Welcome to the InfoSci Platform
Reference Hub1
Communication Analysis and Performance Prediction of Parallel Applications on Large-Scale Machines

Communication Analysis and Performance Prediction of Parallel Applications on Large-Scale Machines

Yan Li, Jidong Zhai, Keqin Li
Copyright: © 2016 |Pages: 26
ISBN13: 9781522502876|ISBN10: 1522502874|EISBN13: 9781522502883
DOI: 10.4018/978-1-5225-0287-6.ch005
Cite Chapter Cite Chapter

MLA

Li, Yan, et al. "Communication Analysis and Performance Prediction of Parallel Applications on Large-Scale Machines." Innovative Research and Applications in Next-Generation High Performance Computing, edited by Qusay F. Hassan, IGI Global, 2016, pp. 80-105. https://doi.org/10.4018/978-1-5225-0287-6.ch005

APA

Li, Y., Zhai, J., & Li, K. (2016). Communication Analysis and Performance Prediction of Parallel Applications on Large-Scale Machines. In Q. Hassan (Ed.), Innovative Research and Applications in Next-Generation High Performance Computing (pp. 80-105). IGI Global. https://doi.org/10.4018/978-1-5225-0287-6.ch005

Chicago

Li, Yan, Jidong Zhai, and Keqin Li. "Communication Analysis and Performance Prediction of Parallel Applications on Large-Scale Machines." In Innovative Research and Applications in Next-Generation High Performance Computing, edited by Qusay F. Hassan, 80-105. Hershey, PA: IGI Global, 2016. https://doi.org/10.4018/978-1-5225-0287-6.ch005

Export Reference

Mendeley
Favorite

Abstract

With the development of high performance computers, communication performance is a key factor affecting the performance of HPC applications. Communication patterns can be obtained by analyzing communication traces. However, existing approaches to generating communication traces need to execute the entire parallel applications on full-scale systems that are time-consuming and expensive. Furthermore, for designers of large-scale parallel computers, it is greatly desired that performance of a parallel application can be predicted at the design phase. Despite previous efforts, it remains an open problem to estimate sequential computation time in each process accurately and efficiently for large-scale parallel applications on non-existing target machines. In this chapter, we will introduce a novel technique for performing fast communication trace collection for large-scale parallel applications and an automatic performance prediction framework with a trace-driven network simulator.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.