{"id":"https://openalex.org/W2811206245","doi":"https://doi.org/10.1109/lca.2018.2851207","title":"KSM: Online Application-Level Performance Slowdown Prediction for Spatial Multitasking GPGPU","display_name":"KSM: Online Application-Level Performance Slowdown Prediction for Spatial Multitasking GPGPU","publication_year":2018,"publication_date":"2018-06-28","ids":{"openalex":"https://openalex.org/W2811206245","doi":"https://doi.org/10.1109/lca.2018.2851207","mag":"2811206245"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2018.2851207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2018.2851207","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-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/A5052936919","display_name":"Wenyi Zhao","orcid":"https://orcid.org/0000-0001-7308-9542"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenyi Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377840","display_name":"Quan Chen","orcid":"https://orcid.org/0000-0001-5832-0347"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052936919"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.2722,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87912491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"17","issue":"2","first_page":"187","last_page":"191"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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":0.9994999766349792,"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":0.8618279695510864},{"id":"https://openalex.org/keywords/human-multitasking","display_name":"Human multitasking","score":0.814064621925354},{"id":"https://openalex.org/keywords/slowdown","display_name":"Slowdown","score":0.72214674949646},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.553320050239563},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5404040217399597},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5061365962028503},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.47786468267440796},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4516932964324951},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4171349108219147},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38641223311424255},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3366125226020813},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.27814075350761414},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2589956521987915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8618279695510864},{"id":"https://openalex.org/C107418235","wikidata":"https://www.wikidata.org/wiki/Q1520565","display_name":"Human multitasking","level":2,"score":0.814064621925354},{"id":"https://openalex.org/C2777242750","wikidata":"https://www.wikidata.org/wiki/Q31351","display_name":"Slowdown","level":2,"score":0.72214674949646},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.553320050239563},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5404040217399597},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5061365962028503},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.47786468267440796},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4516932964324951},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4171349108219147},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38641223311424255},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3366125226020813},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.27814075350761414},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2589956521987915},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2018.2851207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2018.2851207","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G129499350","display_name":null,"funder_award_id":"61632017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1423370025","display_name":null,"funder_award_id":"61602301","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W592737779","https://openalex.org/W1979527452","https://openalex.org/W2023214828","https://openalex.org/W2038666141","https://openalex.org/W2080592089","https://openalex.org/W2097643185","https://openalex.org/W2118231264","https://openalex.org/W2150139096","https://openalex.org/W2150851481","https://openalex.org/W2234128234","https://openalex.org/W2273440736","https://openalex.org/W2323693848","https://openalex.org/W2510980549","https://openalex.org/W4235366964","https://openalex.org/W6694513646"],"related_works":["https://openalex.org/W4242930893","https://openalex.org/W4388263628","https://openalex.org/W2488058330","https://openalex.org/W1988895983","https://openalex.org/W3140336604","https://openalex.org/W2940047422","https://openalex.org/W132134666","https://openalex.org/W1044687203","https://openalex.org/W2886487614","https://openalex.org/W2776718775"],"abstract_inverted_index":{"Colocating":[0],"multiple":[1],"applications":[2,16,83,123,165],"on":[3,25,58,71,112,139,167],"the":[4,10,14,23,67,77,90,113,121,140,153,159,163,168,183,187],"same":[5],"spatial":[6],"multitasking":[7],"GPGPU":[8],"improves":[9],"system-wide":[11],"throughput.":[12],"However,":[13],"colocated":[15,122,164],"are":[17,124],"slowed":[18],"down":[19],"differently":[20],"due":[21,65,75],"to":[22,37,66,76],"contention":[24,70],"streaming":[26],"multiprocessors":[27],"(SMs),":[28],"L2":[29],"cache":[30],"and":[31,99,157,180],"global":[32],"memory":[33],"bandwidth.":[34],"The":[35],"ability":[36],"precisely":[38,181],"predict":[39],"application":[40,60,106],"slowdowns":[41,160,185],"online":[42],"is":[43,62,109],"useful":[44],"in":[45,52],"many":[46],"scenarios,":[47],"e.g.,":[48],"ensuring":[49],"fair":[50],"pricing":[51],"multi-tenant":[53],"Cloud":[54],"systems.":[55],"Prior":[56],"work":[57],"predicting":[59],"slowdown":[61,102,136],"either":[63],"inaccurate,":[64],"ignoring":[68],"of":[69,81,161],"SMs,":[72],"or":[73],"inefficient,":[74],"expensive":[78],"sequential":[79],"profiling":[80],"concurrent":[82],"via":[84],"runtime":[85,178],"environment":[86],"switching.":[87],"To":[88],"solve":[89],"above":[91],"problem,":[92],"we":[93],"propose":[94],"KSM":[95,108,133,151,175],"that":[96,115,174],"enables":[97],"precise":[98],"efficient":[100],"application-level":[101,184],"prediction":[103,188],"without":[104],"priori":[105],"knowledge.":[107],"proposed":[110],"based":[111,138,166],"observation":[114],"hardware":[116,141,154],"event":[117,142,155],"statistics":[118,143],"caused":[119],"by":[120],"strongly":[125],"correlated":[126],"with":[127,186],"their":[128],"slowdowns.":[129],"In":[130],"more":[131],"detail,":[132],"builds":[134],"a":[135],"model":[137],"using":[144],"machine":[145],"learning":[146],"techniques":[147],"offline.":[148],"At":[149],"runtime,":[150],"collects":[152],"statistics,":[156],"predicts":[158,182],"all":[162],"model.":[169],"Our":[170],"experimental":[171],"results":[172],"show":[173],"has":[176],"negligible":[177],"overhead":[179],"error":[189],"smaller":[190],"than":[191],"9.7":[192],"percent.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}