Soft Error Reliability Of Vlsi Circuits

Soft Error Reliability of VLSI Circuits

This book is intended for readers who are interested in the design of robust and reliable electronic digital systems. The authors cover emerging trends in design of today’s reliable electronic systems which are applicable to safety-critical applications, such as automotive or healthcare electronic systems. The emphasis is on modeling approaches and algorithms for analysis and mitigation of soft errors in nano-scale CMOS digital circuits, using techniques that are the cornerstone of Computer Aided Design (CAD) of reliable VLSI circuits. The authors introduce software tools for analysis and mitigation of soft errors in electronic systems, which can be integrated easily with design flows. In addition to discussing soft error aware analysis techniques for combinational logic, the authors also describe new soft error mitigation strategies targeting commercial digital circuits. Coverage includes novel Soft Error Rate (SER) analysis techniques such as process variation aware SER estimation and GPU accelerated SER analysis techniques, in addition to SER reduction methods such as gate sizing and logic restructuring based SER techniques.

Early Soft Error Reliability Assessment of Convolutional Neural Networks Executing on Resource-Constrained IoT Edge Devices

This book describes an extensive and consistent soft error assessment of convolutional neural network (CNN) models from different domains through more than 14.8 million fault injections, considering different precision bit-width configurations, optimization parameters, and processor models. The authors also evaluate the relative performance, memory utilization, and soft error reliability trade-offs analysis of different CNN models considering a compiler-based technique w.r.t. traditional redundancy approaches.

Advanced Simulation and Test Methodologies for VLSI Design