TY - GEN
T1 - Speeding up safety verification by fault abstraction and simulation to transaction level
AU - Tabacaru, Bogdan Andrei
AU - Chaari, Moomen
AU - Ecker, Wolfgang
AU - Kruse, Thomas
AU - Novello, Cristiano
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/11/22
Y1 - 2016/11/22
N2 - The need for safer and more robust hardware systems increased considerably in the automotive industry after the introduction of the safety standard ISO 26262. As a result, fault injection became a major verification milestone for safety-critical applications. However, safety-verification methods for gate level (GL) and RTL models suffer from long simulation time and large fault-injection campaigns due to the high complexity of large-scale SoCs. Virtual prototypes (VP) were employed to address the shortcomings of GL and RTL simulation, however fault injection into VPs usually leads to the observation of different failures than into GL and RTL models. In this paper, we present an approach which ensures 100% correlation of faults injected across VPs and GL models. Using a compiled-code approach, we transform GL net-lists into C++ code, which we then integrate into SystemC/TLM-based VPs. Thus, the new VPs have the same accuracy as the GL net-lists and are executed at near VP speed. Furthermore, since the new models share all fault-injection properties with the original GL net-lists, only realistic failures can be observed after fault injection.
AB - The need for safer and more robust hardware systems increased considerably in the automotive industry after the introduction of the safety standard ISO 26262. As a result, fault injection became a major verification milestone for safety-critical applications. However, safety-verification methods for gate level (GL) and RTL models suffer from long simulation time and large fault-injection campaigns due to the high complexity of large-scale SoCs. Virtual prototypes (VP) were employed to address the shortcomings of GL and RTL simulation, however fault injection into VPs usually leads to the observation of different failures than into GL and RTL models. In this paper, we present an approach which ensures 100% correlation of faults injected across VPs and GL models. Using a compiled-code approach, we transform GL net-lists into C++ code, which we then integrate into SystemC/TLM-based VPs. Thus, the new VPs have the same accuracy as the GL net-lists and are executed at near VP speed. Furthermore, since the new models share all fault-injection properties with the original GL net-lists, only realistic failures can be observed after fault injection.
KW - Automotive
KW - Fault Injection
KW - ISO 26262
KW - Safety Verification
KW - SystemC
KW - TLM
KW - Virtual Prototyping
UR - http://www.scopus.com/inward/record.url?scp=85006717254&partnerID=8YFLogxK
U2 - 10.1109/VLSI-SoC.2016.7753547
DO - 10.1109/VLSI-SoC.2016.7753547
M3 - Conference contribution
AN - SCOPUS:85006717254
T3 - 2016 IFIP/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2016
BT - 2016 IFIP/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 24th Annual IFIP/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2016
Y2 - 26 September 2016 through 28 September 2016
ER -