Abstract
Well over a decade ago, many believed that an engine of growth driving the semiconductor and computing industries---captured nicely by Gordon Moore’s remarkable prophecy (Moore’s law)---was speeding towards a dangerous cliff-edge. Ranging from expressions of concern to doomsday scenarios, the exact time when serious hurdles would beset us varied quite a bit---some of the more optimistic warnings giving Moore’s law until. Needless to say, a lot of people have spent time and effort with great success to find ways for substantially extending the time when we would encounter the dreaded cliff-edge, if not avoiding it altogether. Faced with this issue, we started approaching this in a decidedly different manner---one which suggested falling off the metaphorical cliff as a design choice, but in a controlled way. This resulted in devices that could switch and produce bits that are correct, namely of having the intended value, only with a probabilistic guarantee. As a result, the results could in fact be incorrect. Such devices and associated circuits and computing structures are now broadly referred to as inexact designs, circuits, and architectures. In this article, we will crystallize the essence of inexactness dating back to 2002 through two key principles that we developed: (i) that of admitting error in a design in return for resource savings, and subsequently (ii) making resource investments in the elements of a hardware platform proportional to the value of information they compute. We will also give a broad overview of a range of inexact designs and hardware concepts that our group and other groups around the world have been developing since, based on these two principles. Despite not being deterministically precise, inexact designs can be significantly more efficient in the energy they consume, their speed of execution, and their area needs, which makes them attractive in application contexts that are resilient to error. Significantly, our development of inexactness will be contrasted against the rich backdrop of traditional approaches aimed at realizing reliable computing from unreliable elements, starting with von Neumann’s influential lectures and further developed by Shannon-Weaver and others.
- Akgul, B. E. S., Chakrapani, L. N., Korkmaz, P., and Palem, K. V. 2006. Probabilistic CMOS technology: A survey and future directions. In Proceedings of the IFIP International Conference on VLSI. 1--6.Google Scholar
- Banerjee, N., Karakonstantis, G., and Roy, K. 2007. Process variation tolerant low power DCT architecture. In Proceedings of the Design, Automation and Test in Europe Conference. 630--635. Google Scholar
Digital Library
- Boltzmann, L. and Brush, S. 1995. Lectures on Gas Theory, English translation by S.G. Brush. Dover Publications, Mineola, NY.Google Scholar
- Boole, G. 1847. The mathematical analysis of logic: Being an essay towards a calculus of deductive reasoning. http://www.gutenberg.org/ebooks/36884.Google Scholar
- Chakrapani, L. N., Korkmaz, P., Akgul, B. E. S., and Palem, K. V. 2007. Probabilistic system-on-a-chip architectures. ACM Trans. Design Autom. Electron. Syst. 12, 3, 1--28. Google Scholar
Digital Library
- Chakrapani, L. N., Muntimadugu, K. K., Lingamneni, A., George, J., and Palem, K. V. 2008. Highly energy and performance efficient embedded computing through approximately correct arithmetic: A mathematical foundation and preliminary experimental validation. In Proceedings of the IEEE/ACM International Conference on Compilers, Architectures and Synthesis for Embedded Systems. 187--196. Google Scholar
Digital Library
- Chakrapani, L. N. B. and Palem, K. V. 2008. A probabilistic boolean logic and its meaning. Tech. rep. TR08-05, Rice University, Department of Computer Science, Houston, TX.Google Scholar
- Chang, I. J., Mohapatra, D., and Roy, K. 2009. A voltage-scalable and process variation resilient hybrid sram architecture for mpeg-4 videoprocessors. In Proceedings of the Design Automation Conference. 670--675. Google Scholar
Digital Library
- Cheemalavagu, S., Korkmaz, P., and Palem, K. V. 2004. Ultra low-energy computing via probabilistic algorithms and devices: CMOS device primitives akrishna v palemnd the energy-probability relationship. In Proceedings of the International Conference on Solid State Devices and Materials. 402--403.Google Scholar
- Cheemalavagu, S., Korkmaz, P., Palem, K. V., Akgul, B. E. S., and Chakrapani, L. N. 2005. A probabilistic CMOS switch and its realization by exploiting noise. In Proceedings of the IFIP International Conference on VLSI-SoC. 452--457.Google Scholar
- Chippa, V. K., Mohapatra, D., Raghunathan, A., Roy, K., and Chakradhar, S. T. 2010. Scalable effort hardware design: Exploiting algorithmic resilience for energy efficiency. In Proceedings of the Design Automation Conference. 555--560. Google Scholar
Digital Library
- Cho, M., Schlessman, J., Wolf, W., and Mukhopadhyay, S. 2009. Accuracy- aware sram: A reconfigurable low power sram architecture for mobile multimedia applications. In Proceedings of the Asia and South Pacific Design Automation Conference. 823--828. Google Scholar
Digital Library
- De Micheli, G. 1994. Synthesis and Optimization of Digital Circuits. McGraw-Hill, New York, NY. Google Scholar
Digital Library
- Ernst, D., Kim, N. S., Das, S., Pant, S., Rao, R., Pham, T., Ziesler, C., Blaauw, D., Austin, T., Flautner, K., and Mudge, T. 2003. Razor: A low-power pipeline based on circuit-level timing speculation. In Proceedings of the IEEE/ACM International Symposium on Microarchitecture. 7--18. Google Scholar
Digital Library
- Faggin, F. and Hoff, M. E. 1972. Standard parts and custom design merge in a four-chip processor kit. Electron. Mag.Google Scholar
- Gell-Mann, M. 1997. Trying to make a reliable computer out of unreliable parts. http://www.webofstories.com/play/10585?o=MS.Google Scholar
- George, J., Marr, B., Akgul, B. E. S., and Palem, K. V. 2006. Probabilistic arithmetic and energy efficient embedded signal processing. In Proceedings of the IEEE/ACM International Conference on Compilers, Architectures and Synthesis for Embedded Systems. 158--168. Google Scholar
Digital Library
- Gibbs, J. 1902. Elementary Principles in Statistical Mechanics. Scribner, New York, NY.Google Scholar
- Gyger, S., Corbaz, A., and Beuchat, P.-A. 2009. Hardware development kit for systems based on an icyflex processor. CSEM Scientific and Tech. rep.Google Scholar
- Hegde, R. and Shanbhag, N. R. 1999. Energy-efficient signal processing via algorithmic noise-tolerance. In Proceedings of the International Symposium on Low Power Electronics and Design. 30--35. Google Scholar
Digital Library
- Heinig, A., Mooney, V. J., Schmoll, F., Marwedel, P., Palem, K. V., and Engel, M. 2012. Classification-based improvement of application robustness and quality of service in probabilistic computer systems. In Proceedings of the Architecture of Computing Systems Conference. 1--12. Google Scholar
Digital Library
- Hennessy, J. L. and Patterson, D. A. 2003. Computer Architecture: A Quantitative Approach. Morgan Kaufmann Publishers Inc., Burlington, MA. Google Scholar
Digital Library
- Jonietz, E. 2008. Probabilistic chips. Technol. Rev. MIT, Cambridge, MA. http://www.technologyreview.com/energy/20246/.Google Scholar
- Karakonstantis, G., Panagopoulos, G., and Roy, K. 2010. Herqules: System level cross-layer design exploration for efficient energy-quality trade-offs. In Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design. 117--122. Google Scholar
Digital Library
- Karp, R. 1977. Probabilistic analysis of partitioning algorithms for the traveling-salesman problem in the plane. Math. Oper. Res. 2, 3, 209--224.Google Scholar
Digital Library
- Kaul, H., Anders, M., Mathew, S., Hsu, S., Agarwal, A., Krishnamurthy, R., and Borkar, S. 2008. A 320 mv 56 μw 411 gops/watt ultra-low voltage motion estimation accelerator in 65 nm cmos. IEEE J. Solid-State Circuits.Google Scholar
- Kedem, Z. M., Mooney, V. J., Muntimadugu, K. K., Palem, K. V., Devarasetty, A., and Parasuramuni, P. D. 2010. Optimizing energy to minimize errors in dataflow graphs using approximate adders. In Proceedings of the International Conference on Compilers, Architectures and Synthesis for Embedded Systems. 177--186. Google Scholar
Digital Library
- Kedem, Z. M., Mooney, V. J., Muntimadugu, K. K., and Palem, K. V. 2011. An approach to energy-error tradeoffs in approximate ripple carry adders. In Proceedings of the International Symposium on Low Power Electronics and Design. 211--216. Google Scholar
Digital Library
- Kim, S. H., Mukohopadhyay, S., and Wolf, W. 2009. Experimental analysis of sequence dependence on energy saving for error tolerant image processing. In Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design. Google Scholar
Digital Library
- Kish, L. B. 2002. End of Moore’s law: Thermal (noise) death of integration in micro and nano electronics. Physics Lett. A 305, 144--149.Google Scholar
Cross Ref
- Korkmaz, P. 2007. Probabilistic cmos (PCMOS) in the nanoelectronics regime. Ph.D. thesis, Georgia Institute of Technology, Atlante, GA.Google Scholar
- Korkmaz, P., Akgul, B. E. S., Palem, K. V., and Chakrapani, L. N. 2006. Advocating noise as an agent for ultra low-energy computing: Probabilistic CMOS devices and their characteristics. Japan. J. App. Physics 45, 4B, 3307--3316.Google Scholar
Cross Ref
- Kurdahi, F. J., Eltawil, A., Yi, K., Cheng, S., and Khajeh, A. 2010. Low-power multimedia system design by aggressive voltage scaling. IEEE Trans. VLSI Syst. 18, 5, 852--856. Google Scholar
Digital Library
- Landauer, R. 1961. Irreversibility and heat generation in the computing process. IBM J. Res. Develop. 3. 183--191. Google Scholar
Digital Library
- Leem, L., Cho, H., Bau, J., Jacobson, Q., and Mitra, S. 2010. Ersa: Error resilient system architecture for probabilistic applications. In Proceedings of the Design, Automation and Test in Europe Conference. 1560--1565. Google Scholar
Digital Library
- Lingamneni, A., Enz, C. C., Nagel, J.-L., Palem, K. V., and Piguet, C. 2011a. Energy parsimonious circuit design through probabilistic pruning. In Proceedings of the Design, Automation and Test in Europe Conference. 764--769.Google Scholar
- Lingamneni, A., Enz, C. C., Palem, K. V., and Piguet, C. 2011b. Parsimonious circuit design for error-tolerant applications through probabilistic logic minimization. In Proceedings of the International Workshop on Power And Timing Modeling, Optimization and Simulation. 204--213. Google Scholar
Digital Library
- Lingamneni, A., Muntimadugu, K. K., Enz, C. C., Karp, R. M., Palem, K. V., and Piguet, C. 2012. Algorithmic methodologies for ultra-efficient inexact architectures for sustaining technology scaling. In Proceedings of the ACM International Conference on Computing Frontiers. Google Scholar
Digital Library
- Lingamneni, A., Enz, C. C., Palem, K. V., and Piguet, C. 2013. Synthesizing parsimonious inexact circuits through probabilistic design techniques. ACM Trans. Embed. Comput. Syst. (spl. issue on Probabilistic Embedded Computing). Google Scholar
Digital Library
- Ludwig, J., Nawab, S., and Chandrakasan, A. 1995. Low power filtering using approximate processing for DSP applications. In Proceedings of the IEEE Custom Integrated Circuits Conference. 185--188.Google Scholar
- Mauchly, J. and Eckert, J. 1947. Electrical numerical integrator and calculator. U.S. Patent 3120606, filed June 26, 1947 and issued Feb 4, 1964.Google Scholar
- Maxwell, J. C. 1871. Theory of Heat, Greenword Press, Westport, CT.Google Scholar
- McCulloch, W. and Pitts, W. 1943. A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophysics 7, 115--133.Google Scholar
Cross Ref
- Meindl, J., Naeemi, A., Bakir, M., and Murali, R. 2010. Nanoelectronics in retrospect, prospect and principle. In Proceedings of the IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC). 31--35.Google Scholar
- Minsky, M. 1967. Computation: Finite and Infinite Machines. Prentice-Hall, Inc., Englewood Cliffs, NJ. Google Scholar
Digital Library
- Mohapatra, D., Karakonstantis, G., and Roy, K. 2009. Significance driven computation: A voltage-scalable, variation-aware, quality-tuning motion estimator. In Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design. 195--200. Google Scholar
Digital Library
- Moore, E. and Shannon, C. 1956a. Reliable circuits using less reliable relays I. J. Franklin Instit. 262, 191--208.Google Scholar
Cross Ref
- Moore, E. and Shannon, C. 1956b. Reliable circuits using less reliable relays II. J. Franklin Instit. 262, 281--297.Google Scholar
Cross Ref
- Moore, G. E. 1965. Cramming more components onto integrated circuits. Electron. Mag. 38, 8.Google Scholar
- Mudge, T. 2001. Power: A first-class architectural design constraint. Computer 34, 4, 52--57. Google Scholar
Digital Library
- Narayanan, S., Sartori, J., Kumar, R., and Jones, D. L. 2010. Scalable stochastic processors. In Proceedings of the Design, Automation and Test in Europe Conference. 335--338. Google Scholar
Digital Library
- Nikolic, K., Sadek, A., and Forshaw, M. 2001. Architectures for reliable computing with unreliable nanodevices. In Proceedings of the IEEE Conference on Nanotechnology. 254--259.Google Scholar
- Palem, K. V. 2003a. Energy aware algorithm design via probabilistic computing: From algorithms and models to Moore’s law and novel (semiconductor) devices. In Proceedings of the International Conference on Compilers, Architectures and Synthesis for Embedded Systems. 113--116. Google Scholar
Digital Library
- Palem, K. V. 2003b. Proof as experiment: Probabilistic algorithms from a thermodynamic perspective. In Proceedings of the International Symposium on Verification (Theory and Practice).Google Scholar
Cross Ref
- Palem, K. V. 2005. Energy aware computing through probabilistic switching: A study of limits. IEEE Trans. Comput. 54, 9, 1123--1137 (abridged form appeared as K.V. Palem, Energy aware computing through randomized switching, Tech. rep. GIT--CC--03--16, Georgia Inst. of Technology. Google Scholar
Digital Library
- Palem, K. V., Cheemalavagu, S., Korkmaz, P., and Akgul, B. E. 2005. Probabilistic and introverted switching to conserve energy in a digital system. U.S. Patent 20050240787, filed April 27, 2005 and issued October 27, 2005.Google Scholar
- Palem, K. V., Akgul, B. E. S., and George, J. 2006. Variable scaling for computing elements. Invention Disclosure.Google Scholar
- Palem, K. V., Chakrapani, L. N., Kedem, Z. M., Lingamneni, A., and Muntimadugu, K. K. 2009a. Sustaining moore’s law in embedded computing through probabilistic and approximate design: Retrospects and prospects. In Proceedings of the International Conference on Compilers, Architectures and Synthesis for Embedded Systems. 1--10. Google Scholar
Digital Library
- Palem, K. V., Korkmaz, P., Yeo, K.-S., and Kong, Z.-H. 2009b. Probabilistic cmos (pcmos) logic for nanoscale circuit design. In Proceedings of the International Solid State Circuits Conference: Advanced Solid-State Circuits Forum.Google Scholar
- Palem, K. V. and Lingamneni, A. 2012. What to do about the end of moore’s law, probably! In Proceedings of the 49th Design Automation Conference. Google Scholar
Digital Library
- Rabin, M. O. 1963. Probabilistic automata. Inform. Control 6, 230--245.Google Scholar
Cross Ref
- Randall, V. A. 2006. A lost interview with ENIAC co-inventor J. Presper Eckert. http://www.computerworld.com. April 2011.Google Scholar
- Sartori, J., Sloan, J., and Kumar, R. 2011. Stochastic computing: Embracing errors in architecture and design of processors and applications. In Proceedings of the International Conference on Compilers, Architectures and Synthesis for Embedded Systems, 135--144. Google Scholar
Digital Library
- Shannon, C. 1937. A symbolic analysis of relay and switching circuits. M.S. thesis, Massachusetts Institute of Technology, Cambridge, MA.Google Scholar
- Solovay, R. and Strassen, V. 1977. A fast monte-carlo test for primality. SIAM J. Comput.Google Scholar
- Szilard, L. 1929. Reduction in entropy of a thermodynamic system caused by the interference of intelligent beings. Z. Physik 53, 840--856.Google Scholar
Cross Ref
- Turing, A. M. 1936. On computable numbers, with an application to the entscheidungsproblem. In Proceedings of the London Mathematical Society 42, 230--265.Google Scholar
- Ulam, S., Richtmyer, R. D., and von Neumann, J. 1947. Statistical methods in neutron diffusion. Los Alamos Scientific Laboratory report LAMS-551.Google Scholar
- von Neumann, J. 1956. Probabilistic logics and the synthesis of reliable organisms from unreliable components. In Automata Studies, C. E. Shannon and J. McCarthy Eds., Priceton Univ. Press, Princeton, N.J.Google Scholar
- Zuse, K. 1993. Der Computer. Mein Lebenswerk 3rd Ed. Number 978-3-540-56292-4. Springer-Verlag.Google Scholar
Index Terms
Ten Years of Building Broken Chips: The Physics and Engineering of Inexact Computing
Recommendations
Synthesizing Parsimonious Inexact Circuits through Probabilistic Design Techniques
Special Section on Probabilistic Embedded ComputingThe domain of inexact circuit design, in which accuracy of the circuit can be exchanged for substantial cost (energy, delay, and/or area) savings, has been gathering increasing prominence of late owing to a growing desire for reducing energy consumption ...
What to do about the end of Moore's law, probably!
DAC '12: Proceedings of the 49th Annual Design Automation ConferenceComputers process bits of information. A bit can take a value of 0 or 1, and computers process these bits through some physical mechanism. In the early days of electronic computers, this was done by electromechanical relays [28] which were soon replaced ...






Comments