Thomas Bressoud worked outside of academia both before and after receiving his Ph.D. from Cornell University in 1996. Before his time in Ithaca, Dr. Bressoud spent 7 years working for MIT Lincoln Laboratory in real-time radar systems. After his Ph.D., Dr. Bressoud worked for a startup, Isis Distributed Systems, and, through the acquisition frenzy of the 90’s, was working for Lucent Technologies when he transferred to their research arm, Bell Laboratories in Murray Hill, NJ.
In 2002, Dr. Bressoud joined the Denison faculty. He enjoys teaching courses across the undergraduate curriculum, from introductory courses exposing students from across campus to the fundamental ideas of computer science to upper level electives. In alignment with his research interests, he particularly enjoys teaching systems classes, like Networking and Operating Systems, and a special topics course in parallel programming and high performance systems.
Learning & Teaching
My research interests are within the systems area of computer science and can be partitioned into the subareas of (i) fault-tolerance, (ii) networking and inter-domain routing, and (iii) high performance computing. Where possible, I enjoy the pursuit of research at the intersections of these areas. Within fault tolerance, I specialize in "minimally invasive" techniques of transforming non-fault-tolerant systems and protocols and legacy applications into fault-tolerant versions while minimizing impact on the application. In inter-domain routing I work in connection-oriented fault tolerant protocols and in load-balancing techniques for BGP, and in high performance computing, I study the performance of distributed (cluster) systems as we both scale and introduce failures into the system.
- L. Alvisi, T. Bressoud, A. El-Khashab, P. Weidmann. Method, Apparatus And System For Maintaining Connections Between Computers Using Connection-Oriented Protocols. U.S. Patent Number 7,673,038, Awarded March 2, 2010.
- Thomas C. Bressoud and Michael A. Kozuch, Cluster Fault-Tolerance: An Experimental Evaluation of Checkpointing and MapReduce through Simulation. In Proceedings of the IEEE International Conference on Cluster Computing. New Orleans, LA. Oct. 2009.
- Dmitrii Zagorodnov, Keith Marzullo, Lorenzo Alvisi, and Thomas C. Bressoud. Practical and Low-Overhead Masking of Failures of TCP-Based Servers. ACM Transactions on Computer Systems, 27(2):80-107, May 2009.
- Thomas C. Bressoud and M. Frans Kaashoek (MIT). Chairs’ Report on Twenty-First ACM Symposium on Operating Systems Principles. ACM Operating Systems Review, 42(3): pp123-126, April 2008.
- Thomas C. Bressoud, Rajeev Rastogi, Mark A. Smith. System and Method for Optimally Configuring Border Gateway Selection for Transit Traffic Flows in a Computer Network. U.S. Patent Number 7,197,040, Awarded March 27, 2007.
- Towards a MapReduce Application Performance Model, Jared Gray and Thomas C. Bressoud, Proceedings of the 2012 Midstates Conference on Undergraduate Research in Computer Science and Mathematics (MCURCSM 2012), Delaware, OH.
- The Performance Characteristics of MapReduce Applications on Scalable Clusters, Kenneth Wottrich and Thomas C. Bressoud, Proceedings of the 2011 Midstates Conference on Undergraduate Research in Computer Science and Mathematics (MCURCSM 2011), Granville, OH.
- Investigating Cluster Fault Tolerance: Web Interfaces, Simulation, and Extension, Sarah Mercier and Thomas C. Bressoud. Anderson Summer Research and Denison Summer Scholar Poster Session, 2009.
- The Performance Cost of Virtual Machines on Big Data Problems in Compute Clusters, Neal Barcelo, Nick Legg, and Thomas C. Bressoud, Proceedings of the 2008 Midstates Conference on Undergraduate Research in Computer Science and Mathematics (MCURCSM 2008), Wooster, OH. Also presented to the Big Data research group at Intel Research, Pittsburgh.