{"id":"https://openalex.org/W4403577857","doi":"https://doi.org/10.1145/3627673.3679068","title":"Towards Energy-Efficient Llama2 Architecture on Embedded FPGAs","display_name":"Towards Energy-Efficient Llama2 Architecture on Embedded FPGAs","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403577857","doi":"https://doi.org/10.1145/3627673.3679068"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679068","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110711399","display_name":"Han Xu","orcid":"https://orcid.org/0009-0007-0468-6336"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Xu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0009-0007-0468-6336","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xingyuan Wang","orcid":"https://orcid.org/0009-0009-5011-0666"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingyuan Wang","raw_affiliation_strings":["Meta Platforms Inc., Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0009-0009-5011-0666","affiliations":[{"raw_affiliation_string":"Meta Platforms Inc., Seattle, WA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036338045","display_name":"Shihao Ji","orcid":"https://orcid.org/0000-0002-3573-5379"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shihao Ji","raw_affiliation_strings":["Georgia State University, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3573-5379","affiliations":[{"raw_affiliation_string":"Georgia State University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I181565077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5570","last_page":"5571"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980000257492065,"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9932000041007996,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.784132182598114},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.7025196552276611},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.7004201412200928},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6715793013572693},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5577921271324158},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.412280797958374},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3679806590080261},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06298458576202393}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.784132182598114},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.7025196552276611},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.7004201412200928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6715793013572693},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5577921271324158},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.412280797958374},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3679806590080261},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06298458576202393},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679068","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8399999737739563,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W2963748441"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W2355315220","https://openalex.org/W2096844293","https://openalex.org/W2363944576","https://openalex.org/W2351041855","https://openalex.org/W2570254841","https://openalex.org/W1967938402","https://openalex.org/W2386041993","https://openalex.org/W1608572506","https://openalex.org/W2038503502"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"immense":[6],"potential":[7],"for":[8,24],"applications":[9],"in":[10],"information":[11],"retrieval":[12],"and":[13,19,50,75],"knowledge":[14],"management,":[15],"but":[16],"their":[17],"computational":[18],"memory":[20],"demands":[21],"pose":[22],"challenges":[23],"resource-constrained":[25],"devices.":[26,43],"In":[27],"response,":[28],"this":[29],"work":[30],"introduces":[31],"an":[32],"FPGA-based":[33],"accelerator":[34,53],"designed":[35],"to":[36,54],"improve":[37],"LLM":[38],"inference":[39],"performance":[40],"on":[41,66,84],"embedded":[42],"We":[44],"leverage":[45],"quantization":[46],"techniques,":[47],"asynchronous":[48],"computation,":[49],"a":[51,67,72,76],"fully-pipelined":[52],"enhance":[55],"efficiency.":[56],"Our":[57],"empirical":[58],"evaluations,":[59],"conducted":[60],"using":[61],"the":[62,85],"TinyLlama":[63],"1.1B":[64],"model":[65],"Xilinx":[68],"ZCU102":[69,86],"platform,":[70],"demonstrate":[71],"14.3-15.8x":[73],"speedup":[74],"6.1x":[77],"energy":[78],"efficiency":[79],"improvement":[80],"over":[81],"running":[82],"exclusively":[83],"processing":[87],"system":[88],"(PS).":[89]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}