Scheduling on Manycore and Heterogeneous Graphics Processors

• Main Author: Tzeng, Stanley
• Language: EN
• Published: University of California, Davis 2014
• Subjects: Computer Science
• Online Access: http://pqdtopen.proquest.com/#viewpdf?dispub=3602240

<p>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.