Reconfiguration 4 Reliability design methodology for reliability assessment and enhancement of FPGA-based systems

1
Reconfiguration 4 Reliabilitydesign methodology
for reliability assessment and enhancement of
FPGA-based systems
Dynamic Reconfigurability in Embedded Systems
Design
Reconfiguration 4 Reliability Team r4r_at_dresd.org
2
Outline

• Motivations
• Activities
• Goals
• Sub-projects
• Methodology for reliable reconfigurable systems
  design
• Design of Totally Self-Checking components
• Design of a Fault Injection environment
• General information

3
Motivations

• SRAM-based FPGAs are particularly sensible to
  radiation effects not only in critical
  environment, but also at terrestrial level
• alpha particles hitting devices cause temporary
  and permanent faults
• temporary faults can be modeled as
• Modification in the data being processeduser-memo
  ry corruption
• Modification of the functionality being
  performedconfiguration-memory corruption
• Embedded systems implemented on FPGAs need
  robustness to radiations, achieved by means of
  by-design fault tolerance

4
Activies

• Designing reliable systems implemented on FPGAs,
  able to cope with the effects of faults caused by
  radiations
• Appling already known and well studied detection
  and recovery techniques to the particular FPGA
  scenario
• Exploiting dynamic partial reconfiguration to
  trigger the reconfiguration of the affected
  portion of the architecture
• while the rest of the system is still working
• without needing to entirely reprogram the
  system
• Enabling the assessment of reliable system
  properties by means of fault injection and
  simulation

5
Goals

• Creation of a methodology for the design of
  reliable reconfigurable embedded systems
• Implementation of a library of Totally
  Self-Checking components
• Implementation of a fault injection environment
  for FPGA systems

6
Design Space Exploration

• Definition of a framework for the design space
  exploration aiming at
• Estimating the costs and benefits deriving from
  the possible different solutions
• Exploring the solution space on the based of
  several metrics
• E.g. size of the subsystems, size of the data
  widths
• Identifying most promising solutions
• Implementing the selected solution

7
Totally Self-Checking Components Design

• Design of a library of standard Totally
  Self-Checking components to be provided to the
  methodology for FPGA based reliable system design
• Examples
• Checkers
• Voters
• Controllers
• ...

8
Fault Injection Environment

• Implementing a fault injection platform for
  analyzing
• fault effects (the adopted fault model is the
  Single Event Upset -- SEU) and
• the effectiveness of the applied fault
  detection/tolerance techniques
• Important issues
• Observability and controllability of fault
  injection
• Non intrusiveness
• Efficiency in simulation (e.g., check-points)

9
General Information

• Webpage
• www.dresd.org/?qr4r
• Mailing List
• r4r-ml_at_dresd.org
• Contact
• For more information on Reliability 4
  Reconfiguration
• r4r_at_dresd.org
• For a complete list of information on how to
  contact us
• www.dresd.org/?qcontact_r4r
• Related work wiki
• www.dresd.org/?qsoa_r4r