Abstract
Learning classifier tables (LCTs) are classifier based and lightweight hardware reinforcement learning building blocks which inherit the concepts of learning classifier systems. LCTs are used as a per-core low level controllers to learn and optimize potentially conflicting objectives e.g. achieving a performance target under a power budget. A supervisor is used at the system level which translate system and application requirements into objectives for the LCTs. The classifier population in the LCTs has to be evolved in run-time to adapt to the changes in the mode, performance targets, constraints or workload being executed. Towards this goal, we present GAE-LCT, a genetic algorithm (GA) based classifier evolution for hardware learning classifier tables. The GA uses accuracy to evolve classifiers in run-time. We introduce extensions to the LCT to enable accuracy based genetic algorithm. The GA runs as a software process on one of the cores and interacts with the hardware LCT via interrupts. We evaluate our work using DVFS on an FPGA using Leon3 cores. We demonstrate GAE-LCT’s ability to generate accurate classifiers in run-time from scratch. GAE-LCT achieves 5% lower difference to IPS reference and 51.5% lower power budget overshoot compared to Q-table while requiring 75% less memory. The hybrid GAE-LCT also requires 12 times less software overhead compared to a full software implementation.
We thank our project partners in the IPF project and acknowledge the financial support from the DFG under Grant HE4584/7-1.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bernauer, A., Zeppenfeld, J., Bringmann, O., Herkersdorf, A., Rosenstiel, W.: Combining software and hardware LCS for lightweight on-chip learning. In: Hinchey, M., et al. (eds.) BICC/DIPES -2010. IAICT, vol. 329, pp. 278–289. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15234-4_27
Bitirgen, R., Ipek, E., Martinez, J.F.: Coordinated management of multiple interacting resources in chip multiprocessors: a machine learning approach. In: 2008 41st IEEE/ACM International Symposium on Microarchitecture (2008)
Bolchini, C., Ferrandi, P., Lanzi, P.L., Salice, F.: Evolving classifiers on field programmable gate arrays: migrating XCS to FPGAs. J. Syst. Archit. 52, 516–533 (2006)
Bouajila, A., et al.: Autonomic system on chip platform. In: Müller-Schloer, C., Schmeck, H., Ungerer, T. (eds.) Organic Computing–A Paradigm Shift for Complex System, vol. 1, pp. 413–425. Springer, Basel (2011). https://doi.org/10.1007/978-3-0348-0130-0_27
Butz, M.V., Kovacs, T., Lanzi, P.L., Wilson, S.W.: How XCS evolves accurate classifiers. In: Proceedings of the Third Genetic and Evolutionary Computation Conference (GECCO-2001) (2001)
Chen, Z., Marculescu, D.: Distributed reinforcement learning for power limited many-core system performance optimization. In: 2015 Design, Automation & Test in Europe Conference & Exhibition (DATE) (2015)
Dhiman, G., Rosing, T.S.: Dynamic power management using machine learning. In: Proceedings of the 2006 IEEE/ACM International Conference on Computer-Aided Design (2006)
Donyanavard, B., et al.: SOSA: self-optimizing learning with self-adaptive control for hierarchical system-on-chip management. In: Proceedings of the 52nd Annual IEEE/ACM International Symposium on Microarchitecture (2019)
Gaisler, J., Catovic, E., Isomaki, M., Glembo, K., Habinc, S.: Grlib IP core user’s manual. Gaisler research (2007)
Gupta, U., Mandal, S.K., Mao, M., Chakrabarti, C., Ogras, U.Y.: A deep Q-learning approach for dynamic management of heterogeneous processors. IEEE Comput. Archit. Lett. 18, 14–17 (2019)
Guthaus, M.R., Ringenberg, J.S., Ernst, D., Austin, T.M., Mudge, T., Brown, R.B.: MiBench: a free, commercially representative embedded benchmark suite. In: Proceedings of the Fourth Annual IEEE International Workshop on Workload Characterization (2001)
Hansmeier, T.: Self-aware operation of heterogeneous compute nodes using the learning classifier system XCS. In: Proceedings of the 11th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies (2021)
Hansmeier, T., Platzner, M.: An experimental comparison of explore/exploit strategies for the learning classifier system XCS. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion (2021)
Kovacs, T.: Strength or accuracy? Fitness calculation in learning classifier systems. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 1999. LNCS (LNAI), vol. 1813, pp. 143–160. Springer, Heidelberg (2000). https://doi.org/10.1007/3-540-45027-0_7
Liu, W., Tan, Y., Qiu, Q.: Enhanced Q-learning algorithm for dynamic power management with performance constraint. In: 2010 Design, Automation & Test in Europe Conference & Exhibition (DATE) (2010)
Maurer, F., Donyanavard, B., Rahmani, A.M., Dutt, N., Herkersdorf, A.: Emergent control of MPSOC operation by a hierarchical supervisor/reinforcement learning approach. In: 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE) (2020)
Pagani, S., Manoj, P.S., Jantsch, A., Henkel, J.: Machine learning for power, energy, and thermal management on multicore processors: a survey. IEEE Trans. Comput.-Aided Design Integr. Circ. Syst. 39, 101–116 (2018)
Rajat, R., Meng, Y., Kuppannagari, S., Srivastava, A., Prasanna, V., Kannan, R.: QTAccel: a generic FPGA based design for q-table based reinforcement learning accelerators. In: Proceedings of the 2020 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (2020)
Shen, H., Lu, J., Qiu, Q.: Learning based DVFS for simultaneous temperature, performance and energy management. In: Thirteenth International Symposium on Quality Electronic Design (ISQED) (2012)
Wang, Y.C., Usher, J.M.: Application of reinforcement learning for agent-based production scheduling. Eng. Appl. Artif. Intell. 18, 73–82 (2005)
Zeppenfeld, J., et al.: Applying ASOC to multi-core applications for workload management. In: Müller-Schloer, C., Schmeck, H., Ungerer, T. (eds.) Organic Computing–A Paradigm Shift for Complex Systems. Autonomic Systems, vol. 1, pp. 461–472. Springer, Basel (2011). https://doi.org/10.1007/978-3-0348-0130-0_30
Zeppenfeld, J., Bouajila, A., Stechele, W., Herkersdorf, A.: Learning classifier tables for autonomic systems on chip. INFORMATIK 2008. Beherrschbare Systeme-dank Informatik. Band 2 (2008)
Zhang, Q., Lin, M., Yang, L.T., Chen, Z., Li, P.: Energy-efficient scheduling for real-time systems based on deep Q-learning model. IEEE Trans. Sustain. Comput. 4, 132–141 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Surhonne, A., Doan, N.A.V., Maurer, F., Wild, T., Herkersdorf, A. (2022). GAE-LCT: A Run-Time GA-Based Classifier Evolution Method for Hardware LCT Controlled SoC Performance-Power Optimization. In: Schulz, M., Trinitis, C., Papadopoulou, N., Pionteck, T. (eds) Architecture of Computing Systems. ARCS 2022. Lecture Notes in Computer Science, vol 13642. Springer, Cham. https://doi.org/10.1007/978-3-031-21867-5_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-21867-5_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-21866-8
Online ISBN: 978-3-031-21867-5
eBook Packages: Computer ScienceComputer Science (R0)