Revisit and Benchmarking of Automated Quantization Toward Fair Comparison
- 15 September 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 73 (1) , 18-29
Abstract
Automated quantization has emerged as an entirely new design paradigm to automate the optimal configuration of bitwidth for deep neural networks (DNNs), making the DNN more memory-efficient and faster to execute on hardware with limited resources. Reinforcement learning (RL) and differentiable neural architecture search (DNAS) are two main solution paths that have shown their superiority. Yet, there are countless methods with various implementations within each path. It has been hard to comprehend their differences and make a relatively fair comparison due to the lack of a benchmark framework and a clear analysis of which aspects are common, respectively distinct, between different implementations. To this end, we introduce BenQ to pave the way towards fair comparisons in two separate race tracks, i.e., intra-comparison of the RL-based and the DNAS-based methods, respectively. We provide a systematic approach, which helps to reveal relatively vital aspects of different implementations. Finally, we conduct comprehensive experi-ments on VGG, AlexNet, ResNet, GoogleNet, MobileNet-V2, and Vision Transformer (ViT), and the new observations shed light on potential future directions for automated quantization to move forward.Keywords
Funding Information
- National Natural Science Foundation of China (62172327)
This publication has 25 references indexed in Scilit:
- A Survey of Accelerator Architectures for Deep Neural NetworksEngineering, 2020
- BISMO: A Scalable Bit-Serial Matrix Multiplication Overlay for Reconfigurable Computing2018
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference2018
- Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Network2018
- Efficient Processing of Deep Neural Networks: A Tutorial and SurveyProceedings of the IEEE, 2017
- Deep Learning with Low Precision by Half-Wave Gaussian Quantization2017
- PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning2017
- ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars2016
- Deep Residual Learning for Image Recognition2016