Paper Info
Title
Identifying computational phases from inter-process communication traces of HPC applications
Abstract
Understanding the behaviour of High Performance Computing (HPC) systems is a challenging task due to the large number of processes they involve as well as the complex interactions among these processes. In this paper, we present a novel approach that aims to simplify the analysis of large execution traces generated from HPC applications. We achieve this through a technique that allows semiautomatic extraction of execution phases from large traces. These phases, which characterize the main computations of the traced scenario, can be used by software engineers to browse the content of a trace at different levels of abstraction. Our approach is based on the application of information theory principles to the analysis of sequences of communication patterns found in HPC traces. The results of the proposed approach when applied to traces of a large HPC industrial system demonstrate its effectiveness in identifying the main program phases and their corresponding sub-phases.
Year
DOI
Venue
2012
10.1109/ICPC.2012.6240481
Program Comprehension
Keywords
Field
DocType
distributed processing,information theory,HPC applications,HPC industrial system,communication pattern sequence,computational phase identification,execution phase semiautomatic extraction,execution trace analysis,high performance computing systems,information theory principles,interprocess communication traces,program phases,dynamic analysis,execution phases,high performance computing aystems,inter-process communication traces,program comprehension
Information theory,Abstraction,Supercomputer,Computer science,Industrial systems,Software,Inter-process communication,Program comprehension,Distributed computing,Computation
Conference
ISSN
ISBN
Citations 
1092-8138 E-ISBN : 978-1-4673-1215-8
978-1-4673-1215-8
8
PageRank 
References 
Authors
0.45
14
3
Name
Order
Citations
PageRank
Luay Alawneh1709.18
Abdelwahab Hamou-Lhadj258753.97
Hamou-Lhadj, A.3110.99