{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:34:40Z","timestamp":1756996480126,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":13,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,3]],"date-time":"2022-04-03T00:00:00Z","timestamp":1648944000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science Foundation (NSF)","award":["2016701"],"award-info":[{"award-number":["2016701"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,3]]},"DOI":"10.1145\/3530390.3532734","type":"proceedings-article","created":{"date-parts":[[2022,5,18]],"date-time":"2022-05-18T22:15:49Z","timestamp":1652912149000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Compiler-assisted scheduling for multi-instance GPUs"],"prefix":"10.1145","author":[{"given":"Chris","family":"Porter","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Chao","family":"Chen","sequence":"additional","affiliation":[{"name":"Amazon Web Services"}]},{"given":"Santosh","family":"Pande","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]}],"member":"320","published-online":{"date-parts":[[2022,5,18]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Amazon. High performance computing. URL https:\/\/aws.amazon.com\/hpc\/.  Amazon. High performance computing. URL https:\/\/aws.amazon.com\/hpc\/."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508423"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872362.2872368"},{"key":"e_1_3_2_1_4_1","unstructured":"Google. High performance computing. URL https:\/\/cloud.google.com\/solutions\/hpc.  Google. High performance computing. URL https:\/\/cloud.google.com\/solutions\/hpc."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155656"},{"key":"e_1_3_2_1_8_1","unstructured":"Oracle. High performance computing (hpc) solution. URL https:\/\/www.oracle.com\/cloud\/hpc\/.  Oracle. High performance computing (hpc) solution. URL https:\/\/www.oracle.com\/cloud\/hpc\/."},{"key":"e_1_3_2_1_9_1","unstructured":"Rescale. Big compute 2021 state of cloud hpc report. URL https:\/\/rescale.com\/resources\/big-compute-2021-state-of-cloud-hpc-report\/.  Rescale. Big compute 2021 state of cloud hpc report. URL https:\/\/rescale.com\/resources\/big-compute-2021-state-of-cloud-hpc-report\/."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2335755.2335793"},{"key":"e_1_3_2_1_11_1","volume-title":"Serving DNN models with multi-instance gpus: A case of the reconfigurable machine scheduling problem. CoRR, abs\/2109.11067","author":"Tan C.","year":"2021","unstructured":"C. Tan , Z. Li , J. Zhang , Y. Cao , S. Qi , Z. Liu , Y. Zhu , and C. Guo . Serving DNN models with multi-instance gpus: A case of the reconfigurable machine scheduling problem. CoRR, abs\/2109.11067 , 2021 . URL https:\/\/arxiv.org\/abs\/2109.11067. C. Tan, Z. Li, J. Zhang, Y. Cao, S. Qi, Z. Liu, Y. Zhu, and C. Guo. Serving DNN models with multi-instance gpus: A case of the reconfigurable machine scheduling problem. CoRR, abs\/2109.11067, 2021. URL https:\/\/arxiv.org\/abs\/2109.11067."},{"key":"e_1_3_2_1_12_1","first-page":"595","volume-title":"Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation","author":"Xiao W.","year":"2018","unstructured":"W. Xiao , R. Bhardwaj , R. Ramjee , M. Sivathanu , N. Kwatra , Z. Han , P. Patel , X. Peng , H. Zhao , Q. Zhang , F. Yang , and L. Zhou . Gandiva: Introspective cluster scheduling for deep learning . In Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation , page 595 -- 610 . USENIX, 2018 . ISBN 9781931971478. W. Xiao, R. Bhardwaj, R. Ramjee, M. Sivathanu, N. Kwatra, Z. Han, P. Patel, X. Peng, H. Zhao, Q. Zhang, F. Yang, and L. Zhou. Gandiva: Introspective cluster scheduling for deep learning. In Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation, page 595--610. USENIX, 2018. ISBN 9781931971478."},{"key":"e_1_3_2_1_13_1","volume-title":"12th USENIX Workshop on Hot Topics in Cloud Computing, HotCloud 2020","author":"Yeung G.","year":"2020","unstructured":"G. Yeung , D. Borowiec , A. Friday , R. Harper , and P. Garraghan . Towards GPU utilization prediction for cloud deep learning. In A. Phanishayee and R. Stutsman, editors , 12th USENIX Workshop on Hot Topics in Cloud Computing, HotCloud 2020 , July 13 --14 , 2020 . USENIX Association, 2020. URL https:\/\/www.usenix.org\/conference\/hotcloud20\/presentation\/yeung. G. Yeung, D. Borowiec, A. Friday, R. Harper, and P. Garraghan. Towards GPU utilization prediction for cloud deep learning. In A. Phanishayee and R. Stutsman, editors, 12th USENIX Workshop on Hot Topics in Cloud Computing, HotCloud 2020, July 13--14, 2020. USENIX Association, 2020. URL https:\/\/www.usenix.org\/conference\/hotcloud20\/presentation\/yeung."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/10968987\\_3"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRC.2019.8914707"}],"event":{"name":"PPoPP '22: 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"],"location":"Seoul Republic of Korea","acronym":"PPoPP '22"},"container-title":["Proceedings of the 14th Workshop on General Purpose Processing Using GPU"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3530390.3532734","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3530390.3532734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:24Z","timestamp":1750183764000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3530390.3532734"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,3]]},"references-count":13,"alternative-id":["10.1145\/3530390.3532734","10.1145\/3530390"],"URL":"https:\/\/doi.org\/10.1145\/3530390.3532734","relation":{},"subject":[],"published":{"date-parts":[[2022,4,3]]},"assertion":[{"value":"2022-05-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}