Abstract
We propose a technique to efficiently partition a FSMD (Finite State Machine with Datapath) using a simulated annealing approach. The FSMD is split into two or more simpler communicating processors. These separate processors can then be clock gated or power gated to achieve dramatic power savings since only one processor is active at any given time. We develop a framework to estimate the potential power savings from partitioning. Using several sample circuits, the estimation framework shows that when the original machine is partitioned into two submachines, on average, 32% static power savings and 19% dynamic power savings can be expected, with a performance impact of 2%. The power savings with more than two partitions can be even higher, with a larger performance impact.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hwang, E., Vahid, F., Hsu, Y.C.: FSMD functional partitioning for low power. In: DATE 1999 (1999)
Liu, B., Cai, Y., Zhou, Q., Bian, J., Hong, X.: FSM decomposition for power gating design automation in sequential circuits. In: ASICON 2005 (October 2005)
Gao, F., Hayes, J.P.: ILP-based optimization of sequential circuits for low power. In: ISLPED 2003 (2003)
Hu, Z., Buyuktosunoglu, A., Srinivasan, V., Zyuban, V., Jacobson, H., Bose, P.: Microarchitectural techniques for power gating of execution units. In: ISLPED 2004, pp. 32–37. ACM Press, New York (2004)
Agarwal, N., Dimopoulos, N.J.: Efficient automated clock gating using CoDeL. In: Vassiliadis, S., Wong, S., Hämäläinen, T.D. (eds.) SAMOS 2006. LNCS, vol. 4017, pp. 79–88. Springer, Heidelberg (2006)
Agarwal, N., Dimopoulos, N.J.: Automated power gating of registers using coDeL and FSM branch prediction. In: Vassiliadis, S., Bereković, M., Hämäläinen, T.D. (eds.) SAMOS 2007. LNCS, vol. 4599, pp. 294–303. Springer, Heidelberg (2007)
Kirkpatrick, S., Gelatt Jr., C.D., Vecchi, M.P.: Optimization by simulated annealing. Science 220(4598), 671–680 (1983)
Agarwal, N., Dimopoulos, N.J.: FSMD partitioning for low power using ILP. In: ISVLSI 2008: Proceedings of the 2008 IEEE Computer Society Annual Symposium on VLSI, Washington, DC, USA, pp. 63–68. IEEE Computer Society, Los Alamitos (2008)
Goldberg, D.E.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley Longman Publishing Co., Inc., Boston (1989)
Beni, G., Wang, J.: Swarm intelligence. In: Proceedings of the 7th Annual Meeting of the Robotics Society of Japan, pp. 425–428. RSJ Press (1989)
Agarwal, N., Dimopoulos, N.J.: FSMD partitioning for low power using simulated annealing. In: Proc. ISCAS 2008 (May 2008)
Plackett, R.L., Burman, J.P.: The design of optimum multifactorial experiments. Biometrika 33(4), 305–325 (1946)
Zivojnovic, V., Martinez, J., Schläger, C., Meyr, H.: DSPstone: A DSP-oriented benchmarking methodology. In: Proc. ICSPAT 1994 (October 1994)
Sivakumar, R., Dimakopoulos, V., Dimopoulos, N.: CoDeL: A rapid prototyping environment for the specification and automatic synthesis of controllers for multiprocessor interconnection networks. In: Proc. SAMOS III, July 2003, pp. 58–63 (2003)
Agarwal, N., Dimopoulos, N.J.: Using CoDeL to rapidly prototype network processsor extensions. In: Pimentel, A.D., Vassiliadis, S. (eds.) SAMOS 2004. LNCS, vol. 3133, pp. 333–342. Springer, Heidelberg (2004)
Vandekerckhove, J.: General simulated annealing algorithm, http://www.mathworks.com/matlabcentral/fileexchange/loadCategory.do
MathWorks, http://www.mathworks.com/
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 IFIP International Federation for Information Processing
About this paper
Cite this paper
Agarwal, N., Dimopoulos, N.J. (2009). Towards Automated FSMD Partitioning for Low Power Using Simulated Annealing. In: Bertels, K., Dimopoulos, N., Silvano, C., Wong, S. (eds) Embedded Computer Systems: Architectures, Modeling, and Simulation. SAMOS 2009. Lecture Notes in Computer Science, vol 5657. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03138-0_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-03138-0_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03137-3
Online ISBN: 978-3-642-03138-0
eBook Packages: Computer ScienceComputer Science (R0)