{"id":"https://openalex.org/W4407425079","doi":"https://doi.org/10.1145/3676641.3716267","title":"PIM Is All You Need: A CXL-Enabled GPU-Free System for Large Language Model Inference","display_name":"PIM Is All You Need: A CXL-Enabled GPU-Free System for Large Language Model Inference","publication_year":2025,"publication_date":"2025-03-27","ids":{"openalex":"https://openalex.org/W4407425079","doi":"https://doi.org/10.1145/3676641.3716267"},"language":"en","primary_location":{"id":"doi:10.1145/3676641.3716267","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676641.3716267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.07578","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046763643","display_name":"Yufeng Gu","orcid":"https://orcid.org/0000-0003-1918-7533"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yufeng Gu","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026959597","display_name":"Alireza Khadem","orcid":"https://orcid.org/0000-0002-7615-5514"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alireza Khadem","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088614979","display_name":"Sumanth Umesh","orcid":"https://orcid.org/0000-0003-1893-2845"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sumanth Umesh","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ning Liang","orcid":"https://orcid.org/0009-0000-5700-4991"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ning Liang","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116249053","display_name":"Xavier Servot","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Xavier Servot","raw_affiliation_strings":["ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050695684","display_name":"Onur Mutlu","orcid":"https://orcid.org/0000-0002-0075-2312"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Onur Mutlu","raw_affiliation_strings":["ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102849990","display_name":"Ravishankar Iyer","orcid":"https://orcid.org/0000-0001-5383-9561"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravi Iyer","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027544576","display_name":"Reetuparna Das","orcid":"https://orcid.org/0000-0002-5894-8342"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reetuparna Das","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5046763643"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":53.8924,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.99832222,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"862","last_page":"881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9925000071525574,"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":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.860276460647583},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5841017961502075},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5013415813446045},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4930705726146698},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.48407331109046936},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.45931676030158997},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44197148084640503},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4367714822292328},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3782998323440552},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2332758903503418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19777411222457886},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.15328481793403625},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10748636722564697},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1029873788356781}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.860276460647583},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5841017961502075},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5013415813446045},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4930705726146698},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.48407331109046936},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.45931676030158997},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44197148084640503},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4367714822292328},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3782998323440552},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2332758903503418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19777411222457886},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.15328481793403625},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10748636722564697},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1029873788356781},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3676641.3716267","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676641.3716267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.07578","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.07578","pdf_url":"https://arxiv.org/pdf/2502.07578","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.07578","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.07578","pdf_url":"https://arxiv.org/pdf/2502.07578","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1416736854","display_name":null,"funder_award_id":"1908601","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2342797219","display_name":null,"funder_award_id":"101047160","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G339059864","display_name":null,"funder_award_id":"1652294","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3896616236","display_name":null,"funder_award_id":"1652294, 190860","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G4051374864","display_name":null,"funder_award_id":"101047","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G490593687","display_name":null,"funder_award_id":"Intel","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6755165505","display_name":null,"funder_award_id":"award","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7306266762","display_name":null,"funder_award_id":"CAREER-1652294","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4407425079.pdf"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4282555269","https://openalex.org/W4320067983","https://openalex.org/W4377865306"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2055733372","https://openalex.org/W3022067003"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Model":[2],"(LLM)":[3],"inference":[4,88,149],"uses":[5],"an":[6],"autoregressive":[7],"manner":[8],"to":[9,23,50,61,65,78,135],"generate":[10,66],"one":[11],"token":[12],"at":[13],"a":[14,82,100],"time,":[15,40],"which":[16],"exhibits":[17],"notably":[18],"lower":[19],"operational":[20,93],"intensity":[21,94],"compared":[22],"earlier":[24],"Machine":[25],"Learning":[26],"(ML)":[27],"models":[28],"such":[29,112],"as":[30,113],"encoder-only":[31],"transformers":[32],"and":[33,46,70,95,115,132],"Convolutional":[34],"Neural":[35],"Networks.":[36],"At":[37],"the":[38,87,126,146],"same":[39],"LLMs":[41,55,131],"possess":[42],"large":[43,74,83],"parameter":[44],"sizes":[45],"use":[47],"key-value":[48,75],"caches":[49],"store":[51],"context":[52,57],"information.":[53],"Modern":[54],"support":[56],"windows":[58],"with":[59],"up":[60],"1":[62],"million":[63],"tokens":[64],"versatile":[67],"text,":[68],"audio,":[69],"video":[71],"content.":[72],"A":[73],"cache":[76],"unique":[77],"each":[79],"prompt":[80],"requires":[81],"memory":[84,102],"capacity,":[85],"limiting":[86],"batch":[89,97],"size.":[90],"Both":[91],"low":[92],"limited":[96],"size":[98],"necessitate":[99],"high":[101],"bandwidth.":[103],"However,":[104],"contemporary":[105],"hardware":[106],"systems":[107],"for":[108,120,137,145],"ML":[109],"model":[110],"deployment,":[111],"GPUs":[114],"TPUs,":[116],"are":[117,142],"primarily":[118],"optimized":[119],"compute":[121,139],"throughput.":[122],"This":[123],"mismatch":[124],"challenges":[125],"efficient":[127],"deployment":[128],"of":[129],"advanced":[130],"makes":[133],"users":[134],"pay":[136],"expensive":[138],"resources":[140],"that":[141],"poorly":[143],"utilized":[144],"memory-bound":[147],"LLM":[148],"tasks.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":13}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}