Tyche: A Compact and Configurable Accelerator for Scalable Probabilistic Computing on FPGA

Probabilistic computing is an emerging computing paradigm which involves the systematic control and manipulation of unstable stochastic units called p-bits. Multiple p-bits are connected together to implement p-circuits which have been shown to be capable of solving interesting computationally hard problems. In this work, we present Tyche, a compact and configurable hardware accelerator for scalable probabilistic computing on FPGA. Our architecture allows p-circuits requiring different number of p-bits to be implemented using the same hardware. The use of a single p-bit computing core instead of an array of processing elements provides significant logic resource savings. A logarithmic adder tree is used for single-cycle weight logic computation while ensuring reasonable performance even for large number of p-bits. Various application-specific p-circuits are experimentally demonstrated using our proposed hardware accelerator implemented on Xilinx UltraScale+ FPGA, thus emphasizing the viability of practical scalable probabilistic computing on modern FPGAs.

I. Introduction

The rise of quantum computing technologies has not only opened up a plethora of new opportunities in cryptography, machine learning, bio-informatics, mathematical optimization and other applications [1]–[3] but also led to the emer-gence of several new non-conventional computing paradigms such as stochastic computing [4], probabilistic computing [5] and probabilistic annealing [6]. Probabilistic computing involves the systematic control and manipulation of unstable stochastic units, also known as probabilistic bits or p-bits, interconnected together, also known as probabilistic circuits or p-circuits. The behaviour of p-bits and p-circuits resembles networks of binary stochastic neurons similar to Boltzmann machines and Ising machines [5], [7]. Probabilistic computing has been shown to be capable of solving interesting compu-tationally hard problems such as combinatorial optimization, quantum emulation, Bayesian inference, integer factorization and invertible logic [5], [8], [7], [9], [10].