{"id":"https://openalex.org/W7124166838","doi":"https://doi.org/10.1109/icpads67057.2025.11323041","title":"HIOCS: Heuristic Inter-Operator Co-Scheduling Method for Efficient DNN Inference on GPUs","display_name":"HIOCS: Heuristic Inter-Operator Co-Scheduling Method for Efficient DNN Inference on GPUs","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124166838","doi":"https://doi.org/10.1109/icpads67057.2025.11323041"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11323041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5123009975","display_name":"Ning Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]},{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Ning Wang","raw_affiliation_strings":["University of Auckland,Faculty of Engineering and Design,Auckland,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland,Faculty of Engineering and Design,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895","https://openalex.org/I39854758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053872518","display_name":"Andrea Raith","orcid":"https://orcid.org/0000-0002-0417-2972"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]},{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Andrea Raith","raw_affiliation_strings":["University of Auckland,Faculty of Engineering and Design,Auckland,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland,Faculty of Engineering and Design,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895","https://openalex.org/I39854758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088706361","display_name":"Oliver Sinnen","orcid":"https://orcid.org/0000-0002-1550-7416"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]},{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Oliver Sinnen","raw_affiliation_strings":["University of Auckland,Faculty of Engineering and Design,Auckland,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland,Faculty of Engineering and Design,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895","https://openalex.org/I39854758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.868399977684021,"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":0.868399977684021,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.018300000578165054,"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/T14347","display_name":"Big Data and Digital Economy","score":0.01759999990463257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7652000188827515},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6029000282287598},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5489000082015991},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5223000049591064},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.47690001130104065},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4661000072956085},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.36890000104904175},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.35370001196861267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8557999730110168},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7652000188827515},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6029000282287598},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5489000082015991},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5223000049591064},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4661000072956085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40700000524520874},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.35370001196861267},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.34279999136924744},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.31630000472068787},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2994999885559082},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.2660999894142151},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W616339485","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2963446712","https://openalex.org/W2964081807","https://openalex.org/W3012249773","https://openalex.org/W3157306683","https://openalex.org/W3174230151","https://openalex.org/W3217445637","https://openalex.org/W4200091031","https://openalex.org/W4246193833","https://openalex.org/W4308968707","https://openalex.org/W4360995170","https://openalex.org/W4372271902","https://openalex.org/W4380881063","https://openalex.org/W4382202854","https://openalex.org/W4388855541","https://openalex.org/W4390097178","https://openalex.org/W4390263770","https://openalex.org/W4392543698","https://openalex.org/W4394745249","https://openalex.org/W4394944658","https://openalex.org/W4401408831","https://openalex.org/W4401408934","https://openalex.org/W4403210910","https://openalex.org/W4405055872"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"are":[4],"increasingly":[5],"deployed":[6],"in":[7,172],"real-time":[8],"applications,":[9],"yet":[10],"their":[11],"inference":[12,62,173],"performance":[13],"is":[14,100],"often":[15],"constrained":[16],"by":[17,111],"inefficient":[18],"GPU":[19,43,126,143],"utilization.":[20,127],"While":[21],"various":[22],"inter-operator":[23,56],"scheduling":[24],"methods":[25],"have":[26],"been":[27],"proposed":[28],"to":[29,102,121,149,161],"address":[30],"this":[31,93],"issue,":[32],"many":[33],"suffer":[34],"from":[35],"coarse-grained":[36],"operator":[37],"classifications,":[38],"incomplete":[39],"parallelism,":[40],"unawareness":[41],"of":[42],"resource":[44,116],"contention,":[45,117],"etc.":[46],"To":[47],"overcome":[48],"these":[49],"limitations,":[50],"we":[51],"propose":[52],"HIOCS,":[53],"a":[54,71,96],"heuristic":[55,97],"co-scheduling":[57,98],"framework":[58],"that":[59,78,138],"accelerates":[60],"DNN":[61,132],"on":[63,83,92,130],"GPUs":[64],"through":[65],"fine-grained":[66],"kernel-level":[67],"scheduling.":[68],"HIOCS":[69,139,158],"employs":[70],"graph":[72],"optimization":[73],"technique":[74],"at":[75],"kernel":[76,119],"granularity":[77],"reconstructs":[79],"data":[80],"dependencies":[81],"based":[82],"memory":[84],"access":[85],"patterns,":[86],"thereby":[87],"uncovering":[88],"latent":[89],"parallelism.":[90],"Building":[91],"optimized":[94],"graph,":[95],"algorithm":[99],"introduced":[101],"prioritize":[103],"critical-path":[104],"kernels":[105,110],"and":[106,118,124,145,153,166],"selectively":[107],"co-locate":[108],"non-critical":[109],"jointly":[112],"considering":[113],"latency":[114],"impact,":[115],"affinity":[120],"minimize":[122],"makespan":[123],"maximize":[125],"Extensive":[128],"experiments":[129],"popular":[131],"models":[133],"across":[134],"diverse":[135],"domains":[136],"demonstrate":[137],"consistently":[140],"achieves":[141,159],"higher":[142],"utilization":[144],"better":[146],"scalability.":[147],"Compared":[148],"PyTorch":[150],"default":[151],"mode":[152],"the":[154],"state-of-the-art":[155],"method":[156],"Opara,":[157],"up":[160],"<tex":[162,167],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[163,168],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$21.19":[164],"\\times$</tex>":[165,170],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$1.13":[169],"speedup":[171],"latency,":[174],"respectively,":[175],"making":[176],"it":[177],"well-suited":[178],"for":[179],"latency-sensitive":[180],"deployment":[181],"scenarios.":[182]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-15T00:00:00"}