{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T09:29:06Z","timestamp":1774171746740,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,4,4]],"date-time":"2017-04-04T00:00:00Z","timestamp":1491264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61602301, 61502019"],"award-info":[{"award-number":["61602301, 61502019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-CSR-1419243"],"award-info":[{"award-number":["CNS-CSR-1419243"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Basic Research 973 Program of China","award":["2015CB352403"],"award-info":[{"award-number":["2015CB352403"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,4,4]]},"DOI":"10.1145\/3037697.3037700","type":"proceedings-article","created":{"date-parts":[[2017,4,5]],"date-time":"2017-04-05T08:47:40Z","timestamp":1491382060000},"page":"17-32","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":98,"title":["Prophet"],"prefix":"10.1145","author":[{"given":"Quan","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Hailong","family":"Yang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}]},{"given":"Minyi","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Ram Srivatsa","family":"Kannan","sequence":"additional","affiliation":[{"name":"University of Michigan - Ann Arbor, Ann Arbor, USA"}]},{"given":"Jason","family":"Mars","sequence":"additional","affiliation":[{"name":"University of Michigan - Ann Arbor, Ann Arbor, USA"}]},{"given":"Lingjia","family":"Tang","sequence":"additional","affiliation":[{"name":"University of Michigan - Ann Arbor, Ann Arbor, USA"}]}],"member":"320","published-online":{"date-parts":[[2017,4,4]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Nvidia Multi-Process Service. https:\/\/docs.nvidia.com\/deploy\/pdf\/CUDA\\_Multi\\_Process\\_Service\\_Overview.pdf.  Nvidia Multi-Process Service. https:\/\/docs.nvidia.com\/deploy\/pdf\/CUDA\\_Multi\\_Process\\_Service\\_Overview.pdf."},{"key":"e_1_3_2_1_2_1","unstructured":"Profiler User's Guide. http:\/\/docs.nvidia.com\/cuda\/profiler-users-guide.  Profiler User's Guide. http:\/\/docs.nvidia.com\/cuda\/profiler-users-guide."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2012.6168946"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2014.6742976"},{"key":"e_1_3_2_1_5_1","first-page":"979","volume-title":"PRO: Progress Aware GPU Warp Scheduling Algorithm. In International Parallel and Distributed Processing Symposium (IPDPS)","author":"Anantpur J.","year":"2015","unstructured":"J. Anantpur and R. Govindarajan . PRO: Progress Aware GPU Warp Scheduling Algorithm. In International Parallel and Distributed Processing Symposium (IPDPS) , pages 979 -- 988 . IEEE, 2015 . J. Anantpur and R. Govindarajan. PRO: Progress Aware GPU Warp Scheduling Algorithm. In International Parallel and Distributed Processing Symposium (IPDPS), pages 979--988. IEEE, 2015."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.38"},{"key":"e_1_3_2_1_7_1","volume-title":"The Case for Energy-proportional Computing. Computer, (12): 33--37","author":"Barroso L. A.","year":"2007","unstructured":"le(2007)]barroso2007case L. A. Barroso and U. H\u00f6lzle . The Case for Energy-proportional Computing. Computer, (12): 33--37 , 2007 . le(2007)]barroso2007caseL. A. Barroso and U. H\u00f6lzle. The Case for Energy-proportional Computing. Computer, (12): 33--37, 2007."},{"key":"e_1_3_2_1_8_1","volume-title":"Web Search for a Planet: The Google Cluster Architecture. Micro, 23 (2): 22--28","author":"Barroso L. A.","year":"2003","unstructured":"le]barroso2003web L. A. Barroso , J. Dean , and U. H\u00f6lzle . Web Search for a Planet: The Google Cluster Architecture. Micro, 23 (2): 22--28 , 2003 . le]barroso2003webL. A. Barroso, J. Dean, and U. H\u00f6lzle. Web Search for a Planet: The Google Cluster Architecture. Micro, 23 (2): 22--28, 2003."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2011.6043273"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-013-0280-9"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628109"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872362.2872368"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2013.6704667"},{"key":"e_1_3_2_1_15_1","volume-title":"Paragon: QoS-aware Scheduling for Heterogeneous Datacenters. ACM SIGARCH Computer Architecture News, 41 (1): 77--88","author":"Delimitrou C.","year":"2013","unstructured":"]delimitrou2013paragon C. Delimitrou and C. Kozyrakis . Paragon: QoS-aware Scheduling for Heterogeneous Datacenters. ACM SIGARCH Computer Architecture News, 41 (1): 77--88 , 2013 \\natexlabb. ]delimitrou2013paragonC. Delimitrou and C. Kozyrakis. Paragon: QoS-aware Scheduling for Heterogeneous Datacenters. ACM SIGARCH Computer Architecture News, 41 (1): 77--88, 2013\\natexlabb."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541941"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2013.12"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11241-011-9140-y"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2749472"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694347"},{"key":"e_1_3_2_1_21_1","volume-title":"The Learning Machines","author":"Jones N.","year":"2014","unstructured":"N. Jones . The Learning Machines , 2014 . N. Jones. The Learning Machines, 2014."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE.2014.6776031"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541944"},{"key":"e_1_3_2_1_24_1","first-page":"17","volume-title":"TimeGraph: GPU Scheduling for Real-time Multi-tasking Environments. In USENIX Annual Technical Conference (ATC)","author":"Kato S.","year":"2011","unstructured":"S. Kato , K. Lakshmanan , R. Rajkumar , and Y. Ishikawa . TimeGraph: GPU Scheduling for Real-time Multi-tasking Environments. In USENIX Annual Technical Conference (ATC) , pages 17 -- 30 , 2011 . S. Kato, K. Lakshmanan, R. Rajkumar, and Y. Ishikawa. TimeGraph: GPU Scheduling for Real-time Multi-tasking Environments. In USENIX Annual Technical Conference (ATC), pages 17--30, 2011."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1296907.1296909"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.21"},{"key":"e_1_3_2_1_27_1","first-page":"1","volume-title":"Automation and Test in Europe Conference and Exhibition (DATE)","author":"Lee H.","year":"2014","unstructured":"H. Lee , A. Faruque , and M. Abdullah . GPU-EvR: Run-time Event-based Real-time Scheduling Framework on GPGPU Platform. In Design , Automation and Test in Europe Conference and Exhibition (DATE) , pages 1 -- 6 . IEEE, 2014 . H. Lee, A. Faruque, and M. Abdullah. GPU-EvR: Run-time Event-based Real-time Scheduling Framework on GPGPU Platform. In Design, Automation and Test in Europe Conference and Exhibition (DATE), pages 1--6. IEEE, 2014."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750418"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2592798.2592821"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2749475"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155650"},{"key":"e_1_3_2_1_32_1","first-page":"205","volume-title":"ACM Sigplan Notices","author":"Meisner D.","year":"2009","unstructured":"D. Meisner , B. T. Gold , and T. F. Wenisch . PowerNap: Eliminating Server Idle Power . In ACM Sigplan Notices , volume 44 , pages 205 -- 216 . ACM , 2009 . D. Meisner, B. T. Gold, and T. F. Wenisch. PowerNap: Eliminating Server Idle Power. In ACM Sigplan Notices, volume 44, pages 205--216. ACM, 2009."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2006.24"},{"key":"e_1_3_2_1_34_1","unstructured":"C. Nvidia. Compute Unified Device Architecture Programming Guide. 2007.  C. Nvidia. Compute Unified Device Architecture Programming Guide. 2007."},{"key":"e_1_3_2_1_35_1","volume-title":"CUDA SDK","author":"C.","year":"2010","unstructured":"C. NVIDIA. GPU Occupancy Calculator . CUDA SDK , 2010 . C. NVIDIA. GPU Occupancy Calculator. CUDA SDK, 2010."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451160"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694346"},{"key":"e_1_3_2_1_38_1","first-page":"246","volume-title":"Octopus-Man: QoS-Driven Task Management for Heterogeneous Multicores in Warehouse-Scale Computers. In the 21st International Symposium on High Performance Computer Architecture (HPCA)","author":"Petrucci V.","year":"2015","unstructured":"V. Petrucci , M. Laurenzano , J. Doherty , Y. Zhang , D. Mosse , J. Mars , L. Tang , Octopus-Man: QoS-Driven Task Management for Heterogeneous Multicores in Warehouse-Scale Computers. In the 21st International Symposium on High Performance Computer Architecture (HPCA) , pages 246 -- 258 . IEEE, 2015 . V. Petrucci, M. Laurenzano, J. Doherty, Y. Zhang, D. Mosse, J. Mars, L. Tang, et al. Octopus-Man: QoS-Driven Task Management for Heterogeneous Multicores in Warehouse-Scale Computers. In the 21st International Symposium on High Performance Computer Architecture (HPCA), pages 246--258. IEEE, 2015."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2287076.2287091"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2015.44"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853195"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540718"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493123.2462911"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451126"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750399"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446078"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056063"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485974"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669119"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.53"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.257"}],"event":{"name":"ASPLOS '17: Architectural Support for Programming Languages and Operating Systems","location":"Xi'an China","acronym":"ASPLOS '17","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3037697.3037700","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3037697.3037700","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3037697.3037700","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:50:26Z","timestamp":1750204226000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3037697.3037700"}},"subtitle":["Precise QoS Prediction on Non-Preemptive Accelerators to Improve Utilization in Warehouse-Scale Computers"],"short-title":[],"issued":{"date-parts":[[2017,4,4]]},"references-count":51,"alternative-id":["10.1145\/3037697.3037700","10.1145\/3037697"],"URL":"https:\/\/doi.org\/10.1145\/3037697.3037700","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/3093337.3037700","asserted-by":"object"},{"id-type":"doi","id":"10.1145\/3093336.3037700","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2017,4,4]]},"assertion":[{"value":"2017-04-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}