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

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.

Published in ACM Computing Surveys (Volume 57, Issue 7, 2025)

References in corpus (15)

• Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey
• ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retraining
• DroNet: Efficient convolutional neural network detector for real-time UAV applications
• Efficient ConvNet-based Object Detection for Unmanned Aerial Vehicles by Selective Tile Processing
• Runtime Configurable Deep Neural Networks for Energy-Accuracy Trade-off
• Only Train Once: A One-Shot Neural Network Training And Pruning Framework
• BLASYS: Approximate Logic Synthesis Using Boolean Matrix Factorization
• Positive/Negative Approximate Multipliers for DNN Accelerators
• BlinkML: Efficient Maximum Likelihood Estimation with Probabilistic Guarantees
• CHIP: CHannel Independence-based Pruning for Compact Neural Networks
• Automated Circuit Approximation Method Driven by Data Distribution
• Co-Design of Approximate Multilayer Perceptron for Ultra-Resource Constrained Printed Circuits
• Approximate Computing Survey, Part II: Application-Specific & Architectural Approximation Techniques and Applications
• Model-to-Circuit Cross-Approximation For Printed Machine Learning Classifiers
• MAx-DNN: Multi-Level Arithmetic Approximation for Energy-Efficient DNN Hardware Accelerators

Cited by in corpus (1)

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