The Transprecision Computing Paradigm: Concept, Design, and Applications

A. Cristiano I. Malossi1, Michael Schaffner2, Anca Molnos3, Luca Gammaitoni4,Giuseppe Tagliavini5, Andrew Emerson7, Andrés Tomás7, Dimitrios S. Nikolopoulos 8, Eric Flamand9 and Norbert Wehn10
1IBM Research ‐ Zurich, Switzerland
acm@zurich.ibm.com
2ETHZ, Switzerland
schaffner@iis.ee.ethz.ch
3CEA, France
anca.molnos@cea.fr
4Università di Perugia, Italy
luca.gammaitoni@nipslab.org
5Università di Bologna, Italy
giuseppe.tagliavini@unibo.it
6CINECA, Italy
a.emerson@cineca.it
7Universitat Jaume I, Spain
tomasan@uji.es
8Queen’s University of Belfast, UK
d.nikolopoulos@qub.ac.uk
9GreenWaves Technologies, France
eric.flamand@greenwaves-technologies.com
10University of Kaiserslautern, Germany
wehn@eit.uni-kl.de

ABSTRACT


Guaranteed numerical precision of each elementary step in a complex computation has been the mainstay of traditional computing systems for many years. This era, fueled by Moore’s law and the constant exponential improvement in computing efficiency, is at its twilight: from tiny nodes of the Internet‐of‐Things, to large HPC computing centers, subpicoJoule/ operation energy efficiency is essential for practical realizations. To overcome the power wall, a shift from traditional computing paradigms is now mandatory. In this paper we present the driving motivations, roadmap, and expected impact of the European project OPRECOMP. OPRECOMP aims to (i) develop the first complete transprecision computing framework, (ii) apply it to a wide range of hardware platforms, from the sub‐milliWatt up to the MegaWatt range, and (iii) demonstrate impact in a wide range of computational domains, spanning IoT, Big Data Analytics, Deep Learning, and HPC simulations. By combining together into a seamless design transprecision advances in devices, circuits, software tools, and algorithms, we expect to achieve major energy efficiency improvements, even when there is no freedom to relax end‐to‐end application quality of results. Indeed, OPRECOMP aims at demolishing the ultraconservative “precise” computing abstraction, replacing it with a more flexible and efficient one, namely transprecision computing.

Keywords: Approximate Computing, Inexact Computing, Energy‐Efficiency, Low Power Computing, Architecture Design.



Full Text (PDF)