Approximate logic synthesis for error tolerant applications

Error tolerance formally captures the notion that - for a wide variety of applications including audio, video, graphics, and wireless communications - a defective chip that produces erroneous values at its outputs may be acceptable, provided the errors are of certain types and their severities are within application-specified thresholds. All previous research on error tolerance has focused on identifying such defective but acceptable chips during post-fabrication testing to improve yield. In this paper, we explore a completely new approach to exploit error tolerance based on the following observation: If certain deviations from the nominal output values are acceptable, then we can exploit this flexibility during circuit design to reduce circuit area and delay as well as to increase yield. The specific metric of error tolerance we focus on is error rate, i.e., how often the circuit produces erroneous outputs. We propose a new logic synthesis approach for the new problem of identifying how to exploit a given error rate threshold to maximally reduce the area of the synthesized circuit. Experiment results show that for an error rate threshold within 1%, our approach provides 9.43% literal reductions on average for all the benchmarks that we target.