{"id":"https://openalex.org/W4312038612","doi":"https://doi.org/10.1145/3528535.3565247","title":"Slice-Tune","display_name":"Slice-Tune","publication_year":2022,"publication_date":"2022-11-07","ids":{"openalex":"https://openalex.org/W4312038612","doi":"https://doi.org/10.1145/3528535.3565247"},"language":"en","primary_location":{"id":"doi:10.1145/3528535.3565247","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3528535.3565247","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3528535.3565247","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM/IFIP International Middleware Conference","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/10.1145/3528535.3565247","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077061884","display_name":"Aditya Dhakal","orcid":"https://orcid.org/0000-0002-8297-8525"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Dhakal","raw_affiliation_strings":["University of California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053712998","display_name":"K. K. Ramakrishnan","orcid":"https://orcid.org/0000-0003-1849-5155"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. K. Ramakrishnan","raw_affiliation_strings":["University of California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081037214","display_name":"Sameer G. Kulkarni","orcid":"https://orcid.org/0000-0003-4727-6875"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sameer G. Kulkarni","raw_affiliation_strings":["IIT Gandhinagar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Gandhinagar","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101915392","display_name":"Puneet Sharma","orcid":"https://orcid.org/0000-0003-4594-8164"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Puneet Sharma","raw_affiliation_strings":["Hewlett Packard Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett Packard Labs","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089537772","display_name":"Junguk Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junguk Cho","raw_affiliation_strings":["Hewlett Packard Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett Packard Labs","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3997,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80573477,"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":"228","last_page":"240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9979000091552734,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9976000189781189,"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":0.8810335993766785},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7208131551742554},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7025511860847473},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5667209625244141},{"id":"https://openalex.org/keywords/multiplexing","display_name":"Multiplexing","score":0.4787791967391968},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4654778838157654},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4638082981109619},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44546782970428467},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4429188668727875},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4185648560523987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18907907605171204},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.16921982169151306},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1600174605846405},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12797284126281738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8810335993766785},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7208131551742554},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7025511860847473},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5667209625244141},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.4787791967391968},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4654778838157654},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4638082981109619},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44546782970428467},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4429188668727875},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4185648560523987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18907907605171204},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.16921982169151306},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1600174605846405},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12797284126281738},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3528535.3565247","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3528535.3565247","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3528535.3565247","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM/IFIP International Middleware Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3528535.3565247","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3528535.3565247","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3528535.3565247","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM/IFIP International Middleware Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1925563844","display_name":"CRI: CI-EN: Collaborative Research: OpenNetVM: A Software Platform Enabling Network Function Virtualization Research","funder_award_id":"1823270","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3600336292","display_name":null,"funder_award_id":"CNS-1818971","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6392699063","display_name":null,"funder_award_id":"CRI-1823270","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848313559","display_name":"NeTS: JUNO2: Resilient Disaster Communications in the Social-Media Era","funder_award_id":"1818971","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312038612.pdf","grobid_xml":"https://content.openalex.org/works/W4312038612.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2734941459","https://openalex.org/W2892220819","https://openalex.org/W2952562115","https://openalex.org/W2982157693","https://openalex.org/W3091795552","https://openalex.org/W3095488153","https://openalex.org/W3097411828","https://openalex.org/W3107207569","https://openalex.org/W3127819678","https://openalex.org/W3209166877","https://openalex.org/W3210617645","https://openalex.org/W3214476430","https://openalex.org/W4283727273"],"related_works":["https://openalex.org/W3008625068","https://openalex.org/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W2001568286","https://openalex.org/W3035501883","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820"],"abstract_inverted_index":{"Autotuning":[0],"DNN":[1,55,82,212,225],"models":[2,38,165],"prior":[3],"to":[4,79,125,130,148,205,230],"their":[5],"deployment":[6],"is":[7,22],"an":[8],"essential":[9],"but":[10],"time-consuming":[11],"task.":[12],"Using":[13],"expensive":[14],"(and":[15],"power-hungry)":[16],"GPU":[17,32,46,61,69,103,208,218,221],"and":[18,136,139,162,219,232,248],"TPU":[19],"accelerators":[20],"efficiently":[21,149],"also":[23,201],"key.":[24],"Since":[25],"DNNs":[26],"do":[27],"not":[28],"always":[29],"use":[30,150],"a":[31,54,81,99,122,127,173,198,216,237],"fully,":[33],"spatial":[34],"multiplexing":[35],"of":[36,45,91,102,133,157,194,197,239],"multiple":[37,187],"can":[39],"provide":[40,87],"just":[41],"the":[42,59,88,110,134,155,160,169,183],"right":[43,89],"amount":[44,90],"resources":[47,62,70,93,104,152],"for":[48],"each":[49],"DNN.":[50],"We":[51,76,176,200],"find":[52],"that":[53,85],"model":[56,112,128,185],"tuned":[57,111],"with":[58],"maximum":[60],"has":[63],"higher":[64],"inference":[65,74,108,115],"latency":[66],"if":[67],"less":[68],"are":[71,105,166],"available":[72,106],"at":[73,107],"time.":[75],"present":[77],"methods":[78],"tune":[80,126],"model,":[83],"so":[84],"we":[86],"accelerator":[92],"during":[94,179],"tuning.":[95],"Thus,":[96],"even":[97],"when":[98],"wide":[100],"range":[101],"time,":[109],"achieves":[113],"low":[114],"latency.":[116],"Further,":[117],"existing":[118],"autotuning":[119,146,213,226,234,244],"frameworks":[120,147,245],"take":[121],"long":[123],"time":[124,214,227],"due":[129],"inefficient":[131],"utilization":[132],"client":[135,161],"server-side":[137],"CPU":[138],"GPU.":[140],"Our":[141],"system,":[142],"Slice-Tune,":[143],"improves":[144],"several":[145],"system":[151],"by":[153,181,228,236],"re-thinking":[154],"partitioning":[156],"tasks":[158],"between":[159],"server":[163,170,203],"(where":[164],"profiled":[167],"on":[168],"GPU),":[171],"in":[172,215,220],"Kubernetes":[174],"environment.":[175],"increase":[177,233],"parallelism":[178],"tuning":[180,184,188,193],"sharding":[182],"across":[186,241],"application":[189],"instances,":[190],"providing":[191],"concurrent":[192],"different":[195,243],"operators":[196],"model.":[199],"scale":[202],"instances":[204],"achieve":[206],"better":[207],"multiplexing.":[209],"Slice-Tune":[210,223],"reduces":[211],"single":[217],"clusters.":[222],"decreases":[224],"up":[229],"75%,":[231],"throughput":[235],"factor":[238],"5,":[240],"3":[242],"(TVM,":[246],"Ansor,":[247],"Chameleon).":[249]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-01-04T00:00:00"}