{"id":"https://openalex.org/W4416199201","doi":"https://doi.org/10.1145/3712285.3759846","title":"Compile-Time QoS Scheme for Deep Learning Inferences","display_name":"Compile-Time QoS Scheme for Deep Learning Inferences","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416199201","doi":"https://doi.org/10.1145/3712285.3759846"},"language":null,"primary_location":{"id":"doi:10.1145/3712285.3759846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712285.3759846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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/A5101027331","display_name":"Sungin Hong","orcid":"https://orcid.org/0009-0004-9960-4193"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sungin Hong","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100737610","display_name":"Hyunjun Kim","orcid":"https://orcid.org/0000-0001-6810-0903"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunjun Kim","raw_affiliation_strings":["Samsung Advanced Institute of Technology, Suwon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035561846","display_name":"Hwansoo Han","orcid":"https://orcid.org/0000-0001-7182-8452"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwansoo Han","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101027331"],"corresponding_institution_ids":["https://openalex.org/I848706"],"apc_list":null,"apc_paid":null,"fwci":1.4196,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87783127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1697","last_page":"1709"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.2791000008583069,"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"}},"topics":[{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.2791000008583069,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.2062000036239624,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.131400004029274,"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/scheduling","display_name":"Scheduling (production processes)","score":0.6559000015258789},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.652400016784668},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6373000144958496},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.6345000267028809},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5989000201225281},{"id":"https://openalex.org/keywords/slicing","display_name":"Slicing","score":0.4968000054359436},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4706999957561493},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4081999957561493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8083000183105469},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6559000015258789},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.652400016784668},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6373000144958496},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.6345000267028809},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5989000201225281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5979999899864197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5486999750137329},{"id":"https://openalex.org/C2776190703","wikidata":"https://www.wikidata.org/wiki/Q488148","display_name":"Slicing","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4609000086784363},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4081999957561493},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3133000135421753},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.2515000104904175},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712285.3759846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712285.3759846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G851866139","display_name":null,"funder_award_id":"","funder_id":"https://openalex.org/F4320315121","funder_display_name":"Samsung Advanced Institute of Technology"}],"funders":[{"id":"https://openalex.org/F4320315121","display_name":"Samsung Advanced Institute of Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2110186189","https://openalex.org/W2140348470","https://openalex.org/W2194775991","https://openalex.org/W2581065617","https://openalex.org/W2604514113","https://openalex.org/W2786171709","https://openalex.org/W2952562115","https://openalex.org/W3016939927","https://openalex.org/W3034544214","https://openalex.org/W3043571714","https://openalex.org/W3086560451","https://openalex.org/W3087507349","https://openalex.org/W3095352973","https://openalex.org/W3097411828","https://openalex.org/W3109585842","https://openalex.org/W3121061995","https://openalex.org/W3130689885","https://openalex.org/W3157707676","https://openalex.org/W3158444059","https://openalex.org/W3160694286","https://openalex.org/W3165292244","https://openalex.org/W3174529902","https://openalex.org/W3190445506","https://openalex.org/W3205803342","https://openalex.org/W4210360375","https://openalex.org/W4212986322","https://openalex.org/W4213451626","https://openalex.org/W4214690606","https://openalex.org/W4231332361","https://openalex.org/W4240657935","https://openalex.org/W4280633999","https://openalex.org/W4312641201","https://openalex.org/W4312938066","https://openalex.org/W4313229743","https://openalex.org/W4320063655","https://openalex.org/W4386707684","https://openalex.org/W4394922627"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,11,78],"proliferation":[2],"of":[3,13,45,58,140],"deep":[4,34],"learning":[5,35],"technologies":[6],"across":[7,127],"various":[8],"service":[9],"domains,":[10],"sharing":[12],"accelerators":[14,29],"such":[15],"as":[16],"GPUs,":[17],"TPUs,":[18],"and":[19,114],"NPUs":[20],"for":[21,51],"inference":[22,40],"processing":[23],"has":[24],"become":[25],"increasingly":[26],"common.":[27],"These":[28],"must":[30],"efficiently":[31],"handle":[32],"multiple":[33,84],"services":[36],"operating":[37],"concurrently.":[38],"However,":[39],"requests,":[41],"characterized":[42],"by":[43,137],"sequences":[44],"short-duration":[46],"kernels,":[47],"create":[48],"significant":[49],"challenges":[50],"online":[52],"schedulers":[53],"attempting":[54],"to":[55,76,109,120,143],"maintain":[56],"Quality":[57],"Service":[59],"(QoS)":[60],"guarantees.":[61],"This":[62],"paper":[63],"presents":[64],"QoSlicer,":[65],"a":[66,105],"novel":[67],"compile-time":[68],"QoS":[69,93],"management":[70],"framework":[71],"that":[72,133],"employs":[73],"kernel":[74],"slicing":[75,86,112],"relieve":[77],"burden":[79],"on":[80],"schedulers.":[81],"By":[82],"generating":[83],"pre-determined":[85],"plans,":[87],"QoSlicer":[88,134],"enables":[89],"more":[90],"efficient,":[91],"lightweight":[92],"scheduling":[94,145],"while":[95],"ensuring":[96],"target":[97],"latency":[98],"requirements":[99],"are":[100],"met.":[101],"Our":[102,124],"approach":[103],"incorporates":[104],"heuristic":[106],"search":[107],"algorithm":[108],"identify":[110],"optimal":[111],"plans":[113],"implements":[115],"robust":[116],"performance":[117],"estimation":[118],"models":[119],"validate":[121],"these":[122],"plans.":[123],"experimental":[125],"evaluation":[126],"75":[128],"diverse":[129],"workload":[130],"combinations":[131],"demonstrates":[132],"improves":[135],"throughput":[136],"an":[138],"average":[139],"20.2%":[141],"compared":[142],"state-of-the-art":[144],"techniques.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-12T00:00:00"}