Browsing by Author "Chen, Sheng-Yen"

Now showing 1 - 2 of 2

A Hadoop-based Principle Component Analysis on Embedded Heterogeneous Platform
(2017-01-01)
Chen, Sheng-Yen
;
Wei, Chia-I
;
Chiu, Yu-Chen
;
Lai, Bo-Cheng Charles
;
電子工程學系及電子研究所
Hadoop is a widely adopted distributed processing framework which assumes each computing node a CPU-based system with local memory. This design scheme cannot effectively take full advantage of an embedded heterogeneous many-core platform due the mismatch of data collection and management paradigms between the Hadoop environment and embedded heterogeneous systems. This paper proposes a Hadoop-based design of Principle Component Analysis (PCA) to efficiently leverage the distributed embedded heterogeneous many-core systems. By taking the same data layout of conventional Hadoop applications, the proposed design introduces efficient manners to collect and manage the fine-grained data chunks. The experiments on a Tegra K1 has achieved 5.9x performance enhancement.
A Learning-on-Cloud Power Management Policy for Smart Devices
(2014)
Pan, Gung-Yu
;
Lai, Bo-Cheng Charles
;
Chen, Sheng-Yen
;
Jou, Jing-Yang
;
電子工程學系及電子研究所
Energy consumption poses severe limitations for smart devices, urging the development of effective and efficient power management policies. State-of-the-art learning-based policies are autonomous and adaptive to the environment, but they are subject to costly computational overhead and lengthy convergence time. As smart devices are connected to Internet, this paper proposes the Learning-on-Cloud (LoC) policy to exploit cloud computing for power management. Sophisticated learning engines are offloaded from local devices to the cloud with minimal communication data, thus the runtime overhead is reduced. The learning data are shared between many devices with the same model, hence the convergence rate is raised. With one thousand devices connecting to the cloud, the LoC agent is able to converge within a few iterations; the energy saving is better than both of the greedy and the learning-based policies with less latency penalty. By implementing the LoC policy as an Android App, the measured overhead is only 0.01% of the system time.