{"id":"https://openalex.org/W7140321021","doi":"https://doi.org/10.1109/jetcas.2026.3677596","title":"FLARE: A Fine-Grained In-Memory Computing Heterogeneous Multi-Chiplet Accelerator for Large Language Models","display_name":"FLARE: A Fine-Grained In-Memory Computing Heterogeneous Multi-Chiplet Accelerator for Large Language Models","publication_year":2026,"publication_date":"2026-03-25","ids":{"openalex":"https://openalex.org/W7140321021","doi":"https://doi.org/10.1109/jetcas.2026.3677596"},"language":null,"primary_location":{"id":"doi:10.1109/jetcas.2026.3677596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jetcas.2026.3677596","pdf_url":null,"source":{"id":"https://openalex.org/S142323794","display_name":"IEEE Journal on Emerging and Selected Topics in Circuits and Systems","issn_l":"2156-3357","issn":["2156-3357","2156-3365"],"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 Journal on Emerging and Selected Topics in Circuits and Systems","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/A5130595327","display_name":"Abhishek Tyagi","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Abhishek Tyagi","raw_affiliation_strings":["College of Design and Engineering, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0001-4418-1590","affiliations":[{"raw_affiliation_string":"College of Design and Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zixuan Wang","orcid":"https://orcid.org/0009-0006-9486-3211"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zixuan Wang","raw_affiliation_strings":["College of Design and Engineering, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0006-9486-3211","affiliations":[{"raw_affiliation_string":"College of Design and Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026123240","display_name":"Avadh Harkishanka","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Avadh Harkishanka","raw_affiliation_strings":["College of Design and Engineering, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0004-0352-9839","affiliations":[{"raw_affiliation_string":"College of Design and Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130605616","display_name":"Hong Gao Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hong Gao Wong","raw_affiliation_strings":["College of Design and Engineering, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0002-2453-2784","affiliations":[{"raw_affiliation_string":"College of Design and Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070594442","display_name":"Bharadwaj Veeravalli","orcid":"https://orcid.org/0000-0001-9000-1813"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bharadwaj Veeravalli","raw_affiliation_strings":["College of Design and Engineering, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9000-1813","affiliations":[{"raw_affiliation_string":"College of Design and Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085588788","display_name":"Xuanyao Fong","orcid":"https://orcid.org/0000-0001-5939-7389"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xuanyao Fong","raw_affiliation_strings":["College of Design and Engineering, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5939-7389","affiliations":[{"raw_affiliation_string":"College of Design and Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42409532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"2","first_page":"500","last_page":"513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6172999739646912,"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":0.6172999739646912,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.07850000262260437,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.04650000110268593,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/data-modeling","display_name":"Data modeling","score":0.3021000027656555},{"id":"https://openalex.org/keywords/high-level-programming-language","display_name":"High-level programming language","score":0.28929999470710754},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.24819999933242798},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.243599995970726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7059999704360962},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.42730000615119934},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.31859999895095825},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C19024347","wikidata":"https://www.wikidata.org/wiki/Q211496","display_name":"High-level programming language","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.24819999933242798},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.24639999866485596},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.243599995970726},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.24199999868869781}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jetcas.2026.3677596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jetcas.2026.3677596","pdf_url":null,"source":{"id":"https://openalex.org/S142323794","display_name":"IEEE Journal on Emerging and Selected Topics in Circuits and Systems","issn_l":"2156-3357","issn":["2156-3357","2156-3365"],"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 Journal on Emerging and Selected Topics in Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1316736984","display_name":null,"funder_award_id":"NRF-CRP24-2020-0002","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G2413778509","display_name":null,"funder_award_id":"NRF-CRP24-2020-0003","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G6530144961","display_name":null,"funder_award_id":"MOE-T2EP50221-0008","funder_id":"https://openalex.org/F4320324070","funder_display_name":"Ministry of Education and Research, Romania"},{"id":"https://openalex.org/G7788264592","display_name":null,"funder_award_id":"MOE-T2EP50221-0008","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320324070","display_name":"Ministry of Education and Research, Romania","ror":"https://ror.org/00dh5gw98"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deploying":[0],"multi-billion-parameter":[1],"Large":[2],"Language":[3],"Models":[4],"(LLMs)":[5],"on":[6,181],"modern":[7],"AI":[8],"accelerators":[9],"requires":[10],"both":[11],"low-latency":[12],"communication":[13],"and":[14,30,36,42,67,94,128,134,171],"energy-efficient":[15],"computation.":[16],"Emerging":[17],"heterogeneous":[18,73],"in-memory":[19],"computing":[20],"(IMC)":[21],"architectures":[22,149],"offer":[23],"a":[24,49,72,79,111],"promising":[25],"solution":[26],"by":[27,78],"co-locating":[28],"compute":[29],"storage,":[31],"thereby":[32],"reducing":[33],"data":[34],"movement":[35],"power":[37],"consumption.":[38],"However,":[39],"efficiently":[40],"partitioning":[41],"distributing":[43],"model":[44],"workloads":[45],"across":[46],"cores":[47],"remains":[48],"key":[50],"open":[51],"challenge":[52],"in":[53],"multi-chiplet,":[54],"network-based":[55],"accelerator":[56,75],"systems":[57],"for":[58,89,139,147],"LLMs,":[59,143],"as":[60],"it":[61],"directly":[62],"impacts":[63],"the":[64,117,122,182],"workload\u2019s":[65],"performance":[66],"hardware":[68,97,136],"utilization.":[69],"We":[70],"present":[71],"multi-chiplet":[74],"architecture":[76],"accompanied":[77],"co-designed":[80],"fine-grained":[81],"hardware\u2013software":[82],"stack.":[83],"This":[84],"stack":[85],"incorporates":[86],"custom":[87],"algorithms":[88],"LLM":[90],"partitioning,":[91],"workload":[92],"mapping,":[93],"identification":[95],"of":[96,142],"configurations":[98],"that":[99,161],"ensure":[100],"efficient":[101],"execution.":[102],"In":[103],"contrast":[104],"to":[105,121,125,152,166,177],"prior":[106],"work,":[107],"our":[108,162],"methodology":[109],"adopts":[110],"bottom-up":[112],"perspective,":[113],"addressing":[114],"execution":[115],"from":[116],"core":[118],"level":[119],"up":[120,165],"chiplet-level":[123],"coordination":[124],"enable":[126],"scalability":[127],"flexible":[129],"dataflows.":[130],"Moreover,":[131],"we":[132,159],"assess":[133],"recommend":[135],"setups":[137],"optimized":[138],"different":[140],"classes":[141],"offering":[144],"practical":[145],"guidance":[146],"selecting":[148],"best":[150],"suited":[151],"specific":[153],"models.":[154],"Through":[155],"cycle-accurate":[156],"experimental":[157],"evaluation,":[158],"demonstrate":[160],"approach":[163],"achieves":[164],"4\u00d7":[167],"higher":[168],"token":[169],"throughput":[170],"30\u00d7":[172],"better":[173],"energy":[174],"efficiency":[175],"compared":[176],"state-of-the-art":[178],"H100":[179],"GPUs":[180],"same":[183],"workloads.":[184]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-03-26T00:00:00"}