Approximate Computing: From Circuits to Applications

From Variability-Tolerance to Approximate Computing in Parallel Computing Architectures

Automated High-Level Generation of Low-Power Approximate Computing Circuits

Numerous application domains (e.g., signal and image processing, computer graphics, computer vision, and machine learning) are inherently error tolerant, which can be exploited to produce approximate ASIC implementations with low power consumption at the expense of negligible or small reductions in application quality. A major challenge is the need for approximate and high-level design generati...

Implementing Energy-parsimonious Inexact/Approximate Circuits for Error-tolerant Applications

A. Lingamneni, J.-L. Nagel, P.-A. Beuchat, M. Morgan, C. C. Enz, C. Piguet In this paper, CSEM presents a novel cross-layer co-design framework for implementing high energy-parsimonious inexact circuits, or circuits in which the accuracy of the output can be traded for substantial cost (energy, delay and/or area) savings, with zero hardware overheads. Measured results of a prototype chip (consi...

An introduction to approximate computing

Approximate computing is a research area where we investigate a wide spectrum of techniques to trade off computation accuracy for better performance or energy consumption. In this work, we provide a general introduction to approximate computing. Also, we propose a taxonomy to make it easier to discuss the merits of different approximation techniques. Our taxonomy emphasizes the expected cost of...

Approximate Inference by Compilation to Arithmetic Circuits

Arithmetic circuits (ACs) exploit context-specific independence and determinism to allow exact inference even in networks with high treewidth. In this paper, we introduce the first ever approximate inference methods using ACs, for domains where exact inference remains intractable. We propose and evaluate a variety of techniques based on exact compilation, forward sampling, AC structure learning...