Abstract
Computational grid for high performance computing is the current research focus of computer science. Furthermore, the performance analysis and evaluation toward parallel programs is critical in grid computing environment. This paper studies and analyzes the granularity of MPI parallel programs. By means of basic-block and flow analysis tree, we develop a Program Basic-block Analysis System (PBAS), which is an automatic performance analysis software tool based on source codes. Some parallel algorithms have been analyzed.
Supported by the National Natural Science Foundation of China under grant of 60173026 and Shanghai Science Fund under grant of 025115037 and 03DZ15029.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Zhang, Y.H.: The Application Research of Network Heterogeneous Computing and Its Coarse-Grain User-Directed Implementation, thesis submitted for degree of graduate of Jiaotong University (January 1999)
Snir, M., Otto, S., Huss, S., Walker, D.: MPI: The Complete Reference. MIT Press, Cambridge (1996)
Chen, G.L.: Parallel Computing, May 1999. Higher Education Press, Beijing (1999)
Foster, I., Kesselman, C., Tuecke, S.: The Anatomy of the Grid: Enabling Scalable Virtual Organizations. International J. Supercomputer Applications 15(3) (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Qiao, Wg., Zeng, G. (2004). The Granularity Analysis of MPI Parallel Programs. In: Li, M., Sun, XH., Deng, Qn., Ni, J. (eds) Grid and Cooperative Computing. GCC 2003. Lecture Notes in Computer Science, vol 3032. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24679-4_39
Download citation
DOI: https://doi.org/10.1007/978-3-540-24679-4_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21988-0
Online ISBN: 978-3-540-24679-4
eBook Packages: Springer Book Archive