{"id":"https://openalex.org/W4316252402","doi":"https://doi.org/10.1145/3547276.3548630","title":"Optimizing Hardware Resource Partitioning and Job Allocations on Modern GPUs under Power Caps","display_name":"Optimizing Hardware Resource Partitioning and Job Allocations on Modern GPUs under Power Caps","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4316252402","doi":"https://doi.org/10.1145/3547276.3548630"},"language":"en","primary_location":{"id":"doi:10.1145/3547276.3548630","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3547276.3548630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.03838","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087319091","display_name":"Eishi Arima","orcid":"https://orcid.org/0009-0002-7043-4288"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Eishi Arima","raw_affiliation_strings":["Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108919462","display_name":"Minjoon Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Minjoon Kang","raw_affiliation_strings":["Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043502259","display_name":"Issa Saba","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Issa Saba","raw_affiliation_strings":["Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073800722","display_name":"Josef Weidendorfer","orcid":"https://orcid.org/0000-0001-7159-1432"},"institutions":[{"id":"https://openalex.org/I4210163716","display_name":"Leibniz Supercomputing Centre","ror":"https://ror.org/05558nw16","country_code":"DE","type":"facility","lineage":["https://openalex.org/I109144446","https://openalex.org/I4210163716"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Josef Weidendorfer","raw_affiliation_strings":["Leibniz Supercomputing Centre, Germany"],"affiliations":[{"raw_affiliation_string":"Leibniz Supercomputing Centre, Germany","institution_ids":["https://openalex.org/I4210163716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068174103","display_name":"Carsten Trinitis","orcid":"https://orcid.org/0000-0002-6750-3652"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Carsten Trinitis","raw_affiliation_strings":["Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045289712","display_name":"Martin Schulz","orcid":"https://orcid.org/0000-0001-9013-435X"},"institutions":[{"id":"https://openalex.org/I4210163716","display_name":"Leibniz Supercomputing Centre","ror":"https://ror.org/05558nw16","country_code":"DE","type":"facility","lineage":["https://openalex.org/I109144446","https://openalex.org/I4210163716"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Schulz","raw_affiliation_strings":["Technical University of Munich, Germany and Leibniz Supercomputing Centre, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Germany and Leibniz Supercomputing Centre, Germany","institution_ids":["https://openalex.org/I4210163716","https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5087319091"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":3.2677,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92907165,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9997000098228455,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.6958224773406982},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5185673832893372},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.5130447149276733},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4571083188056946},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3798455595970154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6958224773406982},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5185673832893372},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.5130447149276733},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4571083188056946},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3798455595970154},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3547276.3548630","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3547276.3548630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.03838","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.03838","pdf_url":"https://arxiv.org/pdf/2405.03838","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.03838","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.03838","pdf_url":"https://arxiv.org/pdf/2405.03838","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3575588226","display_name":"An open architecture to equip next generation HPC applications with exascale capabilities","funder_award_id":"956560","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4937468798","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4316252402.pdf","grobid_xml":"https://content.openalex.org/works/W4316252402.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1977661221","https://openalex.org/W1978969737","https://openalex.org/W1981806722","https://openalex.org/W1984135560","https://openalex.org/W2019675177","https://openalex.org/W2027177485","https://openalex.org/W2030553163","https://openalex.org/W2045793256","https://openalex.org/W2072001046","https://openalex.org/W2144017505","https://openalex.org/W2793599434","https://openalex.org/W2794729807","https://openalex.org/W2964330525","https://openalex.org/W3093933627","https://openalex.org/W3159822625"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"CPU-GPU":[0],"heterogeneous":[1,184],"systems":[2,19],"are":[3],"now":[4],"commonly":[5],"used":[6],"in":[7,183,199],"HPC":[8,65,143],"(High-Performance":[9],"Computing).":[10],"However,":[11],"improving":[12],"the":[13,24,60,79,117,131,152],"utilization":[14,182],"and":[15,138,181],"energy-efficiency":[16],"of":[17,23,119,133,154,173],"such":[18,67,177],"is":[20,50,197],"still":[21],"one":[22,29,110],"most":[25],"critical":[26],"issues.":[27],"As":[28],"single":[30,111],"program":[31],"typically":[32],"cannot":[33],"fully":[34],"utilize":[35],"all":[36],"resources":[37,186],"within":[38],"a":[39,51,120,147,171,201],"node/chip,":[40],"co-scheduling":[41,68],"(or":[42],"co-locating)":[43],"multiple":[44,114,206],"programs":[45],"with":[46,98],"complementary":[47],"resource":[48,85],"requirements":[49],"promising":[52],"solution.":[53],"Meanwhile,":[54],"as":[55,159,161,178],"power":[56,100,139,162],"consumption":[57],"has":[58],"become":[59],"first-class":[61],"design":[62],"constraint":[63],"for":[64,73,91,141],"systems,":[66],"techniques":[69],"should":[70],"be":[71],"well-tailored":[72],"power-constrained":[74,142],"environments.":[75],"To":[76],"this":[77,126],"end,":[78],"industry":[80],"recently":[81],"started":[82],"supporting":[83],"hardware-level":[84,134],"partitioning":[86,136],"features":[87,137],"on":[88,165],"modern":[89],"GPUs":[90],"realizing":[92],"efficient":[93],"co-scheduling,":[94],"which":[95],"can":[96],"operate":[97],"existing":[99],"capping":[101,140,163],"features.":[102],"For":[103],"example,":[104],"NVidia\u2019s":[105],"MIG":[106],"(Multi-Instance":[107],"GPU)":[108],"partitions":[109],"GPU":[112,135],"into":[113,175],"instances":[115],"at":[116],"granularity":[118],"GPC":[121],"(Graphics":[122],"Processing":[123],"Cluster).":[124],"In":[125],"paper,":[127],"we":[128],"explicitly":[129],"target":[130],"combination":[132,153,204],"systems.":[144],"We":[145],"provide":[146],"systematic":[148],"methodology":[149],"to":[150],"optimize":[151],"chip":[155],"partitioning,":[156],"job":[157],"allocations,":[158],"well":[160],"based":[164],"our":[166,195],"scalability/interference":[167],"modeling":[168],"while":[169],"taking":[170],"variety":[172],"aspects":[174],"account,":[176],"compute/memory":[179],"intensity":[180],"computational":[185],"(e.g.,":[187],"Tensor":[188],"Cores).":[189],"The":[190],"experimental":[191],"result":[192],"indicates":[193],"that":[194],"approach":[196],"successful":[198],"selecting":[200],"near":[202],"optimal":[203],"across":[205],"different":[207],"workloads.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2023-01-15T00:00:00"}