{"id":"https://openalex.org/W7140078303","doi":"https://doi.org/10.1109/lca.2026.3676795","title":"Enabling Computation and Communication Overlap in PIMs for On-Device LLM Inference","display_name":"Enabling Computation and Communication Overlap in PIMs for On-Device LLM Inference","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140078303","doi":"https://doi.org/10.1109/lca.2026.3676795"},"language":null,"primary_location":{"id":"doi:10.1109/lca.2026.3676795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2026.3676795","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-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/A5130359006","display_name":"Siu Jeong","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":"Siu Jeong","raw_affiliation_strings":["KAIST, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0009-0006-9989-0091","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053359413","display_name":"Suhwan Kim","orcid":"https://orcid.org/0000-0002-5305-7364"},"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":"Suhwan Kim","raw_affiliation_strings":["KAIST, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130376202","display_name":"Changyong Eom","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":"Changyong Eom","raw_affiliation_strings":["KAIST, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0009-0002-4680-4832","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047149607","display_name":"Jaehyuk Huh","orcid":"https://orcid.org/0000-0002-1742-047X"},"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":"Jaehyuk Huh","raw_affiliation_strings":["KAIST, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-1742-047X","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39200881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"1","first_page":"126","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12131","display_name":"Wireless Signal Modulation Classification","score":0.09510000050067902,"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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.09510000050067902,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.041200000792741776,"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/T12334","display_name":"Lung Cancer Research Studies","score":0.03290000185370445,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.582099974155426},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5694000124931335},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3271999955177307},{"id":"https://openalex.org/keywords/algorithm-design","display_name":"Algorithm design","score":0.26570001244544983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8215000033378601},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.582099974155426},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5694000124931335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37950000166893005},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2026.3676795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2026.3676795","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3631365055","display_name":null,"funder_award_id":"RS-2024-00347114","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"DRAM-based":[0],"processing-in-memory":[1],"(PIM)":[2],"exploits":[3],"all-bank":[4,121],"execution":[5,102],"to":[6,43,107,120],"accelerate":[7],"memory-bound":[8],"workloads,":[9],"but":[10],"limited":[11],"PIM":[12,24,99],"capacity":[13],"makes":[14],"runtime":[15],"data":[16,38,67],"movement":[17],"unavoid":[18],"able":[19],"and":[20,29,37,40,87,109,122],"often":[21],"performance-critical.":[22],"Existing":[23],"architectures":[25],"tightly":[26],"couple":[27],"computation":[28,36,72],"memory":[30],"access":[31],"across":[32],"all":[33,80],"banks,":[34],"serializing":[35],"transfer":[39,68],"limiting":[41],"opportunities":[42],"hide":[44],"communication":[45],"latency.":[46],"This":[47],"paper":[48],"proposes":[49],"a":[50,58,96],"bank-level":[51],"computation\u2013communication":[52],"overlap":[53,124],"mechanism":[54],"that":[55],"selectively":[56],"assigns":[57],"subset":[59],"of":[60,79,105],"bank":[61,81],"resources":[62],"for":[63],"communication,":[64],"enabling":[65],"concurrent":[66],"without":[69],"disrupting":[70],"ongoing":[71],"while":[73],"preserving":[74],"the":[75],"unified":[76],"control":[77],"model":[78,91],"PIM.":[82],"Evaluations":[83],"on":[84],"mixture-of-experts":[85],"(MoE)":[86],"multi":[88],"small":[89],"language":[90],"(multi-SLM)":[92],"inference":[93],"workloads":[94],"using":[95],"simulated":[97],"LPDDR5-based":[98],"system":[100],"show":[101],"time":[103],"reductions":[104],"up":[106],"19%":[108],"16%,":[110],"respectively,":[111],"along":[112],"with":[113],"consistently":[114],"improved":[115],"channel":[116],"bandwidth":[117],"utilization":[118],"compared":[119],"channel-level":[123],"baselines.":[125]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}
