Read more
This book contains extended and revised versions of the best papers presented at the 29th IFIP WG 10.5/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2021, held in Singapore, in October 2021*.
The 12 full papers included in this volume were carefully reviewed and selected from the 44 papers (out of 75 submissions) presented at the conference. The papers discuss the latest academic and industrial results and developments as well as future trends in the field of System-on-Chip (SoC) design, considering the challenges of nano-scale, state-of-the-art and emerging manufacturing technologies. In particular they address cutting-edge research fields like low-power design of RF, analog and mixed-signal circuits, EDA tools for the synthesis and verification of heterogenous SoCs, accelerators for cryptography and deep learning and on-chip Interconnection system, reliability and testing, and integration of 3D-ICs.
*The conference was held virtually.
List of contents
On the Efficiency of AdapTTA: an Adaptive Test-Time Augmentation Strategy for Reliable Embedded ConvNets.- Low-overhead Early-stopping Policies for Efficient Random Forests Inference on Microcontrollers.- Transformative Hardware Design following the Model-Driven Architecture Vision.- Exploiting program slicing and instruction clusterization to identify the cause of faulty temporal behaviours at system level.- A DfT Strategy for Detecting Emerging Faults in RRAMs.- FMEA on Critical Systems: a Cross-layer Approach based on High-Level Models.- Design and Mitigation techniques of Radiation induced SEEs on Open-Source Embedded Static RAMs.- Design of A Reconfigurable Optical Computing Architecture Using Phase Change Material.- END-TRUE: Emerging Nanotechnology-based Double-Throughput True Random Number Generator.- A First Approach in Using Super-Steep-Subthreshold-Slope Field-Effect Transistors in Ultra-Low Power Analog Design.- A Regulated Sensing Solution based on a Self-ReferencePrinciple for PCM+OTS Memory Array.- An Improved Deterministic Stochastic MAC (SC-MAC) for High Power Efficiency Design.
