CASL’s paper accepted to Euro-Par 2018
A research paper entitled “CEML: a Coordinated Runtime System for Efficient Machine Learning on Heterogeneous Computing Systems” has been accepted for publication at Euro-Par’18. The paper is co-authored by Jihoon Hyun, Jinsu Park, Kyu Yeun Kim, Seongdae Yu, and Prof. Woongki Baek at Computer Architecture and Systems Lab. (CASL), CSE, UNIST.
This work proposes CEML, a coordinated runtime system for efficient machine learning on heterogeneous computing systems. CEML dynamically analyzes the performance and power characteristics of the target machine-learning application and robustly adapts the system state to enhance its efficiency on heterogeneous computing systems. Through quantitative evaluation, this work demonstrates that CEML significantly improves the efficiency of machine-learning applications on a full heterogeneous computing system.
Euro-Par (International European Conference on Parallel and Distributed Computing) is one of the major conferences in the field of parallel and distributed computing.