2018 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID) (2018)
Washington, DC, USA
May 1, 2018 to May 4, 2018
Existing in-storage processing (ISP) techniques mainly focus on maximizing data processing rate by always utilizing total storage data processing resources for all applications. We find that this "always running in full gear" strategy wastes energy for some applications with a low data processing complexity. In this paper we propose RISP (Reconfigurable ISP), an energy-aware reconfigurable ISP framework that employs FPGA as data processing cells and NVM controllers. It can reconfigure storage data processing resources to achieve a high energy-efficiency without any performance degradation for big data analysis applications. RISP is modeled and then validated on an FPGA board. Experimental results show that compared with traditional host-CPU based computing RISP (with 16 channels or more) improves performance by 1.6-25.4× while saving energy by a factor of 2.2-161. Further, its reconfigurability can provide up to 77.2% additional energy saving by judiciously enabling data processing resources that are sufficient for an application.
Big Data, data analysis, energy consumption, field programmable gate arrays, power aware computing, storage management
X. Song, T. Xie and W. Pan, "RISP: A Reconfigurable In-Storage Processing Framework with Energy-Awareness," 2018 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID), Washington, DC, USA, 2018, pp. 193-202.