Scheduling on Manycore and Heterogeneous Graphics Processors
University of California, Davis
University of California, 2014
@phdthesis{tzeng2014scheduling,
title={Scheduling on Manycore and Heterogeneous Graphics Processors},
author={Tzeng, Stanley},
year={2014},
school={UNIVERSITY OF CALIFORNIA, DAVIS}
}
Through custom software schedulers that distribute work differently than built-in hardware schedulers, data-parallel and heterogenous architectures can be retargeted towards irregular task-parallel graphics workloads. This dissertation examines the role of a GPU scheduler and how it may schedule complicated workloads onto the GPU for efficient parallel processing. This dissertation examines the scheduler through three different properties of workloads: granularity, irregularity, and dependency. Then it moves onto heterogenous architectures and examine how scheduling decisions differ when scheduling for discrete versus heterogeneous chips. The dissertation conclues with future work in scheduling for both discrete and heterogeneous architectures.
January 28, 2014 by hgpu
