Approximate Computing Survey, Part II: Application-Specific & Architectural Approximation Techniques and Applications
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 49 of its 305 references that are in the map. First posted on arXiv 20 Jul 2023.
Builds on
49 of 305 references.
References · 49
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
- 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
- 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
- 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
- 2016Pruning Filters for Efficient ConvNetscited by 1,143
- 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
- 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 702
- 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 618
- 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 569
- 2016Learning Structured Sparsity in Deep Neural Networkscited by 541
- 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 521
- 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 443
37 more
- 2016EIE: Efficient Inference Engine on Compressed Deep Neural Networkcited by 295
- 2016Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architecturescited by 221
- 2017SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networkscited by 135
- 2020Neural Pruning via Growing Regularizationcited by 97
- 2015Fast ConvNets Using Group-wise Brain Damagecited by 82
- 2021CHIP: CHannel Independence-based Pruning for Compact Neural Networkscited by 78
- 2021Only Train Once: A One-Shot Neural Network Training And Pruning Frameworkcited by 70
- 2022ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantizationcited by 51
- 2022Hardware Approximate Techniques for Deep Neural Network Accelerators: A Surveycited by 39
- 2022DropNet: Reducing Neural Network Complexity via Iterative Pruningcited by 29
- 2019ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retrainingcited by 28
- 2019EDEN: Enabling Energy-Efficient, High-Performance Deep Neural Network Inference Using Approximate DRAMcited by 24
- 2016Runtime Configurable Deep Neural Networks for Energy-Accuracy Trade-offcited by 19
- 2021RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networkscited by 19
- 2021RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Mergingcited by 19
- 2018ThUnderVolt: Enabling Aggressive Voltage Underscaling and Timing Error Resilience for Energy Efficient Deep Neural Network Acceleratorscited by 18
- 2021Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platformscited by 18
- 2016Design and Implementation of Probabilistic Programming Language Anglicancited by 15
- 2020A Mixed-Precision RISC-V Processor for Extreme-Edge DNN Inferencecited by 13
- 2022Cross-Layer Approximation For Printed Machine Learning Circuitscited by 12
- 2023Co-Design of Approximate Multilayer Perceptron for Ultra-Resource Constrained Printed Circuitscited by 11
- 2023DeepAxe: A Framework for Exploration of Approximation and Reliability Trade-offs in DNN Acceleratorscited by 11
- 2019Efficient ConvNet-based Object Detection for Unmanned Aerial Vehicles by Selective Tile Processingcited by 9
- 2022ApproxTrain: Fast Simulation of Approximate Multipliers for DNN Training and Inferencecited by 9
- 2018DroNet: Efficient convolutional neural network detector for real-time UAV applicationscited by 8
- 2021Towards a Systematic Survey for Carbon Neutral Data Centerscited by 7
- 2023Model-to-Circuit Cross-Approximation For Printed Machine Learning Classifierscited by 7
- 2019Automated Circuit Approximation Method Driven by Data Distributioncited by 5
- 2021Positive/Negative Approximate Multipliers for DNN Acceleratorscited by 5
- 2018BLASYS: Approximate Logic Synthesis Using Boolean Matrix Factorizationcited by 4
- 2018BlinkML: Efficient Maximum Likelihood Estimation with Probabilistic Guaranteescited by 4
- 2022CoNLoCNN: Exploiting Correlation and Non-Uniform Quantization for Energy-Efficient Low-precision Deep Convolutional Neural Networkscited by 4
- 2014A Programming Model and Runtime System for Significance-Aware Energy-Efficient Computingcited by 2
- 2018Exploiting Errors for Efficiency: A Survey from Circuits to Algorithmscited by 2
- 2015Energy-Efficient Object Detection using Semantic Decompositioncited by 1
- 2017DyVEDeep: Dynamic Variable Effort Deep Neural Networkscited by 1
- 2023DAISM: Digital Approximate In-SRAM Multiplier-based Accelerator for DNN Training and Inferencecited by 1
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.