{"id":"https://openalex.org/W4401408916","doi":"https://doi.org/10.1145/3673038.3673053","title":"IMI: In-memory Multi-job Inference Acceleration for Large Language Models","display_name":"IMI: In-memory Multi-job Inference Acceleration for Large Language Models","publication_year":2024,"publication_date":"2024-08-08","ids":{"openalex":"https://openalex.org/W4401408916","doi":"https://doi.org/10.1145/3673038.3673053"},"language":"en","primary_location":{"id":"doi:10.1145/3673038.3673053","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673053","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673053","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 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673053","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053852861","display_name":"Bin Gao","orcid":"https://orcid.org/0000-0001-5009-3514"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Bin Gao","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5009-3514","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101482096","display_name":"Zhehui Wang","orcid":"https://orcid.org/0000-0002-7139-724X"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhehui Wang","raw_affiliation_strings":["Institute of High-Performance Computing, A*STAR, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7139-724X","affiliations":[{"raw_affiliation_string":"Institute of High-Performance Computing, A*STAR, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087400457","display_name":"Zhuomin He","orcid":"https://orcid.org/0000-0002-3477-0607"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuomin He","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0002-3477-0607","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101630043","display_name":"Tao Luo","orcid":"https://orcid.org/0000-0002-3415-3676"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tao Luo","raw_affiliation_strings":["Institute of High-Performance Computing, A*STAR, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-3415-3676","affiliations":[{"raw_affiliation_string":"Institute of High-Performance Computing, A*STAR, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023989495","display_name":"Weng\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-4281-2053"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weng-Fai Wong","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4281-2053","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102001977","display_name":"Zhi Zhou","orcid":"https://orcid.org/0000-0003-0307-266X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Zhou","raw_affiliation_strings":["Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0000-0003-0307-266X","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5053852861"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.6623,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74268171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"752","last_page":"761"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9905999898910522,"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":0.9905999898910522,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9731000065803528,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7675093412399292},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6932297945022583},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5922253727912903},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4097551107406616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36275115609169006},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35903775691986084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7675093412399292},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6932297945022583},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5922253727912903},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4097551107406616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36275115609169006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35903775691986084},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3673038.3673053","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673053","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673053","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 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3673038.3673053","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673053","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673053","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 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401408916.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W600310561","https://openalex.org/W1978401104","https://openalex.org/W2280183206","https://openalex.org/W2510186576","https://openalex.org/W2518281301","https://openalex.org/W2613989746","https://openalex.org/W3005999147","https://openalex.org/W3092368495","https://openalex.org/W3100710793","https://openalex.org/W3101275799","https://openalex.org/W3111375540","https://openalex.org/W3133696297","https://openalex.org/W3159687150","https://openalex.org/W3189166979","https://openalex.org/W4200477077","https://openalex.org/W4280496502","https://openalex.org/W4287980064","https://openalex.org/W4327486547","https://openalex.org/W4387321091","https://openalex.org/W6790690058"],"related_works":["https://openalex.org/W2390829436","https://openalex.org/W1989791859","https://openalex.org/W2565094479","https://openalex.org/W602859758","https://openalex.org/W2006439817","https://openalex.org/W1971289376","https://openalex.org/W2379101322","https://openalex.org/W2055243143","https://openalex.org/W1992553864","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4,11],"increasingly":[5],"used":[6],"in":[7,53,111,120,128],"various":[8],"applications":[9],"but":[10],"computationally":[12],"complex":[13],"and":[14,57,82,92,126],"energy-consuming":[15],"due":[16,108],"to":[17,63,109,139],"the":[18,77,141,160,164],"high":[19],"volume":[20],"of":[21,51,79,115,123,162,168],"off-chip":[22],"memory":[23],"accesses.":[24],"Processing-in-Memory":[25],"(PIM)":[26],"has":[27],"emerged":[28],"as":[29,157,159],"a":[30,89,135],"potential":[31],"solution":[32,91],"for":[33,41,48],"efficient":[34],"inference.":[35],"However,":[36,99],"existing":[37],"PIM":[38],"accelerators":[39],"designed":[40],"deep":[42],"neural":[43],"networks":[44],"(DNNs)":[45],"aren\u2019t":[46],"suitable":[47],"LLMs":[49],"because":[50],"differences":[52],"operations,":[54],"input":[55],"sizes,":[56],"job":[58,72,93,130,145],"completion":[59],"times.":[60],"This":[61,132],"leads":[62],"performance":[64],"issues":[65],"like":[66],"head-of-line":[67],"blocking":[68],"where":[69],"an":[70],"earlier":[71],"can":[73,152],"monopolize":[74],"resources":[75],"at":[76],"expense":[78],"later":[80],"jobs,":[81],"low":[83],"resource":[84,155],"utilization.":[85],"To":[86],"improve":[87,154],"efficiency,":[88],"time-multiplex":[90],"colocation":[94],"accelerator":[95,138],"could":[96],"be":[97],"beneficial.":[98],"facilitating":[100],"multi-job":[101],"execution":[102],"with":[103],"in-memory":[104],"acceleration":[105],"is":[106],"challenging":[107],"limitations":[110],"memristor":[112],"architecture,":[113],"inefficiency":[114],"non-stationary":[116],"weight":[117],"programming,":[118],"difficulty":[119],"dynamic":[121,129],"partitioning":[122],"hardware":[124],"resources,":[125],"complexity":[127],"scheduling.":[131],"work":[133],"proposes":[134],"PIM-based":[136],"LLM":[137,143],"enable":[140],"concurrent":[142],"inference":[144],"execution.":[146],"The":[147],"experiment":[148],"shows":[149],"that":[150],"IMI":[151],"significantly":[153],"utilization":[156],"well":[158],"rate":[161],"satisfying":[163],"service":[165],"level":[166],"requirements":[167],"jobs.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}