Sung Kyu Lim
Papers
2
Total Citations
6
H-Index
2
About
Sung Kyu Lim is a leading authority in electronic design automation (EDA), with a focus on 3D integrated circuits (3D ICs) and hardware accelerators for machine learning. His pioneering work addresses the critical challenges of power, area, and communication in modern computing systems. Notably, his 2020 paper "LCP: A Low-Communication Parallelization Method for Fast Neural Network Inference in Image Recognition" tackles the bottleneck of data movement in deep neural network (DNN) inference for edge devices, proposing a method to reduce inter-core communication for efficient deployment in robots and IoT systems. This work has garnered 4 citations and highlights his commitment to bridging the gap between advanced algorithms and practical hardware. Earlier, his 2017 study on "The Impact of 3D Stacking and Technology Scaling on the Power and Area of Stereo Matching Processors" demonstrated how through-silicon via (TSV) technology can significantly reduce the power and footprint of real-time vision processors used in autonomous vehicles. With a career spanning decades, Lim’s contributions are foundational to the design of energy-efficient, high-performance computing systems, making him a key figure for students and researchers exploring the intersection of hardware design and AI acceleration.
Research Focus
Key Achievements
Top Papers
- 1
- 2