{"id":"https://openalex.org/W7133350456","doi":"https://doi.org/10.1109/isscc49663.2026.11409285","title":"SMoLPU: 122.1\u00b5J/Token Sparse MoE-Based Speculative Decoding Language Processing Unit with Adaptive-Offload NPU-CIM Core","display_name":"SMoLPU: 122.1\u00b5J/Token Sparse MoE-Based Speculative Decoding Language Processing Unit with Adaptive-Offload NPU-CIM Core","publication_year":2026,"publication_date":"2026-02-15","ids":{"openalex":"https://openalex.org/W7133350456","doi":"https://doi.org/10.1109/isscc49663.2026.11409285"},"language":null,"primary_location":{"id":"doi:10.1109/isscc49663.2026.11409285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isscc49663.2026.11409285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Solid-State Circuits Conference (ISSCC)","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/A5083733804","display_name":"Sangwoo Ha","orcid":"https://orcid.org/0000-0002-9191-6326"},"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":"Sangwoo Ha","raw_affiliation_strings":["KAIST,Daejeon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127979699","display_name":"Jingu Lee","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":"Jingu Lee","raw_affiliation_strings":["KAIST,Daejeon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128034735","display_name":"Youngjin Moon","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":"Youngjin Moon","raw_affiliation_strings":["KAIST,Daejeon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114880908","display_name":"Sunjoo Whang","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":"Sunjoo Whang","raw_affiliation_strings":["KAIST,Daejeon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015963917","display_name":"Wooyoung Jo","orcid":"https://orcid.org/0000-0003-3598-3572"},"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":"Wooyoung Jo","raw_affiliation_strings":["KAIST,Daejeon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029169930","display_name":"Gwangtae Park","orcid":"https://orcid.org/0000-0002-9132-0311"},"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":"Gwangtae Park","raw_affiliation_strings":["KAIST,Daejeon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000767990","display_name":"S. -P. Kim","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":"Sangjin Kim","raw_affiliation_strings":["KAIST,Daejeon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074016364","display_name":"Soyeon Um","orcid":"https://orcid.org/0000-0002-8526-2047"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soyeon Um","raw_affiliation_strings":["Massachusetts Institute of Technology,Cambridge,MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Cambridge,MA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027286037","display_name":"Junha Ryu","orcid":"https://orcid.org/0000-0001-8147-3085"},"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":"Junha Ryu","raw_affiliation_strings":["KAIST,Daejeon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127964166","display_name":"Yurim Jo","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":"Yurim Jo","raw_affiliation_strings":["KAIST,Daejeon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127942058","display_name":"Hoi-Jun Yoo","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":"Hoi-Jun Yoo","raw_affiliation_strings":["KAIST,Daejeon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"312","last_page":"314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2565999925136566,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.2565999925136566,"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"}},{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.040699999779462814,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.03999999910593033,"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/decoding-methods","display_name":"Decoding methods","score":0.5986999869346619},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4715999960899353},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.4327999949455261},{"id":"https://openalex.org/keywords/adder","display_name":"Adder","score":0.40849998593330383},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.40049999952316284},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.3926999866962433},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.3555999994277954}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796999990940094},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5986999869346619},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4715999960899353},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4674000144004822},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C164620267","wikidata":"https://www.wikidata.org/wiki/Q376953","display_name":"Adder","level":3,"score":0.40849998593330383},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3391999900341034},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32249999046325684},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.2994000017642975},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2547999918460846},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isscc49663.2026.11409285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isscc49663.2026.11409285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Solid-State Circuits Conference (ISSCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5035213232040405}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W4360606939","https://openalex.org/W4399146344","https://openalex.org/W4408182783","https://openalex.org/W4408183246","https://openalex.org/W4412963705","https://openalex.org/W4412966175"],"related_works":[],"abstract_inverted_index":{"SMoLPU":[0],"is":[1],"an":[2,10],"energy-efficient":[3],"MoE-based":[4],"speculative":[5],"decoding":[6],"LLM":[7,72],"processor":[8,73],"with":[9],"NPU-CIM":[11,40],"core.":[12],"It":[13],"has":[14],"3":[15],"features:":[16],"1)":[17],"Token-adaptive":[18],"expert":[19,23,27],"refinement":[20],"removes":[21],"redundant":[22],"activations":[24],"and":[25,42],"schedules":[26],"load":[28],"order,":[29],"achieving$2.3":[30],"\\times/4.2":[31],"\\times$energy":[32],"efficiency":[33],"improvement":[34],"in":[35],"prefill/decode;":[36],"2)":[37],"An":[38],"adaptive-offload":[39],"core":[41],"a":[43],"top":[44],"scheduling":[45],"unit":[46],"maintain":[47],"HW":[48],"utilization":[49],"under":[50],"dynamic":[51,68],"INT\u2013FP":[52],"ratios,":[53],"achieving$3.3":[54],"\\times$lower":[55],"latency;":[56],"3)":[57],"A":[58],"reconfigurable":[59],"DRAM-based":[60],"LUT-CIM":[61],"reduces":[62],"adder":[63],"tree":[64],"power/area,":[65],"while":[66],"supporting":[67],"input":[69],"size.":[70],"The":[71],"achieves":[74],"43.5%":[75],"lower":[76],"energy":[77],"per":[78],"parameter":[79],"than":[80],"prior":[81],"SOTA.":[82]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-03-04T00:00:00"}
