Dongliang Xie
Papers
2
Total Citations
29
H-Index
2
About
Dongliang Xie is a leading researcher in high-performance hardware acceleration for deep neural networks, with a focus on convolutional neural network (CNN) architectures for computer vision. His work addresses the critical computational and I/O bottlenecks that limit the deployment of increasingly complex models in real-world applications. Xie’s most notable contribution is the development of XVDPU, a high-performance CNN accelerator on the Versal platform powered by the AI Engine, which has garnered 21 citations for its innovative approach to maximizing throughput. He further advanced the field with A-U3D, a unified 2D/3D CNN accelerator for disparity estimation, achieving 8 citations by tackling the unique computational density challenges of 3D CNNs in autonomous driving and robotics. By leveraging Xilinx’s cutting-edge 7nm Versal architecture, Xie’s accelerators enable practical, high-resolution vision systems that balance computation and I/O efficiency. His work is pivotal for students and researchers exploring edge AI and real-time perception, demonstrating how hardware-software co-design can bridge the gap between algorithmic complexity and deployable performance.
Research Focus
Key Achievements
Top Papers
- 1
- 2