Binary instrumentation support for measuring performance in OpenMP programs

Author

Elfituri, Mustafa ; Cook, Jonathan ; Cook, Jonathan

Author_Institution

Dept. of Comput. Sci., New Mexico State Univ., Las Cruces, NM, USA

fYear

2013

fDate

18-18 May 2013

Firstpage

19

Lastpage

23

Abstract

In parallel computations, evaluating the causes of poor speedup is an important development activity to reach the goal of creating the most efficient parallel computation possible. In our research on irregular parallel computations, especially graph algorithms, we had specific measurement needs for which a dearth of tools could be found. We created PGOMP, a small library-based profiling tool for the Gnu OpenMP implementation, and show its use here in discovering some of the causes of poor speedup in graph computations.

Keywords

application program interfaces; graph theory; parallel programming; software libraries; software metrics; software performance evaluation; software tools; Gnu OpenMP implementation; OpenMP programs; PGOMP; binary instrumentation support; graph algorithms; graph computations; irregular parallel computations; library-based profiling tool; performance measurement; Hardware; Heating; Instruction sets; Instruments; Libraries; Parallel processing; Synchronization; graph computation; measurement; profiling;

fLanguage

English

Publisher

ieee

Conference_Titel

Software Engineering for Computational Science and Engineering (SE-CSE), 2013 5th International Workshop on

Conference_Location

San Francisco, CA

Type

conf

DOI

10.1109/SECSE.2013.6615095

Filename

6615095