Analysis and characterization of inherent application resilience for approximate computing

TLDR

Approximate computing enables highly efficient hardware and software by exploiting application resilience, yet prior work has mainly shown energy and performance gains on a limited set of ad‑hoc techniques. The study aims to deepen understanding of application resilience across a broad set of applications and to provide tools and a framework for quantitatively assessing and characterizing that resilience. The authors analyze 12 widely used applications from recognition, data mining, and search, and introduce the Application Resilience Characterization (ARC) framework that partitions programs into resilient and sensitive components and models the resilient parts with abstractions of various approximation techniques. The analysis yields new insights into how resilience relates to application characteristics, suggesting directions for future research and demonstrating that ARC can help designers adopt approximate computing.

Abstract

Approximate computing is an emerging design paradigm that enables highly efficient hardware and software implementations by exploiting the inherent resilience of applications to in-exactness in their computations. Previous work in this area has demonstrated the potential for significant energy and performance improvements, but largely consists of ad hoc techniques that have been applied to a small number of applications. Taking approximate computing closer to mainstream adoption requires (i) a deeper understanding of inherent application resilience across a broader range of applications (ii) tools that can quantitatively establish the inherent resilience of an application, and (iii) methods to quickly assess the potential of various approximate computing techniques for a given application. We make two key contributions in this direction. Our primary contribution is the analysis and characterization of inherent application resilience present in a suite of 12 widely used applications from the domains of recognition, data mining, and search. Based on this analysis, we present several new insights into the nature of resilience and its relationship to various key application characteristics. To facilitate our analysis, we propose a systematic framework for Application Resilience Characterization (ARC) that (a) partitions an application into resilient and sensitive parts and (b) characterizes the resilient parts using approximation models that abstract a wide range of approximate computing techniques. We believe that the key insights that we present can help shape further research in the area of approximate computing, while automatic resilience characterization frameworks such as ARC can greatly aid designers in the adoption approximate computing.