Approximate Computing Survey, Part II: Application-Specific & Architectural Approximation Techniques and Applications

TL;DR

This survey reviews recent application-specific and architectural approximation techniques in Approximate Computing, highlighting their design, benefits, and challenges across various computing layers for energy-efficient and high-performance systems.

Contribution

It provides a comprehensive classification and technical analysis of approximation techniques at different system layers, along with a quantitative and application spectrum analysis.

Findings

Approximate Computing techniques improve energy efficiency and performance.

Application-specific and architectural methods target resource-efficient processors.

Open challenges include balancing accuracy and efficiency.

Abstract

The challenging deployment of compute-intensive applications from domains such as Artificial Intelligence (AI) and Digital Signal Processing (DSP), forces the community of computing systems to explore new design approaches. Approximate Computing appears as an emerging solution, allowing to tune the quality of results in the design of a system in order to improve the energy efficiency and/or performance. This radical paradigm shift has attracted interest from both academia and industry, resulting in significant research on approximation techniques and methodologies at different design layers (from system down to integrated circuits). Motivated by the wide appeal of Approximate Computing over the last 10 years, we conduct a two-part survey to cover key aspects (e.g., terminology and applications) and review the state-of-the art approximation techniques from all layers of the traditional computing stack. Part II of the survey classifies and presents the technical details of application-specific and architectural approximation techniques, which both target the design of resource-efficient processors/accelerators and systems. Moreover, it reports a quantitative analysis of the techniques and a detailed analysis of the application spectrum of Approximate Computing, and finally, it discusses open challenges and future directions.