Abstract
In recent years, SRAM-based FPGA has been applied in space due to its high density and configurability. However, due to its high sensitivity to SEU, it is difficult to be applied in space. With the decrease of the feature size, SRAM-based FPGA becomes more sensitive to SEU. Therefore, how to evaluate the sensitivity to SEU of a design in FPGA is very important for the application in space. This paper presents a fast fault injection platform for SRAM-based FPGA, which can emulate accumulated multiple SEUs in SRAM-based FPGA to evaluate the sensitivity of the design in FPGA. This paper uses the internal injection through ICAP which is faster than the external injection. In order to speed up the fault injection flow, this paper improves the fault injection from three key points. The proposed fault injection platform can repair the accumulated SEUs automatically by itself after completing an injection flow which can ensure that the next fault injection is valid. The locations for injection are effective at every clock in order to speed up by designing an optimized address generator. A fault injection flow based on pipeline is proposed to speed up the fault injection. We show the sensitivity of ISCAS85 benchmark circuits configured in FPGA and validate the fault injection platform by comparing the error rate and resource utilization. We show the speed in one fault inject flow for the flow based on both pipeline and non-pipeline flow. The results indicate the proposed fault injection flow based on pipeline has a faster speed.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.