{"id":"https://openalex.org/W3202656791","doi":"https://doi.org/10.1145/3464298.3476132","title":"Towards optimal placement and scheduling of DNN operations with Pesto","display_name":"Towards optimal placement and scheduling of DNN operations with Pesto","publication_year":2021,"publication_date":"2021-10-02","ids":{"openalex":"https://openalex.org/W3202656791","doi":"https://doi.org/10.1145/3464298.3476132","mag":"3202656791"},"language":"en","primary_location":{"id":"doi:10.1145/3464298.3476132","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3464298.3476132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Middleware Conference","raw_type":"proceedings-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/A5037377873","display_name":"Ubaid Ullah Hafeez","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ubaid Ullah Hafeez","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077100366","display_name":"Xiao Sun","orcid":"https://orcid.org/0000-0001-7045-0187"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Sun","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024346889","display_name":"Anshul Gandhi","orcid":"https://orcid.org/0000-0002-2351-6523"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anshul Gandhi","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100420216","display_name":"Zhenhua Liu","orcid":"https://orcid.org/0000-0002-8026-4502"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenhua Liu","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0673,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.79414848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9968000054359436,"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":0.8770726919174194},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.7471839785575867},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.6868690848350525},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5707598924636841},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5522661805152893},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45383480191230774},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.44757089018821716},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4296901822090149},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3411429524421692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27101951837539673},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.19995591044425964},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0849645733833313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8770726919174194},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.7471839785575867},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6868690848350525},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5707598924636841},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5522661805152893},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45383480191230774},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44757089018821716},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4296901822090149},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3411429524421692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27101951837539673},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.19995591044425964},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0849645733833313},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3464298.3476132","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3464298.3476132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Middleware Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6672039358","display_name":null,"funder_award_id":"CNS grants 1750109, 1730128, and 1717588","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1442374986","https://openalex.org/W1632114991","https://openalex.org/W1863634311","https://openalex.org/W2105884810","https://openalex.org/W2160815625","https://openalex.org/W2183341477","https://openalex.org/W2335835108","https://openalex.org/W2402144811","https://openalex.org/W2786414509","https://openalex.org/W2808990899","https://openalex.org/W2964081807","https://openalex.org/W2969388332","https://openalex.org/W2970971581","https://openalex.org/W3081168214"],"related_works":["https://openalex.org/W3161249280","https://openalex.org/W2267059662","https://openalex.org/W2364268683","https://openalex.org/W4388411807","https://openalex.org/W1519906715","https://openalex.org/W2478803962","https://openalex.org/W3169430512","https://openalex.org/W2384804534","https://openalex.org/W2154069781","https://openalex.org/W4285818394"],"abstract_inverted_index":{"The":[0,29,115],"increasing":[1,87],"size":[2],"of":[3,12,58,63],"Deep":[4],"Neural":[5],"Networks":[6],"(DNNs)":[7],"has":[8],"necessitated":[9],"the":[10,41,52,56,60,88,124,130,140,144,151,160],"use":[11],"multiple":[13,113],"GPUs":[14,45],"to":[15,25,36,46,76,121,134,142,181,184],"host":[16],"a":[17,21,70,100],"single":[18],"DNN":[19,42,64,190],"model,":[20],"practice":[22],"commonly":[23],"referred":[24],"as":[26,153],"model":[27,33,43,104,125,145,176],"parallelism.":[28],"key":[30,116],"challenge":[31],"for":[32,83,107],"parallelism":[34],"is":[35,120],"efficiently":[37],"and":[38,97,102,127,163,170],"effectively":[39],"partition":[40,80],"across":[44,112,146,187],"avoid":[47],"communication":[48,137],"overheads":[49],"while":[50,138],"maximizing":[51,139],"GPU":[53],"utilization,":[54],"with":[55],"end-goal":[57],"minimizing":[59],"training":[61,90,177],"time":[62,178],"models.":[65,191],"Existing":[66],"approaches":[67],"either":[68],"take":[69],"long":[71],"time(hours":[72],"or":[73,81],"even":[74],"days)":[75],"find":[77],"an":[78,154],"effective":[79],"settle":[82],"sub-optimal":[84],"partitioning,":[85],"invariably":[86],"end-to-end":[89],"effort.":[91],"In":[92],"this":[93],"paper,":[94],"we":[95],"design":[96],"implement":[98,166],"Pesto,":[99],"fast":[101],"near-optimal":[103],"placement":[105,126,162],"technique":[106],"automatically":[108],"partitioning":[109],"arbitrary":[110],"DNNs":[111],"GPUs.":[114,147],"idea":[117],"in":[118,168],"Pesto":[119,157,167,173],"jointly":[122],"optimize":[123],"scheduling":[128],"at":[129],"fine-grained":[131],"operation":[132],"level":[133],"minimize":[135],"inter-GPU":[136],"opportunity":[141],"parallelize":[143],"By":[148],"carefully":[149],"formulating":[150],"problem":[152],"integer":[155],"program,":[156],"can":[158,174],"provide":[159],"optimal":[161],"scheduling.":[164],"We":[165],"TensorFlow":[169],"show":[171],"that":[172],"reduce":[175],"by":[179],"up":[180],"31%":[182],"compared":[183],"state-of-the-art":[185],"approaches,":[186],"several":[188],"large":[189]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}