{"language":[{"iso":"eng"}],"publication":"Proceedings of the 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE)","date_updated":"2023-09-26T13:27:00Z","type":"conference","status":"public","year":"2016","publisher":"EDA Consortium / IEEE","author":[{"first_name":"Achim","id":"43646","last_name":"Lösch","full_name":"Lösch, Achim"},{"full_name":"Beisel, Tobias","last_name":"Beisel","first_name":"Tobias"},{"first_name":"Tobias","full_name":"Kenter, Tobias","id":"3145","last_name":"Kenter"},{"full_name":"Plessl, Christian","last_name":"Plessl","id":"16153","orcid":"0000-0001-5728-9982","first_name":"Christian"},{"first_name":"Marco","full_name":"Platzner, Marco","id":"398","last_name":"Platzner"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"title":"Performance-centric scheduling with task migration for a heterogeneous compute node in the data center","_id":"168","citation":{"bibtex":"@inproceedings{Lösch_Beisel_Kenter_Plessl_Platzner_2016, title={Performance-centric scheduling with task migration for a heterogeneous compute node in the data center}, booktitle={Proceedings of the 2016 Design, Automation &#38; Test in Europe Conference &#38; Exhibition (DATE)}, publisher={EDA Consortium / IEEE}, author={Lösch, Achim and Beisel, Tobias and Kenter, Tobias and Plessl, Christian and Platzner, Marco}, year={2016}, pages={912–917} }","chicago":"Lösch, Achim, Tobias Beisel, Tobias Kenter, Christian Plessl, and Marco Platzner. “Performance-Centric Scheduling with Task Migration for a Heterogeneous Compute Node in the Data Center.” In <i>Proceedings of the 2016 Design, Automation &#38; Test in Europe Conference &#38; Exhibition (DATE)</i>, 912–17. EDA Consortium / IEEE, 2016.","short":"A. Lösch, T. Beisel, T. Kenter, C. Plessl, M. Platzner, in: Proceedings of the 2016 Design, Automation &#38; Test in Europe Conference &#38; Exhibition (DATE), EDA Consortium / IEEE, 2016, pp. 912–917.","ieee":"A. Lösch, T. Beisel, T. Kenter, C. Plessl, and M. Platzner, “Performance-centric scheduling with task migration for a heterogeneous compute node in the data center,” in <i>Proceedings of the 2016 Design, Automation &#38; Test in Europe Conference &#38; Exhibition (DATE)</i>, 2016, pp. 912–917.","ama":"Lösch A, Beisel T, Kenter T, Plessl C, Platzner M. Performance-centric scheduling with task migration for a heterogeneous compute node in the data center. In: <i>Proceedings of the 2016 Design, Automation &#38; Test in Europe Conference &#38; Exhibition (DATE)</i>. EDA Consortium / IEEE; 2016:912-917.","mla":"Lösch, Achim, et al. “Performance-Centric Scheduling with Task Migration for a Heterogeneous Compute Node in the Data Center.” <i>Proceedings of the 2016 Design, Automation &#38; Test in Europe Conference &#38; Exhibition (DATE)</i>, EDA Consortium / IEEE, 2016, pp. 912–17.","apa":"Lösch, A., Beisel, T., Kenter, T., Plessl, C., &#38; Platzner, M. (2016). Performance-centric scheduling with task migration for a heterogeneous compute node in the data center. <i>Proceedings of the 2016 Design, Automation &#38; Test in Europe Conference &#38; Exhibition (DATE)</i>, 912–917."},"user_id":"15278","ddc":["040"],"file":[{"relation":"main_file","access_level":"closed","content_type":"application/pdf","creator":"florida","file_size":261356,"date_updated":"2018-03-21T12:41:55Z","date_created":"2018-03-21T12:41:55Z","success":1,"file_name":"168-07459438.pdf","file_id":"1541"}],"page":"912-917","project":[{"grant_number":"160364472","_id":"1","name":"SFB 901"},{"name":"SFB 901 - Subprojekt C2","_id":"14","grant_number":"160364472"},{"_id":"4","name":"SFB 901 - Project Area C"},{"grant_number":"01|H11004A","_id":"30","name":"Enabling Heterogeneous Hardware Acceleration using Novel Programming and Scheduling Models"}],"has_accepted_license":"1","quality_controlled":"1","abstract":[{"lang":"eng","text":"The use of heterogeneous computing resources, such as Graphic Processing Units or other specialized coprocessors, has become widespread in recent years because of their per- formance and energy efficiency advantages. Approaches for managing and scheduling tasks to heterogeneous resources are still subject to research. Although queuing systems have recently been extended to support accelerator resources, a general solution that manages heterogeneous resources at the operating system- level to exploit a global view of the system state is still missing.In this paper we present a user space scheduler that enables task scheduling and migration on heterogeneous processing resources in Linux. Using run queues for available resources we perform scheduling decisions based on the system state and on task characterization from earlier measurements. With a pro- gramming pattern that supports the integration of checkpoints into applications, we preempt tasks and migrate them between three very different compute resources. Considering static and dynamic workload scenarios, we show that this approach can gain up to 17% performance, on average 7%, by effectively avoiding idle resources. We demonstrate that a work-conserving strategy without migration is no suitable alternative."}],"file_date_updated":"2018-03-21T12:41:55Z","date_created":"2017-10-17T12:41:24Z"}