{"id":"https://openalex.org/W4411485931","doi":"https://doi.org/10.1145/3695053.3731008","title":"H <sup>2</sup> -LLM: Hardware-Dataflow Co-Exploration for Heterogeneous Hybrid-Bonding-based Low-Batch LLM Inference","display_name":"H <sup>2</sup> -LLM: Hardware-Dataflow Co-Exploration for Heterogeneous Hybrid-Bonding-based Low-Batch LLM Inference","publication_year":2025,"publication_date":"2025-06-20","ids":{"openalex":"https://openalex.org/W4411485931","doi":"https://doi.org/10.1145/3695053.3731008"},"language":"en","primary_location":{"id":"doi:10.1145/3695053.3731008","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3695053.3731008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","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/A5089919148","display_name":"Cong Li","orcid":"https://orcid.org/0000-0001-7760-3254"},"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":"Cong Li","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112797885","display_name":"Y. Q. Yin","orcid":null},"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":"Yihan Yin","raw_affiliation_strings":["School of EECS, Peking university, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of EECS, Peking university, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087202209","display_name":"Xintong Wu","orcid":null},"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":"Xintong Wu","raw_affiliation_strings":["School of EECS, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of EECS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073752740","display_name":"Jingchen Zhu","orcid":"https://orcid.org/0000-0002-4321-7694"},"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":"Jingchen Zhu","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082612170","display_name":"Zhen-Ran Gao","orcid":"https://orcid.org/0009-0008-1013-5781"},"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":"Zhutianya Gao","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068606980","display_name":"Dimin Niu","orcid":"https://orcid.org/0000-0001-8440-3875"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimin Niu","raw_affiliation_strings":["Alibaba Group Inc., Sunnyvale, USA"],"affiliations":[{"raw_affiliation_string":"Alibaba Group Inc., Sunnyvale, USA","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104048273","display_name":"Qiang Wu","orcid":"https://orcid.org/0009-0009-8981-2876"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Wu","raw_affiliation_strings":["Houmo AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Houmo AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000787204","display_name":"Xin Si","orcid":"https://orcid.org/0000-0002-4993-0087"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Si","raw_affiliation_strings":["SouthEast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"SouthEast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385336","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0003-2093-1788"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["HKUST, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"HKUST, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374175","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0003-2762-2726"},"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":"Chen Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089719475","display_name":"Guangyu Sun","orcid":"https://orcid.org/0000-0002-7315-6589"},"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/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyu Sun","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, China and Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China and Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","institution_ids":["https://openalex.org/I4210165198","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5089919148"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":7.8804,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.97579904,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"194","last_page":"210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11338","display_name":"Advancements in Photolithography Techniques","score":0.9937999844551086,"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/T11338","display_name":"Advancements in Photolithography Techniques","score":0.9937999844551086,"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9740999937057495,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.972000002861023,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.8827502727508545},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6536154747009277},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5216336846351624},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.46247851848602295},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4225865602493286},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3427315652370453},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.32776328921318054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12281522154808044}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8827502727508545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6536154747009277},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5216336846351624},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46247851848602295},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4225865602493286},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3427315652370453},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.32776328921318054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12281522154808044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3695053.3731008","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3695053.3731008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4460768019","display_name":null,"funder_award_id":"62032001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2794532328","https://openalex.org/W2884361556","https://openalex.org/W2896090304","https://openalex.org/W2940862705","https://openalex.org/W2979823675","https://openalex.org/W2982008795","https://openalex.org/W2998732502","https://openalex.org/W3017521908","https://openalex.org/W3042598257","https://openalex.org/W3043023836","https://openalex.org/W3100710793","https://openalex.org/W3136346557","https://openalex.org/W3158275024","https://openalex.org/W3189166979","https://openalex.org/W3190062760","https://openalex.org/W3190092209","https://openalex.org/W3205200804","https://openalex.org/W4220889234","https://openalex.org/W4220943275","https://openalex.org/W4220972538","https://openalex.org/W4226070038","https://openalex.org/W4250503569","https://openalex.org/W4281932226","https://openalex.org/W4285217154","https://openalex.org/W4308083513","https://openalex.org/W4318328413","https://openalex.org/W4360831749","https://openalex.org/W4386763946","https://openalex.org/W4387064011","https://openalex.org/W4387064057","https://openalex.org/W4387421577","https://openalex.org/W4389491877","https://openalex.org/W4389518760","https://openalex.org/W4392427708","https://openalex.org/W4393592481","https://openalex.org/W4394773691","https://openalex.org/W4394998968","https://openalex.org/W4394999021","https://openalex.org/W4395106409","https://openalex.org/W4401211704","https://openalex.org/W4401211878","https://openalex.org/W4402475900","https://openalex.org/W4409248687"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W2171015181","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W1998888015"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}
