{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:34:04Z","timestamp":1773192844489,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,3,28]],"date-time":"2022-03-28T00:00:00Z","timestamp":1648425600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,2]]},"DOI":"10.1145\/3503221.3508423","type":"proceedings-article","created":{"date-parts":[[2022,3,28]],"date-time":"2022-03-28T13:58:22Z","timestamp":1648475902000},"page":"17-31","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["CASE"],"prefix":"10.1145","author":[{"given":"Chao","family":"Chen","sequence":"first","affiliation":[{"name":"Amazon Web Service"}]},{"given":"Chris","family":"Porter","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Santosh","family":"Pande","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]}],"member":"320","published-online":{"date-parts":[[2022,3,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"2018 USENIX Annual Technical Conference, Haryadi S. Gunawi and Benjamin Reed (Eds.). USENIX Association","author":"Amvrosiadis George","year":"2018","unstructured":"George Amvrosiadis, Jun Woo Park, Gregory R. Ganger, Garth A. Gibson, Elisabeth Baseman, and Nathan DeBardeleben. July 11--13, 2018. On the diversity of cluster workloads and its impact on research results. In 2018 USENIX Annual Technical Conference, Haryadi S. Gunawi and Benjamin Reed (Eds.). USENIX Association, Boston, MA, USA, 533--546."},{"key":"e_1_3_2_1_2_1","volume-title":"Supporting Preemptive Task Executions and Memory Copies in GPGPUs. In 2012 24th Euromicro Conference on Real-Time Systems. IEEE","author":"Basaran C.","unstructured":"C. Basaran and K. Kang. 2012. Supporting Preemptive Task Executions and Memory Copies in GPGPUs. In 2012 24th Euromicro Conference on Real-Time Systems. IEEE, Pisa, Italy."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2010.5650274"},{"key":"e_1_3_2_1_5_1","volume-title":"MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems. ArXiv abs\/1512.01274","author":"Chen T.","year":"2015","unstructured":"T. Chen, Mu Li, Y. Li, M. Lin, Naiyan Wang, Minjie Wang, Tianjun Xiao, B. Xu, C. Zhang, and Zheng Zhang. 2015. MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems. ArXiv abs\/1512.01274 (2015)."},{"key":"e_1_3_2_1_6_1","volume-title":"2010 International Conference on High Performance Computing Simulation. IEEE","author":"Duato J.","unstructured":"J. Duato, A. J. Pe\u00f1a, F. Silla, R. Mayo, and E. S. Quintana-Ort\u00ed. 2010. rCUDA: Reducing the number of GPU-based accelerators in high performance clusters. In 2010 International Conference on High Performance Computing Simulation. IEEE, Caen, France, 224--231."},{"key":"e_1_3_2_1_7_1","volume-title":"Workshop on Programming Models for Emerging Architectures","volume":"9","author":"Guevara Marisabel","year":"2009","unstructured":"Marisabel Guevara, Chris Gregg, Kim Hazelwood, and Kevin Skadron. 2009. Enabling task parallelism in the cuda scheduler. In Workshop on Programming Models for Emerging Architectures, Vol. 9. Citeseer."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 2011 USENIX Conference on USENIX Annual Technical Conference","author":"Gupta Vishakha","year":"2011","unstructured":"Vishakha Gupta, Karsten Schwan, Niraj Tolia, Vanish Talwar, and Parthasarathy Ranganathan. 2011. Pegasus: Coordinated Scheduling for Virtualized Accelerator-Based Systems. In Proceedings of the 2011 USENIX Conference on USENIX Annual Technical Conference (Portland, OR). USENIX Association, USA, 3."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid49817.2020.00-66"},{"key":"e_1_3_2_1_10_1","volume-title":"Deep Residual Learning for Image Recognition. CoRR abs\/1512.03385","author":"He Kaiming","year":"2015","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. CoRR abs\/1512.03385 (2015). arXiv:1512.03385 http:\/\/arxiv.org\/abs\/1512.03385"},{"key":"e_1_3_2_1_11_1","volume-title":"Gdev: First-Class GPU Resource Management in the Operating System. In Preceedings of 2012 USENIX Annual Technical Conference. USENIX","author":"Kato Shinpei","year":"2012","unstructured":"Shinpei Kato, Michael McThrow, Carlos Maltzahn, and Scott Brandt. 2012. Gdev: First-Class GPU Resource Management in the Operating System. In Preceedings of 2012 USENIX Annual Technical Conference. USENIX, Boston, MA, 401--412."},{"key":"e_1_3_2_1_12_1","unstructured":"Alex Krizhevsky Vinod Nair and Geoffrey Hinton. [n.d.]. CIFAR-10 (Canadian Institute for Advanced Research). ([n.d.]). http:\/\/www.cs.toronto.edu\/~kriz\/cifar.html"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694346"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2784428"},{"key":"e_1_3_2_1_16_1","unstructured":"Joseph Redmon. 2013--2016. Darknet: Open Source Neural Networks in C. http:\/\/pjreddie.com\/darknet\/."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2043556.2043579"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493123.2462911"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2011.112"},{"key":"e_1_3_2_1_21_1","volume-title":"3rd International Conference on Learning Representations, ICLR","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_2_1_22_1","unstructured":"Erich Strohmaier Jack Dongarra Horst Simon and Martin Meuer. [n.d.]. Top500 The List. https:\/\/www.top500.org\/"},{"key":"e_1_3_2_1_23_1","volume-title":"2014 ACM\/IEEE 41st International Symposium on Computer Architecture (ISCA).","author":"Tanasic I.","unstructured":"I. Tanasic, I. Gelado, J. Cabezas, A. Ramirez, N. Navarro, and M. Valero. 2014. Enabling preemptive multiprogramming on GPUs. In 2014 ACM\/IEEE 41st International Symposium on Computer Architecture (ISCA)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037742"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation","author":"Xiao Wencong","year":"2018","unstructured":"Wencong Xiao, Romil Bhardwaj, Ramachandran Ramjee, Muthian Sivathanu, Nipun Kwatra, Zhenhua Han, Pratyush Patel, Xuan Peng, Hanyu Zhao, Quanlu Zhang, Fan Yang, and Lidong Zhou. 2018. Gandiva: Introspective Cluster Scheduling for Deep Learning. In Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation (Carlsbad, CA, USA). USENIX, 595--610."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/10968987_3"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2688500.2688505"},{"key":"e_1_3_2_1_29_1","volume-title":"21st IEEE Real-Time and Embedded Technology and Applications Symposium. 87--97","author":"Zhou H.","unstructured":"H. Zhou, G. Tong, and C. Liu. 2015. GPES: a preemptive execution system for GPGPU computing. In 21st IEEE Real-Time and Embedded Technology and Applications Symposium. 87--97."}],"event":{"name":"PPoPP '22: 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","location":"Seoul Republic of Korea","acronym":"PPoPP '22","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"]},"container-title":["Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503221.3508423","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503221.3508423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:49Z","timestamp":1750186849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503221.3508423"}},"subtitle":["a compiler-assisted SchEduling framework for multi-GPU systems"],"short-title":[],"issued":{"date-parts":[[2022,3,28]]},"references-count":28,"alternative-id":["10.1145\/3503221.3508423","10.1145\/3503221"],"URL":"https:\/\/doi.org\/10.1145\/3503221.3508423","relation":{},"subject":[],"published":{"date-parts":[[2022,3,28]]},"assertion":[{"value":"2022-03-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}