Stochastic Computing

Paper is accepted in ASP-DAC 2021

This paper introduces a metric to identify better SC units and predict the timing for early termination.

In-Stream Stochastic Division and Square Root via Correlation

Present division and square root design in stochastic computing, which achieve high accuracy and efficiency by leveraging stochastic correlation among bit streams.

In-Stream Stochastic Division and Square Root via Correlation

Stochastic Computing (SC) is designed to minimize hardware area and power consumption compared to traditional binary-encoded computation, stemming from the bit-serial data representation and extremely straightforward logic. Though existing Stochastic …

Nonlinear Stochastic Functions for Capsule Neural Network

Present design of nonlinear functions for stochastic computing, which can be used in Capsule Neural Network.

Convergence-Optimized Variable Node Structure for Stochastic LDPC Decoder

By using stochastic computation, a fully-parallel low-density parity-check (LDPC) decoder can be implemented using a lower wire complexity. In order to enhance the decoder performance, probability tracers, such as up/down counters, are added at each …

Strategies for Reducing Decoding Cycles in Stochastic LDPC Decoders

This brief presents three strategies, including initialization based on Look Up Table (LUT), postprocessing based on bit flipping and hard decision based on the posterior information, to reduce the number of decoding cycles (DCs) for stochastic …

An Area-Efficient Architecture for Stochastic LDPC Decoder

Stochastic computation is an excellent approach for low-density parity-check codes decoding. By adding edge memories at each edge in the Tanner graph, fully parallel hardware implementation can be designed with much lower wire complexity. This …

Latency-Optimized Stochastic LDPC Decoder for High-Throughput Applications

Stochastic decoding can be applied to Low-Density Parity-Check codes in order to achieve high throughput with less area. However, most architectures suffer from large decoding latencies, due to the mechanism of stochastic computation. In this paper, …