Recent Advances in Periscope for Performance Analysis and Tuning

Yury Oleynik (), Robert Mijaković, Isaías A. Comprés Ureña, Michael Firbach and Michael Gerndt
Additional contact information
Yury Oleynik: Technical University of Munich (TUM), Institute of Informatics
Robert Mijaković: Technical University of Munich (TUM), Institute of Informatics
Isaías A. Comprés Ureña: Technical University of Munich (TUM), Institute of Informatics
Michael Firbach: Technical University of Munich (TUM), Institute of Informatics
Michael Gerndt: Technical University of Munich (TUM), Institute of Informatics

Chapter Chapter 4 in Tools for High Performance Computing 2013, 2014, pp 39-51 from Springer

Abstract: Abstract State of the art High Performance Computing (HPC) systems pose considerable programming challenges to application developers when tuning their applications. Periscope toolkit is one of a number of performance engineering instruments supporting application programmers in meeting those challenges. Due to the variety of architectures, programming models, runtime environments, and compilers on those systems, programmers need to apply multiple tools to understand and improve program performance. In this paper, we present the latest developments in Periscope aiming at (1) improving its interoperability and integration with other tools, (2) integrating automatic tuning support with performance analysis and (3) further extending performance analysis capabilities. The add-on for Periscope, called PAThWay, allows for the integration of multiple tools into performance tuning workflows. Further, Periscope is currently being extended with the ability to automatically tune parallel applications with respect to execution performance and energy consumption. And finally, new analysis capabilities were added to Periscope for the automatic evaluation of the temporal performance behavior of long-running applications.

Keywords: High Performance Computing; Parallel Application; Application Developer; Tuning Process; Dynamic Profile (search for similar items in EconPapers)
Date: 2014
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-319-08144-1_4

Ordering information: This item can be ordered from
http://www.springer.com/9783319081441

DOI: 10.1007/978-3-319-08144-1_4

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().