Abstract
Performance optimization remains one of the key issues in parallel computing. Many parallel applications do not benefit from the continually increasing peak performance of todays massively parallel computers, mainly because they have not been designed to operate efficiently on the 1000s of processors of todays top of the range systems. Conventional performance analysis is typically restricted to accumulated data on such large systems, severely limiting its use when dealing with real-world performance bottlenecks. Event based performance analysis can give the detailed insight required, but has to deal with extreme amounts of data, severely limiting its scalability. In this paper, we present an approach for scalable event-driven performance analysis that combines proven tool technology with novel concepts for hierarchical data layout and visualization. This evolutionary approach is being validated by implementing extensions to the performance analysis tool Vampir.
Chapter PDF
Similar content being viewed by others
Keywords
References
D. J. Becker, T. Sterling, D. Saverese, J. E. Dorband, U. A. Ranawak, and C. V. Packer. Beowulf: A Parallel Workstation for Scientific Computation. In Proceedings, International Conference on Parallel Processing, 1995. http://www.beofulf.org.
S. Bova, C. Breshears, H. Gabb, R. Eigenmann, G. Gaertner, B. Kuhn, B. Magro, and S. Salvini. Parallel programming with message passing and directives. SIAM News, 11 1999.
S. Browne, J. Dongarra, and K. London. Review of performance analysis tools for mpi parallel programs. http://www.cs.utk.edu/~browne/perftools-review.
B. Buck and J. K. Hollingsworth. An API for Runtime Code Patching. Technical report, Computer Science Department, University of Maryland, College Park, MD 20742 USA, 1998. http://www.cs.umd.edu/projects/dyninstAPI.
Cray Research. Introducing the MPP Apprentice Tool, IN-2511 3.0 edition, 1997.
D. Dent, G. Mozdzynski, D. Salmond, and B. Carruthers. Implementation and performance of OpenMP in ECWMF’s IFS code. In Proc. of the 5th SGI/CRAY MPP-Workshop, Bologna, 1999. http://www.cineca.it/mpp-workshop/abstract/bcarruthers.htm.
[10]A. Geist, A. Beguelin, J. Dongarra, W. Jiang, R. Manchek, and V. Sunderam. PVM: Parallel Virtual Machine. The MIT Press, 1994. http://www.epm.ornl.gov/pvm.
The GuideView performance analysis tool. http://www.kai.com.
F. Hoßfeld and W. E. Nagel. Per aspera ad astra: On the way to parallel processing. In H.-W. Meuer, editor, Anwendungen, Architekturen, Trends, FOKUS Praxis Informationen und Kommunikation, volume 13, pages 246–259, Munich, 1995. K. G. Saur.
The Jumpshot performance analysis tool. http://www-unix.mcs.anl.gov/mpi/mpich.
Lund Institute of Technology. Proceedings of EWOMP’99, 1st European Workshop on OpenMP, 1999.
Message Passing Interface Forum. MPI-2: Extensions to the Message-Passing Interface, August 1997. http://www.mpi-forum.org/index.html.
B. P. Miller, M. D. Callaghan, J. M. Cargille, J. K. Hollingsworth, R. B. Irvin, K. L. Karavanic, K. Kunchithapadam, and T. Newhall. The Paradyn Parallel Performance Measurement Tools. IEEE Computer, 28(11):37–46, November 1995. http://www.cs.wisc.edu/~paradyn.
W. E. Nagel, A. Arnold, M. Weber, H.-C. Hoppe, and K. Solchenbach. VAMPIR: Visualization and Analysis of MPI Resources. Supercomputer 63, XII(1):69–80, January 1996. http://www.pallas.de/pages/vampir.htm.
Tutorial on OpenMP Parallel Programming, 1998. http://www.openmp.org.
D. Ridge, D. Becker, P. Merkey, and T. Sterling. Beowulf: Harnessing the Power of Parallelism in a Pile-of-PCs. In Proceedings, IEEE Aerospace, 1997. http://www.beofulf.org.
L. Smarr. Special issue on computational infrastructure: Toward the 21st century. Comm. ACM, 40(11):28–94, 11 1997.
The Speedshop performance analysis tool. http://www.sgi.com.
Pointers to tools, modules, APIs and documents related to parallel performance analysis. http://www.fz-juelich.de/apart/wp3/modmain.html.
The Xprofiler performance analysis tool. http://www.ibm.com.
The XPVM performance analysis tool. http://www.netlib.org/utk/icl/xpvm/xpvm.html.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Brunst, H., Winkler, M., Nagel, W.E., Hoppe, HC. (2001). Performance Optimization for Large Scale Computing: The Scalable VAMPIR Approach. In: Alexandrov, V.N., Dongarra, J.J., Juliano, B.A., Renner, R.S., Tan, C.J.K. (eds) Computational Science - ICCS 2001. ICCS 2001. Lecture Notes in Computer Science, vol 2074. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45718-6_80
Download citation
DOI: https://doi.org/10.1007/3-540-45718-6_80
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42233-4
Online ISBN: 978-3-540-45718-3
eBook Packages: Springer Book Archive