On the Use of System-on-Chip Technology in Next-Generation Instruments Avionics for Space Exploration
System-on-Chip (SoC) technology enables integrating all the functionality required to control and process science data delivered by space instruments in a single silicon chip (e.g., microprocessor + programmable logic). This chapter discusses the implicat
- PDF / 5,299,920 Bytes
- 22 Pages / 439.37 x 666.142 pts Page_size
- 94 Downloads / 327 Views
3
ARM Research, Cambridge, UK {xabier.iturbe,emre.ozer}@arm.com 2 NASA Jet Propulsion Laboratory, Pasadena, CA, USA [email protected] Massachusetts Institute of Technology, Cambridge, MA, USA [email protected]
Abstract. System-on-Chip (SoC) technology enables integrating all the functionality required to control and process science data delivered by space instruments in a single silicon chip (e.g., microprocessor + programmable logic). This chapter discusses the implications of using this technology in deep-space exploration avionics, namely in the next generation of NASA science instruments that will be used to explore our Solar system. We present here our experience at the NASA Jet Propulsion Laboratory (JPL) using Xilinx Zynq SoC devices to implement the data processing of a Fourier transform spectrometer, namely the Compositional InfraRed Imaging Spectrometer (CIRIS). Besides, we also discuss the different fault-tolerance techniques that have been implemented in the CIRIS controller SoC to deal with harsh radiation conditions prevailing in deep-space environments. Keywords: Fault-tolerance · Avionics ARM processor · Signal processing
1
·
System-on-chip integration
·
Introduction
Hybrid System-on-Chip (SoC) devices that embed the most energy efficient processor (ARM cores [1]) and the latest and most powerful FPGA architecture (Xilinx 7-series [2]) into a single chip (Xilinx Zynq [3]) promise new opportunities due to the performance, power consumption, weight and volume benefits they bring. This is especially relevant for building more capable space avionics. Xabier Iturbe was also affiliated with the NASA Jet Propulsion Laboratory, California Institute of Technology, when conducting this research. Patrick Yiu was affiliated with the California Institute of Technology when conducting this research. c IFIP International Federation for Information Processing 2016 Published by Springer International Publishing AG 2016. All Rights Reserved Y. Shin et al. (Eds.): VLSI-SoC 2015, IFIP AICT 483, pp. 1–22, 2016. DOI: 10.1007/978-3-319-46097-0 1
2
X. Iturbe et al.
Currently most of these systems combine programmable logic and processors as separate components distributed along one or several PCB board(s), which results in power consumption overheads and larger volume to be put into space [4,5]. Besides, currently existing space-grade processors (e.g., RAD750 [6]) are not suitable to be used in the next-generation spacecraft computing platforms because they do not provide sufficient performance and energy efficiency [7]. As a result, NASA and other space agencies have approached ARM and SoC technology, hoping to pave the way for future space exploration missions that are becoming ever more performance demanding. Despite the fact that currently there are no space-qualified SoC parts, NASA is testing commercial Xilinx Zynq SoC devices in the International Space Station (ISS) as well as in precursor CubeSats operating in Low Earth Orbit (LEO), where the exposure to radiation is limited. In view of a potential radiatio
Data Loading...
