Table of Contents

Eagles Cluster: An Infrastructure for Multidisciplinary Scientific Computing and Simulation

This project is supported by an NSF award CNS-1059376 titled as II-New: A Compute and Storage Cluster for Multidisciplinary Research on Computer Systems and Scientific Simulations.

Contact: Dr. Weikuan Yu

Project Mission

This project is carried out by a team of scientific computing researchers, computer systems researchers, and computer science educators. A cutting-edge compute and storage cluster is built to enable multidisciplinary research on computer systems and scientific simulations. This cluster consists of a stable compute partition with GPGPU processors for scientific computing and an experimental storage partition for computer systems research. Leading groups at Auburn University in the areas of computational atomic physics, climate and ecosystem modeling, and computer science plan to use this computing infrastructure in their research.

Enabling Research and Education Activities

This research infrastructure strengthens computer science research on parallel programming models, parallel I/O, file systems, storage, and data-intensive analytics. In addition, it cultivates new multidisciplinary research projects on computational climate modeling, computational atomic physics, and applied computer science. Furthermore, it allows better pedagogical methods and education activities to attract more students, particularly from underrepresented groups, for computing careers. The project's research is expected to result in optimized scientific codes, fine-grained ecosystem simulations, and accurate environmental change predictions. Research results will be published in computational and computer science journals and international conferences. Open source software packages from this project will be released for community services.

Multidisciplinary CUDA Teaching Center

People

  1. Bin Wang
  2. Kevin Vasko
  3. Patrick Carpenter
  4. Hai Pham

Research Publications Enabled by this cluster

  1. Zhuo Liu, Bin Wang, Patrick Carpenter, Dong Li, Jeffrey S. Vetter, Weikuan Yu. “PCM-Based Durable Write Cache for Fast Disk I/O,” MASCOTS, 2012.
  2. Yu W., Wu K.J., Ku W.S., Xu C., Gao J.. “BMF: Bitmapped Mass Fingerprinting for Fast Protein Identification,” International Conference on Cluster Computing (Cluster11), 2011.
  3. Dong Li, Jeffrey S. Vetter, Weikuan Yu. “Classifying soft error vulnerabilities in extreme-scale scientific applications using a binary instrumentation tool,” Supercomputing, 2012.
  4. Tian Y.. “SRC: Enabling Petascale Data Analysis for Scientific Applications Through Data Reorganization,” Research Poster in the International Conference on Supercomputing (ICS'11). First Prize Award., 2011.
  5. Gu B., Yu W., Kwak Y.. “Communication and Computation Overlap through Task Synchronization in Multi-Locale Chapel Environment,” The 3rd International Workshop on IT Service and Cloud Computing (ISCC'11), 2011.
  6. Tipparaju, V; Apra E.; Yu, W.; Que X.; Vetter J.S.. “Runtime Techniques to Enable a Highly-Scalable Global Address Space Model for Petascale Computing,” International Journal of Parallel Programming, v.40, 2012, p. 633.
  7. Wang Y., Que X., Yu W., Goldenberg D., Sehgal D.. “Hadoop Acceleration through Network Levitated Merge,” International Conference for High Performance Computing, Networking, Storage and Analysis (SC11), 2011.
  8. Yuan Tian, Scott Klasky, Weikuan Yu, Hasan Abbasi, Bin Wang, Norbert Podhorszki, Ray W. Grout, Matthew Wolf. “SMART-IO: SysteM-AwaRe Two-Level Data Organization for Efficient Scientific Analytics,” MASCOTS, 2012.
  9. Liu Z., Zhou J., Yu W., Wu F., Qin X., Xie C.S.. “MIND: A Black-Box Energy Consumption Model for Disk Arrays.,” The First International Workshop on Energy Consumption and Reliability of Storage Systems (ERSS'11), 2011.
  10. Que X., Yu W., Tipparaju V., Vetter J.S., Wang B.. “Network-Friendly One-Sided Communication Through Multinode Cooperation on Petascale Cray XT5 Systems,” IEEE International Symposium on Cluster Computing and the Grid (CCGrid'11), 2011.
  11. Yu W., Tipparaju V., Que X., Vetter J.S.. “Virtual Topologies for Scalable Resource Management and Contention Attenuation in a Global Address Space Model on the Cray XT5,” IEEE International Conference on Parallel Processing (ICPP'11), 2011.
  12. Li D., Vetter J.S., Marin G., McCurdy C., Cira C., Liu Z., Yu W.. “Identifying Opportunities for Byte-Addressable Non-Volatile Memory in Extreme-Scale Scientific Applications,” International Parallel and Distributed Processing Symposium (IPDPS'12), 2012.
  13. Tian Y., Klasky S., Abbasi H., Lofstead G., Grout R., Podhorszki N., Liu Q., Wang Y., Yu W.. “EDO: Improving Read Performance for Scientific Applications Through Elastic Data Organization.,” International Conference on Cluster Computing (Cluster11), 2011.
  14. Dong Li, Jeffrey S. Vetter, Gabriel Marin, Collin McCurdy, Cristian Cira, Zhuo Liu, Weikuan Yu. “Identifying Opportunities for Byte-Addressable Non-Volatile Memory in Extreme-Scale Scientific Applications.,” IEEE International Parallel & Distributed Processing Symposium, 2012.
  15. Tian Y., Yu W., Vetter J.S.. “RXIO: Design and Implementation of High Performance RDMA-capable GridFTP,” International Journal on Computers and Electrical Engineering, 2011.
  16. Yu W., Que X., Tipparaju V., Vetter J.S.. “HiCOO: Hierarchical Cooperation for Scalable Communication in Global Address Space Programming Models on Cray XT Systems,” Journal of Parallel and Distributed Computing, 2012.

Acknowledgements

This work is funded in part by National Science Foundation awards CNS-1059376 and by an NVIDIA gift for the CUDA teaching center.

Course Material

If you are interested in course material from our CUDA teaching courses, please visit COMP7330 Fall 2012 or COMP7330 Fall 2014.