A scheduling framework for dynamically resizable parallel applications

Applications in science and engineering require large parallel systems in order to solve computational problems within a reasonable timeframe. These applications can benefit from dynamic resizing during the course of their execution. Dynamic resizing enables fine-grained control over resource allocation to jobs and results in better system throughput and job turn around time. We have implemented a framework that enabled dynamic resizing of MPI applications. Our framework uses the recently released MPI-2 standard that enables dynamic resizing. The work described in this thesis is part of a larger effort to design and implement a system for supporting and leveraging dynamically resizable parallel applications. We provide a scheduling framework, an API for dynamic resizing and libraries to efficiently redistribute data to new processor topologies.