A Flexible Fault Injection Platform for the Analysis of the Symptoms of Soft Errors in FPGA Soft Processors

Due to the high vulnerability of SRAM-based FPGAs in single-event upsets (SEUs), effective fault tolerant soft processor architectures must be considered when we use FPGAs to build embedded systems for critical applications. In the past, the detection of symptoms of soft errors in the behavior of microprocessors has been used for the implementation of low-budget error detection techniques, instead of costly hardware redundancy techniques. To enable the development of such low-cost error detection techniques for FPGA soft processors, we propose an in-depth analysis of the symptoms of SEUs in the FPGA configuration memory. To this end, we present a flexible fault injection platform based on an open-source CAD framework (RapidSmith) for the soft error sensitivity analysis of soft processors in Xilinx SRAM-based FPGAs. Our platform supports the estimation of soft error sensitivity per configuration bit/frame, processor component and benchmark. The fault injection is performed on-chip by a dedicated microcontroller which also monitors processor behavior to identify specific symptoms as consequences of soft errors. The performed analysis showed that these symptoms can be used to build an efficient, low-cost error detection scheme. The proposed platform is demonstrated through an extensive fault injection campaign in the Leon3 soft processor.

[1]  L. Sterpone,et al.  A New Partial Reconfiguration-Based Fault-Injection System to Evaluate SEU Effects in SRAM-Based FPGAs , 2007, IEEE Transactions on Nuclear Science.

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

[3]  Mihalis Psarakis,et al.  A soft error vulnerability analysis framework for Xilinx FPGAs , 2014, FPGA.

[4]  Seyed Ghassem Miremadi,et al.  A fast, flexible, and easy-to-develop FPGA-based fault injection technique , 2014, Microelectron. Reliab..

[5]  Michael J. Wirthlin,et al.  Estimating Soft Processor Soft Error Sensitivity through Fault Injection , 2015, 2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines.

[6]  Sarita V. Adve,et al.  Understanding the propagation of hard errors to software and implications for resilient system design , 2008, ASPLOS.

[7]  C. Carmichael,et al.  A fault injection analysis of Virtex FPGA TMR design methodology , 2001, RADECS 2001. 2001 6th European Conference on Radiation and Its Effects on Components and Systems (Cat. No.01TH8605).

[8]  Paul Graham,et al.  Accelerator validation of an FPGA SEU simulator , 2003 .

[9]  C. Lopez-Ongil,et al.  A Unified Environment for Fault Injection at Any Design Level Based on Emulation , 2007, IEEE Transactions on Nuclear Science.

[10]  M.B. Tahoori,et al.  Soft Error Susceptibility Analysis of SRAM-Based FPGAs in High-Performance Information Systems , 2007, IEEE Transactions on Nuclear Science.

[11]  R. Velazco,et al.  Combining Results of Accelerated Radiation Tests and Fault Injections to Predict the Error Rate of an Application Implemented in SRAM-Based FPGAs , 2010, IEEE Transactions on Nuclear Science.

[12]  Sergio D'Angelo,et al.  Evaluation of Single Event Upset Mitigation Schemes for SRAM based FPGAs using the FLIPPER Fault Injection Platform , 2007, 22nd IEEE International Symposium on Defect and Fault-Tolerance in VLSI Systems (DFT 2007).

[13]  Brent E. Nelson,et al.  RapidSmith: Do-It-Yourself CAD Tools for Xilinx FPGAs , 2011, 2011 21st International Conference on Field Programmable Logic and Applications.

[14]  Sanjay J. Patel,et al.  ReStore: Symptom-Based Soft Error Detection in Microprocessors , 2006, IEEE Trans. Dependable Secur. Comput..

[15]  Michael J. Wirthlin,et al.  The reliability of FPGA circuit designs in the presence of radiation induced configuration upsets , 2003, 11th Annual IEEE Symposium on Field-Programmable Custom Computing Machines, 2003. FCCM 2003..

[16]  A. Lesea,et al.  The rosetta experiment: atmospheric soft error rate testing in differing technology FPGAs , 2005, IEEE Transactions on Device and Materials Reliability.

[17]  Paolo Prinetto,et al.  A fault injection methodology and infrastructure for fast single event upsets emulation on Xilinx SRAM-based FPGAs , 2014, 2014 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT).

[18]  David Lee,et al.  SEU Mitigation and Validation of the LEON3 Soft Processor Using Triple Modular Redundancy for Space Processing , 2016, FPGA.

[19]  J.N. Tombs,et al.  Selective Protection Analysis Using a SEU Emulator: Testing Protocol and Case Study Over the Leon2 Processor , 2007, IEEE Transactions on Nuclear Science.

[20]  Brendan Tran Morris,et al.  Fast FPGA-based fault injection tool for embedded processors , 2013, International Symposium on Quality Electronic Design (ISQED).

[21]  Gabriel L. Nazar,et al.  Fast single-FPGA fault injection platform , 2012, 2012 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT).

[22]  M. Hatzimihail,et al.  A methodology for detecting performance faults in microprocessors via performance monitoring hardware , 2007, 2007 IEEE International Test Conference.