Title: Advances in Fault Tolerance Support for FPGA Embedded Processors
Primary Author: French, Matthew
Organization: USC / ISI
Co-Author(s): John Paul Walters and Mark Bucciero

Abstract:
The Autonomous On-board Processing for Sensor Systems (A-OPSS) project fuses high performance reconfigurable processors with emerging fault-tolerance and autonomous processing techniques in order to realize high performance, autonomous sensor systems. By enabling fault-tolerant use of high performance on-board processing the utility of sensor systems will be greatly enhanced, achieving 10-100x decrease in processing time, which directly translates into more science experiments conducted per day and a more thorough, timely analysis of captured data. This research also addresses the ability to quickly react and adapt processing or mission objectives in real-time, by combining autonomous agents with reconfigurable computing techniques. Using A-OPSS, satellites, air borne or ground sensors will be able to perform high performance, fault tolerant computation, and develop situational awareness about their operating environment and tune or adapt the application algorithm such that they return the most useful and significant data to human and automated decision support systems. This paper focuses on the first year’s efforts which revolve around developing robustness to radiation induced upsets that occur in the embedded PowerPC within Xilinx FPGAs. This work presents an analysis of the sensitive cross section of both the architecture and a SAR application mapped to the PowerPC405. We then introduce a series of fault tolerance software routines used by the High Performance Computing (HPC) community and adapt them to an embedded system, such as the NASA GSFC developed SpaceCube 1.0. Our approach allows us to parallelize an application, so we will present both the processing performance gain as well as reliability metrics as compared to traditional fault tolerance methodologies such as Triple Modular Redundancy (TMR) and dual processor lock step approaches.