Preview

SibScript

Advanced search

AN APPROACH TO TRACING AND PREPARING DATA FOR PERFORMANCE ANALYSIS OF UPC APPLICATIONS

Abstract

Partitioned Global Address Space (PGAS) programming model is a relatively new area of parallel applications development. New model demands new tools to support applications development process. Paper describes approach to tracing and preparing data for performance analysis of parallel applications written in Unified Parallel C which is a most mature PGAS language.

About the Authors

Nikita E. Andreev
Kemerovo State University
Russian Federation


Konstantin E. Afanasiev
Kemerovo State University
Russian Federation


References

1. High Productivity Computing Systems Program [Электронный ресурс]. URL: <http://www. highproductivity.org/> (дата обращения: 30.08.2010).

2. Bell, C. Optimizing Bandwidth Limited Problems Using One-Sided Communication and Overlap [Текст] / C. Bell, D. Bonachea, R. Nishtala, K. Yelick // 20th International Parallel & Distributed Processing Symposium, 2006.

3. El-Ghazawi, T. UPC Language Specifications [Электронный ресурс]. URL: <http://www.gwu. edu~upc/documentation.html> (дата обращения: 30.08.2010).

4. Leko, A. Performance Analysis Strategies [Электронный ресурс]. URL: <http://www.hcs.ufl. edu/prj/upcgroup/upcperf/documents/20050302-AnalysisDraft.pdf> (дата обращения: 30.08.2010).

5. Su, H. GASP! A Standardized Performance Analysis Tool Interface for Global Address Space Programming Models [Текст] / H. Su, D. Bonachea, A. Leko, H. Sherburne, M. Billingsley III, and A. George // Proc. of Workshop on State-of-the-Art in Scientific and Parallel Computing (PARA06), Umea, Sweden, June 18-21, 2006.

6. Bonachea, D. Proposal for High-Performance Wall-Clock Timers in UPC [Электронный ресурс]. URL: https://upc-wiki.lbl.gov/images/9/9b/Upc_tick_ 0.2.pdf (дата обращения: 30.08.2010).


Review

For citations:


Andreev N.E., Afanasiev K.E. AN APPROACH TO TRACING AND PREPARING DATA FOR PERFORMANCE ANALYSIS OF UPC APPLICATIONS. The Bulletin of Kemerovo State University. 2010;(4):4-10. (In Russ.)

Views: 189


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


ISSN 2949-2122 (Print)
ISSN 2949-2092 (Online)