doi: 10.3850/978-3-9815370-4-8_1116


Opportunities for Energy Efficient Computing: A Study of Inexact General Purpose Processors for High-Performance and Big-Data Applications


Peter Düben1,a, Jeremy Schlachter2,c, Parishkrati3,e, Sreelatha Yenugula3,f, John Augustine3,g, Christian Enz2,d, K. Palem4 and T. N. Palmer1,b

1AOPP, University of Oxford Oxford, United Kingdom.

adueben@atm.ox.ac.uk
bt.n.palmer@atm.ox.ac.uk

2EPFL Lausanne, Switzerland.

cjeremy.schlachter@epfl.ch
dchristian.enz@epfl.ch

3Indian Institute of Technology Madras India.

eparishkratihhh@gmail.com
fsreelathayenugula@gmail.com
gaugustine@cse.iitm.ac.in

4Electrical Engineering and Computer Science Rice University, Houston, USA.

kvp1@rice.edu

ABSTRACT

In this paper, we demonstrate that disproportionate gains are possible through a simple devise for injecting inexactness or approximation into the hardware architecture of a computing system with a general purpose template including a complete memory hierarchy. The focus of the study is on energy savings possible through this approach in the context of large and challenging applications. We choose two such from different ends of the computing spectrum–the IGCM model for weather and climate modeling which embodies significant features of a high-performance computing workload, and the ubiquitous PageRank algorithm used in Internet search. In both cases, we are able to show in the affirmative that an inexact system outperforms its exact counterpart in terms of its efficiency quantified through the relative metric of operations per virtual Joule (OPVJ)–a relative metric that is not tied to particular hardware technology. As one example, the IGCM application can be used to achieve savings through inexactness of (almost) a factor of 3 in energy without compromising the quality of the forecast, quantified through the forecast error metric, in a noticeable manner. As another example finding, we show that in the case of PageRank, an inexact system is able to outperform its exact counterpart by close to a factor of 1.5 using the OPVJ metric.



Full Text (PDF)