Dynamic Data Structures for Taskgraph Scheduling Policies with Applications in OpenCL Accelerators
School of Computer Science, The University of Nottingham, Nottingham NG8 1BB, UK
MISTA 2011
@article{marecek2011dynamic,
title={Dynamic Data Structures for Taskgraph Scheduling Policies with Applications in OpenCL Accelerators},
author={Marecek, J. and Parkes, A.J. and Burke, E.K. and Elliot, R. and Francis, H. and Lokhmotov, A.},
year={2011}
}
OpenCL is an emerging open framework for parallel programming in heterogenous systems. OpenCL accelerators need to schedule the execution of submitted jobs with no (or only very imprecise) estimates of execution times, but respecting dependencies among them, which are given in the form of directed acyclic graph. This problem is known as stochastic taskgraph scheduling, stochastic scheduling with precedencies, or stochastic scheduling with data dependencies. We study the complexity of implementing out-of-order static scheduling policies, which approach optimality in the long run, under certain simplifying assumptions. We present a simple data structure allowing for the "what next" query of a number of out-of-order taskgraph scheduling policies to be answered in time O(1), while vertices can be added in time O(1).
September 24, 2011 by hgpu
