Selecting simulation models when predicting parallel program behavior
| Document type: | Conference Papers |
|---|---|
| Peer reviewed: | Yes |
| Author(s): | Magnus Broberg, Lars Lundberg, Håkan Grahn |
| Title: | Selecting simulation models when predicting parallel program behavior |
| Conference name: | ISCA 15th International Conference on Parallel and Distributed Computing Systems |
| Year: | 2002 |
| Pagination: | 165-172 |
| ISBN: | 1-880843-44-7 |
| Publisher: | INTERNATIONAL SOCIETY COMPUTER S & THEIR APPLICATIONS (ISCA) |
| City: | LOUISVILLE, KY |
| ISI number: | 000179776300027 |
| Organization: | Blekinge Institute of Technology |
| Department: | Department of Software Engineering and Computer Science (Institutionen för programvaruteknik och datavetenskap) Dept. of Software Engineering and Computer Science S-372 25 Ronneby +46 455 38 50 00 http://www.bth.se/eng/ipd/ |
| Language: | English |
| Abstract: | The use of multiprocessors is an important way to increase the performance of a parallel program. This means that. the program has to be parallelized to make use of the multiple processors. The parallelization is unfortunately not an easy task. Development tools supporting parallel programs are important. Further, it is the customer that decides the number of processors in the target machine, and as a result the developer has to make sure that the program runs efficiently on any number of processors. Many simulation tools support the developer by simulating any number of processors and predict the performance based on a uniprocessor execution trace. This popular technique gives reliable results in many cases. Based on our experience from developing such a tool, and studying other (commercial) tools, we have identified three basic simulation models. Due to the flexibility of general purpose programming languages and operating systems, like C/C++ and Sun Solaris, two of the models may cause deadlock in a deadlock-free program. Selecting the appropriate model is difficult, we show that the three models have significantly different accuracy when using real world programs. Based on the findings we present a practical scheme when to use the models. |
| Subject: | Software Engineering\General |
| Keywords: | simulation models, trace-driven simulation, development tool, performance prediction |
