Cluster Computing - Overview
We maintain several research computing clusters. These powerful computing resources relieve you of the burden of purchasing, provisioning, configuring, and maintaining your own servers. By making these clusters available, we enable you to concentrate on your own specialties, secure in the knowledge that technical resources are available when needed. Our systems can support concurrent use for different projects simultaneously, thereby reducing competition among users for computing resources.
Our computing clusters consist of two main pools of resources:
- Batch servers - Intended for long-running processes that are CPU intensive and able to run in parallel. You use the batch processing utilities to submit you jobs to the batch servers.
- Interactive servers - Intended for large processes that are memory intensive. You use the RCE tools to submit your jobs to the interactive servers.
Our computing clusters use parallel processing to enable faster execution of computation-intensive tasks. Many computing tasks can benefit from implementation in a parallel processing form. A thorough explanation of parallel processing and how to use it is available in Introduction to Parallel Computing, from Lawrence Livermore National Laboratory.
We designed our computing clusters around open standards for reliability, scalability, extensibility, and interoperability. We use hardware from major vendors and a standard, enterprise-grade Linux distribution customized to address the specific needs of our users. Our infrastructure is designed to provide the greatest possible range of options to you, rather than obliging you to restrict yourself to a narrow range of tools and methodologies. We provide a stable platform on which a wide range of technologies can be deployed.
Access to our computing clusters is available to all RCE users. To learn about how to get an RCE account please refer to Research Computing Environment.