PROJECT TITLE :

Comparing Stochastic and Deterministic Computing

ABSTRACT:

Technology scaling has raised the specter of myriads of cheap, however unreliable and/or stochastic devices that must be creatively combined to form a reliable computing system. This has renewed the interest in computing that exploits stochasticity-embracing, not combating the device physics. If a stochastic representation is used to implement a programmable general-purpose design equivalent to CPUs, GPUs, or FPGAs, the preponderance of evidence indicates that most of the system energy will be expended in communication and storage vs computation. This paper presents an analytical treatment of the benefits and downsides of adopting a stochastic approach by examining the value of representing a price. We have a tendency to show each scaling laws and costs for low precision representations. We tend to also analyze the value of multiplication implemented using stochastic versus deterministic approaches, since multiplication is the prototypical inexpensive stochastic operation. We show that the deterministic approach compares favorably to the stochastic approach when holding precision and reliability constant.