Fast and high quality topology-aware task mapping

Warning The system is temporarily closed to updates for reporting purpose.

Deveci, Mehmet and Kaya, Kamer and Uçar, Bora and Çatalyürek, Ümit V. (2015) Fast and high quality topology-aware task mapping. In: 29th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2015), Hyderabad, India

[thumbnail of paper.pdf] PDF
paper.pdf

Download (490kB)

Abstract

Considering the large number of processors and the size of the interconnection networks on exascale capable supercomputers, mapping concurrently executable and communicating tasks of an application is a complex problem that needs to be dealt with care. For parallel applications, the communication overhead can be a significant bottleneck on scalability. Topology-aware task-mapping methods that map the tasks to the processors (i.e., cores) by exploiting the underlying network information are very effective to avoid, or at worst bend, this limitation. We propose novel, efficient, and effective task mapping algorithms employing a graph model. The experiments show that the methods are faster than the existing approaches proposed for the same task, and on 4096 processors, the algorithms improve the communication hops and link contentions by 16% and 32%, respectively, on the average. In addition, they improve the average execution time of a parallel SpMV kernel and a communication-only application by 9% and 14%, respectively.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: Task mapping, communication graph, partitioning
Subjects: Q Science > QA Mathematics > QA075 Electronic computers. Computer science
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Computer Science & Eng.
Faculty of Engineering and Natural Sciences
Depositing User: Kamer Kaya
Date Deposited: 16 Dec 2015 11:59
Last Modified: 26 Apr 2022 09:19
URI: https://research.sabanciuniv.edu/id/eprint/27704

Actions (login required)

View Item
View Item