An Interrupt-Driven Work-Sharing For-Loop Scheduler
Department of Computing, Imperial College London, London SW7 2AZ, UK
arXiv:1505.04134 [cs.DC], (15 May 2015)
@article{rokos2015interruptdriven,
title={An Interrupt-Driven Work-Sharing For-Loop Scheduler},
author={Rokos, Georgios and Gorman, Gerard J. and Kelly, Paul H. J.},
year={2015},
month={may},
archivePrefix={"arXiv"},
primaryClass={cs.DC}
}
In this paper we present a parallel for-loop scheduler which is based on work-stealing principles but runs under a completely cooperative scheme. POSIX signals are used by idle threads to interrupt left-behind workers, which in turn decide what portion of their workload can be given to the requester. We call this scheme Interrupt-Driven Work-Sharing (IDWS). This article describes how IDWS works, how it can be integrated into any POSIX-compliant OpenMP implementation and how a user can manually replace OpenMP parallel for-loops with IDWS in existing POSIX-compliant C++ applications. Additionally, we measure its performance using both a synthetic benchmark with varying distributions of workload across the iteration space and a real-life application on Sandy Bridge and Xeon Phi systems. Regardless the workload distribution and the underlying hardware, IDWS is always the best or among the best-performing strategies, providing a good all-around solution to the scheduling-choice dilemma.
May 19, 2015 by hgpu
