LAUSR

Polar codes, being the first class of codes with provable capacity-achieving property, have aroused extensive attention. The belief propagation (BP) algorithm, which is one of the popular decoding approaches for polar codes, possesses inherent high parallelism but also high computational complexity. With low complexity and high fault tolerance, stochastic computing has been well studied and applied to BP decoding for polar codes. However, existing stochastic BP decoders suffer from high decoding latency. In this paper, firstly, a novel dual-bit-wise iterative message update method is proposed for stochastic BP, reducing the decoding latency by more than half. Based on the dual-bit-wise decoding, more special nodes in the factor graph are investigated and then fully exploited to pursue lower decoding complexity than prior arts. Moreover, a well-optimized architecture is developed for the proposed stochastic decoder, where the random number generator (RNG), tracking forecast memory (TFM), and hard decision unit are intelligently designed for reduced hardware cost. Experimental results demonstrate that the presented decoder can exhibit 61.7% lower decoding latency than the state-of-the-art works. Besides, the throughput and hardware efficiency can be improved by nearly $2.8\times$ and $2.7\times$, respectively.