{"id":"https://openalex.org/W4404134143","doi":"https://doi.org/10.1145/3649329.3657373","title":"AIG-CIM: A Scalable Chiplet Module with Tri-Gear Heterogeneous Compute-in-Memory for Diffusion Acceleration","display_name":"AIG-CIM: A Scalable Chiplet Module with Tri-Gear Heterogeneous Compute-in-Memory for Diffusion Acceleration","publication_year":2024,"publication_date":"2024-06-23","ids":{"openalex":"https://openalex.org/W4404134143","doi":"https://doi.org/10.1145/3649329.3657373"},"language":"en","primary_location":{"id":"doi:10.1145/3649329.3657373","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649329.3657373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","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/A5114069394","display_name":"Yiqi Jing","orcid":"https://orcid.org/0009-0004-7690-5356"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiqi Jing","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Meng Wu","orcid":"https://orcid.org/0000-0002-7676-343X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wu","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110453448","display_name":"John L. Zhou","orcid":"https://orcid.org/0009-0005-7697-1414"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Zhou","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107789976","display_name":"Yiyang Sun","orcid":"https://orcid.org/0009-0003-6353-4624"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyang Sun","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068840674","display_name":"Yufei Ma","orcid":"https://orcid.org/0000-0002-2670-524X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Ma","raw_affiliation_strings":["Institute for Artificial Intelligence, Peking University, Beijing, Beijing, China","School of Integrated Circuits, Peking University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062886480","display_name":"Ru Huang","orcid":"https://orcid.org/0000-0002-8146-4821"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ru Huang","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003039083","display_name":"Le Ye","orcid":"https://orcid.org/0000-0003-0599-7762"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Jia","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088551028","display_name":"Tianyu Jia","orcid":"https://orcid.org/0000-0002-4570-4613"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Ye","raw_affiliation_strings":["Advanced Institute of Information Technology of Peking University, Hangzhou, Zhejiang, China","School of Integrated Circuits, Peking University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Advanced Institute of Information Technology of Peking University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5114069394"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":2.4471,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90832916,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9970999956130981,"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":0.9970999956130981,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9886999726295471,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9825999736785889,"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/acceleration","display_name":"Acceleration","score":0.8150964975357056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7198466062545776},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7109835147857666},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5775502920150757},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.44621074199676514},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.41777849197387695},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2460118532180786},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1370941400527954}],"concepts":[{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.8150964975357056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7198466062545776},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7109835147857666},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5775502920150757},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44621074199676514},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.41777849197387695},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2460118532180786},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1370941400527954},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649329.3657373","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649329.3657373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2118231264","https://openalex.org/W2289252105","https://openalex.org/W3134526034","https://openalex.org/W3187788856","https://openalex.org/W3201613041","https://openalex.org/W4224035735","https://openalex.org/W4226317937","https://openalex.org/W4309398467","https://openalex.org/W4360605703","https://openalex.org/W4383665097","https://openalex.org/W6782174589"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W2565094479","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2390829436","https://openalex.org/W2095886385","https://openalex.org/W1989791859","https://openalex.org/W2889616422","https://openalex.org/W4401278057"],"abstract_inverted_index":{"The":[0],"emergence":[1],"of":[2,12,114],"Diffusion":[3,18,63,97],"models":[4,75],"has":[5],"gained":[6],"significant":[7],"attention":[8],"in":[9,62],"the":[10,57,77,81,88],"field":[11],"Artificial":[13],"Intelligence":[14],"Generated":[15],"Content.":[16],"While":[17],"demonstrates":[19],"impressive":[20],"image":[21],"generation":[22],"capability,":[23],"it":[24],"faces":[25],"hardware":[26,44],"deployment":[27],"challenges":[28],"due":[29],"to":[30,55,80,107,120],"its":[31],"unique":[32],"model":[33],"architecture":[34],"and":[35,86,111],"computation":[36],"requirement.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"present":[42],"a":[43,68],"accelerator":[45,90],"design,":[46],"i.e.":[47],"AIG-CIM,":[48],"which":[49],"incorporates":[50],"tri-gear":[51],"heterogeneous":[52],"digital":[53],"compute-in-memory":[54],"address":[56],"flexible":[58],"data":[59],"reuse":[60],"demands":[61],"models.":[64],"Our":[65],"framework":[66],"offers":[67],"collaborative":[69],"design":[70],"methodology":[71],"for":[72],"large":[73],"generative":[74],"from":[76],"computational":[78],"circuit-level":[79],"multi-chip-module":[82],"system-level.":[83],"We":[84],"implemented":[85],"evaluated":[87],"AIG-CIM":[89,100],"using":[91],"TSMC":[92],"22nm":[93],"technology.":[94],"For":[95],"several":[96],"inferences,":[98],"scalable":[99],"chiplets":[101],"achieve":[102],"21.3\u00d7":[103],"latency":[104],"reduction,":[105],"up":[106],"231.2\u00d7":[108],"throughput":[109],"improvement":[110,118],"three":[112],"orders":[113],"magnitude":[115],"energy":[116],"efficiency":[117],"compared":[119],"RTX":[121],"3090":[122],"GPU.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}