Doing Moore with Less -- Leapfrogging Moore's Law with Inexactness for Supercomputing

TL;DR

This paper explores how inexact computing and lower-precision arithmetic in commercial hardware can overcome energy limitations in supercomputing, using an inexact Newton algorithm and reinvestment techniques to improve results.

Contribution

It introduces the concept of reinvestment, using energy savings from inexactness to enhance solution quality in supercomputing.

Findings

Lower-precision arithmetic reduces energy consumption.

Reinvestment techniques improve solution accuracy.

Inexact Newton algorithm demonstrates energy-quality trade-offs.

Abstract

Energy and power consumption are major limitations to continued scaling of computing systems. Inexactness, where the quality of the solution can be traded for energy savings, has been proposed as an approach to overcoming those limitations. In the past, however, inexactness necessitated the need for highly customized or specialized hardware. The current evolution of commercial off-the-shelf(COTS) processors facilitates the use of lower-precision arithmetic in ways that reduce energy consumption. We study these new opportunities in this paper, using the example of an inexact Newton algorithm for solving nonlinear equations. Moreover, we have begun developing a set of techniques we call reinvestment that, paradoxically, use reduced precision to improve the quality of the computed result: They do so by reinvesting the energy saved by reduced precision.