Survey of Stochastic Computing

Abstract

Stochastic computing (SC) was proposed in the 1960s as a low-cost alternative to conventional binary computing. It is unique in that it represents and processes information in the form of digitized probabilities. SC employs very low-complexity arithmetic units which was a primary design concern in the past. Despite this advantage and also its inherent error tolerance, SC was seen as impractical because of very long computation times and relatively low accuracy. However, current technology trends tend to increase uncertainty in circuit behavior and imply a need to better understand, and perhaps exploit, probability in computation. This article surveys SC from a modern perspective where the small size, error resilience, and probabilistic features of SC may compete successfully with conventional methodologies in certain applications. First, we survey the literature and review the key concepts of stochastic number representation and circuit structure. We then describe the design of SC-based circuits and evaluate their advantages and disadvantages. Finally, we give examples of the potential applications of SC and discuss some practical problems that are yet to be solved.

Low-Energy Truly Random Number Generation with Superparamagnetic Tunnel Junctions for Unconventional Computing

“…Many of these emerging ideas, such as stochastic computing [2][3][4][5][6] and some brain-inspired (or neuromorphic) schemes [7][8][9] , require a large quantity of random numbers. However, the circuit area and the energy required to generate these random numbers are major limitations of such computing schemes.…”

A novel method for the approximation of multiplierless constant matrix vector multiplication

“…The reader is referred to [18][19][20], for detailed surveys on approximate, stochastic, and probabilistic computing. The approaches for the design of approximate DSP systems can generally be grouped in three categories: (i) transistor level, (ii) gate level, and (iii) algorithmic level.…”

“…This relaxation allows trading the accuracy of numerical outputs for reductions in area, delay, or power dissipation of the design [12]. Research activities on approximate computing range from a transistor level to an algorithmic level [13][14][15][16][17][18][19][20][21][22].…”

Low Cost and Fault Tolerant Parallel Computing Using Stochastic Two-Dimensional Finite State Machine

“…There has been some effort by using techniques for generating multiple uncorrelated pseudorandom sources [6], [17]. However, they still dominate the area cost of the architecture.…”

“…An effective solution for reducing area and noise-sensitivity is to move from deterministic values toward probabilistic values. Some stochastic data processing designs have been already introduced [6]- [8]. For example, Brown and Card [9], [10] showed that for complex operations, such as the exponentiation and sine functions, stochastic computing consumes less energy than binary radix computing, and the latency problem can be resolved using parallel processing method or a higher operating frequency owning to its simple circuit structure.…”