{"id":"https://openalex.org/W4283379731","doi":"https://doi.org/10.1145/3502181.3531462","title":"Hare","display_name":"Hare","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4283379731","doi":"https://doi.org/10.1145/3502181.3531462"},"language":"en","primary_location":{"id":"doi:10.1145/3502181.3531462","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3502181.3531462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing","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/A5088461411","display_name":"Fahao Chen","orcid":"https://orcid.org/0000-0002-4345-1296"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fahao Chen","raw_affiliation_strings":["The University of Aizu, Aizu-wakamatsu, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Aizu, Aizu-wakamatsu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432795","display_name":"Peng Li","orcid":"https://orcid.org/0000-0003-4981-0496"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Peng Li","raw_affiliation_strings":["The University of Aizu, Aizu-wakamatsu, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Aizu, Aizu-wakamatsu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046333931","display_name":"Celimuge Wu","orcid":"https://orcid.org/0000-0001-6853-5878"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Celimuge Wu","raw_affiliation_strings":["University of Electro-Communications, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043464306","display_name":"Song Guo","orcid":"https://orcid.org/0000-0001-9831-2202"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Song Guo","raw_affiliation_strings":["The Hong Kong Polytechnic University & The Hong Kong Polytechnic University Shenzhen Research Institute, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University & The Hong Kong Polytechnic University Shenzhen Research Institute, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9995999932289124,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9995999932289124,"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":0.9990000128746033,"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":0.9955000281333923,"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":0.8741958141326904},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.6643214821815491},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5703787803649902},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5468409657478333},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4897148907184601},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4798314571380615},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.47880396246910095},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4340325593948364},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4311324954032898},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.42739391326904297},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.414220929145813},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.20022991299629211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19924893975257874},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07132086157798767},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.06926393508911133}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8741958141326904},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.6643214821815491},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5703787803649902},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5468409657478333},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4897148907184601},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4798314571380615},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.47880396246910095},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4340325593948364},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4311324954032898},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.42739391326904297},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.414220929145813},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.20022991299629211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19924893975257874},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07132086157798767},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.06926393508911133},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3502181.3531462","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3502181.3531462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-129433","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2022&rft.spage=253&rft.aulast=Chen&rft.aufirst=Fahao&rft.atitle=Hare%3A+Exploiting+Inter-job+and+Intra-job+Parallelism+of+Distributed+Machine+Learning+on+Heterogeneous+GPUs&rft.title=HPDC+2022+-+Proceedings+of+the+31st+International+Symposium+on+High-Performance+Parallel+and+Distributed+Computing","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G7111805306","display_name":"\u9762\u5411\u8fb9\u7f18\u667a\u80fd\u7684\u8d44\u6e90\u914d\u7f6e\u4e0e\u90e8\u7f72\u4f18\u5316\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61872310","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1528469369","https://openalex.org/W2057332538","https://openalex.org/W2060393849","https://openalex.org/W2075265959","https://openalex.org/W2121927366","https://openalex.org/W2183341477","https://openalex.org/W2189465200","https://openalex.org/W2194775991","https://openalex.org/W2798515322","https://openalex.org/W2899071864","https://openalex.org/W2946671346","https://openalex.org/W2969388332","https://openalex.org/W3022298203","https://openalex.org/W3022548332","https://openalex.org/W3091992486","https://openalex.org/W3213120752","https://openalex.org/W3213577517","https://openalex.org/W4301361180","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W123872086","https://openalex.org/W1534022569","https://openalex.org/W2160425906","https://openalex.org/W2350861899","https://openalex.org/W1669499690","https://openalex.org/W1882733036","https://openalex.org/W2765352472","https://openalex.org/W2391167130","https://openalex.org/W2131630752","https://openalex.org/W1546966627"],"abstract_inverted_index":{"Distributed":[0],"machine":[1],"learning":[2,26],"(DML)":[3],"has":[4,75,125],"shown":[5],"great":[6,87],"promise":[7],"in":[8,65,97,119],"accelerating":[9],"model":[10],"training":[11,165],"on":[12,45,70],"multiple":[13,25,71],"GPUs.":[14,46,60],"To":[15],"increase":[16],"GPU":[17,29,61,122,132],"utilization,":[18],"a":[19,108,120,150,164,170,199,203],"common":[20,64],"practice":[21],"is":[22,38,63,193],"to":[23,40,56,135,159,174],"let":[24],"jobs":[27,44,81],"share":[28],"clusters,":[30],"where":[31],"the":[32,98,176,213],"most":[33],"fundamental":[34],"and":[35,116,187,202],"critical":[36],"challenge":[37],"how":[39],"efficiently":[41],"schedule":[42],"these":[43],"However,":[47],"existing":[48],"works":[49],"about":[50,216],"DML":[51,72,80,109,145],"job":[52,73,110,179,185],"scheduling":[53,74],"are":[54],"constrained":[55],"settings":[57],"with":[58],"homogeneous":[59],"heterogeneity":[62],"practice,":[66],"but":[67],"its":[68],"influence":[69],"been":[76,94],"seldom":[77],"studied.":[78],"Moreover,":[79],"have":[82,91],"internal":[83],"structures":[84],"that":[85,112,155,209],"contain":[86],"parallelism":[88,118],"potentials,":[89],"which":[90],"not":[92],"yet":[93],"fully":[95],"exploited":[96],"heterogeneous":[99,121],"computing":[100],"environment.":[101],"In":[102],"this":[103],"paper,":[104],"we":[105,168],"propose":[106,169],"Hare,":[107],"scheduler":[111],"exploits":[113],"both":[114],"inter-job":[115],"intra-job":[117],"cluster.":[123],"Hare":[124,130,148,197],"three":[126],"novel":[127],"designs.":[128],"First,":[129],"optimizes":[131],"execution":[133],"environment":[134],"reduce":[136],"task":[137],"switching":[138],"overhead":[139],"by":[140,182,215],"exploiting":[141],"unique":[142],"features":[143,186],"of":[144],"scheduling.":[146],"Second,":[147],"adopts":[149],"relaxed":[151],"fixed-scale":[152],"synchronization":[153],"scheme":[154],"allows":[156],"independent":[157],"tasks":[158],"be":[160],"flexibly":[161],"scheduled":[162],"within":[163],"round.":[166],"Finally,":[167],"fast":[171],"heuristic":[172],"algorithm":[173],"minimize":[175],"total":[177],"weighted":[178],"completion":[180],"time":[181],"jointly":[183],"considering":[184],"hardware":[188],"heterogeneity.":[189],"Its":[190],"theoretical":[191],"bound":[192],"derived.":[194],"We":[195],"evaluate":[196],"using":[198],"small-scale":[200],"testbed":[201],"trace-driven":[204],"simulator.":[205],"The":[206],"results":[207],"show":[208],"it":[210],"can":[211],"outperform":[212],"state-of-the-art":[214],"2x.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-06-25T00:00:00"}