A Scalable, Deterministic Approach to Stochastic Computing

Abstract

Stochastic computing is a paradigm in which logical operations are performed on randomly generated bit streams. Complex arithmetic operations can be performed by simple logic circuits, with a much smaller area footprint than conventional binary counterparts. However, the random or pseudorandom sources required to generate the bit streams are costly in terms of area and offset the gains. Also, due to randomness, the computation is not precise, which limits the applicability of the paradigm. Most importantly, to achieve reasonable accuracy, high latency is necessitated. Recently, deterministic approaches to stochastic computing have been proposed. They demonstrated that randomness is not a requirement. By structuring the computation deterministically, the result is exact and the latency is greatly reduced. However, despite being an improvement over conventional stochastic techniques, the latency increases quadratically with each level of logic. Beyond a few levels of logic, it becomes unmanageable. In this paper, we present a method for approximating the results of their deterministic method, with latency that only increases linearly with each level. The improvement comes at the cost of additional logic, but we demonstrate that the increase in area scales with √n, where n is the equivalent number of binary bits of precision. The new approach is general, efficient, composable, and applicable to all arithmetic operations performed with stochastic logic.