Structural Prediction Models for
High-Performance Distributed Applications
Jennifer Schopf
Department of Computer Science and Engineering
University of California San Diego
Email: jenny@cs.ucsd.edu
Presented at the
Cluster Computing Conference - CCC '97
We present a structural performance model to predict an
application's performance on a set of distributed
resources. We decompose application performance in
accordance with the structure of the application, that is,
into interacting component models that correspond to
component sub-tasks. Then, using the application profile
and available information as guides, we select models
for each component appropriately. This allows different
modeling approaches for different application components as
needed.
As a proof-of-concept, we have implemented this approach
for two distributed applications, a master-slave genetic
algorithm code and a red-black stencil successive
over-relaxation code. We achieve predictions within 10%
while demonstrating the flexibility this framework allows.
Back to
my page.
Last updated 3/19/97