Jennifer Schopf's Thesis

Jennifer M. Schopf, Performance Prediction and Scheduling for Parallel Applications on Multi-user Clusters, UCSD CS Dept Tech Report #CS98-607, December 1998.

My thesis work involves developing structural performance models for parallel distributed applications. I have extended this work to allow for stochastic input parameters, that is, values for system and application characteristics that have a range and a distribution associated with them. In addition, I am interested in showing how such models can be used to achieve performance-efficient schedules.

In order to PRINT my thesis you may have to do it a chapter at a time.

Full thesis in PDF, 3.4 meg Postscript files for my thesis:


jms@mcs.anl.gov