Guest Editors' Introduction

Sybille Hellebrand, Jörg Henkel, Anand Raghunathan, Hans-Joachim Wunderlich

Abstract: Approximate computing exploits the inherent error resilience of many applications to optimize power consumption, run time, or chip area. Especially in audio, image, and video processing, but also in data mining or resource allocation tasks, approximate results are “good enough” for many application domains and may be hard to distinguish from perfect results. But even in domains where accurate results are required, approximate computing can be applied in various layers of the computing stack. Approximate computing promises to significantly increase computing efficiency (especially performance per power) and power density and is therefore of particular interest for embedded computing where these metrics are key.