{"id":"https://openalex.org/W4396686523","doi":"https://doi.org/10.1145/3629527.3651436","title":"Performance Optimization in the LLM World 2024","display_name":"Performance Optimization in the LLM World 2024","publication_year":2024,"publication_date":"2024-05-07","ids":{"openalex":"https://openalex.org/W4396686523","doi":"https://doi.org/10.1145/3629527.3651436"},"language":"en","primary_location":{"id":"doi:10.1145/3629527.3651436","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629527.3651436","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629527.3651436","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 15th ACM/SPEC International Conference on Performance Engineering","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/10.1145/3629527.3651436","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5096717924","display_name":"Kingsum Chow","orcid":"https://orcid.org/0009-0004-8385-3638"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kingsum Chow","raw_affiliation_strings":["College of Software Technology, Zhejiang University, Ningbo, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0004-8385-3638","affiliations":[{"raw_affiliation_string":"College of Software Technology, Zhejiang University, Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014032595","display_name":"Yu Tang","orcid":"https://orcid.org/0009-0002-1837-1160"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Tang","raw_affiliation_strings":["College of Software Technology, Zhejiang University, Ningbo City, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0002-1837-1160","affiliations":[{"raw_affiliation_string":"College of Software Technology, Zhejiang University, Ningbo City, Zhejiang, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096717925","display_name":"Zhiheng Lyu","orcid":"https://orcid.org/0009-0005-0580-8476"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiheng Lyu","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0005-0580-8476","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096717926","display_name":"Anil Rajput","orcid":"https://orcid.org/0009-0003-2782-2469"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anil Rajput","raw_affiliation_strings":["Datacenter Ecosystem, AMD Corporation, Portland, OR, USA"],"raw_orcid":"https://orcid.org/0009-0003-2782-2469","affiliations":[{"raw_affiliation_string":"Datacenter Ecosystem, AMD Corporation, Portland, OR, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052842523","display_name":"Khun Ban","orcid":"https://orcid.org/0009-0006-8787-1651"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khun Ban","raw_affiliation_strings":["Datacenter and AI, Intel Corporation, Portland, OR, USA"],"raw_orcid":"https://orcid.org/0009-0006-8787-1651","affiliations":[{"raw_affiliation_string":"Datacenter and AI, Intel Corporation, Portland, OR, USA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5096717924"],"corresponding_institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.0092,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75968193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.8694999814033508,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13553","display_name":"Age of Information Optimization","score":0.8694999814033508,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8068000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.6549192667007446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5287463665008545},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.48829150199890137},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.4647936224937439},{"id":"https://openalex.org/keywords/consumption","display_name":"Consumption (sociology)","score":0.4324359893798828},{"id":"https://openalex.org/keywords/cost-reduction","display_name":"Cost reduction","score":0.4189550578594208},{"id":"https://openalex.org/keywords/operational-costs","display_name":"Operational costs","score":0.4120379686355591},{"id":"https://openalex.org/keywords/engineering-management","display_name":"Engineering management","score":0.37646061182022095},{"id":"https://openalex.org/keywords/environmental-economics","display_name":"Environmental economics","score":0.33075106143951416},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.27648043632507324},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2703440189361572},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.250293105840683},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.17085912823677063},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11917626857757568},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.09575897455215454}],"concepts":[{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.6549192667007446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5287463665008545},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.48829150199890137},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.4647936224937439},{"id":"https://openalex.org/C30772137","wikidata":"https://www.wikidata.org/wiki/Q5164762","display_name":"Consumption (sociology)","level":2,"score":0.4324359893798828},{"id":"https://openalex.org/C2778820799","wikidata":"https://www.wikidata.org/wiki/Q3454688","display_name":"Cost reduction","level":2,"score":0.4189550578594208},{"id":"https://openalex.org/C2986883954","wikidata":"https://www.wikidata.org/wiki/Q1362005","display_name":"Operational costs","level":2,"score":0.4120379686355591},{"id":"https://openalex.org/C110354214","wikidata":"https://www.wikidata.org/wiki/Q6314146","display_name":"Engineering management","level":1,"score":0.37646061182022095},{"id":"https://openalex.org/C134560507","wikidata":"https://www.wikidata.org/wiki/Q753291","display_name":"Environmental economics","level":1,"score":0.33075106143951416},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.27648043632507324},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2703440189361572},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.250293105840683},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.17085912823677063},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11917626857757568},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09575897455215454},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3629527.3651436","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629527.3651436","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629527.3651436","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3629527.3651436","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629527.3651436","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629527.3651436","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396686523.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2055404047","https://openalex.org/W2368997467","https://openalex.org/W2033838163","https://openalex.org/W2034245280","https://openalex.org/W2027182549","https://openalex.org/W2527765084","https://openalex.org/W1794828807","https://openalex.org/W2090207500","https://openalex.org/W2413294739","https://openalex.org/W2492414969"],"abstract_inverted_index":{"The":[0,45,103,132],"popularity":[1],"and":[2,29,48,78,98,156,162],"adoption":[3],"of":[4,106,114,129,134,142,146],"large":[5],"language":[6],"models":[7],"(LLM)":[8],"like":[9],"ChatGPT":[10,18],"has":[11],"evolved":[12],"rapidly.":[13],"LLM":[14,58,147,169],"pre-training":[15],"is":[16,19,122,137],"expensive.":[17],"estimated":[20],"to":[21,27,32,61,73,81,138,158],"cost":[22,37,80,110],"over":[23,41],"700,000":[24],"per":[25],"day":[26],"operate,":[28],"using":[30],"GPT-4":[31],"support":[33],"customer":[34],"service":[35],"can":[36],"a":[38,43],"small":[39],"business":[40],"21,000":[42],"month.":[44],"high":[46],"infrastructure":[47],"financial":[49],"costs,":[50],"coupled":[51],"with":[52],"the":[53,66,70,75,79,86,91,107,112,116,119,140,154,168],"specialized":[54],"talent":[55],"required,":[56],"make":[57],"technology":[59],"inaccessible":[60],"most":[62],"organizations.":[63],"For":[64],"instance,":[65],"up-front":[67],"costs":[68],"include":[69],"emissions":[71],"generated":[72],"manufacture":[74],"relevant":[76],"hardware":[77,84],"run":[82],"that":[83],"during":[85],"training":[87],"procedure,":[88],"both":[89],"while":[90,99],"machines":[92],"are":[93,101],"operating":[94],"at":[95],"full":[96],"capacity":[97],"they":[100],"not.":[102],"best":[104],"estimate":[105],"dynamic":[108],"computing":[109],"in":[111,164,167],"case":[113],"GPT-3,":[115],"model":[117],"behind":[118],"original":[120],"ChatGPT,":[121],"approximately":[123],"1,287,000":[124],"kWh,":[125],"or":[126],"552":[127],"tons":[128],"carbon":[130],"dioxide.":[131],"goal":[133],"this":[135],"workshop":[136],"address":[139],"urgency":[141],"reducing":[143],"energy":[144],"consumption":[145],"applications,":[148],"by":[149],"bringing":[150],"together":[151],"researchers":[152],"from":[153],"academia":[155],"industry":[157],"share":[159],"their":[160],"experience":[161],"insights":[163],"performance":[165],"engineering":[166],"world.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}