Partial TMR in FPGAs Using Approximate Logic Circuits

Sanchez-Clemente, Antonio; Entrena, Luis; García-Valderas, M.

doi:10.1109/radecs.2015.7365645

Cited by 8 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Assume that the check bits are C 4 C 3 C 2 C 1 C 0 and C 0 will be decided by (43). If the equation is set up, C 0 returns 1.…”

Section: Error Correction Codes (Eccs)mentioning

confidence: 99%

“…Theoretically, partial redundancy design achieves a balance between circuit size and stability. Sánchez-Clemente et al [43] simplified practical circuits into approximate functional circuits and applied partial redundancy techniques in the simplified circuits to achieve a trade-off between system stability and area/power overhead. Although several researchers have proposed methods for partial TMR, there is no universal approach among the existing methods, nor have they presented evaluation metrics for the effectiveness of circuit hardening.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Advancements in Spaceborne Synthetic Aperture Radar Imaging with System-on-Chip Architecture and System Fault-Tolerant Technology

Xie,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

With the continuous development of satellite payload and system-on-chip (SoC) technology, spaceborne real-time synthetic aperture radar (SAR) imaging systems play a crucial role in various defense and civilian domains, including Earth remote sensing, military reconnaissance, disaster mitigation, and resource exploration. However, designing high-performance and high-reliability SAR imaging systems that operate in harsh environmental conditions while adhering to strict size, weight, and power consumption constraints remains a significant challenge. In this paper, we introduce a spaceborne SAR imaging chip based on a SoC architecture with system fault-tolerant technology. The fault-tolerant SAR SoC architecture has a CPU, interface subsystem, memory subsystem, data transit subsystem, and data processing subsystem. The data processing subsystem, which includes fast Fourier transform (FFT) modules, coordinated rotation digital computer (CORDIC) modules (for phase factor calculation), and complex multiplication modules, is the most critical component and can achieve various modes of SAR imaging. Through analyzing the computational requirements of various modes of SAR, we found that FFT accounted for over 50% of the total computational workload in SAR imaging processing, while the CORDIC modules for phase factor generation accounted for around 30%. Therefore, ensuring the fault tolerance of these two modules is crucial. To address this issue, we propose a word-length optimization redundancy (WLOR) method to make the fixed-point pipelined FFT processors in FFT modules fault tolerant. Additionally, we propose a fault-tolerant pipeline CORDIC architecture utilizing error correction code (ECC) and sum of squares (SOS) check. For other parts of the SoC architecture, we propose a generic partial triple modular redundancy (TMR) hardening method based on the HITS algorithm to improve fault tolerance. Finally, we developed a fully automated FPGA-based fault injection platform to test the design’s effectiveness by injecting errors at arbitrary locations. The simulation results demonstrate that the proposed methods significantly improved the chip’s fault tolerance, making the SAR imaging chip safer and more reliable. We also implemented a prototype measurement system with a chip-included board and demonstrated the proposed design’s performance on the Chinese Gaofen-3 strip-map continuous imaging system. The chip requires 9.2 s, 50.6 s, and 7.4 s for a strip-map with 16,384 × 16,384 granularity, multi-channel strip-map with 65,536 × 8192 granularity, and multi-channel scan mode with 32,768 × 4096 granularity, respectively, and the system hardware consumes 6.9 W of power to process the SAR raw data.

show abstract

“…Assume that the check bits are C 4 C 3 C 2 C 1 C 0 and C 0 will be decided by (43). If the equation is set up, C 0 returns 1.…”

Section: Error Correction Codes (Eccs)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%