Research Repository

A self-scrubbing scheme for embedded systems in radiation environments

Lu, Yufan and Zhai, Xiaojun and Saha, Sangeet and Ehsan, Shoaib and McDonald-Maier, Klaus (2020) A self-scrubbing scheme for embedded systems in radiation environments. In: 26th IEEE International Symposium on On-Line Testing and Robust System Design 2020, 2020-07-13 - 2020-07-15, Naples, Italy / Virtual. (In Press)

ECCRAM__Copy__conference (3).pdf - Accepted Version

Download (357kB) | Preview


SRAMs are very sensitive to radiation effects. When embedded systems working in the extreme radiation environments, bit flips may occur frequently and decrease the reliability of the systems significantly. In this paper, a self-scrubbing scheme is proposed for embedded systems in extreme radiation environments. In the proposed scheme, both scrubbing and error correcting codes are used to mitigate a large number of the errors in the RAMs. Along with this, a separate scrubber is designed to scrub the RAM independently, when the CPUs are busy. In addition, the scrubber is a portable module and the hardware cost does not grow with the size of the available RAM. The results of the experiments show that, in the neutron radiation environments where the error rate in the unhardened RAMs is approximately 1.2bit/(KB.h), while the error rate of the self-scrubbing RAMs is less than 8.7x10‾⁵bit=(KB.h), which is one fifth of the error rate of the conventional ECC RAMs.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: _not provided_
Uncontrolled Keywords: Neutron Radiation; SRAM; SEU Mitigation; ECC
Divisions: Faculty of Science and Health
Faculty of Science and Health > Computer Science and Electronic Engineering, School of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 17 Jun 2020 16:34
Last Modified: 18 Aug 2022 12:17

Actions (login required)

View Item View Item