Soft Error Resilient System Design through Error Correction

摘要

This paper presents an overview of the Built-in Soft Error Resilience (BISER) technique for correcting soft errors in latches, flip-flops and combinational logic. The BISER technique enables more than an order of magnitude reduction in chip-level soft error rate with minimal area impact, 7-11% chip-level power impact, and 1-5% performance impact (depending on whether combinational logic error correction is implemented or not). In comparison, several classical error-detection techniques introduce 40-100% power, performance and area overheads, and require significant efforts in designing and validating corresponding recovery mechanisms. Design trade-offs associated with the BISER technique and other existing soft error protection techniques are also analyzed.