A Feedback Approach to Task Partitioning in Heterogeneous Architectures
Department of Computer Sciences, School of Science and Engineering, Lahore University of Management Sciences, Lahore, Pakistan
Lahore University of Management Sciences, 2013
@article{ali2013feedback,
title={A Feedback Approach to Task Partitioning in Heterogeneous Architectures},
author={Ali, Yasir and Qadir, Zuhair},
year={2013}
}
Personal Computers of today are based on complex architectures often with multiple high performance computational units for various dedicated purposes. The General Purpose GPU is one such example where Graphic Processing Units are being used for more general purpose computing. In this paper, we target such architectures and focus on Load Balancing and Task Partitioning on Heterogeneous Architectures. We present some related implementations, discussing a specific implementation in detail and present our proposal as an improvement over the system model. We present the idea of a State of Equilibrium for the machine, where a feedback based task partitioning system keeps the system load over multiple computation devices balanced and optimized for maximum performance.
August 30, 2013 by hgpu
