|
Description: |
We propose a model for describing and predicting the performance of
parallel numerical multilevel software on distributed memory architectures
within a multi-cluster environment. The goal of the model is to allow
reliable predictions to be made as to the execution time of a given code
on a large number of processors of a given parallel system, and on a
combination of systems, by only benchmarking the code on small numbers of
processors. We analyze the performance of our model with respect to the
information available regarding the parallel system and the code used. In
addition to reporting the results applied to benchmark multigrid codes, we
also provide results which demonstrate that this performance is also
achieved when applied to a practical multilevel engineering code.
Area(s):
|
