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

View Sample PDF

Author(s): Yan Li (Intel Labs China, China), Jidong Zhai (Tsinghua University, China)and Keqin Li (State University of New York, USA)
Copyright: 2016
Pages: 26
Source title: Innovative Research and Applications in Next-Generation High Performance Computing
Source Author(s)/Editor(s): Qusay F. Hassan (Mansoura University, Egypt)
DOI: 10.4018/978-1-5225-0287-6.ch005

Keywords: Computer Science & IT / Engineering Science Reference / Grid & High Performance Computing / High Performance Computing

Purchase

View Communication Analysis and Performance Prediction of Parallel Applications on Large-Scale Machines on the publisher's website for pricing and purchasing information.

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.

The IRMA Community

Research IRM

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

Purchase

Abstract

Related Content

IRMA Sponsors