University of Southern Mississippi Gains Campus-Wide HPC Cluster for Research

Share Article

The University of Southern Mississippi has a new HPC Cluster called Magnolia that will facilitate research and training in computational and data-enabled science and engineering.

The University of Southern Mississippi has acquired a supercomputer to support research and training in computational and data-enabled science and engineering. The acquisition was made possible through a $622,986 Major Research Instrumentation grant from the National Science Foundation.

This new campus-wide resource, which will be called Magnolia, is a high performance computing cluster with 1,896 cores for all compute nodes (and an additional 7,168 CUDA cores for the graphics processing units or GPU nodes). The cluster will facilitate student learning and research in four main areas including Materials Science, Biological Sciences, Coastal and Marine Sciences, and Data Mining, Bioinformatics, and Geoinformatics.

Gopinath Subramanian, Assistant Professor of Polymer Science & Engineering, is the Principal Investigator for the project, assisted by co-principal investigators Jeremy Wiggert, Jacob Schaefer, Chaoyang (Joe) Zhang and Jeffrey Wiggins.

The HPC cluster, built by Advanced Clustering Technologies, is comprised of standard compute nodes, high-core compute nodes, large memory nodes, and nodes equipped with GPUs. The system enables academicians, researchers, and students to pursue research and education in areas of national and international importance, such as climate change, coastal hazard mitigation and resilience building efforts, advanced manufacturing, natural resource management, the materials genome initiative, and big data science.

Access to the cluster’s computational resources will be made available to students, staff, and faculty at the University of Southern Mississippi and regional community colleges and high schools.

Share article on social media or email:

View article via:

Pdf Print

Contact Author

Wade Sisson
@ACT_CLUSTER
Follow >
Visit website