{"id":"https://openalex.org/W3130137783","doi":"https://doi.org/10.1109/icdcs47774.2020.00125","title":"Safe Process Quitting for GPU Multi-Process Service (MPS)","display_name":"Safe Process Quitting for GPU Multi-Process Service (MPS)","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W3130137783","doi":"https://doi.org/10.1109/icdcs47774.2020.00125","mag":"3130137783"},"language":"en","primary_location":{"id":"doi:10.1109/icdcs47774.2020.00125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdcs47774.2020.00125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)","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/A5101874776","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0002-0372-5504"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Wu","raw_affiliation_strings":["TuSimple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TuSimple","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431757","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-2187-8125"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["TuSimple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TuSimple","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["TuSimple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TuSimple","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031914716","display_name":"Jiangming Jin","orcid":"https://orcid.org/0000-0001-7552-6937"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiangming Jin","raw_affiliation_strings":["TuSimple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TuSimple","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2274,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.52871696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1169","last_page":"1170"},"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9993000030517578,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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":0.8587855696678162},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5979626178741455},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5953413844108582},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5649687647819519},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5525434613227844},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5321751236915588},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5080564022064209},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4901295602321625},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4586790204048157},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15601247549057007},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1519542932510376},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11025473475456238},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.09398752450942993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8587855696678162},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5979626178741455},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5953413844108582},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5649687647819519},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5525434613227844},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5321751236915588},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5080564022064209},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4901295602321625},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4586790204048157},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15601247549057007},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1519542932510376},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11025473475456238},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.09398752450942993},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdcs47774.2020.00125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdcs47774.2020.00125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2323909431","https://openalex.org/W2604514113"],"related_works":["https://openalex.org/W2057774067","https://openalex.org/W2374814454","https://openalex.org/W2070865675","https://openalex.org/W1928605871","https://openalex.org/W564427","https://openalex.org/W1997643379","https://openalex.org/W2156943226","https://openalex.org/W2588972138","https://openalex.org/W4285216004","https://openalex.org/W2008492897"],"abstract_inverted_index":{"GPUs":[0,23],"have":[1],"been":[2],"widely":[3],"adopted":[4],"to":[5,24,40,54,67,104,131],"speedup":[6],"various":[7],"throughput-originated":[8],"applications":[9],"running":[10],"on":[11],"HPC":[12],"platforms,":[13],"where":[14],"typically":[15],"there":[16],"are":[17,129],"a":[18],"number":[19],"of":[20,71,92,107],"tasks":[21],"sharing":[22],"maximize":[25],"GPU":[26,30,32,52,75,94,127,137],"utilization.":[27],"To":[28],"facilitate":[29],"sharing,":[31],"vendors":[33],"provide":[34],"tools,":[35],"allowing":[36],"multiple":[37],"processes":[38,53,83,128],"concurrently":[39],"use":[41],"GPUs.":[42],"For":[43],"example,":[44],"Nvidia":[45],"provides":[46],"MPS":[47],"(Multi-Process":[48],"Service)":[49],"managing":[50],"all":[51,74],"achieve":[55],"high":[56],"throughput":[57],"by":[58,98],"fully":[59],"exploiting":[60],"hardware":[61],"resources.":[62],"However,":[63],"such":[64],"tool":[65],"leads":[66],"undesired":[68],"single":[69],"point":[70],"failure":[72],"for":[73],"processes,":[76],"namely,":[77],"one":[78,106],"process\u2019s":[79],"exception":[80],"makes":[81],"other":[82,136],"abnormal.":[84],"In":[85],"this":[86,93,125],"work,":[87],"we":[88],"investigate":[89],"the":[90],"seriousness":[91],"process":[95,114],"interferences":[96],"caused":[97],"MPS,":[99],"and":[100,120],"propose":[101],"an":[102],"approach":[103],"address":[105],"these":[108],"interferences,":[109],"which":[110],"takes":[111],"place":[112],"during":[113],"quitting.":[115],"By":[116],"using":[117],"signal":[118],"handling":[119],"thread":[121],"synchronization":[122],"techniques":[123],"in":[124],"approach,":[126],"able":[130],"quit":[132],"safely":[133],"without":[134],"interfering":[135],"processes.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}