GP-ENGINE
NSF CC* Regional ComputING
University of Missouri
PI - J. Alex Hurt
Assistant Research Professor
Center for Geospatial Intelligence
&
Dept. of Electrical Engineering and Computer Science
NSF Office of Advanced Cyberinfrastructure (OAC)
CC* Regional Computing: Great Plains Extended Network of GPUs for Interactive Experimenters
(GP-ENGINE)
The GP-ENGINE project advances the adoption of advanced computing and data resources in the Great Plains Network region. This project will increase the number of researchers and students served by both local and national computing resources, strengthen the capacity and capabilities of campus research computing professionals, and expand the regional capacity for research. Researchers will be able to transition nascent ideas and codes into advanced computing code using locally provisioned advanced computing resources. These codes can be later executed on national high-throughput computing resources. These successes will enhance institutional buy-in for sustainable regional and national research computing systems.
NSF Award OAC #2322218
Check out the GP-ENGINE Usage Dashboard: http://gp-engine.org/
Thanks to Derek and the UN-L team!
About the GP-ENGINE compute nodes
4x Nvidia A100
320GB GPU RAM
27,648 CUDA cores
2x AMD 7713
128 Cores / 256 Threads
1 TB RAM
2x - 25Gbe NIC
Support for Researcher GPU Workbench to develop research codes that can migrated to HTC environments.
Jupyter Containers for AI/ML, Data Science, and STEM w/ GUI as needed
Interactive learning environment!
NVIDIA MIG (7x4x11) = 308 vGPU
Can divide into 7 vGPU per A100
Each node can be 28 vGPU
Training researchers to use GP-ENGINE
Want to Acknowledge GP-ENGINE in a publication? Please use this, or similar, language.
"Computational resources for this research have been supported by the NSF National Research Platform, as part of GP-ENGINE (award OAC #2322218)."
GP-ENGINE Team
J. Alex Hurt (PI)
Research Assistant Professor
Center for Geospatial Intelligence, University of Missouri
Derek Weitzel (Co-PI)
Research Assistant Professor,
University of Nebraska-Lincoln
Co-PI - Prototype NRP (NSF #2112167)
Dan Andresen (former Co-PI)
Professor - Computer Science,
Kansas State University
PI - GP-ARGO (AOC #2018766)
Brian Burkhart (Co-PI)
Chief Technology Officer,
OneNet/OK State Regents for Higher Ed.
Paul Kern (Co-PI)
Chief Information Security Officer,
South Dakota State University
Elon Turner (SP)
Executive Director
ARE-ON
Kevin Brandt (SP)
Assistant Vice President for Research Cyberinfrastructure,
South Dakota State University
Ryan Johnson (SP)
Director of Research Computing,
The University of South Dakota
Mark Bookout
Direction of IT - Research Support Services
University of Missouri System
Jenn Nixon
Senior IT Mgr - Research Support Services
Missouri University of Science & Technology
Matthew Keeler
Associate Director of IT- Research Support Services
University of Missouri
Pallavi Gupta (GRA)
Graduate Research Assistant (Informatics) and Graduate Teaching Assistant (Data Science)
University of Missouri
Anes Ouadou (GRA)
Graduate Research Assistant (Computer Science) and Graduate Teaching Assistant (Data Science)
University of Missouri
GPN
The greatest collaborative regional research and education network!
Resource Links
MU High-Performance Data Intensive Computing Systems Lab - NPR Nautilus Resources
https://github.com/MU-HPDI/nautilus
More Links Coming Soon
Related NSF Projects
CC* Great Plains CyberTEAM
The Great Plains CyberTeam is a distributed mentor-mentee workforce development program that works with institutions within the region that have growing Cyberinfrastructure needs; participants work together to determine the institution’s research computing needs and work through the process from identification to implementation, developing best practices along the way, to enhance campus capabilities that enable research.
CC* Great PLAINS ARGO
GP-ARGO: The Great Plains Augmented Regional Gateway to the Open Science Grid
The goals of GP-ARGO are expanding GPN CyberTeam’s model by training researcher-facing staff and deploying 15-20 HTC compute nodes across the region. These nodes function as both gateways to local HPC resources and OSG.
Watch HERE for FUTURE LINKED Projects
...from the Great Plains Network and our state and national partners!