{"id":"https://openalex.org/W7092290176","doi":"https://doi.org/10.1109/tmc.2025.3622698","title":"Cola: Cross-Processor Operator Parallelism for Asynchronous Deep Learning Inference","display_name":"Cola: Cross-Processor Operator Parallelism for Asynchronous Deep Learning Inference","publication_year":2025,"publication_date":"2025-10-17","ids":{"openalex":"https://openalex.org/W7092290176","doi":"https://doi.org/10.1109/tmc.2025.3622698"},"language":null,"primary_location":{"id":"doi:10.1109/tmc.2025.3622698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3622698","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-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":null,"display_name":"Changyao Lin","orcid":"https://orcid.org/0000-0001-6805-2649"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyao Lin","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-6805-2649","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenming Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I874390226","display_name":"China Construction Bank","ror":"https://ror.org/00xkrw816","country_code":"CN","type":"other","lineage":["https://openalex.org/I874390226"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenming Chen","raw_affiliation_strings":["China Construction Steel Structure Engineering Corporation, LTD, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Construction Steel Structure Engineering Corporation, LTD, Shenzhen, China","institution_ids":["https://openalex.org/I874390226"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziyang Zhang","orcid":"https://orcid.org/0000-0003-2539-8257"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ziyang Zhang","raw_affiliation_strings":["NESLab, Politecnico di Milano, Milano, Italy"],"raw_orcid":"https://orcid.org/0000-0003-2539-8257","affiliations":[{"raw_affiliation_string":"NESLab, Politecnico di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jie Liu","orcid":"https://orcid.org/0000-0001-6209-6886"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["National Key Laboratory of Smart Farm Technologies and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-6209-6886","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Smart Farm Technologies and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47611201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"3","first_page":"4346","last_page":"4362"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5414999723434448,"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":0.5414999723434448,"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/T14347","display_name":"Big Data and Digital Economy","score":0.09239999949932098,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.07829999923706055,"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/inference","display_name":"Inference","score":0.7803999781608582},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.739799976348877},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6121000051498413},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.39820000529289246},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3797000050544739},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.3427000045776367},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.33660000562667847},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.32850000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8880000114440918},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7803999781608582},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.739799976348877},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6121000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45100000500679016},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44929999113082886},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.384799987077713},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3822000026702881},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.32850000262260437},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.3190000057220459},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C134765980","wikidata":"https://www.wikidata.org/wiki/Q879126","display_name":"Bitwise operation","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2025.3622698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3622698","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5593098402023315,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G3537643952","display_name":null,"funder_award_id":"62350710797","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2416799949","https://openalex.org/W2531409750","https://openalex.org/W2896457183","https://openalex.org/W2962851801","https://openalex.org/W2963125010","https://openalex.org/W2963163009","https://openalex.org/W3011667710","https://openalex.org/W3014810041","https://openalex.org/W3107241502","https://openalex.org/W3111535274","https://openalex.org/W3164008977","https://openalex.org/W3177372937","https://openalex.org/W3212184265","https://openalex.org/W3212621679","https://openalex.org/W3215253865","https://openalex.org/W3217445637","https://openalex.org/W4282970339","https://openalex.org/W4283020086","https://openalex.org/W4320060064","https://openalex.org/W4372271902","https://openalex.org/W4380926962","https://openalex.org/W4385245566","https://openalex.org/W4395681046","https://openalex.org/W4402897415","https://openalex.org/W4405055872","https://openalex.org/W4410068132","https://openalex.org/W4412915583"],"related_works":[],"abstract_inverted_index":{"Multi-task":[0],"inference,":[1],"as":[2,33],"a":[3,102,151],"prevalent":[4],"inference":[5,21,54,67,78,136],"paradigm":[6],"nowadays,":[7],"requires":[8],"deploying":[9],"multiple":[10],"deep":[11],"learning":[12],"models":[13],"on":[14,90,134,150],"the":[15,46,56,91,108,128,135,161],"hardware":[16],"platform":[17],"to":[18,76,106,119],"concurrently":[19],"process":[20],"tasks.":[22,114],"Modern":[23],"platforms":[24],"are":[25],"typically":[26],"equipped":[27],"with":[28,173],"various":[29],"heterogeneous":[30],"processors,":[31],"such":[32,70,123],"CPU-GPU":[34],"platform.":[35],"To":[36],"reduce":[37],"resource":[38,171],"contention":[39],"and":[40,121,138,147,170],"improve":[41],"quality":[42],"of":[43,130,154],"service":[44],"in":[45,167],"multi-task":[47,66],"scenario,":[48],"existing":[49],"work":[50],"has":[51],"studied":[52],"cross-processor":[53,109,163],"at":[55],"fine-grained":[57],"operator-level.":[58],"However,":[59],"it":[60],"lacks":[61],"specific":[62],"optimizations":[63],"for":[64,80,112],"asynchronous":[65,113],"systems.":[68],"In":[69],"systems,":[71],"tasks":[72],"arrive":[73],"dynamically,":[74],"leading":[75],"diverse":[77],"progress":[79],"each":[81],"model.":[82],"This":[83],"renders":[84],"offline":[85],"optimization":[86],"strategies":[87],"based":[88],"solely":[89],"original":[92],"computation":[93],"graph":[94],"suboptimal":[95],"or":[96],"even":[97],"invalid.":[98],"Therefore,":[99],"we":[100],"propose":[101],"novel":[103],"framework,":[104],"Cola,":[105],"address":[107],"operator":[110,164],"scheduling":[111,125,165],"Cola":[115,149,159],"introduces":[116],"intermediate":[117],"representation":[118],"abstract":[120],"simplify":[122],"dynamic":[124],"problem,":[126],"considering":[127],"impact":[129],"task":[131],"arrival":[132],"patterns":[133],"progress,":[137],"employs":[139],"an":[140],"efficient":[141],"two-phase":[142],"search":[143],"algorithm.":[144],"We":[145],"implemented":[146],"validated":[148],"real-world":[152],"case":[153],"intelligent":[155],"steel":[156],"structure":[157],"manufacturing.":[158],"outperforms":[160],"state-of-the-art":[162],"framework":[166],"both":[168],"throughput":[169],"utilization":[172],"highly":[174],"acceptable":[175],"runtime":[176],"overhead.":[177]},"counts_by_year":[],"updated_date":"2026-02-07T06:11:34.122080","created_date":"2025-10-18T00:00:00"}