Performance prediction for complex parallel applications
- Hannover Univ. (Germany). Inst. fuer Rechnerstrukturen und Betriebssysteme
- Oak Ridge National Lab., TN (United States)
Today`s massively parallel machines are typically message-passing systems consisting of hundreds or thousands of processors. Implementing parallel applications efficiently in this environment is a challenging task, and poor parallel design decisions can be expensive to correct. Tools and techniques that allow the fast and accurate evaluation of different parallelization strategies would significantly improve the productivity of application developers and increase throughput on parallel architectures. This paper investigates one of the major issues in building tools to compare parallelization strategies: determining what type of performance models of the application code and of the computer system are sufficient for a fast and accurate comparison of different strategies. The paper is built around a case study employing the Performance Prediction Tool (PerPreT) to predict performance of the Parallel Spectral Transform Shallow Water Model code (PSTSWM) on the Intel Paragon. 13 refs., 6 tabs.
- Research Organization:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE Office of Energy Research, Washington, DC (United States); Alexander von Humboldt-Stiftung, Bonn (Germany)
- DOE Contract Number:
- AC05-96OR22464
- OSTI ID:
- 467122
- Report Number(s):
- CONF-970477-2; ON: DE97004729
- Resource Relation:
- Conference: IPPS `97: international parallel processing symposium, Geneva (Switzerland), 1-5 Apr 1997; Other Information: PBD: [1997]
- Country of Publication:
- United States
- Language:
- English
Similar Records
The message passing version of the parallel Community Climate Model
A study of application sensitivity to variation in message passing latency and bandwidth