex.org/C95986675","wikidata":"https://www.wikidata.org/wiki/Q185168","display_name":"Quantitative analysis (chemistry)","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34049999713897705},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.336899995803833},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3271999955177307},{"id":"https://openalex.org/C151342819","wikidata":"https://www.wikidata.org/wiki/Q62542","display_name":"Phase space","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C130187892","wikidata":"https://www.wikidata.org/wiki/Q133327","display_name":"Spacetime","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2025.3609283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2025.3609283","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4308083513","https://openalex.org/W4400276831"],"related_works":["https://openalex.org/W2593555778","https://openalex.org/W4253372294","https://openalex.org/W88297779","https://openalex.org/W2026789159","https://openalex.org/W2384039353","https://openalex.org/W2165483356","https://openalex.org/W2160662427","https://openalex.org/W183833198","https://openalex.org/W2089739134","https://openalex.org/W4205852385"],"abstract_inverted_index":{"Mamba":[0,23],"is":[1],"based":[2],"on":[3,87],"a":[4,66,74],"state":[5,49],"space":[6,50],"model":[7],"(SSM)":[8],"to":[9,27],"address":[10],"limitations":[11],"of":[12,41,77,96],"attention-based":[13,28],"large":[14],"language":[15],"models":[16],"(LLMs)":[17],"associated":[18],"with":[19],"long-context":[20],"processing.":[21,58],"While":[22],"achieves":[24],"accuracy":[25],"comparable":[26],"LLMs,":[29],"it":[30],"introduces":[31,47],"recurrent":[32],"computation":[33],"that":[34],"limits":[35],"efficiency":[36],"during":[37,56],"the":[38,48,93,100],"prefill":[39],"phase":[40],"inference.":[42],"To":[43],"mitigate":[44],"this,":[45],"Mamba-2":[46],"duality":[51],"(SSD),":[52],"which":[53],"increases":[54],"parallelism":[55],"multi-token":[57],"However,":[59],"its":[60,82,105],"workload":[61],"characteristics":[62,95],"remain":[63],"unexamined":[64],"from":[65],"systems":[67],"and":[68,84,98,113],"architectural":[69,102],"perspective.":[70],"This":[71],"work":[72],"presents":[73],"system-level":[75],"analysis":[76],"SSD":[78,97],"in":[79,119],"Mamba2,":[80],"characterizing":[81],"compute":[83],"memory":[85],"behavior":[86],"modern":[88],"hardware.":[89],"Our":[90],"findings":[91],"reveal":[92],"computational":[94],"provide":[99],"first":[101],"insight":[103],"into":[104],"execution.":[106],"In":[107],"addition,":[108],"we":[109],"identify":[110],"performance":[111],"bottlenecks":[112],"propose":[114],"directions":[115],"for":[116],"addressing":[117],"them":[118],"future":[120],"work.":[121]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
