Issue No. 01 - Jan.-Feb. (2017 vol. 19)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MCSE.2017.14
Letian Yi , Central South University, China
Jianbin Li , Central South University, China
Yaoxue Zhang , Central South University, China
The authors present a highly scalable system for power-efficient wearable devices, TCID (transparent computing-based intelligent device), which leverages streaming-based execution to make applications in a wearable device obtain data from a server at runtime, eliminating limitations on the size of storage space for program execution on the device. To improve performance of streaming-based execution, adaptive network operations and an object-based cache are proposed. The adaptive network operations are designed to deliver high network throughput for various data access patterns, and the object-based cache makes the cache management adaptive to the running mode. The authors have implemented TCID in an intelligent watch. Measurements of a wide range of workloads demonstrate the benefits of this design.
Servers, Random access memory, Scalability, Runtime, Flash memories, Hardware, Performance evaluation, Pervasive computing, Heterogeneous networks, Mobile computing, Mobile communications
L. Yi, J. Li and Y. Zhang, "Improving the Scalability of Wearable Devices via Transparent Computing Technology," in Computing in Science & Engineering, vol. 19, no. 1, pp. 29-37, 2017.