{"id":"https://openalex.org/W4392427708","doi":"https://doi.org/10.1145/3620666.3651380","title":"NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing","display_name":"NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing","publication_year":2024,"publication_date":"2024-04-24","ids":{"openalex":"https://openalex.org/W4392427708","doi":"https://doi.org/10.1145/3620666.3651380"},"language":"en","primary_location":{"id":"doi:10.1145/3620666.3651380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3620666.3651380","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3620666.3651380","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103115015","display_name":"Guseul Heo","orcid":"https://orcid.org/0009-0008-3179-8541"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Guseul Heo","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0008-3179-8541","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600367","display_name":"Sangyeop Lee","orcid":"https://orcid.org/0009-0004-7645-6503"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangyeop Lee","raw_affiliation_strings":["KAIST, Daejeon, Korea, South ? Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0004-7645-6503","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Korea, South ? Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029070493","display_name":"Jaehong Cho","orcid":"https://orcid.org/0009-0008-8973-5164"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehong Cho","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0008-8973-5164","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100997517","display_name":"Hyunmin Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunmin Choi","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-4116-3896","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067740021","display_name":"S. K. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanghyeon Lee","raw_affiliation_strings":["KAIST, Daejeon, Korea, South ? Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0003-7060-6315","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Korea, South ? Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074288663","display_name":"Hyungkyu Ham","orcid":"https://orcid.org/0000-0002-4989-2834"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungkyu Ham","raw_affiliation_strings":["POSTECH, Pohang, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-4989-2834","affiliations":[{"raw_affiliation_string":"POSTECH, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334897","display_name":"Gwangsun Kim","orcid":"https://orcid.org/0000-0001-5749-5794"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gwangsun Kim","raw_affiliation_strings":["POSTECH, Pohang, Korea, South ? Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-5749-5794","affiliations":[{"raw_affiliation_string":"POSTECH, Pohang, Korea, South ? Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089590312","display_name":"Divya Mahajan","orcid":"https://orcid.org/0009-0007-8184-0528"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divya Mahajan","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, United States of America"],"raw_orcid":"https://orcid.org/0009-0007-8184-0528","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, United States of America","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037553165","display_name":"Jongse Park","orcid":"https://orcid.org/0000-0002-6629-449X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongse Park","raw_affiliation_strings":["KAIST, Daejeon, Korea, South ? Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-6629-449X","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Korea, South ? Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5103115015"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":16.6444,"has_fulltext":true,"cited_by_count":89,"citation_normalized_percentile":{"value":0.99568183,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"722","last_page":"737"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9979000091552734,"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":0.9979000091552734,"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/T10028","display_name":"Topic Modeling","score":0.9733999967575073,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9434999823570251,"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/computer-science","display_name":"Computer science","score":0.851225733757019},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6702066659927368},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4996349811553955},{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.48827052116394043},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4823684096336365},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42533016204833984},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36210525035858154},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19417554140090942},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10777583718299866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.851225733757019},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6702066659927368},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4996349811553955},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.48827052116394043},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4823684096336365},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42533016204833984},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36210525035858154},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19417554140090942},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10777583718299866},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3620666.3651380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3620666.3651380","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.00579","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.00579","pdf_url":"https://arxiv.org/pdf/2403.00579","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3620666.3651380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3620666.3651380","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1769687045","display_name":null,"funder_award_id":"2019-0-00075","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2148870006","display_name":null,"funder_award_id":"2019-0-00075","funder_id":"https://openalex.org/F4320324161","funder_display_name":"Korea Advanced Institute of Science and Technology"},{"id":"https://openalex.org/G4628738581","display_name":null,"funder_award_id":"No. 2019-0-00075","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5292070027","display_name":null,"funder_award_id":"IITP-2024-2020-0-01795","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G5415505637","display_name":null,"funder_award_id":"2019-0-00075","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5906391025","display_name":null,"funder_award_id":"2022-0-01037","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6776584021","display_name":null,"funder_award_id":"2019-0-00075","funder_id":"https://openalex.org/F4320324891","funder_display_name":"Iran Telecommunication Research Center"},{"id":"https://openalex.org/G7159222638","display_name":null,"funder_award_id":"IITP-2024-2020-0-01795","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G79798675","display_name":null,"funder_award_id":"2018-0-00503","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320324161","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1981943579","https://openalex.org/W2086112773","https://openalex.org/W2261808795","https://openalex.org/W2562773490","https://openalex.org/W2612654866","https://openalex.org/W2725159389","https://openalex.org/W2779888504","https://openalex.org/W2782800349","https://openalex.org/W2896457183","https://openalex.org/W2901299405","https://openalex.org/W2965643269","https://openalex.org/W2969388332","https://openalex.org/W2970971581","https://openalex.org/W2979874885","https://openalex.org/W3006586535","https://openalex.org/W3039050620","https://openalex.org/W3043023836","https://openalex.org/W3100710793","https://openalex.org/W3103415979","https://openalex.org/W3106937018","https://openalex.org/W3144382362","https://openalex.org/W3158275024","https://openalex.org/W3158634533","https://openalex.org/W3177813494","https://openalex.org/W3185889905","https://openalex.org/W3189166979","https://openalex.org/W3200211247","https://openalex.org/W3205088407","https://openalex.org/W3207399097","https://openalex.org/W3210038683","https://openalex.org/W3210580311","https://openalex.org/W4211105506","https://openalex.org/W4221159132","https://openalex.org/W4224035735","https://openalex.org/W4224051134","https://openalex.org/W4225591000","https://openalex.org/W4226479682","https://openalex.org/W4249322926","https://openalex.org/W4280496502","https://openalex.org/W4280542458","https://openalex.org/W4281733247","https://openalex.org/W4284886102","https://openalex.org/W4285121610","https://openalex.org/W4293731257","https://openalex.org/W4312258681","https://openalex.org/W4312438982","https://openalex.org/W4320023979","https://openalex.org/W4321853806","https://openalex.org/W4322718191","https://openalex.org/W4327930430","https://openalex.org/W4362655494","https://openalex.org/W4380881178","https://openalex.org/W4385834084","https://openalex.org/W4386185625","https://openalex.org/W4387321091","https://openalex.org/W4389163115","https://openalex.org/W4389476267","https://openalex.org/W4390280330","https://openalex.org/W4392015341","https://openalex.org/W4393407040","https://openalex.org/W6745386328","https://openalex.org/W6811340617","https://openalex.org/W6846002521","https://openalex.org/W6846659131"],"related_works":["https://openalex.org/W1655266410","https://openalex.org/W2389051085","https://openalex.org/W2330343234","https://openalex.org/W1901012776","https://openalex.org/W2463883322","https://openalex.org/W2229382548","https://openalex.org/W2391789612","https://openalex.org/W2814468324","https://openalex.org/W2389236462","https://openalex.org/W2029210135"],"abstract_inverted_index":{"Modern":[0],"transformer-based":[1],"Large":[2],"Language":[3],"Models":[4],"(LLMs)":[5],"are":[6,58,64],"constructed":[7],"with":[8],"a":[9],"series":[10],"of":[11],"decoder":[12],"blocks.":[13],"Each":[14],"block":[15],"comprises":[16],"three":[17],"key":[18],"components:":[19],"(1)":[20],"QKV":[21,33],"generation,":[22],"(2)":[23],"multi-head":[24,44],"attention,":[25],"and":[26,35],"(3)":[27],"feed-forward":[28,36],"networks.":[29],"In":[30],"batched":[31],"processing,":[32],"generation":[34],"networks":[37],"involve":[38],"compute-intensive":[39],"matrix-matrix":[40],"multiplications":[41,49],"(GEMM),":[42],"while":[43,80],"attention":[45],"requires":[46],"bandwidth-heavy":[47],"matrix-vector":[48],"(GEMV).":[50],"Machine":[51],"learning":[52],"accelerators":[53],"like":[54],"TPUs":[55],"or":[56],"NPUs":[57],"proficient":[59],"in":[60],"handling":[61],"GEMM":[62,88],"but":[63],"less":[65],"efficient":[66,77],"for":[67,76],"GEMV":[68,78],"computations.":[69],"Conversely,":[70],"Processing-in-Memory":[71],"(PIM)":[72],"technology":[73],"is":[74],"tailored":[75],"computation,":[79],"it":[81],"lacks":[82],"the":[83],"computational":[84],"power":[85],"to":[86],"handle":[87],"effectively.":[89]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":64},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}