Abstract
SSD has become an indispensable element in today’s computer systems, and their architecture is constantly evolving with new host interfaces for higher performance and larger storage capacities thanks to incessant flash technology development. As the complexity of SSD architecture increases, it is necessary to use a systematic methodology for architecture design. In this paper, we propose a novel methodology to explore the design space of an SSD based on a genetic algorithm at the early design stage. The key technical challenge in the design space exploration (DSE) is fast and accurate performance estimation or fitness evaluation in the genetic algorithm. To tackle this challenge, we propose two performance estimation methods. One is based on the scheduling of the task graph abstracted from the firmware and the other one is based on a neural network (NN) regression model. While the NN-based method is faster, the accuracy of the NN-based method depends on the training data set that consists of hardware configurations and performance. The scheduling-based performance estimator is used to generate the training data set fast. The viability of the proposed methodology is confirmed by comparison with a state-of-the-art SSD simulator in terms of accuracy and speed for design space exploration.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015)
Bucy, J., et al.: The DiskSim simulation environment version 4.0 reference manual (2008)
Chen, Z., et al.: Explore the design space of solid state drive by an analytical model. In: 2011 Sixth Annual Chinagrid Conference, pp. 81–88. IEEE (2011)
Chollet, F., et al.: Keras. https://keras.io (2015)
Fortin, F.A., et al.: DEAP: evolutionary algorithms made easy. J. Mach. Learn. Res. 13, 2171–2175 (2012)
Gouk, D., et al.: Amber*: enabling precise full-system simulation with detailed modeling of all SSD resources. In: 2018 51st Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), pp. 469–481. IEEE (2018)
Hu, Y., et al.: Performance impact and interplay of SSD parallelism through advanced commands, allocation strategy and data granularity. In: Proceedings of the International Conference on Supercomputing, pp. 96–107. ACM (2011)
Huang, H.H., et al.: Performance modeling and analysis of flash-based storage devices. In: 2011 IEEE 27th Symposium on Mass Storage Systems and Technologies (MSST), pp. 1–11. IEEE (2011)
Ipek, E., et al.: Efficiently exploring architectural design spaces via predictive modeling. ACM SIGOPS Oper. Syst. Rev. 41, 195–206 (2006)
Jung, M., et al.: SimpleSSD: modeling solid state drives for holistic system simulation. IEEE Comput. Archit. Lett. 17(1), 37–41 (2017)
Keller, B.: Opportunities for fine-grained adaptive voltage scaling to improve system-level energy efficiency. Master’s thesis, EECS Department, University of California, Berkeley (2015)
Kim, J., et al.: Machine learning based performance modeling of flash SSDs. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp. 2135–2138. ACM (2017)
Kim, Y., et al.: FlashSim: a simulator for NAND flash-based solid-state drives. In: 2009 First International Conference on Advances in System Simulation, pp. 125–131. IEEE (2009)
Oyamada, M.S., et al.: Accurate software performance estimation using domain classification and neural networks. In: Proceedings of the 17th Symposium on Integrated Circuits and System Design, pp. 175–180. ACM (2004)
Ozisikyilmaz, B., et al.: Machine learning models to predict performance of computer system design alternatives. In: 2008 37th International Conference on Parallel Processing, pp. 495–502. IEEE (2008)
Panerati, J., et al.: Optimization strategies in design space exploration. In: Ha, S., Teich, J. (eds.) Handbook of Hardware/Software Codesign, pp. 189–216. Springer, Netherlands (2017). https://doi.org/10.1007/978-94-017-7267-9_7
Sherwood, T., et al.: Automatically characterizing large scale program behavior. ACM SIGARCH Comput. Archit. News 30(5), 45–57 (2002)
Tavakkol, A., et al.: MQSim: a framework for enabling realistic studies of modern multi-queue \(\{\)SSD\(\}\) devices. In: 16th \(\{\)USENIX\(\}\) Conference on File and Storage Technologies (\(\{\)FAST\(\}\) 2018), pp. 49–66 (2018)
Wu, G., et al.: GPGPU performance and power estimation using machine learning. In: 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA), pp. 564–576. IEEE (2015)
Yoo, J., et al.: VSSIM: virtual machine based SSD simulator. In: 2013 IEEE 29th Symposium on Mass Storage Systems and Technologies (MSST), pp. 1–14. IEEE (2013)
Yoo, J., et al.: Analytical model of SSD parallelism. In: 2014 4th International Conference on Simulation and Modeling Methodologies, Technologies and Applications (SIMULTECH), pp. 551–559. IEEE (2014)
Zuolo, L., et al.: SSDExplorer: a virtual platform for fine-grained design space exploration of solid state drives. In: Proceedings of the Conference on Design, Automation & Test in Europe, p. 284. European Design and Automation Association (2014)
Acknowledgement
This work is supported by Memory Division, Semiconductor Business, Samsung Electronics.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Kim, J., Ha, S. (2020). Fast Performance Estimation and Design Space Exploration of SSD Using AI Techniques. In: Orailoglu, A., Jung, M., Reichenbach, M. (eds) Embedded Computer Systems: Architectures, Modeling, and Simulation. SAMOS 2020. Lecture Notes in Computer Science(), vol 12471. Springer, Cham. https://doi.org/10.1007/978-3-030-60939-9_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-60939-9_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60938-2
Online ISBN: 978-3-030-60939-9
eBook Packages: Computer ScienceComputer Science (R0)