Low-overhead scheduling for improving performance of scientific applications

Application performance can degrade significantly due to node-local load imbalances during application execution on a large number of SMP nodes. These imbalances can arise from the machine, operating system, or the application itself. Although dynamic load balancing within a node can mitigate imbalances, such load balancing is challenging because of its impact to data movement and synchronization overhead. We developed a series of scheduling strategies that mitigate imbalances without incurring high overhead. Our strategies provide performance gains for various HPC codes, and perform better than widely known scheduling strategies such as OpenMP guided scheduling. Our developed scheme and methodology allows for scaling applications to next-generation clusters of SMPs with minimal application programmer intervention. We expect these techniques to be increasingly useful for future machines approaching exascale.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2015

Author dc:creator

• Kale, Vivek

Contributors dc:contributor

• Gropp, William D.
• de Supinski, Bronis
• Garzaran, Maria J.
• Padua, David A.

• multicore architecture
• dynamic scheduling
• scientific computing
• performance tuning

Statement dc:rights

• Copyright 2015 Vivek Kale

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/78642

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/78642