ILP models for the allocation of recurrent workloads upon heterogeneous multiprocessors
- 126 Downloads
The problem of partitioning systems of independent constrained-deadline sporadic tasks upon heterogeneous multiprocessor platforms is considered. Several different integer linear program (ILP) formulations of this problem, offering different trade-offs between effectiveness (as quantified by speedup bound) and running time efficiency, are presented. One of the formulations is leveraged to improve the best speedup guarantee known for a polynomial-time partitioning algorithm, from 12.9 to 7.83. Extensive computational results on synthetically generated instances are also provided to establish the effectiveness of the ILP formulations.
KeywordsTask partitioning Sporadic tasks Unrelated machines Speedup bound ILP rounding
Work supported by NSF Grants CNS 1115284, CNS 1218693, CNS 1409175, and CPS 1446631, AFOSR Grant FA9550-14-1-0161, ARO Grant W911NF-14-1-0499, and a Grant from General Motors Corp. This work has also been partially supported by the research project “Designing Human-Agent Collectives for Sustainable Future Societies” (C26A15TXCF) of Sapienza University of Rome, by MIUR PRIN Grant 2012JXB3YF_003, and by the National Group of Computing Science (GNCS-INDAM).
- Gurobi Optimizer. http://www.gurobi.com.
- Albers, K., & Slomka, F. (2004). An event stream driven approximation for the analysis of real-time systems. In Proceedings of 16th Euromicro Conference on Real-Time Systems, (pp. 187–195). IEEEGoogle Scholar
- Andersson, B., & Raravi, G. (2016). Scheduling constrained-deadline parallel tasks on two-type heterogeneous multiprocessors. In Proceedings of 24th International Conference on Real-Time Networks, (pp. 247–256). ACMGoogle Scholar
- Baruah, S., & Bini, E. (2008). Partitioned scheduling of sporadic task systems: An ILP-based approach. In Proceedings of 2008 Conference on Design and Architectures for Signal and Image Processing Google Scholar
- Baruah, S., Mok, A., & Rosier, L. (1990). Preemptively scheduling hard-real-time sporadic tasks on one processor. In Proceedings of 11th Real-Time Systems Symposium, (pp. 182–190). IEEEGoogle Scholar
- Bonifaci, V., D’Angelo, G., & Marchetti-Spaccamela, A. (2017). Algorithms for hierarchical and semi-partitioned machine scheduling. In To Appear in 31st International Parallel and Distributed Processing Symposium (IPDPS 2017), IEEE.Google Scholar
- Chwa, H. S., Seo, J., Lee, J., & Shin, I. (2015). Optimal real-time scheduling on two-type heterogeneous multicore platforms. In Proceedings of Real-Time Systems Symposium, IEEEGoogle Scholar
- Dertouzos, M. (1974). Control robotics: The procedural control of physical processors. In Proceedings of the IFIP Congress, (pp. 807–813)Google Scholar
- Lau, L. C., Ravi, R., & Singh, M. (2011). Iterative methods in combinatorial optimization. Cambridge: Cambridge University Press.Google Scholar
- Marchetti-Spaccamela, A., Rutten, C., van der Ster, S., & Wiese, A. (2014). Assigning sporadic tasks to unrelated machines. Mathematical Programming, 152, 1–28.Google Scholar
- Raravi, G. (2014). Real-Time Scheduling on Heterogeneous Multiprocessors. PhD thesis, Technical Institute of Porto (Portugal)Google Scholar
- Raravi, G., & Nélis, V. (2012). A PTAS for assigning sporadic tasks on two-type heterogeneous multiprocessors. In Proceedings of 33rd Real-Time Systems Symposium, pp. 117–126. IEEEGoogle Scholar