Notice

A research paper entitled “HERTI: a Reinforcement Learning-Augmented System for Efficient Real-Time Inference on Heterogeneous Embedded Systems” has been accepted for publication at PACT’21. The paper is co-authored by Myeonggyun Han and Prof. Woongki Baek at Intelligent System Software Lab. (ISSL), CSE, UNIST.

This work proposes HERTI, a reinforcement learning-augmented system for efficient real-time inference on heterogeneous embedded systems. HERTI efficiently explores the state space and robustly finds an efficient state that significantly improves the efficiency of the target inference workload while satisfying its deadline constraint through reinforcement learning. Our quantitative evaluation conducted on a real heterogeneous embedded system demonstrates the effectiveness of HERTI in that HERTI achieves high inference efficiency in multiple metrics (i.e., energy and energy-delay product) with a strong deadline guarantee in contrast to the state-of-the-art techniques, delivers larger gains as the inference deadline and the system heterogeneity increase, provides strong generality for hyper-parameter tuning, and significantly reduces the training time through its estimation-based approach across all the evaluated inference workloads and scenarios.

PACT (International Conference on Parallel Architectures and Compilation Techniques) is one of the top-tier conferences in the field of parallel computing.