Abstract
Many emerging applications such as IoT, wearables, implantables, and sensor networks are power- and energy-constrained. These applications rely on ultra-low-power processors that have rapidly become the most abundant type of processor manufactured today. In the ultra-low-power embedded systems used by these applications, peak power and energy requirements are the primary factors that determine critical system characteristics, such as size, weight, cost, and lifetime. While the power and energy requirements of these systems tend to be application-specific, conventional techniques for rating peak power and energy cannot accurately bound the power and energy requirements of an application running on a processor, leading to over-provisioning that increases system size and weight. In this paper, we present an automated technique that performs hardware-software co-analysis of the application and ultra-low-power processor in an embedded system to determine application-specific peak power and energy requirements. Our technique provides more accurate, tighter bounds than conventional techniques for determining peak power and energy requirements, reporting 15% lower peak power and 17% lower peak energy, on average, than a conventional approach based on profiling and guardbanding. Compared to an aggressive stressmark-based approach, our technique reports power and energy bounds that are 26% and 26% lower, respectively, on average. Also, unlike conventional approaches, our technique reports guaranteed bounds on peak power and energy independent of an application's input set. Tighter bounds on peak power and energy can be exploited to reduce system size, weight, and cost.
- EEMBC, Embedded Microprocessor Benchmark Consortium. http://www.eembc.org.Google Scholar
- International Technology Roadmap for Semiconductors 2.0 2015 Edition Executive Report. http://www.semiconductors.org/main/2015_international_technology_roadmap_for_semiconductors_itrs/.Google Scholar
- Microcontroller Sales Regain Momentum After Slump. www.icinsights.com/news/bulletins/Microcontroller-Sales-Regian-Momentum-After-Slump.Google Scholar
- Intel corporation: Intel pentium 4 processor in the 423-pin package thermal design guidelines, 2000.Google Scholar
- Battery energy. http://www.aboutbatteries.com/Battery-Energy.html, 2015.Google Scholar
- arm_mbedARM. ARM mbed IoT Device Platform. URL https://www.mbed.com/en/.Google Scholar
- H. Blodget, M. Ballve, T. Danova, C. Smith, J. Heggestuen, M. Hoelzel, E. Adler, C. Weissman, H. King, N. Quah, J. Greenough, and J. Smith. The internet of everything: 2015. BI Intelligence, 2014.Google Scholar
- J. Borgeson. Ultra-low-power pioneers: TI slashes total MCU power by 50 percent with new "Wolverine" MCU platform. Texas Instruments White Paper, 2012. URL http://www.ti.com/lit/wp/slay019a/slay019a.pdf.Google Scholar
- R. E. Bryant. Symbolic Simulation -- Techniques and Applications. In Proceedings of the 27th ACM/IEEE Design Automation Conference, pages 517--521. ACM, 1991.Google Scholar
Digital Library
- I. Buchmann. The Secrets of Battery Runtime. Battery University, 2016.Google Scholar
- C. Cadar and K. Sen. Symbolic execution for software testing: Three decades later. Commun. ACM, 56 (2): 82--90, Feb. 2013. ISSN 0001-0782. 10.1145/2408776.2408795. URL http://doi.acm.org/10.1145/2408776.2408795.Google Scholar
Digital Library
- Cadence. Encounter Digital Implementation User Guide. URL http://www.cadence.com/.Google Scholar
- B. Calhoun, S. Khanna, Y. Zhang, J. Ryan, and B. Otis. System design principles combining sub-threshold circuit and architectures with energy scavenging mechanisms. In Circuits and Systems (ISCAS), Proceedings of 2010 IEEE International Symposium on, pages 269--272, May 2010. 10.1109/ISCAS.2010.5537887. Google Scholar
Cross Ref
- H. Cherupalli, R. Kumar, and J. Sartori. Exploiting dynamic timing slack for energy efficiency in ultra-low-power embedded systems. In Computer Architecture (ISCA), 2016 43th Annual International Symposium on. IEEE, 2016. Google Scholar
Digital Library
- C. Compiling. Cloud Compiling. URL http://www.cloudcompiling.com/.Google Scholar
- A. Dunkels, J. Eriksson, N. Finne, F. Osterlind, N. Tsiftes, J. Abeillé, and M. Durvy. Low-Power IPv6 for the internet of things. In Networked Sensing Systems (INSS), 2012 Ninth International Conference on, pages 1--6. IEEE, 2012. Google Scholar
Cross Ref
- D. Evans. The internet of things: How the next evolution of the internet is changing everything. April 2011.Google Scholar
- T. Feng, L. C. Wang, K.-T. Cheng, M. Pandey, and M. S. Abadir. Enhanced symbolic simulation for efficient verification of embedded array systems. In Design Automation Conference, 2003. Proceedings of the ASP-DAC 2003. Asia and South Pacific, pages 302--307, Jan 2003. 10.1109/ASPDAC.2003.1195032. Google Scholar
Cross Ref
- K. Furset and P. Hoffman. High pulse drain impact on CR2032 coin cell battery capacity. Nordic Semiconductor and Energizer, 2011.Google Scholar
- O. Girard. OpenMSP430 project. available at opencores.org, 2013.Google Scholar
- K. Hamaguchi. Symbolic simulation heuristics for high-level design descriptions with uninterpreted functions. In High-Level Design Validation and Test Workshop, 2001. Proceedings. Sixth IEEE International, pages 25--30, 2001. Google Scholar
Cross Ref
- M. S. Hsiao. Peak power estimation using genetic spot optimization for large vlsi circuits. In Proceedings of the conference on Design, automation and test in Europe, page 38. ACM, 1999.Google Scholar
- M. S. Hsiao, E. M. Rudnick, and J. H. Patel. K2: an estimator for peak sustainable power of vlsi circuits. In Low Power Electronics and Design, 1997. Proceedings., 1997 International Symposium on, pages 178--183. IEEE. Google Scholar
Digital Library
- N. Instruments. Compile Faster with the LabVIEW FPGA Compile Cloud Service. URL http://www.ni.com/white-paper/52328/en/.Google Scholar
- T. Instruments. eZ430-RF2500-SEH Solar Energy Harvesting Development Tool User's Guide. 2013.Google Scholar
- P. Jain and G. Gopalakrishnan. Efficient symbolic simulation-based verification using the parametric form of boolean expressions. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 13 (8): 1005--1015, Aug 1994. ISSN 0278-0070. 10.1109/43.298036.Google Scholar
Digital Library
- R. Jayaseelan, T. Mitra, and X. Li. Estimating the worst-case energy consumption of embedded software. In 12th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS'06), pages 81--90. IEEE, 2006. Google Scholar
Digital Library
- Y. Kim, L. K. John, S. Pant, S. Manne, M. Schulte, W. L. Bircher, and M. S. S. Govindan. Audit: Stress testing the automatic way. In Proceedings of the 2012 45th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO-45, pages 212--223, Washington, DC, USA, 2012. IEEE Computer Society. ISBN 978-0--7695--4924--8. 10.1109/MICRO.2012.28. URL http://dx.doi.org/10.1109/MICRO.2012.28. Google Scholar
Digital Library
- A. Kolbi, J. Kukula, and R. Damiano. Symbolic RTL simulation. In Design Automation Conference, 2001. Proceedings, pages 47--52, 2001. 10.1109/DAC.2001.156106.Google Scholar
Cross Ref
- V. Kontorinis, A. Shayan, D. M. Tullsen, and R. Kumar. Reducing peak power with a table-driven adaptive processor core. In Proceedings of the 42Nd Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 42, pages 189--200, New York, NY, USA, 2009. ACM. ISBN 978--1--60558--798--1. 10.1145/1669112.1669137. URL http://doi.acm.org/10.1145/1669112.1669137.Google Scholar
Digital Library
- L. Liu and S. Vasudevan. Efficient validation input generation in RTL by hybridized source code analysis. In Design, Automation Test in Europe Conference Exhibition (DATE), 2011, pages 1--6, March 2011. 10.1109/DATE.2011.5763253. Google Scholar
Cross Ref
- M. Magno, L. Benini, C. Spagnol, and E. Popovici. Wearable low power dry surface wireless sensor node for healthcare monitoring application. In Wireless and Mobile Computing, Networking and Communications (WiMob), 2013 IEEE 9th International Conference on, pages 189--195. IEEE, 2013. Google Scholar
Cross Ref
- J. Morse, S. Kerrison, and K. Eder. On the infeasibility of analysing worst-case dynamic energy. pharXiv preprint arXiv:1603.02580, 2016.Google Scholar
- K. Najeeb, V. Vardhan, R. Konda, S. Kumar, S. Hari, V. Kamakoti, and V. M. Vedula. Power virus generation using behavioral models of circuits. In VLSI Test Symposium, 2007. 25th IEEE, pages 35--42, May 2007. 10.1109/VTS.2007.49. Google Scholar
Digital Library
- J. A. Paradiso and T. Starner. Energy scavenging for mobile and wireless electronics. IEEE Pervasive Computing, 4 (1): 18--27, Jan 2005. 10.1109/MPRV.2005.9. Google Scholar
Digital Library
- C. Park, P. H. Chou, Y. Bai, R. Matthews, and A. Hibbs. An ultra-wearable, wireless, low power ECG monitoring system. In Biomedical Circuits and Systems Conference, 2006. BioCAS 2006. IEEE, pages 241--244. IEEE, 2006. Google Scholar
Cross Ref
- G. Press. Internet of Things By The Numbers: Market Estimates And Forecasts. Forbes, 2014.Google Scholar
- S. Sambamurthy, S. Gurumurthy, R. Vemu, and J. A. Abraham. Functionally valid gate-level peak power estimation for processors. In Quality of Electronic Design, 2009. ISQED 2009. Quality Electronic Design, pages 753--758. IEEE, 2009. Google Scholar
Digital Library
- J. Sartori and R. Kumar. Distributed peak power management for many-core architectures. In Design, Automation Test in Europe Conference Exhibition, 2009. DATE '09., pages 1556--1559, April 2009. 10.1109/DATE.2009.5090910. Google Scholar
Cross Ref
- K. Seth, A. Anantaraman, F. Mueller, and E. Rotenberg. Fast: Frequency-aware static timing analysis. ACM Transactions on Embedded Computing Systems (TECS), 5 (1): 200--224, 2006. Google Scholar
Digital Library
- Synopsys. Design Compiler User Guide,natexlaba. URL http://www.synopsys.com/.Google Scholar
- Synopsys. PrimeTime User Guide,natexlabb. URL http://www.synopsys.com/.Google Scholar
- R. Tessier, D. Jasinski, A. Maheshwari, A. Natarajan, W. Xu, and W. Burleson. An energy-aware active smart card. Very Large Scale Integration (VLSI) Systems, IEEE Transactions on, 13 (10): 1190--1199, 2005.Google Scholar
- P. Wägemann, T. Distler, T. Hönig, H. Janker, R. Kapitza, and W. Schröder-Preikschat. Worst-case energy consumption analysis for energy-constrained embedded systems. In 2015 27th Euromicro Conference on Real-Time Systems, pages 105--114. IEEE, 2015. Google Scholar
Digital Library
- C.-Y. Wang and K. Roy. Maximum power estimation for cmos circuits using deterministic and statistical approaches. Very Large Scale Integration (VLSI) Systems, IEEE Transactions on, 6 (1): 134--140, 1998.Google Scholar
- Wikipedia. List of wireless sensor nodes, 2016. URL https://en.wikipedia.org/wiki/List_of_wireless_sensor_nodes. [Online; accessed 7-April-2016].Google Scholar
- R. Yu and T. Watteyne. Reliable, Low Power Wireless Sensor Networks for the Internet of Things: Making Wireless Sensors as Accessible as Web Servers. Linear Technology, 2013. URL http://cds.linear.com/docs/en/white-paper/wp003.pdf.Google Scholar
- B. Zhai, S. Pant, L. Nazhandali, S. Hanson, J. Olson, A. Reeves, M. Minuth, R. Helfand, T. Austin, D. Sylvester, et al. Energy-efficient subthreshold processor design. Very Large Scale Integration (VLSI) Systems, IEEE Transactions on, 17 (8): 1127--1137, 2009.Google Scholar
- Y. Zhang, Z. Chen, and J. Wang. Speculative symbolic execution. In Software Reliability Engineering (ISSRE), 2012 IEEE 23rd International Symposium on, pages 101--110, 2012. 10.1109/ISSRE.2012.8. Google Scholar
Digital Library
Recommendations
Determining Application-specific Peak Power and Energy Requirements for Ultra-low Power Processors
ASPLOS '17: Proceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating SystemsMany emerging applications such as IoT, wearables, implantables, and sensor networks are power- and energy-constrained. These applications rely on ultra-low-power processors that have rapidly become the most abundant type of processor manufactured ...
Determining Application-specific Peak Power and Energy Requirements for Ultra-low Power Processors
Asplos'17Many emerging applications such as IoT, wearables, implantables, and sensor networks are power- and energy-constrained. These applications rely on ultra-low-power processors that have rapidly become the most abundant type of processor manufactured ...
Determining Application-Specific Peak Power and Energy Requirements for Ultra-Low-Power Processors
Many emerging applications such as the Internet of Things, wearables, implantables, and sensor networks are constrained by power and energy. These applications rely on ultra-low-power processors that have rapidly become the most abundant type of ...







Comments