Breadcrumb

Research work on machine-learning based thermal hotspot modeling has been accepted for TCAD

Sheriff Sadiqbatcha and Jinwei Zhang's work on machine learning based hotspot identification for commercial multi-core processors has been accepted by IEEE Transaction on CAD, the primary journal in EDA area. This work presents a significant advance for transient hotspot identifications using latest recurrent neural networks for commercial multi-core processors. The method can be used for new runtime reliability and thermal management for multi-core processors. 

S. Sadiqbatcha, J. Zhang, H. Zhao, H. Amrouch, J. Hankel, S. X.-D. Tan, “Post-silicon heat-Source identification and machine-learning-based thermal  modeling using infrared thermal imaging”, IEEE Transaction on Computer-Aided Design of Integrated Circuits and Systems (TCAD).