University of Florida
High-Performance Computing Center
Campus Research Grid
The campus research grid is a network of different computing clusters around campus to enable the sharing of computational resources, presenting them as a single resource for solving large computational and data intensive problems. The University of Florida is striving to create a system that does this for the faculty, staff, and students of the university.
Grid computing is different from computing on a server or cluster. The focus of grid computing is to provide access to compute cycles from a large pool of available resources. As a result, one usually does not obtain a standard in a grid system, but instead you get access to the resources and can store files. As these files are general visible to other grid users, you should not count on the files being either private or permanent.
UF HPC Clusters
- UF HPC Center
- Physics
- Quantum Theory Project (QTP)
- College of Education (COE)
- Advanced Computing and Information Systems Laboratory (ACIS)
- McKnight Brain Institute (MBI)
Current Layout
The Campus Research Grid is designed to provide high speed communication
between the different clusters distributed around campus. Data storage
servers are also distributed
(concept)
throughout this network in order to provide repositories for researchers
to access when doing their research.
Concept Drawing
Grid Usage and Access
In order to use a grid, you need to have access to the grid via an account on the grid system. Once that is in place, you prepare input and data files for your project, upload them to a storage resource on the grid, then submit a job to the grid that will use the data you have uploaded. Once the job has finished it will be necessary to review the results and move any output files you wish to keep to a permanent storage location.
- Obtaining a UF Grid Certificate
- Creating a UF GridPort Account
- Using GridPort to run Gaussian
- Available software on the UF Grid
