{"id":"https://openalex.org/W4407691652","doi":"https://doi.org/10.1109/lca.2025.3540058","title":"Optically Connected Multi-Stack HBM Modules for Large Language Model Training and Inference","display_name":"Optically Connected Multi-Stack HBM Modules for Large Language Model Training and Inference","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407691652","doi":"https://doi.org/10.1109/lca.2025.3540058"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2025.3540058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2025.3540058","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/A5033494020","display_name":"Yanghui Ou","orcid":"https://orcid.org/0000-0001-9481-9882"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanghui Ou","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-9481-9882","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101714293","display_name":"Hengrui Zhang","orcid":"https://orcid.org/0000-0001-5090-3177"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hengrui Zhang","raw_affiliation_strings":["Princeton University, Princeton, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0001-5090-3177","affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043944816","display_name":"Austin Rovinski","orcid":"https://orcid.org/0000-0003-1761-1898"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Austin Rovinski","raw_affiliation_strings":["New York University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-1761-1898","affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080019688","display_name":"David Wentzlaff","orcid":"https://orcid.org/0000-0002-6337-5630"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Wentzlaff","raw_affiliation_strings":["Princeton University, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091660287","display_name":"Christopher Batten","orcid":"https://orcid.org/0000-0002-2835-667X"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Batten","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-2835-667X","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1081,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75809873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"24","issue":"1","first_page":"49","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.6930000185966492,"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"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.6930000185966492,"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/computer-science","display_name":"Computer science","score":0.8267977237701416},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6414747834205627},{"id":"https://openalex.org/keywords/stack","display_name":"Stack (abstract data type)","score":0.5879532694816589},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5545799732208252},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4862919747829437},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4005233347415924},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3919615149497986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3476591110229492},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3458790183067322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267977237701416},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6414747834205627},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.5879532694816589},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5545799732208252},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4862919747829437},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4005233347415924},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3919615149497986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3476591110229492},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3458790183067322},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2025.3540058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2025.3540058","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G7203148941","display_name":null,"funder_award_id":"FA8650-18-2-7862","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2969388332","https://openalex.org/W3015022197","https://openalex.org/W3107122212","https://openalex.org/W3188706325","https://openalex.org/W4226338823","https://openalex.org/W4318541517","https://openalex.org/W4393407316","https://openalex.org/W4396918675","https://openalex.org/W4400235409","https://openalex.org/W4401211642","https://openalex.org/W6755207826","https://openalex.org/W6767997687","https://openalex.org/W6778883912","https://openalex.org/W6779863968","https://openalex.org/W6788811087","https://openalex.org/W6857711315"],"related_works":["https://openalex.org/W2380576232","https://openalex.org/W2937054111","https://openalex.org/W2066223521","https://openalex.org/W2013178899","https://openalex.org/W373327546","https://openalex.org/W2321534397","https://openalex.org/W2058958858","https://openalex.org/W230091440","https://openalex.org/W2077601556","https://openalex.org/W2148243540"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"grown":[5],"exponentially":[6],"in":[7],"size,":[8],"presenting":[9],"significant":[10],"challenges":[11],"to":[12,40,58,108,125],"traditional":[13],"memory":[14,19,50,60,78],"architectures.":[15],"Current":[16],"high":[17],"bandwidth":[18,27,63],"(HBM)":[20],"systems":[21],"are":[22],"constrained":[23],"by":[24,105,118],"chiplet":[25],"I/O":[26],"and":[28,62],"the":[29,76,81,86,121],"limited":[30],"number":[31,87],"of":[32,88],"HBM":[33,72,77,89],"stacks":[34],"that":[35,53,94],"can":[36,97],"be":[37],"integrated":[38],"due":[39],"packaging":[41],"constraints.":[42],"In":[43],"this":[44,95],"letter,":[45],"we":[46,74],"propose":[47],"a":[48,102,109],"novel":[49],"system":[51,79],"architecture":[52,96],"leverages":[54],"silicon":[55],"photonic":[56],"interconnects":[57],"increase":[59],"capacity":[61],"for":[64,101],"compute":[65,82],"devices.":[66],"By":[67],"introducing":[68],"optically":[69],"connected":[70],"multi-stack":[71],"modules,":[73],"extend":[75],"off":[80],"chip,":[83],"significantly":[84],"increasing":[85],"stacks.":[90],"Our":[91],"evaluations":[92],"show":[93],"improve":[98],"training":[99],"efficiency":[100],"trillion-parameter":[103],"model":[104],"1.4\u00d7":[106],"compared":[107],"modeled":[110],"A100":[111],"baseline,":[112],"while":[113],"also":[114],"enhancing":[115],"inference":[116],"performance":[117],"4.2\u00d7":[119],"if":[120],"L2":[122],"is":[123],"modified":[124],"provide":[126],"sufficient":[127],"bandwidth.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}