{"id":"https://openalex.org/W7160409312","doi":"https://doi.org/10.1109/lca.2026.3691007","title":"A Simulator for LLM Inference Systems Exploiting CXL Memory Pools","display_name":"A Simulator for LLM Inference Systems Exploiting CXL Memory Pools","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160409312","doi":"https://doi.org/10.1109/lca.2026.3691007"},"language":null,"primary_location":{"id":"doi:10.1109/lca.2026.3691007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2026.3691007","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/A5135494320","display_name":"Jinghan Huang","orcid":null},"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":"Jinghan Huang","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":"https://orcid.org/0009-0009-2314-2734","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108932700","display_name":"Hongkun Zeng","orcid":null},"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":"Hongkun Zeng","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135436249","display_name":"Mike Montano","orcid":null},"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":"Mike Montano","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"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":["School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0009-0008-8973-5164","affiliations":[{"raw_affiliation_string":"School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South 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":["School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0009-0002-4116-3896","affiliations":[{"raw_affiliation_string":"School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081625166","display_name":"Jinin So","orcid":"https://orcid.org/0000-0002-7569-3505"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinin So","raw_affiliation_strings":["Samsung Electronics Corporation, Suwon-si, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-7569-3505","affiliations":[{"raw_affiliation_string":"Samsung Electronics Corporation, Suwon-si, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123917780","display_name":"Junhyeok Im","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junhyeok Im","raw_affiliation_strings":["Samsung Electronics Corporation, Suwon-si, South Korea"],"raw_orcid":"https://orcid.org/0009-0009-5601-3701","affiliations":[{"raw_affiliation_string":"Samsung Electronics Corporation, Suwon-si, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028948116","display_name":"H LEE","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Handeok Lee","raw_affiliation_strings":["Samsung Electronics Corporation, Suwon-si, South Korea"],"raw_orcid":"https://orcid.org/0009-0003-7838-3187","affiliations":[{"raw_affiliation_string":"Samsung Electronics Corporation, Suwon-si, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","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":["School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6629-449X","affiliations":[{"raw_affiliation_string":"School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135491461","display_name":"Nam Sung Kim","orcid":null},"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":"Nam Sung Kim","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":"https://orcid.org/0000-0002-0442-5634","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.55990299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"1","first_page":"202","last_page":"205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.24690000712871552,"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":0.24690000712871552,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.12330000102519989,"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":0.027000000700354576,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5248000025749207},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.35989999771118164},{"id":"https://openalex.org/keywords/random-access-memory","display_name":"Random access memory","score":0.3393999934196472},{"id":"https://openalex.org/keywords/computer-architecture-simulator","display_name":"Computer architecture simulator","score":0.30630001425743103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8127999901771545},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5248000025749207},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.361299991607666},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.35989999771118164},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34790000319480896},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33970001339912415},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.336899995803833},{"id":"https://openalex.org/C201203610","wikidata":"https://www.wikidata.org/wiki/Q5157524","display_name":"Computer architecture simulator","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2922999858856201},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29109999537467957}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2026.3691007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2026.3691007","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"cost":[1],"of":[2,74,130,169],"large":[3],"language":[4],"model":[5,19,54,97],"(LLM)":[6],"inference":[7,43,151,163,187],"is":[8],"heavily":[9],"tied":[10],"to":[11,17,33,50,95,124],"the":[12,72,98,102,106,131,141,166,170,182],"immense":[13],"memory":[14,48,103,122,172],"capacity":[15],"required":[16],"store":[18,51],"parameters\u2014a":[20],"challenge":[21],"exacerbated":[22],"by":[23,71,189],"current":[24],"systems":[25,44],"that":[26,85,175],"replicate":[27],"these":[28],"parameters":[29,55],"across":[30,56,134],"multiple":[31,57],"servers":[32,126],"scale.":[34],"To":[35],"tackle":[36],"this":[37,113],"challenge,":[38],"we":[39,80,111,157],"may":[40],"consider":[41],"LLM":[42],"exploiting":[45],"a":[46,83,116,144,159],"CXL":[47,99,107,121,171],"pool":[49,123],"and":[52,63,88,93,101,139,165,191,195],"share":[53],"servers,":[58],"while":[59],"keeping":[60],"server-specific":[61],"activations":[62],"KV-caches":[64],"within":[65,105],"each":[66],"server\u2019s":[67],"local":[68],"memory.":[69],"Motivated":[70],"lack":[73],"existing":[75],"simulators":[76],"for":[77,137,193],"such":[78],"systems,":[79],"first":[81],"develop":[82],"simulator":[84,114,142],"extends":[86],"LLMServingSim":[87],"integrates":[89],"it":[90],"with":[91],"NS-3":[92],"Mess":[94],"accurately":[96],"switch":[100],"modules":[104],"pool,":[108,173],"respectively.":[109,197],"Second,":[110],"validate":[112],"against":[115],"system":[117],"connecting":[118],"an":[119,177],"industry":[120],"two":[125,128],"running":[127],"instances":[129],"same":[132],"LLM;":[133],"separate":[135],"evaluations":[136],"OPT-1.6B":[138,194],"OPT-6.7B,":[140,196],"demonstrates":[143],"<inline-formula":[145],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[146],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[147],"notation=\"LaTeX\">$\\approx$</tex-math></inline-formula>3%":[148],"error":[149],"in":[150],"latency.":[152],"Lastly,":[153],"using":[154],"our":[155],"simulator,":[156],"uncover":[158],"significant":[160],"sensitivity":[161],"between":[162],"latency":[164,188],"interconnect":[167,180],"bandwidth":[168],"demonstrating":[174],"adopting":[176],"emerging":[178],"optical":[179],"over":[181],"traditional":[183],"electrical":[184],"counterpart":[185],"reduces":[186],"67.9%":[190],"64.4%":[192]},"counts_by_year":[],"updated_date":"2026-05-30T06:14:24.967023","created_date":"2026-05-07T00:00:00"}
