Title: Energy and performance improvement using real-time DVFS for graph traversal on GPU

Authors: Ashish Mishra; Nilay Khare

Addresses: Department of Computer Science and Engineering, Maulana Azad National Institute of Technology, Bhopal, M.P, India ' Department of Computer Science and Engineering, Maulana Azad National Institute of Technology, Bhopal, M.P, India

Abstract: Graphical-processing unit (GPU) handles massive data, effectively, as compared to CPU but has high power consumption which is a primary concern recently. A real-time dynamic voltage frequency scaling technique (DVFS) to save energy as well as improve performance, and to set the core and the memory frequency at a run time are proposed. Real-time DVFS is well investigated for saving energy and improving the performance by executing a breadth-first search (BFS) graph traversal algorithm from scalable heterogeneous computing (SHOC) benchmark suite. Two modes: energy saving and performance mode, can be realised by implementation of the proposed real-time DVFS algorithm. In energy saving mode, 28.2% energy can be saved with a performance improvement of 1.4%. On the other hand, 14.2% performance improvement is accomplished while maintaining the energy saving of 11.2% in performance mode. The proposed work is realised on K40c GPU received as a grant from NVidia.

Keywords: graph traversal; breadth first search; BFS; power consumption; dynamic voltage frequency scaling; DVFS; graphical-processing unit; GPU; energy; real-time; scalable heterogeneous computing; SHOC; power.

DOI: 10.1504/IJETP.2019.098972

International Journal of Energy Technology and Policy, 2019 Vol.15 No.2/3, pp.254 - 279

Received: 24 Aug 2017
Accepted: 09 Jun 2018
Published online: 10 Apr 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article