Abstract
We present a low-cost methodology to find the highest energy efficiency operating conditions (voltage and frequency) for a processor with given performance requirements. Taking a black box approach, we start with processor specifications: nominal voltage, clock frequency, thermal design power (TDP), maximum frequency and maximum power, and a knowledge of the device technology. To determine the behavior of the processor, we use a small model circuit that can be economically but accurately simulated in Spice to learn the delay and energy characteristics of the technology. We simulate the model with random vectors to determine power consumption profiles and critical path delays at several voltages. Comparisons between the model data and processor specifications provide scale factors for area, voltage, nominal frequency and maximum frequency. We then optimize the operating modes of the processor for highest cycle efficiency (clock cycles per unit energy). An illustration considers a processor with 3.3 GHz clock, 1.2 V nominal voltage, and 95 W thermal design power. Several optimization scenarios are possible. Observing that the clock is power constrained, we reduce the voltage to 0.92 V, keeping the clock at 3.3 GHz, which now becomes structure-constrained. This gives a 127% higher cycle efficiency over the nominal operation. For highest performance, we set the voltage to 1.1 V and increase the clock to 4.5 GHz while holding power unchanged at 95 W. This gives 38% higher cycle efficiency than the nominal operation. The highest cycle efficiency, ten times greater than the nominal, occurs for subthreshold voltage operation at 0.35 V and 36 MHz.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
HSPICE Signal Integrity User Guide: Synopsys Inc., 700 East Middlefield Road, Mountain View, CA 94043 (2010)
Predictive Technology Model. Nanoscale Simulation and Modeling (NIMO) Group, Arizona State University (2012). http://ptm.asu.edu/
Intel core i5–2500k processor specifications (2016). http://ark.intel.com/products/52210/Intel-Core-i5-2500K-Processor-6M-Cache-up-to-3_70-GHz. Accessed 20 Feb 2016
Annavaram, M., Grochowski, E., Shen, J.: Mitigating Amdahl’s law through EPI throttling. In: Proceedings of 32nd IEEE International Symposium on Computer Architecture (ISCA), pp. 298–309 (2005)
Borkar, S., Chien, A.A.: The future of microprocessors. Commun. ACM 54(5), 67–77 (2011)
Dreslinski, R.G., Wieckowski, M., Blaauw, D., Sylvester, D., Mudge, T.: Near-threshold computing: reclaiming Moore’s law through energy efficient integrated circuits. Proc. IEEE 98(2), 253–266 (2010)
Ghasemazar, M., Pakbaznia, E., Pedram, M.: Minimizing the power consumption of a chip multiprocessor under an average throughput constraint. In: Proceedings of 11th International Symposium on Quality Electronic Design (ISQED), pp. 362–371, March 2010
Goyal, H.: Characterizing processors for time and energy optimization. Master’s thesis, Auburn University, Auburn, Alabama, USA, August 2016
Grochowski, E., Ronen, R., Shen, J., Wang, H.: Best of both latency and throughput. In: Proceedings of the International Conference on Computer Design, pp. 236–243 (2004)
Rabaey, J.M., Chandrakasan, A.P., Nikolic, B.: Digital Integrated Circuits, vol. 2. Prentice-Hall, Englewood Cliffs (2002)
Rotem, E., Naveh, A., Rajwan, D., Ananthakrishnan, A., Weissmann, E.: Power-management architecture of the Intel micoarchitecture code-names Sandy Bridge. IEEE Micro 32, 20–27 (2012)
Rubio, J., Rajamani, K., Rawson, F., Hanson, H., Ghiasi, S., Keller, T.: Dynamic processor over-clocking for improving performance of power-constrained systems. Technical Report RC23666 (W0507-124), IBM Research Division, Austin Research Laboratory, Texas, USA, July 2005
Sankari, A.: Proactive thermal-aware scheduling. Ph.D. thesis, Auburn University, Auburn, Alabama, USA, December 2014
Sartori, J., Kumar, R.: Software canaries: software-based path delay fault testing for variation-aware energy-efficient design. In: Proceedings of International Symposium on Low Power Electronics and Design, pp. 159–164 (2014)
Shinde, A.: Managing performance and efficiency of a processor. Master’s thesis, Auburn University, Auburn, Alabama, USA, December 2012
Travers, M.: CPU power consumption experiments and results analysis of Intel i7-4820K. Technical Report NCL-EEE-MICRO-TR-2015-19, Newcastle University, Newcastle-upon-Tyne, NE17RU, UK, June 2015
Venkataramani, P.: Reducing ATE test time by voltage and frequency scaling. Ph.D. thesis, Auburn University, Auburn, Alabama, USA, May 2014
Venkataramani, P., Sindia, S., Agrawal, V.D.: A test time theorem and its applications. J. Electron. Test.: Theory Appl. 30(2), 229–236 (2014)
Wang, A., Calhoun, B.H., Chandrakasan, A.P.: Sub-Threshold Design for Ultra Low-Power Systems. ICIR. Springer, Boston (2006). https://doi.org/10.1007/978-0-387-34501-7
Wang, J., Calhoun, B.H.: Techniques to extend canary-based standby \(V_{DD}\) scaling for SRAMs to 45 nm and beyond. IEEE Jour. Solid-State Circ. 43(11), 2514–2523 (2008)
Wong, H.: A comparison of Intel’s 32nm and 22nm core i5 CPUs: power, voltage, temperature, and frequency (2012). http://blog.stuffedcow.net/2012/10/intel32nm-22nm-core-i5-comparison. Accessed 13 Nov 2015
Ye, R., Xu, Q.: Learning-based power management for multicore processors via idle period manipulation. IEEE Trans. Comput. Aided Des. 33(7), 1043–1055 (2014)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Goyal, H., Agrawal, V.D. (2019). Technology Characterization Model and Scaling for Energy Management. In: Sengupta, A., Dasgupta, S., Singh, V., Sharma, R., Kumar Vishvakarma, S. (eds) VLSI Design and Test. VDAT 2019. Communications in Computer and Information Science, vol 1066. Springer, Singapore. https://doi.org/10.1007/978-981-32-9767-8_56
Download citation
DOI: https://doi.org/10.1007/978-981-32-9767-8_56
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-32-9766-1
Online ISBN: 978-981-32-9767-8
eBook Packages: Computer ScienceComputer Science (R0)