Project

Drastic energy reduction for IoT devices Energy issues are central to the ICT industry, and especially to the evolution of the Internet of Things (IoT). Current low-power design techniques cannot support the estimated growth in number IoT objects and in the same time keep the ICT energy consumption within sustainable bounds.

Exploitation of approximate computing in ARTEFaCT project. This project aims to build  inexact and exact near-threshold and sub-threshold circuit  to achieve major energy consumption reductions by enabling adaptive accuracy control of applications. To drastically reduce energy consumption, we envision a node that is able to largely scale its workload, to adapt to the energy constraints from the environment, and fulfill application demands. The novel key components of this node are: (1) the compute unit designed for adaptation, supporting variable degree of inexactness, on the hardware side, and (2) the accuracy-aware implementation of the application, and (3) the run-time accuracy adaptation, on the software side.

overview-executionOverview of ARTEFaCT adaptive computation

This project proposes to address, in a consistent fashion, the entire design stack, from physical hardware design, up to software application analysis, compiler optimizations, and dynamic energy management. We do believe that combining sub-near-threshold with inexact circuits on the hardware side and, in addition, extending this with intelligent and adaptive power management on the software side will produce outstanding results in terms of energy reduction, i.e., at least one order of magnitude, in IoT.

overview-designOverview of ARTEFaCT design approach

Project contributions The project will contribute along three research directions:

  • approximate, ultra low-power circuit design,

  • modeling and analysis of variable levels of computation precision in applications

  • accuracy-energy trade-offs in software.