Profiling Non-numeric OpenSHMEM Applications with the TAU Performance System

Thumbnail Image

Files

openshmem.pdf (883.6 KB)

Links to Files

https://link.springer.com/chapter/10.1007/978-3-319-05215-1_8

Permanent Link

https://doi.org/10.1007/978-3-319-05215-1_8
 http://hdl.handle.net/11603/30409

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection

Author/Creator

Author/Creator ORCID

Date

2014

Type of Work

book chapters
conference papers and proceedings
postprints
Text

Department

Program

Citation of Original Publication

Linford, J., Simon, T.A., Shende, S., Malony, A.D. (2014). Profiling Non-numeric OpenSHMEM Applications with the TAU Performance System. In: Poole, S., Hernandez, O., Shamis, P. (eds) OpenSHMEM and Related Technologies. Experiences, Implementations, and Tools. OpenSHMEM 2014. Lecture Notes in Computer Science, vol 8356. Springer, Cham. https://doi.org/10.1007/978-3-319-05215-1_8

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.

Subjects

Abstract

The recent development of a unified SHMEM framework, OpenSHMEM, has enabled further study in the porting and scaling of applications that can benefit from the SHMEM programming model. This paper focuses on non-numerical graph algorithms, which typically have a low FLOPS/byte ratio. An overview of the space and time complexity of Kruskal’s and Prim’s algorithms for generating a minimum spanning tree (MST) is presented, along with an implementation of Kruskal’s algorithm that uses OpenSHEM to generate the MST in parallel without intermediate communication. Additionally, a procedure for applying the TAU Performance System to OpenSHMEM applications to produce indepth performance profiles showing time spent in code regions, memory access patterns, and network load is presented. Performance evaluations from the Cray XK7 “Titan” system at Oak Ridge National Laboratory and a 48 core shared memory system at University of Maryland, Baltimore County are provided.