{"id":"https://openalex.org/W4214540558","doi":"https://doi.org/10.1145/3503222.3507721","title":"Astraea: towards QoS-aware and resource-efficient multi-stage GPU services","display_name":"Astraea: towards QoS-aware and resource-efficient multi-stage GPU services","publication_year":2022,"publication_date":"2022-02-22","ids":{"openalex":"https://openalex.org/W4214540558","doi":"https://doi.org/10.1145/3503222.3507721"},"language":"en","primary_location":{"id":"doi:10.1145/3503222.3507721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503222.3507721","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 International Conference on Architectural Support for Programming Languages and Operating Systems","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/A5103019753","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-6076-6425"},"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":"Wei Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, 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":["Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037447327","display_name":"Kaihua Fu","orcid":"https://orcid.org/0000-0001-5117-7162"},"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":"Kaihua Fu","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018118687","display_name":"Ningxin Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningxin Zheng","raw_affiliation_strings":["Microsoft Research, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090297023","display_name":"Zhiyi Huang","orcid":"https://orcid.org/0000-0001-8561-2556"},"institutions":[{"id":"https://openalex.org/I80281795","display_name":"University of Otago","ror":"https://ror.org/01jmxt844","country_code":"NZ","type":"education","lineage":["https://openalex.org/I80281795"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Zhiyi Huang","raw_affiliation_strings":["University of Otago, New Zealand"],"affiliations":[{"raw_affiliation_string":"University of Otago, New Zealand","institution_ids":["https://openalex.org/I80281795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003939279","display_name":"Jingwen Leng","orcid":"https://orcid.org/0000-0002-5660-5493"},"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":"Jingwen Leng","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, 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":["Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103019753"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":6.6713,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.96811907,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"570","last_page":"582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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/T12127","display_name":"Software System Performance and Reliability","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/T10714","display_name":"Software-Defined Networks and 5G","score":0.9979000091552734,"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/microservices","display_name":"Microservices","score":0.9854105710983276},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8670227527618408},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6660733222961426},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.6427172422409058},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6028377413749695},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.532389760017395},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5239593982696533},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4281196892261505},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.36123138666152954},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.3489154577255249},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3247220516204834},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.27029603719711304},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18485212326049805}],"concepts":[{"id":"https://openalex.org/C2778505942","wikidata":"https://www.wikidata.org/wiki/Q18344624","display_name":"Microservices","level":3,"score":0.9854105710983276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8670227527618408},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6660733222961426},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.6427172422409058},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6028377413749695},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.532389760017395},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5239593982696533},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4281196892261505},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36123138666152954},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.3489154577255249},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3247220516204834},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.27029603719711304},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18485212326049805},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503222.3507721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503222.3507721","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 International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2589935567","display_name":null,"funder_award_id":"2019YFF0302600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1982063824","https://openalex.org/W2015518316","https://openalex.org/W2062482040","https://openalex.org/W2080592089","https://openalex.org/W2102041666","https://openalex.org/W2118297542","https://openalex.org/W2170616854","https://openalex.org/W2216946510","https://openalex.org/W2293634267","https://openalex.org/W2322240213","https://openalex.org/W2323909431","https://openalex.org/W2503339013","https://openalex.org/W2581065617","https://openalex.org/W2604514113","https://openalex.org/W2612225380","https://openalex.org/W2612387305","https://openalex.org/W2616747538","https://openalex.org/W2798291715","https://openalex.org/W2798748382","https://openalex.org/W2887500939","https://openalex.org/W2899134946","https://openalex.org/W2903838325","https://openalex.org/W2916954860","https://openalex.org/W2928897890","https://openalex.org/W2930500175","https://openalex.org/W2931122162","https://openalex.org/W2948000013","https://openalex.org/W2949380140","https://openalex.org/W2952562115","https://openalex.org/W2953038929","https://openalex.org/W2955831855","https://openalex.org/W2963612019","https://openalex.org/W2964161387","https://openalex.org/W2966792645","https://openalex.org/W2982157693","https://openalex.org/W2982506996","https://openalex.org/W2982576723","https://openalex.org/W3014810041","https://openalex.org/W3016842236","https://openalex.org/W3017148238","https://openalex.org/W3043433718","https://openalex.org/W3099214871","https://openalex.org/W3126616698","https://openalex.org/W3156127671","https://openalex.org/W3208777667","https://openalex.org/W3214539954","https://openalex.org/W4200542591","https://openalex.org/W4288269198"],"related_works":["https://openalex.org/W4210334847","https://openalex.org/W3181741639","https://openalex.org/W4367181468","https://openalex.org/W2767473057","https://openalex.org/W4225586032","https://openalex.org/W3003367851","https://openalex.org/W1492892507","https://openalex.org/W3119944216","https://openalex.org/W2994988622","https://openalex.org/W2953155972"],"abstract_inverted_index":{"Multi-stage":[0],"user-facing":[1],"applications":[2],"on":[3,96],"GPUs":[4],"are":[5,10,20],"widely-used":[6],"nowa-":[7],"days,":[8],"and":[9,35,102,105],"often":[11],"implemented":[12],"to":[13,23,30,42,59,80,110,122],"be":[14],"microservices.":[15],"Prior":[16],"re-":[17],"search":[18],"works":[19],"not":[21],"applicable":[22],"ensuring":[24,67],"QoS":[25],"of":[26],"GPU-based":[27],"microservices":[28,45,78],"due":[29],"the":[31,47,61,68,74,97,116,126],"different":[32,81],"communication":[33,75],"patterns":[34],"shared":[36],"resource":[37],"contentions.":[38],"We":[39],"propose":[40,84],"Astraea":[41,114],"manage":[43],"GPU":[44,87],"considering":[46],"above":[48],"factors.":[49],"In":[50],"Astraea,":[51],"a":[52],"microser-":[53],"vice":[54],"deployment":[55],"policy":[56],"is":[57],"used":[58,99],"maximize":[60],"supported":[62,117],"peak":[63,118],"service":[64],"load":[65,119],"while":[66,124],"required":[69],"QoS.":[70],"To":[71],"adaptively":[72],"switch":[73],"methods":[76],"between":[77],"according":[79],"deployments,":[82],"we":[83],"an":[85],"auto-scaling":[86],"communi-":[88],"cation":[89],"framework.":[90],"The":[91],"framework":[92],"automatically":[93],"scales":[94],"based":[95],"currently":[98],"hardware":[100],"topology":[101],"microservice":[103],"location,":[104],"adopts":[106],"global":[107],"memory-based":[108],"techniques":[109],"reduce":[111],"intra-GPU":[112],"communication.":[113],"increases":[115],"by":[120],"up":[121],"82.3%":[123],"achieving":[125],"desired":[127],"99%-ile":[128],"latency":[129],"target":[130],"compared":[131],"with":[132],"state-of-the-art":[133],"solutions.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
