Self-Aware Computing for Cyber Physical Systems

2013.01 – 2019.12

Principal Investigators

Mingoo Seok (Columbia University)

Peter Kinget (Columbia University)

Student

SeongJong Kim (Columbia University)

Abstract

Novel cyber physical systems require digital systems that are very energy efficient. This program will develop a self-aware digital computation system that measures a range of static and dynamic variations, and adapts itself to them, so that performance, energy-efficiency, and reliability can be significantly increased. To enable this vision, we are investigating a range of approaches including the integration of a multitude of precision and flexible-supply-voltage analog sensors in the digital system but with a minimal area/testing overhead. We are further developing a framework to use the measured parameters, which can be imperfect, to effectively determine the optimal operating scenario. We strongly anticipate that such extensive instrumentation and control can advance the combination of performance, efficiency and reliability of digital computing systems beyond the current state of the art.

Publications

  1. Shihui Yin, Zhewei Jiang, Jae-sun Seo, Mingoo Seok, “XNOR-SRAM: In-Memory Computing SRAM Macro for Binary and Ternary Deep Neural Networks,” IEEE Journal of Solid-State Circuits (JSSC), 2020. DOI: 10.1109/JSSC.2019.2963616
  2. Zhewei Jiang, Shihui Yin, Jae-sun Seo, Mingoo Seok, “C3SRAM: An In-Memory-Computing SRAM Macro Based on Robust Capacitive Coupling Computing Mechanism,” IEEE Journal of Solid-State Circuits (JSSC), 2020. (invited)  DOI: 10.1109/JSSC.2020.2992886
  3. Doyun Kim, Peter R. Kinget, Mingoo Seok, “SRAM-ADC: SRAM Circuits Transformable to a Stochastic ADC at Ultralow Area Overhead,” IEEE Solid-State Circuits Letters, vol. 2, no. 10, pp. 215-218, Oct. 2019. DOI: 10.1109/LSSC.2019.2943874
  4. Seongjong Kim, Joao Pedro Cerqueira, Mingoo Seok, “A Near-Threshold Spiking Neural Network Accelerator with a Body-Swapping based In-Situ Error Detection and Correction Technique,” IEEE Transactions of Very Large Scale Integration Systems, vol. 27, no. 8, pp. 1886-1896, Aug. 2019. DOI: 10.1109/TVLSI.2019.2910792
  5. Teng Yang, Doyun Kim, Jiangyi Li, Peter R. Kinget, Mingoo Seok, “In-Situ and In-Field Technique for Monitoring and Decelerating NBTI in 6T-SRAM Register Files,” IEEE Transactions of Very Large Scale Integration Systems (TVLSI), vol. 26, no. 11, pp. 2241-2253, Nov. 2018. DOI: 10.1109/TVLSI.2018.2856528
  6. Seongjong Kim, Mingoo Seok, A Sub-50μm2, Voltage-Scalable, Digital-Standard-Cell-Compatible Thermal Sensor Frontend for On-Chip Thermal Monitoring,” Journal of Low Power Electronics and Applications – Special Issue on CMOS Low Power Design, vol. 8, no. 2, 2018. DOI: 10.3390/jlpea8020016
  7. Jiangyi Li, Teng Yang, Minhao Yang, Peter R. Kinget, Mingoo Seok, “An Area-Efficient Microprocessor based SoC with an Instruction-Cache Transformable to an Ambient Temperature Sensor and a Physically Unclonable Function,” IEEE Journal of Solid-State Circuits, vol. 53, no. 3, pp. 728-737, March 2018. DOI: 10.1109/JSSC.2018.2791460
  8. Jiangyi Li, Pavan Kumar Chundi, Sung Justin Kim, Zhewei Jiang, Minhao Yang, Joonseong Kang, Seungchul Jung, Sang Joon Kim, Mingoo Seok,” A 0.78-μW 96-Ch. Neural Signal Processor Integrated with a Nanowatt Power Management Unit based on Energy-Robustness Co-Optimization Control,” IEEE European Solid-State Circuits Conference (ESSCIRC), 2018. DOI:10.1109/ESSCIRC.2018.8494273
  9. Sheng Zhang, Adrian Tang, Zhewei Jiang, Simha Sethumadhavan, Mingoo Seok, “Blacklist Core: Machine-Learning Based Dynamic Operating-Performance-Point Blacklisting for Mitigating Power-Management Security Attacks,” ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED), 2018. DOI: 10.1145/3218603.3218624
  10. Mingoo Seok, Peter R. Kinget, Teng Yang, Jiangyi Li, Doyun Kim, “Recent Advances in In-situ and In-field Transistor-Aging and Compensation Techniques,” IEEE International Reliability Physics Symposium (IRPS), 2018. (invited) DOI: 10.1109/IRPS.2018.8353612
  11. Seongjong Kim, Joao Pedro Cerqueira, Mingoo Seok, “A 450mV Timing-Margin-Free Waveform Sorter based on Body Swapping Error Correction,” IEEE Symposium on VLSI Circuits (VLSI), 2016. DOI: 10.1109/VLSIC.2016.7573561
  12. Teng Yang, Doyun Kim, Peter R. Kinget, Mingoo Seok, “In-situ Techniques for In-field Sensing of NBTI Degradation in an SRAM Register File,” IEEE International Solid-State Circuits Conference (ISSCC), 2015. DOI: 10.1109/ISSCC.2015.7063027

Report

Link to PDF: 2018 Progress Report