Application-aware soft error sensitivity evaluation without fault injections — application to Leon3

Design-time evaluations of the sensitivity of circuits with respect to soft errors are usually done by means of fault injection campaigns. Such campaigns are time-consuming, either in order to prepare the hardware set-up (e.g., prototype on emulation platform) or in terms of simulation run. We propose here an approach avoiding any fault injections but able to evaluate the intrinsic sensitivity of the circuit for a given application by leveraging the work done for functional verification. This approach provides worst-case evaluations with good accuracy and no specific investment. The approach is demonstrated on several applications executed on a Leon3 microprocessor.

[1]  Johan Karlsson,et al.  Fault injection into VHDL models: the MEFISTO tool , 1994 .

[2]  R. Leveugle,et al.  Efficiency of probabilistic testability analysis for soft error effect analysis: A case study , 2009, 2009 4th International Conference on Design & Technology of Integrated Systems in Nanoscal Era.

[3]  Régis Leveugle,et al.  Statistical fault injection: Quantified error and confidence , 2009, 2009 Design, Automation & Test in Europe Conference & Exhibition.

[4]  Alfredo Benso,et al.  Statistical Reliability Estimation of Microprocessor-Based Systems , 2012, IEEE Transactions on Computers.

[5]  Régis Leveugle,et al.  Evaluating application-aware soft error effects in digital circuits without fault injections or probabilistic computations , 2016, 2016 IEEE 22nd International Symposium on On-Line Testing and Robust System Design (IOLTS).

[6]  Xiaodong Li,et al.  SoftArch: an architecture-level tool for modeling and analyzing soft errors , 2005, 2005 International Conference on Dependable Systems and Networks (DSN'05).

[7]  Aviral Shrivastava,et al.  Static Analysis of Register File Vulnerability , 2011, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[8]  Raoul Velazco,et al.  Sensitivity to SEUs evaluation using probabilistic testability analysis at RTL , 2007 .

[9]  Joel Emer,et al.  A systematic methodology to compute the architectural vulnerability factors for a high-performance microprocessor , 2003, Proceedings. 36th Annual IEEE/ACM International Symposium on Microarchitecture, 2003. MICRO-36..

[10]  Régis Leveugle,et al.  Fast accurate evaluation of register lifetime and criticality in a pipelined microprocessor , 2014, 2014 22nd International Conference on Very Large Scale Integration (VLSI-SoC).