2014 International Conference on High Performance Computing &Amp; Simulation (HPCS) 2014
DOI: 10.1109/hpcsim.2014.6903791
|View full text |Cite
|
Sign up to set email alerts
|

Efficient analysis methodology for huge application traces

Abstract: The growing complexity of computer system hardware and software makes their behavior analysis a challenging task. In this context, tracing appears to be a promising solution as it provides relevant information about the system execution. However, trace analysis techniques and tools lack in providing the analyst the way to perform an efficient analysis flow because of several issues. First, traces contain a huge volume of data difficult to store, load in memory and work with. Then, the analysis flow is hindered… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
9
0

Year Published

2015
2015
2016
2016

Publication Types

Select...
2
1

Relationship

1
2

Authors

Journals

citations
Cited by 3 publications
(9 citation statements)
references
References 16 publications
0
9
0
Order By: Relevance
“…The algorithms and complexity measure calculation are presented in our previous works [4,3,13]. The aggregation steps are the following: the algorithm first calculates the quality measures of each possible time interval.…”
Section: Methodology Applicationmentioning
confidence: 99%
See 2 more Smart Citations
“…The algorithms and complexity measure calculation are presented in our previous works [4,3,13]. The aggregation steps are the following: the algorithm first calculates the quality measures of each possible time interval.…”
Section: Methodology Applicationmentioning
confidence: 99%
“…In this section, we remind two applications of an aggregation methodology we already described in previous documents: temporal [4,3,13] and spatiotemporal [2] data aggregations that provide overviews of the trace and address issues evoked in Section 2. For each technique, we designed an algorithm which gathers the parts of the trace where the behavior is homogeneous.…”
Section: Provide a Trace Overview Using Data Aggregationmentioning
confidence: 99%
See 1 more Smart Citation
“…It gives a detailed view of the connections between the actors. One of the earliest work to use Gantt Chart for representing traces in parallel systems is Paragraph [13] and many later work do so, from proprietary industrial solution [24,1] to various open source projects such as Eclipse Trace Compass [2] and Frame-SoC [9]. However, due to the high visual clutters of Gantt Charts, aliasing problems quickly arise as the amount of information to represent on the screen increases.…”
Section: Visualization Of Execution Tracesmentioning
confidence: 99%
“…Ocelotl [21,9] proposes a visualization that aggregates both the actors and the time dimension to obtain an overview of the execution. It comes with user interactions that allow to choose the aggregation level enabling the analyst to explore the macro-behaviors at different scale.…”
Section: Visualization Of Execution Tracesmentioning
confidence: 99%