Abstract
Modern processors cannot deliver high performance without applying caching mechanisms. However, the cache-conscious programming requires from the developer quite a deep knowledge about the underlying processor’s hardware architecture and is thus very hard to be adopted by the software codes. The cache-aware application optimization is getting even more challenging for the parallel (multi-threaded) applications running in multi-processor and/or multi-core environments. We introduce the Rogue Wave Software’s ThreadSpotter performance analysis tool, which is designed to simplify the cache-aware application development by leveraging the unique performance optimization techniques. Following an original statistical approach, ThreadSpotter enables the in-depth application analysis on the wide range of hardware platforms.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
This statistical metric is introduced by Rogue Wave Software.
References
Berg, Hakan and Hagersten. A Statistical Multiprocessor Cache Model by Erik Berg, Hȧkan Zeffer, and Erik Hagersten. In Proceedings of the 2006 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS-2006), Austin, Texas, USA, March 2006.
Rogue Wave Software. ThreadSpotter Manual Version 2012.1 Boulder, CO, USA. 2012
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lüdtke, R., Gottbrath, C. (2013). Cache-Related Performance Analysis Using Rogue Wave Software’s ThreadSpotter. In: Cheptsov, A., Brinkmann, S., Gracia, J., Resch, M., Nagel, W. (eds) Tools for High Performance Computing 2012. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37349-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-37349-7_6
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37348-0
Online ISBN: 978-3-642-37349-7
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)