You are here:

Efficient Workload Balancing on Heterogeneous GPUs using MixedInteger Non-Linear Programming
ARTICLE

, Department of Computer Science and Information Engineering, National Chung Cheng University, Taiwan ; , , National Center for High-Performance Computing, Taiwan ; , Department of Computer Science and Information Engineering, National Chung Cheng University, Taiwan

Journal of Applied Research and Technology Volume 12, Number 6, ISSN 1665-6423 Publisher: Elsevier Ltd

Abstract

Recently, heterogeneous system architectures are becoming mainstream for achieving high performance and power efficiency. In particular, many-core graphics processing units (GPUs) now play an important role for computing in heterogeneous architectures. However, for application designers, computational workload still needs to be distributed to heterogeneous GPUs manually and remains inefficient. In this paper, we propose a mixed integer non-linear programming (MINLP) based method for efficient workload distribution on heterogeneous GPUs by considering asymmetric capabilities of GPUs for various applications. Compared to the previous methods, the experimental results show that our proposed method improves performance and balance up to 33% and 116%, respectively. Moreover, our method only requires a few overhead while achieving high performance and load balancing.

Citation

Lin, C.S., Hsieh, C.W., Chang, H.Y. & Hsiung, P.A. (2014). Efficient Workload Balancing on Heterogeneous GPUs using MixedInteger Non-Linear Programming. Journal of Applied Research and Technology, 12(6), 1176-1186. Elsevier Ltd. Retrieved October 21, 2019 from .

This record was imported from Journal of Applied Research and Technology on January 29, 2019. Journal of Applied Research and Technology is a publication of Elsevier.

Full text is availabe on Science Direct: http://dx.doi.org/10.1016/S1665-6423(14)71676-1

Keywords