{"id":"https://openalex.org/W4414594363","doi":"https://doi.org/10.1145/3768168","title":"Ultrafast Generative AI by Ultradense 3D Integration: A Case Study on LLM-based Edge Inference","display_name":"Ultrafast Generative AI by Ultradense 3D Integration: A Case Study on LLM-based Edge Inference","publication_year":2025,"publication_date":"2025-09-12","ids":{"openalex":"https://openalex.org/W4414594363","doi":"https://doi.org/10.1145/3768168"},"language":"en","primary_location":{"id":"doi:10.1145/3768168","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768168","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3768168","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067464561","display_name":"Kerem Akarvardar","orcid":"https://orcid.org/0000-0001-5957-826X"},"institutions":[{"id":"https://openalex.org/I1334877674","display_name":"Taiwan Semiconductor Manufacturing Company (United States)","ror":"https://ror.org/02rvfjx92","country_code":"US","type":"company","lineage":["https://openalex.org/I1334877674","https://openalex.org/I4210120917"]},{"id":"https://openalex.org/I4210120917","display_name":"Taiwan Semiconductor Manufacturing Company (Taiwan)","ror":"https://ror.org/02wx79d08","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210120917"]}],"countries":["TW","US"],"is_corresponding":true,"raw_author_name":"Kerem Akarvardar","raw_affiliation_strings":["Taiwan Semiconductor Manufacturing Company North America","Taiwan Semiconductor Manufacturing Company North America, San Jose, United States"],"raw_orcid":"https://orcid.org/0000-0001-5957-826X","affiliations":[{"raw_affiliation_string":"Taiwan Semiconductor Manufacturing Company North America","institution_ids":["https://openalex.org/I4210120917"]},{"raw_affiliation_string":"Taiwan Semiconductor Manufacturing Company North America, San Jose, United States","institution_ids":["https://openalex.org/I1334877674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062894678","display_name":"Xiaoyu Sun","orcid":"https://orcid.org/0000-0001-5337-5680"},"institutions":[{"id":"https://openalex.org/I1334877674","display_name":"Taiwan Semiconductor Manufacturing Company (United States)","ror":"https://ror.org/02rvfjx92","country_code":"US","type":"company","lineage":["https://openalex.org/I1334877674","https://openalex.org/I4210120917"]},{"id":"https://openalex.org/I4210120917","display_name":"Taiwan Semiconductor Manufacturing Company (Taiwan)","ror":"https://ror.org/02wx79d08","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210120917"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Xiaoyu Sun","raw_affiliation_strings":["Taiwan Semiconductor Manufacturing Company North America","Taiwan Semiconductor Manufacturing Company North America, San Jose, United States"],"raw_orcid":"https://orcid.org/0000-0001-5337-5680","affiliations":[{"raw_affiliation_string":"Taiwan Semiconductor Manufacturing Company North America","institution_ids":["https://openalex.org/I4210120917"]},{"raw_affiliation_string":"Taiwan Semiconductor Manufacturing Company North America, San Jose, United States","institution_ids":["https://openalex.org/I1334877674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089938000","display_name":"Brian Crafton","orcid":"https://orcid.org/0000-0002-0227-0421"},"institutions":[{"id":"https://openalex.org/I1334877674","display_name":"Taiwan Semiconductor Manufacturing Company (United States)","ror":"https://ror.org/02rvfjx92","country_code":"US","type":"company","lineage":["https://openalex.org/I1334877674","https://openalex.org/I4210120917"]},{"id":"https://openalex.org/I4210120917","display_name":"Taiwan Semiconductor Manufacturing Company (Taiwan)","ror":"https://ror.org/02wx79d08","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210120917"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Brian Crafton","raw_affiliation_strings":["Taiwan Semiconductor Manufacturing Company North America","Taiwan Semiconductor Manufacturing Company North America, San Jose, United States"],"raw_orcid":"https://orcid.org/0009-0000-0693-6887","affiliations":[{"raw_affiliation_string":"Taiwan Semiconductor Manufacturing Company North America","institution_ids":["https://openalex.org/I4210120917"]},{"raw_affiliation_string":"Taiwan Semiconductor Manufacturing Company North America, San Jose, United States","institution_ids":["https://openalex.org/I1334877674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076031530","display_name":"Xiaochen Peng","orcid":"https://orcid.org/0000-0001-6148-7711"},"institutions":[{"id":"https://openalex.org/I1334877674","display_name":"Taiwan Semiconductor Manufacturing Company (United States)","ror":"https://ror.org/02rvfjx92","country_code":"US","type":"company","lineage":["https://openalex.org/I1334877674","https://openalex.org/I4210120917"]},{"id":"https://openalex.org/I4210120917","display_name":"Taiwan Semiconductor Manufacturing Company (Taiwan)","ror":"https://ror.org/02wx79d08","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210120917"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Xiaochen Peng","raw_affiliation_strings":["Taiwan Semiconductor Manufacturing Company North America","Taiwan Semiconductor Manufacturing Company North America, San Jose, United States"],"raw_orcid":"https://orcid.org/0000-0001-6148-7711","affiliations":[{"raw_affiliation_string":"Taiwan Semiconductor Manufacturing Company North America","institution_ids":["https://openalex.org/I4210120917"]},{"raw_affiliation_string":"Taiwan Semiconductor Manufacturing Company North America, San Jose, United States","institution_ids":["https://openalex.org/I1334877674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101884505","display_name":"H. Mori","orcid":"https://orcid.org/0000-0002-8149-393X"},"institutions":[{"id":"https://openalex.org/I4210119559","display_name":"Taiwan Semiconductor Manufacturing Company (China)","ror":"https://ror.org/02s0wcj29","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210119559","https://openalex.org/I4210120917"]},{"id":"https://openalex.org/I4210120917","display_name":"Taiwan Semiconductor Manufacturing Company (Taiwan)","ror":"https://ror.org/02wx79d08","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210120917"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Haruki Mori","raw_affiliation_strings":["Taiwan Semiconductor Manufacturing Co Ltd","Taiwan Semiconductor Manufacturing Co Ltd, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-8149-393X","affiliations":[{"raw_affiliation_string":"Taiwan Semiconductor Manufacturing Co Ltd","institution_ids":["https://openalex.org/I4210119559","https://openalex.org/I4210120917"]},{"raw_affiliation_string":"Taiwan Semiconductor Manufacturing Co Ltd, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I4210120917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004629816","display_name":"Abhiroop Bhattacharjee","orcid":"https://orcid.org/0000-0002-7721-271X"},"institutions":[{"id":"https://openalex.org/I1334877674","display_name":"Taiwan Semiconductor Manufacturing Company (United States)","ror":"https://ror.org/02rvfjx92","country_code":"US","type":"company","lineage":["https://openalex.org/I1334877674","https://openalex.org/I4210120917"]},{"id":"https://openalex.org/I4210120917","display_name":"Taiwan Semiconductor Manufacturing Company (Taiwan)","ror":"https://ror.org/02wx79d08","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210120917"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Abhiroop Bhattacharjee","raw_affiliation_strings":["Taiwan Semiconductor Manufacturing Company North America","Taiwan Semiconductor Manufacturing Company North America, San Jose, United States"],"raw_orcid":"https://orcid.org/0000-0002-7721-271X","affiliations":[{"raw_affiliation_string":"Taiwan Semiconductor Manufacturing Company North America","institution_ids":["https://openalex.org/I4210120917"]},{"raw_affiliation_string":"Taiwan Semiconductor Manufacturing Company North America, San Jose, United States","institution_ids":["https://openalex.org/I1334877674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100989173","display_name":"Hidehiro Fujiwara","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119559","display_name":"Taiwan Semiconductor Manufacturing Company (China)","ror":"https://ror.org/02s0wcj29","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210119559","https://openalex.org/I4210120917"]},{"id":"https://openalex.org/I4210120917","display_name":"Taiwan Semiconductor Manufacturing Company (Taiwan)","ror":"https://ror.org/02wx79d08","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210120917"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Hidehiro Fujiwara","raw_affiliation_strings":["Taiwan Semiconductor Manufacturing Co Ltd","Taiwan Semiconductor Manufacturing Co Ltd, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0009-0004-0992-5859","affiliations":[{"raw_affiliation_string":"Taiwan Semiconductor Manufacturing Co Ltd","institution_ids":["https://openalex.org/I4210119559","https://openalex.org/I4210120917"]},{"raw_affiliation_string":"Taiwan Semiconductor Manufacturing Co Ltd, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I4210120917"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059975258","display_name":"H.\u2010S. Philip Wong","orcid":"https://orcid.org/0000-0002-0096-1472"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H.-S. Philip Wong","raw_affiliation_strings":["Electrical Engineering, Stanford University","Electrical Engineering, Stanford University, Stanford, United States"],"raw_orcid":"https://orcid.org/0000-0002-0096-1472","affiliations":[{"raw_affiliation_string":"Electrical Engineering, Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Electrical Engineering, Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5067464561"],"corresponding_institution_ids":["https://openalex.org/I1334877674","https://openalex.org/I4210120917"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23352434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":"1","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9998000264167786,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9984999895095825,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.628600001335144},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.579800009727478},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5425000190734863},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5228000283241272},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.4027999937534332},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3806000053882599},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.3693999946117401},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.35659998655319214},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.35350000858306885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.892300009727478},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.628600001335144},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.579800009727478},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5228000283241272},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3806000053882599},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35659998655319214},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.35659998655319214},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.35350000858306885},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C47798520","wikidata":"https://www.wikidata.org/wiki/Q190157","display_name":"Transmitter","level":3,"score":0.3449000120162964},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34310001134872437},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.30160000920295715},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2962999939918518},{"id":"https://openalex.org/C10418432","wikidata":"https://www.wikidata.org/wiki/Q560370","display_name":"AND gate","level":3,"score":0.289900004863739},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C164620267","wikidata":"https://www.wikidata.org/wiki/Q376953","display_name":"Adder","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3768168","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768168","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3768168","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768168","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1538245821","https://openalex.org/W1994309919","https://openalex.org/W2067627272","https://openalex.org/W2518511512","https://openalex.org/W2612695082","https://openalex.org/W2801748224","https://openalex.org/W2914959946","https://openalex.org/W2915915007","https://openalex.org/W3016154121","https://openalex.org/W3085458932","https://openalex.org/W3134526034","https://openalex.org/W3217045543","https://openalex.org/W4221038786","https://openalex.org/W4286300805","https://openalex.org/W4308480476","https://openalex.org/W4315631022","https://openalex.org/W4376130831","https://openalex.org/W4383222101","https://openalex.org/W4388692445","https://openalex.org/W4389352483","https://openalex.org/W4392240059","https://openalex.org/W4393145114","https://openalex.org/W4399115604","https://openalex.org/W4399454483","https://openalex.org/W4400034006","https://openalex.org/W4400034405","https://openalex.org/W4402349378","https://openalex.org/W4404848416","https://openalex.org/W4405348597","https://openalex.org/W4405562786","https://openalex.org/W4406549091","https://openalex.org/W4407638835","https://openalex.org/W4407693449","https://openalex.org/W4408183030","https://openalex.org/W4408183178","https://openalex.org/W4411485931","https://openalex.org/W4411688591"],"related_works":[],"abstract_inverted_index":{"Generative":[0],"AI":[1],"(GenAI)":[2],"is":[3],"one":[4],"of":[5,15,122],"the":[6,13,73,105,114,120,137],"most":[7],"critical":[8],"applications":[9],"today,":[10],"continually":[11],"challenging":[12],"limits":[14],"semiconductor":[16],"technology.":[17],"We":[18,117],"introduce":[19],"a":[20,28,67],"very":[21],"fine-grained":[22],"3D":[23,52,98,115],"memory-on-logic":[24],"architecture":[25],"along":[26],"with":[27,140],"novel":[29],"data":[30],"mapping":[31],"strategy":[32],"to":[33,156],"support":[34],"Large":[35],"Language":[36],"Model":[37],"(LLM)-based":[38],"GenAI,":[39],"including":[40],"both":[41],"prefill":[42,132],"and":[43,59,91,108,126,144,151],"generation":[44,57,77],"stages.":[45],"Our":[46],"conceptual":[47],"analysis":[48],"shows":[49],"how":[50],"ultradense":[51],"connectivity":[53],"can":[54],"enhance":[55],"text":[56],"speed":[58],"energy-efficiency":[60],"well-beyond":[61],"current":[62],"limits.":[63],"Preliminary":[64],"findings":[65],"from":[66],"basic":[68],"analytical":[69],"model":[70],"indicate":[71],"that":[72],"single":[74],"batch":[75],"autoregressive":[76],"rate":[78],"for":[79],"Llama":[80],"3.2":[81],"1B":[82],"could":[83],"surpass":[84],"5K":[85],"tokens/sec":[86],"by":[87],"maximizing":[88],"weight":[89],"locality":[90],"enhancing":[92],"memory":[93,111,141],"bandwidth":[94,149],"through":[95],"massively":[96],"parallel":[97],"links":[99],"between":[100],"Multiply-Accumulate":[101],"(MAC)":[102],"units":[103],"in":[104,113,130],"logic":[106,124],"tier":[107],"their":[109,128],"dedicated":[110],"partitions":[112],"stack.":[116],"also":[118],"explore":[119],"impact":[121],"advanced":[123],"nodes":[125],"quantify":[127],"benefits":[129],"reducing":[131],"latency.":[133],"Finally,":[134],"we":[135],"examine":[136],"challenges":[138],"associated":[139],"access":[142,154],"power":[143,145],"density":[146],"under":[147],"extreme":[148],"conditions":[150],"present":[152],"pipelined":[153],"strategies":[155],"address":[157],"them.":[158]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
