{"id":"https://openalex.org/W4220728567","doi":"https://doi.org/10.1145/3503221.3508423","title":"CASE","display_name":"CASE","publication_year":2022,"publication_date":"2022-03-28","ids":{"openalex":"https://openalex.org/W4220728567","doi":"https://doi.org/10.1145/3503221.3508423"},"language":"en","primary_location":{"id":"doi:10.1145/3503221.3508423","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503221.3508423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","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/A5100408398","display_name":"Chao Chen","orcid":"https://orcid.org/0000-0003-1960-4042"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chao Chen","raw_affiliation_strings":["Amazon Web Service"],"affiliations":[{"raw_affiliation_string":"Amazon Web Service","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049228142","display_name":"Chris Porter","orcid":"https://orcid.org/0000-0002-2821-2668"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Porter","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061235810","display_name":"Santosh Pande","orcid":"https://orcid.org/0000-0001-6723-8062"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Santosh Pande","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100408398"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0282,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91335022,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9980999827384949,"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":0.9028184413909912},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6025778651237488},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6020519733428955},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.5640907287597656},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5600138902664185},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5444513559341431},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5101094841957092},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4110981822013855},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34324347972869873},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.28526735305786133}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9028184413909912},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6025778651237488},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6020519733428955},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.5640907287597656},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5600138902664185},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5444513559341431},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5101094841957092},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4110981822013855},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34324347972869873},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.28526735305786133},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503221.3508423","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503221.3508423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1596936080","https://openalex.org/W1996212904","https://openalex.org/W2005574683","https://openalex.org/W2076661703","https://openalex.org/W2078994750","https://openalex.org/W2080592089","https://openalex.org/W2117539524","https://openalex.org/W2125551452","https://openalex.org/W2141992894","https://openalex.org/W2153375074","https://openalex.org/W2604787577","https://openalex.org/W2914209329","https://openalex.org/W2915025126","https://openalex.org/W2964330525","https://openalex.org/W3043004181","https://openalex.org/W4236267470","https://openalex.org/W4253267708","https://openalex.org/W4254680874"],"related_works":["https://openalex.org/W4399354997","https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W1977763331","https://openalex.org/W66594024","https://openalex.org/W2084925448"],"abstract_inverted_index":{"Modern":[0],"computing":[1,18],"platforms":[2],"tend":[3],"to":[4,12,51,133,152,164,191,200,206,217,229,238],"deploy":[5],"multiple":[6,48],"GPUs":[7,15],"on":[8,54,69,210,262],"a":[9,55,71,82,106,134,144,149,158,263],"single":[10,56],"node":[11],"boost":[13],"performance.":[14],"have":[16],"large":[17],"capacities":[19],"and":[20,38,101,125,174,204,231,258],"are":[21],"an":[22,36,92],"expensive":[23],"resource.":[24],"Increasing":[25],"their":[26],"utilization":[27,226,253],"without":[28],"causing":[29],"performance":[30,245],"degradation":[31,246],"of":[32,91,128,254],"individual":[33,243],"workloads":[34],"is":[35,162],"important":[37],"challenging":[39],"problem.":[40],"Although":[41],"services":[42],"such":[43,70,122],"as":[44,123,189],"NVIDIA's":[45],"MPS":[46],"allow":[47],"cooperative":[49],"kernels":[50,68],"simultaneously":[52],"run":[53],"device,":[57],"they":[58],"do":[59],"not":[60],"solve":[61],"the":[62,89,103,126,153,175,218,223,232],"co-execution":[63],"problem":[64],"for":[65,202,208,256,260],"uncooperative,":[66],"independent":[67],"multi-GPU":[72],"system.":[73,154,265],"To":[74],"tackle":[75],"this":[76],"problem,":[77],"we":[78],"propose":[79],"CASE":[80,94,195,249],"---":[81],"fully":[83],"automated":[84],"compiler-assisted":[85],"scheduling":[86,160,168],"framework.":[87,169],"During":[88],"compilation":[90],"application,":[93],"constructs":[95],"GPU":[96,213],"tasks":[97],"from":[98],"CUDA":[99],"programs":[100],"instruments":[102],"code":[104],"with":[105],"probe":[107,114],"before":[108],"each":[109,113,141],"one.":[110],"At":[111],"runtime,":[112],"conveys":[115],"information":[116],"about":[117],"its":[118],"task's":[119],"resource":[120],"requirements":[121],"memory":[124],"number":[127],"streaming":[129],"multiprocessor":[130],"(SMs)":[131],"needed":[132],"user-level":[135],"scheduler.":[136],"The":[137,170,185],"scheduler":[138],"then":[139],"places":[140],"task":[142],"onto":[143],"suitable":[145],"device":[146],"by":[147,198,227,236],"employing":[148],"policy":[150,161],"appropriate":[151],"In":[155],"our":[156,166,183],"prototype,":[157],"throughput-oriented":[159],"implemented":[163],"evaluate":[165],"resource-aware":[167],"Rodinia":[171,257],"benchmark":[172],"suite":[173],"Darknet":[176,209,261],"neural":[177],"network":[178],"framework":[179],"were":[180],"used":[181],"in":[182],"evaluation.":[184],"results":[186],"show":[187],"that,":[188],"compared":[190],"existing":[192],"state-of-the-art":[193],"methods,":[194],"improves":[196,222],"throughput":[197],"up":[199,205,228,237],"2.5X":[201],"Rodinia,":[203],"2.7X":[207],"modern":[211],"NVIDIA":[212],"platforms,":[214],"mainly":[215],"due":[216],"fact":[219],"that":[220],"it":[221,241],"average":[224],"system":[225,252],"3.36X":[230],"job":[233],"turnaround":[234],"time":[235],"4.9X.":[239],"Meanwhile,":[240],"limits":[242],"kernel":[244],"within":[247],"2.5%.":[248],"achieved":[250],"peak":[251],"78%":[255],"80%":[259],"4XV100":[264]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2022-04-03T00:00:00"}