Soontae Kim

Soontae Kim is a Faculty member in the School of Computing at KAIST. Their research focuses on embedded computing, with contributions to areas such as quantized convolutional neural networks, SSD optimization, and secure memory systems. Kim's work has been published in IEEE Transactions on Computers, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, and Sensors. They are affiliated with the Embedded Computing Laboratory at KAIST, and their research is accessible via http://ecl.kaist.ac.kr. Kim's academic profile includes collaborations with researchers at various institutions and participation in conferences such as DATE and MICRO.

Soontae Kim is a researcher specializing in embedded systems and computer architecture. Their work focuses on optimizing energy efficiency and reliability in hardware systems, particularly in the context of secure and low-power computing. Kim's research includes the development of novel cache architectures, such as Residue Cache and Ternary Cache, which leverage compression and STT-RAM technologies to reduce energy consumption and improve performance. They have also explored error protection mechanisms for caches, power-aware scheduling algorithms, and secure data management in mobile payment systems. Their contributions address critical challenges in embedded systems, including energy efficiency, fault tolerance, and security.