Abstract
To meet application-specific performance demands, recent embedded platforms often involve the use of intricate micro-architectural designs and very small feature sizes leading to complex chips with multi-million gates. Such ultra-high gate densities often make these chips susceptible to inappropriate surges in core temperatures. Temperature surges above a specific threshold may throttle processor performance, enhance cooling costs, and reduce processor life expectancy. This work proposes a generic temperature management strategy that can be easily employed to adapt existing state-of-the-art task graph schedulers so that schedules generated by them never violate stipulated thermal bounds. The overall temperature-aware task graph scheduling problem has first been formally modeled as a constraint optimization formulation whose solution is shown to be prohibitively expensive in terms of computational overheads. Based on insights obtained through the formal model, a new fast and efficient heuristic algorithm called TMDS has been designed. Experimental evaluation over diverse test case scenarios shows that TMDS is able to deliver lower schedule lengths compared to the temperature-aware versions of four prominent makespan minimizing algorithms, namely, HEFT, PEFT, PPTS, and PSLS. Additionally, a case study with an adaptive cruise controller in automotive systems has been included to exhibit the applicability of TMDS in real-world settings.
- [1] . 2014. List scheduling algorithm for heterogeneous systems by an optimistic cost table. IEEE Trans. Parallel Distrib. Syst. 25, 3 (2014), 682–694.Google ScholarDigital Library
- [2] . 2013. On multiprocessor temperature-aware scheduling problems. J. Sched. 16, 5 (2013), 529–538.Google ScholarDigital Library
- [3] . 2014. Temperature aware online scheduling for throughput maximisation: The effect of the cooling factor. Sustain. Comput.: Inform. Syst.s 4, 3 (2014), 151–159.Google ScholarCross Ref
- [4] . 2010. DAG scheduling using a lookahead variant of the heterogeneous earliest finish time algorithm. In Proceedings of the 18th Euromicro Conference on Parallel, Distributed, and Network-Based Processing (PDP’10). IEEE, 27–34.Google ScholarDigital Library
- [5] . 2008. Comparative evaluation of the robustness of dag scheduling heuristics. In Grid Computing. Springer, 73–84.Google ScholarCross Ref
- [6] . 2008. A high performance algorithm for static task scheduling in heterogeneous distributed computing systems. J. Parallel Distrib. Comput. 68, 4 (2008), 399–409.Google ScholarDigital Library
- [7] . 2019. Task scheduling for heterogeneous computing using a predict cost matrix. In Proceedings of the 48th International Conference on Parallel Processing: Workshops. 1–10.Google ScholarDigital Library
- [8] . 2014. Throughput maximization for periodic real-time systems under the maximal temperature constraint. ACM Trans. Embed. Comput. Syst. 13, 2s (2014), 1–22.Google ScholarDigital Library
- [9] . 2020. Dynamic DAG scheduling on multiprocessor systems: Reliability, energy, and makespan. IEEE Trans. Comput.-Aided Design Integr. Circ. Syst. 39, 11 (2020), 3336–3347.
DOI: Google ScholarCross Ref - [10] . 2007. Low complexity performance effective task scheduling algorithm for heterogeneous computing environments. J. Comput. Sci. 3, 2 (2007), 94–103.Google ScholarCross Ref
- [11] . 2005. High performance task scheduling algorithm for heterogeneous computing system. In Proceedings of the International Conference on Algorithms and Architectures for Parallel Processing. Springer, 193–203.Google ScholarDigital Library
- [12] . 2005. Dependable communication synthesis for distributed embedded systems. Reliabil. Eng. Syst. Safety 89, 1 (2005), 81–92.Google ScholarCross Ref
- [13] . 2014. Tradeoffs between power management and tail latency in warehouse-scale applications. In Proceedings of the IEEE International Symposium on Workload Characterization (IISWC’14). IEEE, 31–40.Google ScholarCross Ref
- [14] . 2010. Energy conscious scheduling for distributed computing systems under different operating conditions. IEEE Trans. Parallel Distrib. Syst. 22, 8 (2010), 1374–1381.Google ScholarDigital Library
- [15] . 2021. Thermal-aware adaptive platform management for heterogeneous embedded systems. ACM Trans. Embed. Comput. Syst. 20, 5s (2021), 1–28.Google ScholarDigital Library
- [16] . 2020. HEARS: A heterogeneous energy-aware real-time scheduler. Microprocess. Microsyst. 72 (2020), 102939.Google ScholarDigital Library
- [17] . 2021. TARTS: A temperature-aware real-time deadline-partitioned fair scheduler. J. Syst. Architect. 112 (2021), 101847.Google ScholarCross Ref
- [18] . 2021. An efficient proactive thermal-aware scheduler for DVFS-enabled single-core processors. In Proceedings of the 29th International Conference on Real-Time N/W and Systems. 144–154.Google Scholar
- [19] . 2021. SLAQA: Quality-level aware scheduling of task graphs on heterogeneous distributed systems. ACM Trans. Embed. Comput. Syst. 20, 5 (2021), 1–31.Google ScholarDigital Library
- [20] . 2012. Thermal-constrained energy-aware partitioning for heterogeneous multi-core multiprocessor real-time systems. In Proceedings of the IEEE International Conference on Embedded and Real-Time Computing Systems and Applications. IEEE, 41–50.Google ScholarDigital Library
- [21] . 2021. HMDS: A makespan minimizing DAG scheduler for heterogeneous distributed systems. ACM Trans. Embed. Comput. Syst. 20, 5s (2021), 1–26.Google ScholarDigital Library
- [22] . 2022. PRESTO: A penalty-aware real-time scheduler for task graphs on heterogeneous platforms. IEEE Trans. Comput. 71, 2 (2022), 421–435.
DOI: Google ScholarDigital Library - [23] . 2023. Energy-aware real-time scheduling of multiple periodic DAGs on heterogeneous systems. IEEE Trans. Comput.-Aided Design Integr. Circ. Syst. 42, 8 (2023), 2447–2460.
DOI: Google ScholarDigital Library - [24] . 2022. ETA-HP: An energy and temperature-aware real-time scheduler for heterogeneous platforms. J. Supercomput. 78 (2022), 1–25.Google ScholarDigital Library
- [25] . 2011. Fast algorithms for thermal constrained performance optimization in DAG scheduling on multi-core processors. In Proceedings of the International Green Computing Conference and Workshops. IEEE, 1–8.Google ScholarDigital Library
- [26] . 2012. Fast algorithms for simultaneous optimization of performance, energy and temperature in DAG scheduling on multi-core processors. In Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA’12). 1.Google Scholar
- [27] . 2012. An overview and classification of thermal-aware scheduling techniques for multi-core processing systems. Sustain. Comput.: Inform. Syst. 2, 3 (2012), 151–169.Google ScholarCross Ref
- [28] . 2004. Hybrid architectural dynamic thermal management. In Proceedings of the Design, Automation, and Test in Europe Conference and Exhibition, Vol. 1. IEEE, 10–15.Google ScholarCross Ref
- [29] . 2003. Temperature-aware microarchitecture. ACM SIGARCH Comput. Architect. News 31, 2 (2003), 2–13.Google ScholarDigital Library
- [30] . 2002. Performance-effective and low-complexity task scheduling for heterogeneous computing. IEEE Trans. Parallel Distrib. Syst. 13, 3 (2002), 260–274.Google ScholarDigital Library
- [31] . 1975. NP-complete scheduling problems. J. Comput. Syst. Sci. 10, 3 (1975), 384–393.Google ScholarDigital Library
- [32] . 2022. A survey of low-energy parallel scheduling algorithms. IEEE Trans. Sustain. Comput. 7, 1 (2022), 27–46.
DOI: Google ScholarCross Ref - [33] . 2017. Energy-aware processor merging algorithms for deadline constrained parallel applications in heterogeneous cloud computing. IEEE Trans. Sustain. Comput. 2, 2 (2017), 62–75.Google ScholarCross Ref
- [34] . 2003. Thermal management of microelectronic equipment: Heat transfer theory, analysis methods, and design practices. ASME press book series on electronic packaging. Appl. Mech. Rev. 56, 3 (2003), B46–B48.Google ScholarCross Ref
- [35] . 2016. Carb: A c-state power management arbiter for latency-critical workloads. IEEE Comput. Architect. Lett. 16, 1 (2016), 6–9.Google ScholarDigital Library
- [36] . 2019. Energy-efficient scheduling for real-time systems based on deep Q-learning model. IEEE Trans. Sustain. Comput. 4, 1 (2019), 132–141.
DOI: Google ScholarCross Ref - [37] . 2019. List scheduling algorithm based on pre-scheduling for heterogeneous computing. In Proceedings of the IEEE International Conference on Parallel and Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing and Communications, Social Computing, and Networking (ISPA/BDCloud/SocialCom/SustainCom’19). IEEE, 588–595.Google Scholar
- [38] . 2017. Reliability and temperature constrained task scheduling for makespan minimization on heterogeneous multi-core platforms. J. Syst. Softw. 133 (2017), 1–16.Google ScholarCross Ref
Index Terms
- TMDS: Temperature-aware Makespan Minimizing DAG Scheduler for Heterogeneous Distributed Systems
Recommendations
Performance-Effective DAG Scheduling for Heterogeneous Distributed Systems
ICDCN '22: Proceedings of the 23rd International Conference on Distributed Computing and NetworkingThe problem of scheduling Directed Acyclic Graphs (DAGs) in order to minimize schedule length (also known as makespan), is known to be a challenging as well as computationally hard problem. Therefore, researchers have endeavored towards the design of ...
HMDS: A Makespan Minimizing DAG Scheduler for Heterogeneous Distributed Systems
Special Issue ESWEEK 2021, CASES 2021, CODES+ISSS 2021 and EMSOFT 2021The problem of scheduling Directed Acyclic Graphs in order to minimize makespan (schedule length), is known to be a challenging and computationally hard problem. Therefore, researchers have endeavored towards the design of various heuristic solution ...
Metaheuristics for minimizing the makespan of the dynamic shop scheduling problem
For the shop scheduling problems such as flow-shop, job-shop, open-shop, mixed-shop, and group-shop, most research focuses on optimizing the makespan under static conditions and does not take into consideration dynamic disturbances such as machine ...
Comments