2015
DOI: 10.1109/tpds.2014.2329688
|View full text |Cite
|
Sign up to set email alerts
|

Parallel Application Signature for Performance Analysis and Prediction

Abstract: Predicting the performance of parallel scientific applications is becoming increasingly complex. Our goal was to characterize the behavior of message-passing applications on different target machines. To achieve this goal, we developed a method called parallel application signature for performance prediction (PAS2P), which strives to describe an application based on its behavior. Based on the application's message-passing activity, we identified and extracted representative phases, with which we created a para… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
12
0

Year Published

2016
2016
2023
2023

Publication Types

Select...
5
3

Relationship

3
5

Authors

Journals

citations
Cited by 35 publications
(12 citation statements)
references
References 23 publications
0
12
0
Order By: Relevance
“…We have analyzed the execution of each of these benchmarks with the PAS2P tool [26]. We find that the communications represent 82% of the execution time of the CG class B with 16 processes.…”
Section: Limitations and Overhead Analysismentioning
confidence: 99%
See 1 more Smart Citation
“…We have analyzed the execution of each of these benchmarks with the PAS2P tool [26]. We find that the communications represent 82% of the execution time of the CG class B with 16 processes.…”
Section: Limitations and Overhead Analysismentioning
confidence: 99%
“…Scientific parallel applications are normally composed of a set of phases that are repeated during application execution [26]. Some of these phases could be computation bound and others communication bound.…”
Section: Limitations and Overhead Analysismentioning
confidence: 99%
“…Another important element is to find the communication pattern (source and destination of the package) and volume (size of the message sent). In this sense, we have used a tool called PAS2P (Parallel Application Signature for Performance Prediction), which allows us to know the behavior of the SPMD-MPI application making a signature of it [33] [34]. This tool gives us the communication pattern that is a key step in order to know the communication behavior of the application.…”
Section: Characterization Phasementioning
confidence: 99%
“…PAS2P (Parallel Application Signature for Performance Prediction) [12] is a tool that allows us to analyze the dynamic behavior of the application, charac terizing it in a set of phases that represent the performance of the application. With the phases, PAS2P constructs the application signature, which is defined by the set of phases which represent the application behavior at the performance level.…”
Section: Introductionmentioning
confidence: 99%