Computing Cluster

In 2016, Dr. Olsen and Dr. Binkley from the computer science department, along with Dr. Albrecht from Chemistry and Dr. Schwartz from Economics, had an NSF MRI grant proposal funded to purchase a university-wide computer cluster. A computing cluster is essentially a networked set of many computers, which can be used for computationally expensive tasks. Our computing cluster has is powered by Linux (CentOS 7), and has

676 CPU cores spread across 29 compute nodes,
10 nvidia Tesla K80 GPUs,
256GB RAM per node, 7.4 terabytes of RAM in total,
146 terabytes of disk storage,
25 terabytes of fast SSD storage, and
56 gigabit Infiniband network fabric

This computing cluster started its service in January 2017, and is available for any Loyola faculty member who needs access for a research project. Students working on research with faculty who use the cluster may also gain access to the cluster for the research project. Any faculty member who believes the cluster will be useful for their research, but isn’t sure, can contact Dr. Olsen to discuss if it could help their research. Any faculty member who wants access to the cluster, or needs assistance with using it, can contact System Administrator George Hall for an account.

The usage policies and information on how to connect to and run jobs on the cluster can be found on the cluster information page, which is only accessible from on-campus computers. Additionally, you can only SSH into the computing cluster from a campus computer, for security purposes.

As of 2019, the cluster has lead to the following publications, in addition to unlisted presentations and works in progress:

C. Maalouf, M. Olsen, M. Raunak (2019). Combinatorial Testing For Parameter Exploration. Proceedings of the 2019 Winter Simulation Conference (WSC).
D. Binkley, N. Gold, S. Islam, J. Krinke, S. Yoo (2019). A comparison of tree- and line-oriented observational slicing. Empirical Software Engineering. 10.1007/s10664-018-9675-9.
D. H. K. Hoe (2019). “Bayesian Inference Using Stochastic Logic: A Study of Buffering Schemes for Mitigating Autocorrelation,” International J. of Approximate Reasoning, vol. 112, pp. 4-21. Published online on May 22, 2019.
D. H. K. Hoe, and C. Pajardo II (2019). Implementing Stochastic Bayesian Inference: Design of the Stochastic Number Generators, Proceedings of IEEE 62th International Midwest Symposium on Circuits and Systems, pp. 1105-1109.
J. Schwartz (Accepted). Job Competition, Human Capital, and the Lock-in Effect: Can Unemployment Insurance Efficiently Allocate Human Capital. B.E. Journal of Macroeconomics.
A. Samuel, J. Schwartz. (2019). Product Market Competition’s Effect on Earnings Management When Audit Quality Is Endogenous: Theory and Evidence.Review of Law and Economics, 1–35. https://doi.org/10.1515/rle-2018-0044
D. Lawrie and D. Binkley (2018). On the Value of Bug Reports for Retrieval-based Bug Localization. New Ideas and Emerging Results Track, 2018 IEEE International Conference on Software Maintenance and Evolution (ICSME), Madrid, 2018, pp. 524-528. doi: 10.1109/ICSME.2018.00048
M. Olsen, J. Laspesa, T. Taylor D'Ambrosio (2018). On Genetic Algorithm Effectiveness for Finding Behaviors in Agent-based Predator Prey Models. Proceedings of the Summer Simulation Multi-Conference (SummerSim'18).
D. Binkley, D. Lawrie, C. Morrell (2017). The need for software specific natural language techniques. Journal of Empirical Software Engineering. 23 (4), 2398.
D. W. Binkley, N. Gold, S. S. Islam, J. Krinke, S. Yoo (2017). Tree-Oriented vs. Line-Oriented Observation-Based Slicing. Proceedings of SCAM. 21.
D. H. K. Hoe, “Bayesian Inference using Spintronic Technology: A Proposal for an MRAM-based Stochastic Logic Gate,” Proceedings of IEEE 60th International Midwest Symposium on Circuits and Systems, 2017.

For access to the publications, please see the faculty member's websites or contact them.