Identifier

etd-04202011-091322

Degree

Doctor of Philosophy (PhD)

Department

Computer Science

Document Type

Dissertation

Abstract

Distributed supercomputers have been widely used for solving complex computational problems and modeling complex phenomena such as black holes, the environment, supply-chain economics, etc. In this work we analyze the use of these distributed supercomputers for time sensitive data-driven applications. We present the scheduling challenges involved in running deadline sensitive applications on shared distributed supercomputers running large parallel jobs and introduce a ``data-aware'' scheduling paradigm that overcomes these challenges by making use of Quality of Service classes for running applications on shared resources. We evaluate the new data-aware scheduling paradigm using an event-driven hurricane simulation framework which attempts to run various simulations modeling storm surge, wave height, etc. in a timely fashion to be used by first responders and emergency officials. We further generalize the work and demonstrate with examples how data-aware computing can be used in other applications with similar requirements.

Date

2011

Document Availability at the Time of Submission

Release the entire work immediately for access worldwide.

Committee Chair

Allen, Gabrielle

DOI

10.31390/gradschool_dissertations.2070

Share

COinS