Partial Dynamic Reconfiguration in an FPGA-based Fault-Tolerant System: Simulation-based Evaluation

Field Programmable Gate Arrays (FPGAs) are popular not only for their wide range of usage in embedded systems, however, they are susceptible to radiation effects. Charged particles cause the so-called Single Event Upsets (SEUs) in their configuration memory. SEUs can induce failure of the whole system. This problem is fundamental for space applications where sun radiation is more considerable than in the Earth. Two main approaches to SEU mitigation technique exist: fault masking and repair. The most popular masking method is Triple Modular Redundancy (TMR). For the faults repair, FPGA's capability of reconfiguration is used. It is possible to combine these approaches to obtain improved fault tolerant system. It is important to assess reliability rate of this system and, therefore, its estimation by a simulation is the main part of this paper. We propose evaluation environment which assesses the reliability of a TMR system with malfunction module reconfiguration depending on faults occurrence frequency and reconfiguration time necessary for fault repair.

[1]  Luca Fossati,et al.  A Reliable Reconfiguration Controller for Fault-Tolerant Embedded Systems on Multi-FPGA Platforms , 2010, 2010 IEEE 25th International Symposium on Defect and Fault Tolerance in VLSI Systems.

[2]  Marco D. Santambrogio,et al.  TMR and Partial Dynamic Reconfiguration to mitigate SEU faults in FPGAs , 2007, 22nd IEEE International Symposium on Defect and Fault-Tolerance in VLSI Systems (DFT 2007).

[3]  Tanya Vladimirova,et al.  Mitigation of Radiation Effects in SRAM-Based FPGAs for Space Applications , 2014, ACM Comput. Surv..

[4]  Jan Schmidt,et al.  Error masking method based on the short-duration offline test , 2017, Microprocess. Microsystems.

[5]  David Bol,et al.  A Partial Reconfiguration-based scheme to mitigate Multiple-Bit Upsets for FPGAs in low-cost space applications , 2015, 2015 10th International Symposium on Reconfigurable Communication-centric Systems-on-Chip (ReCoSoC).

[6]  Mei Song Zheng,et al.  Reliability Oriented Selective Triple Modular Redundancy for SRAM-Based FPGAs , 2015 .

[7]  Pierre-Emmanuel Gaillardon,et al.  Reconfigurable Logic : Architecture, Tools, and Applications , 2015 .

[8]  M. Caffrey,et al.  Correcting single-event upsets through virtex partial configuration , 2000 .

[9]  Martin Straka,et al.  Generic partial dynamic reconfiguration controller for fault tolerant designs based on FPGA , 2010, NORCHIP 2010.

[10]  James J. Filliben,et al.  NIST/SEMATECH e-Handbook of Statistical Methods; Chapter 1: Exploratory Data Analysis , 2003 .

[11]  Jakub Podivinsky,et al.  Reliability Analysis and Improvement of FPGA-Based Robot Controller , 2017, 2017 Euromicro Conference on Digital System Design (DSD).

[12]  Youmin Zhang,et al.  Bibliographical review on reconfigurable fault-tolerant control systems , 2003, Annu. Rev. Control..