{"id":"https://openalex.org/W4402130049","doi":"https://doi.org/10.1109/lca.2024.3452699","title":"SmartQuant: CXL-Based AI Model Store in Support of Runtime Configurable Weight Quantization","display_name":"SmartQuant: CXL-Based AI Model Store in Support of Runtime Configurable Weight Quantization","publication_year":2024,"publication_date":"2024-07-01","ids":{"openalex":"https://openalex.org/W4402130049","doi":"https://doi.org/10.1109/lca.2024.3452699"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2024.3452699","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lca.2024.3452699","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/A5045139717","display_name":"Rui Xie","orcid":"https://orcid.org/0000-0003-3177-5071"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rui Xie","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY, USA","Rensselaer Polytechnic Institute, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-3177-5071","affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]},{"raw_affiliation_string":"Rensselaer Polytechnic Institute, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113362542","display_name":"Asad Ul Haq","orcid":null},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asad Ul Haq","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY, USA","Rensselaer Polytechnic Institute, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]},{"raw_affiliation_string":"Rensselaer Polytechnic Institute, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101209866","display_name":"Linsen Ma","orcid":"https://orcid.org/0009-0000-8535-7911"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linsen Ma","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY, USA","Rensselaer Polytechnic Institute, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]},{"raw_affiliation_string":"Rensselaer Polytechnic Institute, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108978655","display_name":"Krystal Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088937","display_name":"Ion Physics (United States)","ror":"https://ror.org/00aac7f28","country_code":"US","type":"company","lineage":["https://openalex.org/I4210088937"]},{"id":"https://openalex.org/I4210129168","display_name":"BASIS International (United States)","ror":"https://ror.org/03q4sef08","country_code":"US","type":"company","lineage":["https://openalex.org/I4210129168"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krystal Sun","raw_affiliation_strings":["BASIS Independent Fremont, Fremont, CA, USA","BASIS Independent Fremont, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BASIS Independent Fremont, Fremont, CA, USA","institution_ids":["https://openalex.org/I4210088937"]},{"raw_affiliation_string":"BASIS Independent Fremont, CA, USA","institution_ids":["https://openalex.org/I4210129168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021284824","display_name":"Sanchari Sen","orcid":"https://orcid.org/0000-0003-0080-2882"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanchari Sen","raw_affiliation_strings":["IBM, Armonk, NY, USA","IBM, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-0080-2882","affiliations":[{"raw_affiliation_string":"IBM, Armonk, NY, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010094713","display_name":"Swagath Venkataramani","orcid":"https://orcid.org/0000-0002-0470-6364"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Swagath Venkataramani","raw_affiliation_strings":["IBM, Armonk, NY, USA","IBM, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-0470-6364","affiliations":[{"raw_affiliation_string":"IBM, Armonk, NY, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324294","display_name":"Liu Liu","orcid":"https://orcid.org/0000-0003-0792-8146"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu Liu","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY, USA","Rensselaer Polytechnic Institute, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]},{"raw_affiliation_string":"Rensselaer Polytechnic Institute, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0003-0985-7986"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY, USA","Rensselaer Polytechnic Institute, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-0985-7986","affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]},{"raw_affiliation_string":"Rensselaer Polytechnic Institute, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5045139717"],"corresponding_institution_ids":["https://openalex.org/I165799507"],"apc_list":null,"apc_paid":null,"fwci":0.9283,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.77453416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"23","issue":"2","first_page":"199","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9344000220298767,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9344000220298767,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9192000031471252,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8164888024330139},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5353854894638062},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5124221444129944},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.44248804450035095},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4379260838031769},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.33815866708755493},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3353264331817627},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16489383578300476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8164888024330139},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5353854894638062},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5124221444129944},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.44248804450035095},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4379260838031769},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.33815866708755493},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3353264331817627},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16489383578300476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2024.3452699","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lca.2024.3452699","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2906364736","https://openalex.org/W3006586535","https://openalex.org/W4385245566","https://openalex.org/W4399677840","https://openalex.org/W6727099177","https://openalex.org/W6769627184","https://openalex.org/W6772383348","https://openalex.org/W6811340617","https://openalex.org/W6850625674","https://openalex.org/W6857551316"],"related_works":["https://openalex.org/W2418291489","https://openalex.org/W2068121105","https://openalex.org/W3096519538","https://openalex.org/W2744747300","https://openalex.org/W4241166160","https://openalex.org/W2384826897","https://openalex.org/W1997466117","https://openalex.org/W2795695574","https://openalex.org/W2300282708","https://openalex.org/W2979160909"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"revealed":[3],"that,":[4],"during":[5],"the":[6,15,37,49,76,87,138,141],"inference":[7,40],"on":[8],"generative":[9,38,128],"AI":[10,39,59,77,129],"models":[11],"such":[12],"as":[13,125],"transformer,":[14],"importance":[16],"of":[17,30,52,140],"different":[18],"weights":[19],"exhibits":[20],"substantial":[21],"context-dependent":[22],"variations.":[23],"This":[24],"naturally":[25],"manifests":[26],"a":[27,95,126],"promising":[28],"potential":[29],"adaptively":[31],"configuring":[32],"weight":[33,44,71,121],"quantization":[34,45,72],"to":[35,73,99,106],"improve":[36,75],"efficiency.":[41,84],"Although":[42],"configurable":[43,120],"can":[46],"readily":[47],"leverage":[48],"hardware":[50],"support":[51],"variable-precision":[53],"arithmetics":[54],"in":[55,115],"modern":[56],"GPU":[57],"and":[58,82,117],"accelerators,":[60],"little":[61],"prior":[62],"research":[63],"has":[64],"studied":[65],"how":[66],"one":[67],"could":[68],"exploit":[69],"variable":[70],"proportionally":[74],"model":[78],"memory":[79,109],"access":[80],"speed":[81],"energy":[83],"Motivated":[85],"by":[86],"rapidly":[88],"maturing":[89],"CXL":[90,108],"ecosystem,":[91],"this":[92,101],"work":[93],"develops":[94],"CXL-based":[96],"design":[97,143],"solution":[98],"fill":[100],"gap.":[102],"The":[103],"key":[104],"is":[105],"allow":[107],"controllers":[110],"play":[111],"an":[112],"active":[113],"role":[114],"supporting":[116],"exploiting":[118],"runtime":[119],"quantization.":[122],"Using":[123],"transformer":[124],"representative":[127],"model,":[130],"we":[131],"carried":[132],"out":[133],"experiments":[134],"that":[135],"well":[136],"demonstrate":[137],"effectiveness":[139],"proposed":[142],"solution.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}