Towards Smart Edge Devices: Challenges and Opportunities Gigascale Reliable Energy Efficient Nanosystem (GREEN) Lab School of Electrical and Computer Engineering, Georgia Tech Exploring reliable, energy efficient computing solutions at nanometer nodes — from devices to circuits to systems Towards Smart Edge Devices: Challenges and Opportunities Prof. Saibal Mukhopadhyay School of ECE, Georgia Institute of Technology Email: saibal@ece.gatech.edu Intel Corporation IBM Qualcomm
Evolution of Smart Edge Platforms Intelligent Computing Security Energy Future growth of computing will defined by small and ubiquitous devices We need smart, energy-efficient, and secure edge platforms.
Our Vision: Intelligent, Autonomous and Secure Edge Platforms Smart Edge Devices
Research Overview Algorithm/Architecture Circuits/Devices Intelligent computing Accelerators for new computing models - Machine learning, Neuro-inspired, Dynamical systems, Bayesian Innovative sensors Digital/mixed-signal circuits Post-CMOS devices for new computing models Energy-efficiency Memory-aware algorithms Approximate algorithms Electro-thermal co-design Adaptive digital circuits Integrated voltage regulators Energy harvesting 3D ICs Security Energy-aware security Secure power management Low-power crypto Side-channel resistance