Optimizing CNN Hardware Acceleration with Configurable Vector Units and Feature Layout Strategies
Open Access
- 12 March 2024
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 13 (6) , 1050
Abstract
Convolutional neural network (CNN) hardware acceleration is critical to improve the performance and facilitate the deployment of CNNs in edge applications. Due to its efficiency and simplicity, channel group parallelism has become a popular method for CNN hardware acceleration. However, when processing data involving small channels, there will be a mismatch between feature data and computing units, resulting in a low utilization of the computing units. When processing the middle layer of the convolutional neural network, the mismatch between the feature-usage order and the feature-loading order leads to a low input feature cache hit rate. To address these challenges, this paper proposes an innovative method inspired by data reordering technology, aiming to achieve CNN hardware acceleration that reuses the same multiplier resources. This method focuses on transforming the hardware acceleration process into feature organization, feature block scheduling and allocation, and feature calculation subtasks to ensure the efficient mapping of continuous loading and the calculation of feature data. Specifically, this paper introduces a convolutional algorithm mapping strategy and a configurable vector operation unit to enhance multiplier utilization for different feature map sizes and channel numbers. In addition, an off-chip address mapping and on-chip cache management mechanism is proposed to effectively improve the feature access efficiency and on-chip feature cache hit rate. Furthermore, a configurable feature block scheduling policy is proposed to strike a balance between weight reuse and feature writeback pressure. Experimental results demonstrate the effectiveness of this method. When using 512 multipliers and accelerating VGG16 at 100 MHz, the actual computing performance reaches 102.3 giga operations per second (GOPS). Compared with other CNN hardware acceleration methods, the average computing array utilization is as high as 99.88% and the computing density is higher.Keywords
Funding Information
- Key-Area Research and Development Program of Guangdong Province (2019B010107001)
This publication has 28 references indexed in Scilit:
- SparkNoC: An energy-efficiency FPGA-based accelerator using optimized lightweight CNN for edge computingJournal of Systems Architecture, 2021
- FPGA-Based High-Throughput CNN Hardware Accelerator With High Computing Resource Utilization RatioIEEE Transactions on Neural Networks and Learning Systems, 2021
- CNN-on-AWS: Efficient Allocation of Multikernel Applications on Multi-FPGA PlatformsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2020
- Tanji: a General-purpose Neural Network Accelerator with Unified Crossbar ArchitectureIEEE Design & Test, 2019
- Evaluating Fast Algorithms for Convolutional Neural Networks on FPGAsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2019
- Scalable FPGA Accelerator for Deep Convolutional Neural Networks with Stochastic StreamingIEEE Transactions on Multi-Scale Computing Systems, 2018
- Optimizing the Convolution Operation to Accelerate Deep Neural Networks on FPGAIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2018
- A High Throughput Acceleration for Hybrid Neural Networks With Efficient Resource Management on FPGAIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2018
- FP-BNN: Binarized neural network on FPGANeurocomputing, 2018
- Efficient Processing of Deep Neural Networks: A Tutorial and SurveyProceedings of the IEEE, 2017