LHA: Layer-wise Hardware Acceleration of Progressive Quantizing Inference through Partial Reconfiguration for Edge Computing

As the need for real-time, low-power deep learning at the edge increases, efficient hardware acceleration becomes crucial. Traditional edge hardware designs often scale to accommodate neural network sizes, which can degrade overall performance by taxing the hardware. To solve this, we propose a novel Layer-wise Hardware Acceleration (LHA) approach for Deep Neural Network (DNN) inference, leveraging progressive quantization and Partial Reconfiguration (PR). We first apply progressive quantization to systematically reduce the bit-width of network weights and activations, lowering computational and memory demands. Then, we utilize Field Programmable Gate Arrays (FPGAs) with PR capabilities to dynamically reconfigure hardware for each quantized network layer in sequence. This method optimizes FPGA resource usage, tailors to each layer’s needs, and reallocates freed resources to boost overall performance. Experiments show that LHA significantly enhances resource efficiency while maintaining inference performance on edge devices. Recommended citation:

@INPROCEEDINGS{11229400, author={Yue, Zongcheng and Ma, Sean Longyu and Sham, Chiu-Wing and Fu, Chong}, booktitle={2025 International Joint Conference on Neural Networks (IJCNN)}, title={LHA: Layer-wise Hardware Acceleration of Progressive Quantizing Inference through Partial Reconfiguration for Edge Computing}, year={2025}, volume={}, number={}, pages={1-8}, keywords={Performance evaluation;Deep learning;Quantization (signal);Power demand;Artificial neural networks;Throughput;Real-time systems;Field programmable gate arrays;Hardware acceleration;Edge computing;Quantization;FPGA;Deep Learning;Edge Computing}, doi={10.1109/IJCNN64981.2025.11229400}}