Litcius/Paper detail

XVDPU: A High-Performance CNN Accelerator on the Versal Platform Powered by the AI Engine

Xijie Jia, Yu Zhang, Guangdong Liu, Xinlin Yang, Tianyu Zhang, Jia Zheng, Dongdong Xu, Zhuohuan Liu, Mengke Liu, Xiaoyang Yan, Hong Wang, Rongzhang Zheng, Wang Li, Dong Li, Satyaprakash Pareek, Jian Weng, Lu Tian, Dongliang Xie, Hong Luo, Yi Shan

2023ACM Transactions on Reconfigurable Technology and Systems18 citationsDOI

Abstract

Today, convolutional neural networks (CNNs) are widely used in computer vision applications. However, the trends of higher accuracy and higher resolution generate larger networks. The requirements of computation or I/O are the key bottlenecks. In this article, we propose XVDPU: the AI Engine (AIE)-based CNN accelerator on Versal chips to meet heavy computation requirements. To resolve the IO bottleneck, we adopt several techniques to improve data reuse and reduce I/O requirements. An arithmetic logic unit is further proposed that can better balance resource utilization, new feature support, and efficiency of the whole system. We have successfully deployed more than 100 CNN models with our accelerator. Our experimental results show that the 96-AIE-core implementation can achieve 1,653 frames per second (FPS) for ResNet50 on VCK190, which is 9.8× faster than the design on ZCU102 running at 168.5 FPS. The 256-AIE-core implementation can further achieve 4,050 FPS. We propose a tilling strategy to achieve feature-map-stationary for high-definition CNN with the accelerator, achieving 3.8× FPS improvement on the residual channel attention network and 3.1× on super-efficient super-resolution. This accelerator can also solve the 3D convolution task in disparity estimation, achieving end-to-end performance of 10.1 FPS with all the optimizations.

Topics & Concepts

Computer scienceBottleneckConvolutional neural networkFeature (linguistics)ComputationHardware accelerationCompilerComputer hardwareKey (lock)FLOPSConvolution (computer science)Embedded systemComputer engineeringArtificial intelligenceArtificial neural networkField-programmable gate arrayParallel computingOperating systemAlgorithmPhilosophyLinguisticsAdvanced Image Processing TechniquesAdvanced Neural Network ApplicationsAdvanced Vision and Imaging