Matteo Sonza Reorda - Böcker

Software-Implemented Hardware Fault Tolerance addresses the innovative topic of software-implemented hardware fault tolerance (SIHFT), i.e., how to deal with faults affecting the hardware by only (or mainly) acting on the software.The first SIHFT techniques were proposed and adopted several decades ago, but they have been the object of new interest in the past few years, mainly due to the need for developing low-cost safety-critical computer-based applications in fields such as automotive, biomedics, and telecommunications. Therefore, several new approaches to detect, and when possible correct, transient and permanent faults in the hardware have been recently proposed. These approaches are innovative (with respect to those proposed in the past) since they are of higher applicability (often starting from the source-level code of an application) and generality, being capable of coping with many different fault types. The book presents the theory behind software-implemented hardware fault tolerance, as well as the practical aspects related to put it at work on real examples. By evaluating accurately the advantages and disadvantages of the already available approaches, the book provides a guide to developers willing to adopt software-implemented hardware fault tolerance in their applications. Moreover, the book identifies open issues for researchers willing to improve the already available techniques.

Software-Implemented Hardware Fault Tolerance addresses the innovative topic of software-implemented hardware fault tolerance (SIHFT), i.e., how to deal with faults affecting the hardware by only (or mainly) acting on the software.The first SIHFT techniques were proposed and adopted several decades ago, but they have been the object of new interest in the past few years, mainly due to the need for developing low-cost safety-critical computer-based applications in fields such as automotive, biomedics, and telecommunications. Therefore, several new approaches to detect, and when possible correct, transient and permanent faults in the hardware have been recently proposed. These approaches are innovative (with respect to those proposed in the past) since they are of higher applicability (often starting from the source-level code of an application) and generality, being capable of coping with many different fault types. The book presents the theory behind software-implemented hardware fault tolerance, as well as the practical aspects related to put it at work on real examples. By evaluating accurately the advantages and disadvantages of the already available approaches, the book provides a guide to developers willing to adopt software-implemented hardware fault tolerance in their applications. Moreover, the book identifies open issues for researchers willing to improve the already available techniques.

New manufacturing technologies have made possible the integration of entire systems on a single chip. This new design paradigm, termed system-on-chip (SOC), together with its associated manufacturing problems, represents a real challenge for designers. SOC is also reshaping approaches to test and validation activities. These are beginning to migrate from the traditional register-transfer or gate levels of abstraction to the system level. Until now, test and validation have not been supported by system-level design tools so designers have lacked the infrastructure to exploit all the benefits stemming from the adoption of the system level of abstraction. Research efforts are already addressing this issue. This monograph provides a state-of-the-art overview of the current validation and test techniques by covering all aspects of the subject including: modeling of bugs and defects; stimulus generation for validation and test purposes (including timing errors; design for testability.

New manufacturing technologies have made possible the integration of entire systems on a single chip. This new design paradigm, termed system-on-chip (SOC), together with its associated manufacturing problems, represents a real challenge for designers.SOC is also reshaping approaches to test and validation activities. These are beginning to migrate from the traditional register-transfer or gate levels of abstraction to the system level. Until now, test and validation have not been supported by system-level design tools so designers have lacked the infrastructure to exploit all the benefits stemming from the adoption of the system level of abstraction. Research efforts are already addressing this issue.This monograph provides a state-of-the-art overview of the current validation and test techniques by covering all aspects of the subject including:modeling of bugs and defects;stimulus generation for validation and test purposes (including timing errors;design for testability.

This book contains extended and revised versions of the best papers presented at the 25th IFIP WG 10.5/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2017, held in Abu Dhabi, United Arab Emirates, in August 2017.