Improving scheduling techniques in heterogeneous systems with dynamic, on-line optimisations

Marcin Bogdanski, Peter R. Lewis, Tobias Becker and Xin Yao
In Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems (CISIS) 2011, pp 496-501. Seoul, Korea. IEEE Computer Society Press, 2011.

Computational performance increasingly depends on parallelism, and many systems rely on heterogeneous resources such as GPUs and FPGAs to accelerate computationally intensive applications. However, implementations for such heterogeneous systems are often hand-crafted and optimised to one computation scenario, and it can be challenging to maintain high performance when application parameters change. In this paper, we demonstrate that machine learning can help to dynamically choose parameters for task scheduling and load-balancing based on changing characteristics of the incoming workload. We use a financial option pricing application as a case study. We propose a simulation of processing financial tasks on a heterogeneous system with GPUs and FPGAs, and show how dynamic, on-line optimisations could improve such a system. We compare on-line and batch processing algorithms, and we also consider cases with no dynamic optimisations.

@InProceedings{bogdanski_2011a,
title = "Improving scheduling techniques in heterogeneous systems with dynamic, on-line optimisations",
booktitle = "Proceedings of the International Conference on Complex, Intelligent, and Software Intensive Systems (CISIS) 2011",
author = "Marcin Bogdanski, Peter R. Lewis, Tobias Becker and Xin Yao",
pages = "496--501",
location = "Seoul, Korea",
publisher = "IEEE Computer Society Press",
year = "2011"
}