{"id":"https://openalex.org/W4400811042","doi":"https://doi.org/10.1109/aicas59952.2024.10595886","title":"AICAS Grand Challenge 2024: Software and Hardware Co-optimization for General Large Language Model Inference on CPU","display_name":"AICAS Grand Challenge 2024: Software and Hardware Co-optimization for General Large Language Model Inference on CPU","publication_year":2024,"publication_date":"2024-04-22","ids":{"openalex":"https://openalex.org/W4400811042","doi":"https://doi.org/10.1109/aicas59952.2024.10595886"},"language":"en","primary_location":{"id":"doi:10.1109/aicas59952.2024.10595886","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/aicas59952.2024.10595886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 6th International Conference on AI Circuits and Systems (AICAS)","raw_type":"proceedings-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/A5068846370","display_name":"Junfeng Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junfeng Tan","raw_affiliation_strings":["Xidian University,Hangzhou Institute of Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,Hangzhou Institute of Technology,Hangzhou,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101135416","display_name":"Guosheng Yu","orcid":"https://orcid.org/0009-0007-2552-3982"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guosheng Yu","raw_affiliation_strings":["T-HEAD Semiconductor Co., Ltd,China"],"affiliations":[{"raw_affiliation_string":"T-HEAD Semiconductor Co., Ltd,China","institution_ids":["https://openalex.org/I4210119559"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402797","display_name":"Jianing Li","orcid":"https://orcid.org/0000-0001-9552-2247"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianing Li","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101499924","display_name":"Xiaohan Ma","orcid":"https://orcid.org/0000-0002-0640-8467"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohan Ma","raw_affiliation_strings":["T-HEAD Semiconductor Co., Ltd,China"],"affiliations":[{"raw_affiliation_string":"T-HEAD Semiconductor Co., Ltd,China","institution_ids":["https://openalex.org/I4210119559"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112467460","display_name":"Fang Bao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang Bao","raw_affiliation_strings":["Arm Technology (China) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Arm Technology (China) Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104800014","display_name":"Evens Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Evens Pan","raw_affiliation_strings":["Arm Technology (China) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Arm Technology (China) Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104749084","display_name":"David Bian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Bian","raw_affiliation_strings":["Arm Technology (China) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Arm Technology (China) Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764158","display_name":"Yongfu Li","orcid":"https://orcid.org/0000-0002-6322-8614"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongfu Li","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Micro-Nano Electronics,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Micro-Nano Electronics,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084816122","display_name":"Yuan Du","orcid":"https://orcid.org/0000-0002-5316-619X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Du","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039665206","display_name":"Li Du","orcid":"https://orcid.org/0000-0003-2687-6978"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Du","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046508099","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-1415-4444"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Xidian University,Hangzhou Institute of Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,Hangzhou Institute of Technology,Hangzhou,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113296016","display_name":"Wei Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Mao","raw_affiliation_strings":["Xidian University,Hangzhou Institute of Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,Hangzhou Institute of Technology,Hangzhou,China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5068846370"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64698697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"25","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9336000084877014,"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/T10028","display_name":"Topic Modeling","score":0.9336000084877014,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9326000213623047,"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/computer-science","display_name":"Computer science","score":0.782333493232727},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5792186260223389},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5548280477523804},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.53493332862854},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.38735127449035645},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36374443769454956},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32677435874938965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24784287810325623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.782333493232727},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5792186260223389},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5548280477523804},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.53493332862854},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.38735127449035645},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36374443769454956},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32677435874938965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24784287810325623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aicas59952.2024.10595886","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/aicas59952.2024.10595886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 6th International Conference on AI Circuits and Systems (AICAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2794325560","https://openalex.org/W2946609015","https://openalex.org/W2963122961","https://openalex.org/W2998617917","https://openalex.org/W3174529902","https://openalex.org/W4212774754","https://openalex.org/W4309242571","https://openalex.org/W4381586827","https://openalex.org/W4383501769","https://openalex.org/W4386437475","https://openalex.org/W4390993434","https://openalex.org/W6684859321","https://openalex.org/W6749838110","https://openalex.org/W6778883912","https://openalex.org/W6796581206","https://openalex.org/W6852962002","https://openalex.org/W6853048723","https://openalex.org/W6853251322","https://openalex.org/W6854094408","https://openalex.org/W6856250771","https://openalex.org/W6856800273","https://openalex.org/W6857690716"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W2418291489","https://openalex.org/W2068121105","https://openalex.org/W3096519538","https://openalex.org/W2744747300","https://openalex.org/W4321636575","https://openalex.org/W4241166160","https://openalex.org/W2384826897","https://openalex.org/W1986418932","https://openalex.org/W1997466117"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"attained":[5],"remarkable":[6],"achievements":[7],"in":[8,126],"multi-domain":[9],"tasks.":[10],"However,":[11],"LLMs\u2019":[12],"performance":[13,114],"is":[14,43],"limited":[15],"by":[16],"hardware":[17,31,67],"conditions":[18],"due":[19],"to":[20,85,104,111],"billions":[21],"of":[22,115],"parameters.":[23],"It":[24],"requires":[25],"highly":[26],"efficient":[27],"deployment":[28],"and":[29,37,66,90],"software":[30,65],"co-optimization":[32,68],"such":[33],"as":[34],"quantization,":[35],"pruning":[36],"operator":[38],"fusion":[39],"methods.":[40],"Meanwhile,":[41],"there":[42],"an":[44],"emerging":[45],"trend":[46],"that":[47],"LLMs":[48,79],"run":[49],"on":[50,64,80],"edge":[51],"devices":[52],"like":[53],"Arm-based":[54,106],"CPUs.":[55],"Thus,":[56],"we":[57],"organized":[58],"the":[59,73,94,97,105,113,127],"2024":[60],"AICAS":[61,128],"Grand":[62],"Challenge":[63],"for":[69],"general":[70],"LLMs.":[71],"In":[72,93],"preliminary":[74],"round,":[75,96],"participating":[76],"teams":[77,99,122],"deployed":[78],"either":[81],"GPUs":[82],"or":[83],"CPUs":[84],"reduce":[86],"model":[87],"memory":[88],"consumption":[89],"increase":[91],"throughput.":[92],"final":[95],"qualified":[98],"applied":[100],"different":[101],"optimization":[102],"methods":[103],"multi-core":[107],"Yitian":[108],"710":[109],"CPU":[110],"maximize":[112],"their":[116,124],"model.":[117],"The":[118],"top":[119],"6":[120],"best":[121],"presented":[123],"work":[125],"2024.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}
