{"id":"https://openalex.org/W4391316601","doi":"https://doi.org/10.1145/3638264.3638278","title":"AIGPU: An Arithmetic-Intensity-Guided Single-GPU Scheduling Model","display_name":"AIGPU: An Arithmetic-Intensity-Guided Single-GPU Scheduling Model","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391316601","doi":"https://doi.org/10.1145/3638264.3638278"},"language":"en","primary_location":{"id":"doi:10.1145/3638264.3638278","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3638264.3638278","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3638264.3638278","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Mathematics Intelligent Computing and Machine Learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3638264.3638278","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024213719","display_name":"Jiabin Zheng","orcid":"https://orcid.org/0009-0000-7628-9320"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabin Zheng","raw_affiliation_strings":["Dongguan University of Technology, China"],"raw_orcid":"https://orcid.org/0009-0000-7628-9320","affiliations":[{"raw_affiliation_string":"Dongguan University of Technology, China","institution_ids":["https://openalex.org/I2799850029"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026734359","display_name":"Wei Tan","orcid":"https://orcid.org/0000-0003-2621-8473"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Tan","raw_affiliation_strings":["Dongguan University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-2621-8473","affiliations":[{"raw_affiliation_string":"Dongguan University of Technology, China","institution_ids":["https://openalex.org/I2799850029"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2799850029"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21997226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"64","last_page":"69"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9973000288009644,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8701302409172058},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7894625067710876},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7476193308830261},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6440668106079102},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.545168399810791},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.49578461050987244},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4473945200443268},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.42215681076049805},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4122089445590973},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.10919135808944702},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10734570026397705},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.0927090048789978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8701302409172058},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7894625067710876},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7476193308830261},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6440668106079102},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.545168399810791},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.49578461050987244},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4473945200443268},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.42215681076049805},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4122089445590973},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.10919135808944702},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10734570026397705},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.0927090048789978},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"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:10.1145/3638264.3638278","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3638264.3638278","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3638264.3638278","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Mathematics Intelligent Computing and Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3638264.3638278","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3638264.3638278","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3638264.3638278","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Mathematics Intelligent Computing and Machine Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G7169601710","display_name":null,"funder_award_id":"221106024","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391316601.pdf","grobid_xml":"https://content.openalex.org/works/W4391316601.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2002555321","https://openalex.org/W2011039300","https://openalex.org/W2080592089","https://openalex.org/W2910063209","https://openalex.org/W2964330525","https://openalex.org/W4220728567"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"With":[0],"the":[1,15,62,70,95,105,157,160,175,180,192,200],"advent":[2],"of":[3,64,97,122,195,211],"large":[4],"AI":[5],"models,":[6],"GPU":[7,35,46,71,161,201,209],"has":[8,24],"become":[9],"a":[10,26,33,44,120],"primary":[11],"co-processor":[12],"for":[13,100],"accelerating":[14],"training":[16],"processes.":[17],"Research":[18],"on":[19,144],"efficiently":[20,31],"utilizing":[21],"multi-GPU":[22,182],"systems":[23],"been":[25],"lot;":[27],"nevertheless,":[28],"studies":[29],"about":[30],"exploiting":[32],"single":[34,45],"are":[36,135],"scarce.":[37],"The":[38,154],"common":[39],"throughput-oriented":[40],"way":[41],"to":[42,48,93,118,124,137,165,174],"control":[43],"is":[47,187,202],"launch":[49,125],"kernels":[50,66,123,197],"as":[51,53,107],"many":[52],"possible":[54],"under":[55],"memory":[56],"safety.":[57],"However,":[58],"in":[59,74],"this":[60,81],"case,":[61],"set":[63,121],"launched":[65],"might":[67],"not":[68],"utilize":[69],"efficiently,":[72],"resulting":[73],"idle":[75],"compute":[76],"or":[77],"bandwidth":[78],"resources.":[79],"In":[80,127],"paper,":[82],"we":[83],"propose":[84],"AIGPU":[85,206],"\u2014":[86,92],"an":[87,108],"arithmetic-intensity-guided":[88],"single-GPU":[89,177],"scheduling":[90,116,178,183],"model":[91,106],"evaluate":[94,138],"degree":[96],"overlapped":[98,193],"execution":[99,194],"multiple":[101,196],"kernels.":[102],"We":[103,140],"formulate":[104],"integer":[109],"linear":[110],"programming(ILP)":[111],"problem":[112],"and":[113,169,179],"use":[114],"its":[115],"decisions":[117],"select":[119],"concurrently.":[126],"our":[128,142],"implementation,":[129],"two":[130],"policies":[131],"with":[132],"different":[133],"granularities":[134],"proposed":[136],"AIGPU.":[139],"demonstrate":[141],"method":[143],"NVIDIA":[145],"RTX":[146],"3080Ti":[147],"using":[148],"eight":[149],"benchmarks":[150],"from":[151],"CUDA":[152],"SDK.":[153],"experiments":[155],"show":[156],"technique":[158],"improves":[159],"throughput":[162],"by":[163],"up":[164],"78.6%(on":[166],"average":[167,171,213],"21%)":[168],"267%(on":[170],"133%)":[172],"compared":[173],"state-of-the-art":[176,181],"algorithm,":[184],"respectively.":[185],"This":[186],"mainly":[188],"because":[189],"it":[190],"explores":[191],"such":[198],"that":[199],"utilized":[203],"more":[204],"efficiently.":[205],"achieves":[207],"peak":[208],"utilization":[210],"94%(on":[212],"25.05%).":[214]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}