Jingwei Sun
Papers
1
Total Citations
12
H-Index
1
About
Jingwei Sun is a prominent researcher in computer architecture and energy-efficient deep learning acceleration, with a focus on Coarse-Grained Reconfigurable Arrays (CGRA) for neural network inference. His most-cited work, "A CGRA based Neural Network Inference Engine for Deep Reinforcement Learning" (2018, 12 citations), addresses the critical need for dedicated, low-power accelerators that can deploy advanced AI algorithms on edge devices. Sun’s key contributions lie in designing specialized hardware architectures that bridge the gap between high-performance neural network inference and the stringent power constraints of edge computing. By leveraging CGRAs, he enables real-time execution of deep reinforcement learning models—a domain traditionally limited by computational overhead—while maintaining energy efficiency. His work is foundational for researchers exploring reconfigurable computing and edge AI, demonstrating how tailored hardware can unlock new possibilities for autonomous systems and IoT applications. Sun’s research continues to influence the development of next-generation accelerators, making him a notable figure in the intersection of hardware design and machine learning deployment.
Research Focus
Key Achievements
Top Papers
- 1A CGRA based Neural Network Inference Engine for Deep Reinforcement Learning12 citations · 2018