{"id":"https://openalex.org/W4407218648","doi":"https://doi.org/10.1145/3669940.3707282","title":"Tally: Non-Intrusive Performance Isolation for Concurrent Deep Learning Workloads","display_name":"Tally: Non-Intrusive Performance Isolation for Concurrent Deep Learning Workloads","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407218648","doi":"https://doi.org/10.1145/3669940.3707282"},"language":"en","primary_location":{"id":"doi:10.1145/3669940.3707282","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3669940.3707282","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3669940.3707282","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066877556","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0002-0622-9258"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["Stanford University, Stanford, USA, & CentML, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA, & CentML, Toronto, Canada","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022583753","display_name":"Anand Jayarajan","orcid":"https://orcid.org/0000-0002-2118-5935"},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Anand Jayarajan","raw_affiliation_strings":["University of Toronto, Toronto, Canada, Vector Institute, Toronto, Canada, & CentML, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada, Vector Institute, Toronto, Canada, & CentML, Toronto, Canada","institution_ids":["https://openalex.org/I4210127509","https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007585346","display_name":"Gennady Pekhimenko","orcid":"https://orcid.org/0000-0002-3839-0919"},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gennady Pekhimenko","raw_affiliation_strings":["University of Toronto, Toronto, Canada, Vector Institute, Toronto, Canada, & CentML, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada, Vector Institute, Toronto, Canada, & CentML, Toronto, Canada","institution_ids":["https://openalex.org/I4210127509","https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066877556"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":3.1318,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89724275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1052","last_page":"1068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9991999864578247,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9991999864578247,"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":0.9991000294685364,"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":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8273293972015381},{"id":"https://openalex.org/keywords/isolation","display_name":"Isolation (microbiology)","score":0.6760981678962708},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4559221863746643},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.41109979152679443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3660046458244324},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32020676136016846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8273293972015381},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.6760981678962708},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4559221863746643},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.41109979152679443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3660046458244324},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32020676136016846},{"id":"https://openalex.org/C89423630","wikidata":"https://www.wikidata.org/wiki/Q7193","display_name":"Microbiology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3669940.3707282","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3669940.3707282","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3669940.3707282","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3669940.3707282","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1494198834","https://openalex.org/W1506474685","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2133564696","https://openalex.org/W2134427337","https://openalex.org/W2140348470","https://openalex.org/W2153190325","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2323693848","https://openalex.org/W2340897893","https://openalex.org/W2560609797","https://openalex.org/W2565600385","https://openalex.org/W2604184171","https://openalex.org/W2604272474","https://openalex.org/W2734941459","https://openalex.org/W2739273093","https://openalex.org/W2750779823","https://openalex.org/W2888482885","https://openalex.org/W2896457183","https://openalex.org/W2899071864","https://openalex.org/W2912500072","https://openalex.org/W2934208298","https://openalex.org/W2953303875","https://openalex.org/W2956461999","https://openalex.org/W2963748441","https://openalex.org/W2970971581","https://openalex.org/W2971447174","https://openalex.org/W2996264288","https://openalex.org/W3005664618","https://openalex.org/W3034999214","https://openalex.org/W3080999573","https://openalex.org/W3105227206","https://openalex.org/W3128271665","https://openalex.org/W3137350414","https://openalex.org/W3197816522","https://openalex.org/W3202465876","https://openalex.org/W3205898353","https://openalex.org/W4220818654","https://openalex.org/W4232069359","https://openalex.org/W4239521792","https://openalex.org/W4251430302","https://openalex.org/W4252742548","https://openalex.org/W4280633999","https://openalex.org/W4298422451","https://openalex.org/W4311000453","https://openalex.org/W4312901420","https://openalex.org/W4312933868","https://openalex.org/W4318541647","https://openalex.org/W4318541676","https://openalex.org/W4321853806","https://openalex.org/W4376272906","https://openalex.org/W4384918448","https://openalex.org/W4394944658","https://openalex.org/W4394998532","https://openalex.org/W6679436768","https://openalex.org/W6713134421","https://openalex.org/W6727099177","https://openalex.org/W6767098714","https://openalex.org/W6778883912","https://openalex.org/W6784871562","https://openalex.org/W7067822191"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W3086377361"],"abstract_inverted_index":{"GPU":[0,28,47,82,107,166],"underutilization":[1],"is":[2,27],"a":[3,42,80,127],"significant":[4],"concern":[5],"in":[6,49,103],"many":[7],"production":[8,50],"deep":[9],"learning":[10],"clusters,":[11],"leading":[12],"to":[13,24,38,56,96,115,159],"prolonged":[14],"job":[15],"queues":[16],"and":[17,69,90,132],"increased":[18],"operational":[19],"expenses.":[20],"A":[21],"promising":[22],"solution":[23],"this":[25],"inefficiency":[26],"sharing,":[29],"which":[30,111],"improves":[31],"resource":[32],"utilization":[33],"by":[34,120,163],"allowing":[35],"multiple":[36],"workloads":[37,131],"execute":[39],"concurrently":[40,153],"on":[41,126,143],"single":[43],"GPU.":[44],"However,":[45],"deploying":[46],"sharing":[48,83,167],"settings":[51],"faces":[52],"critical":[53],"obstacles":[54],"due":[55],"the":[57,113,144,164],"limitations":[58],"of":[59,130,140,147,175],"existing":[60],"mechanisms,":[61],"including":[62],"high":[63],"integration":[64],"costs,":[65],"inadequate":[66],"performance":[67,88,99],"isolation,":[68],"limited":[70],"application":[71],"compatibility.":[72,93],"To":[73],"address":[74],"these":[75],"issues,":[76],"we":[77],"introduce":[78],"Tally,":[79],"non-intrusive":[81],"mechanism":[84],"that":[85,134],"provides":[86],"robust":[87,98],"isolation":[89,100],"comprehensive":[91],"workload":[92,121],"The":[94],"key":[95],"Tally's":[97],"capability":[101],"lies":[102],"its":[104],"fine-grained":[105],"thread-block-level":[106],"kernel":[108],"scheduling":[109],"strategy,":[110],"allows":[112],"system":[114,177],"effectively":[116],"mitigate":[117],"interference":[118],"caused":[119],"co-execution.":[122],"We":[123],"evaluate":[124],"Tally":[125],"diverse":[128],"range":[129],"show":[133],"it":[135],"incurs":[136],"an":[137],"average":[138],"overhead":[139,161],"only":[141],"7.2%":[142],"99th-percentile":[145],"latency":[146],"high-priority":[148],"inference":[149],"tasks":[150],"when":[151],"executed":[152],"with":[154],"best-effort":[155],"training":[156],"workloads,":[157],"compared":[158],"188.9%":[160],"exhibited":[162],"state-of-the-art":[165],"systems":[168],"like":[169],"TGS,":[170],"while":[171],"achieving":[172],"over":[173],"80%":[174],"TGS's":[176],"throughput.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}