Computation
The Scientific Computing and Visualization group (SCV) administers advanced, multiprocessor supercomputing systems for research computing. These Scientific Computing Facility (SCF) systems are available to all University faculty, their students, and their collaborators for research and for educational use in courses related to computational science. Our staff of systems administrators, programmers, trainers, and consultants are available to help with the use of the systems and to provide programming assistance for serial and parallel applications. A broad set of software packages is available.
The use of high-performance computing systems can dramatically reduce the time to obtain solutions for computationally and data intensive problems. High performance, high availability storage is shared across all of the systems, thereby reducing the time and complexity of data access.
High Performance Computing Resources
The newest system, just coming on line in mid 2013, is the Shared Computing Cluster (SCC) at the Massachusetts Green High-Performance Computing Center (MGHPCC) in Holyoke, MA. This is a large Linux cluster with significantly increased computing power and storage capacity. We expect this already large cluster to grow substantially over the next decade.
Since December, 2007 the SCF has also included the Katana Linux Cluster, which has been expanded many times in the years since and is made up of machines of several configurations. The cluster currently has 173 nodes with a combined 1572 processors. The Katana Cluster runs the BULinux 5.0 operating system. The more modern elements of this system will eventually be moved to Holyoke and integrated into the SCC.
The final high performance computing element of the SCF is the IBM Blue Gene, first installed in May, 2005. This system comprises 1024 compute nodes, each containing a dual-processor PowerPC chip and 512 MB of memory. The peak performance of this system is 5.7 TFLOPS (trillion floating point operations per second). This system was ranked 59th in the June 2005 TOP500 list of the world’s fastest supercomputers. This system will be decommissioned at the end of the 2013 calendar year.
More details on all of these computing resources is available in our Technical Summary.
Please go to the SCF Accounts page if you are interested in getting access to these specialized computing resources. If you need resources beyond what BU can provide, you also may want to look into the XSEDE (eXtreme Science and Engineering Discovery Environment) initiative of the National Science Foundation.
Service Models
Several service models are available for the systems maintained by SCV. The available service models are shared, buy-in, dedicated, and co-location.
The great majority of people use these systems under the shared service model. This model applies to equipment which is acquired with a significant university contribution, either fully funded centrally or under an institutional-level infrastructure grant leveraged by substantial matching funds. These computing resources are offered without charge to all faculty and research staff on a fair-share allocation basis. Allocations are reviewed by a committee of faculty and staff. The majority of elements of all of the computing systems described above are under the shared service model.
For those groups with special requirements, please talk with us about our other service models. In particular, right now the 2013 Buy-in Program Call for Ownership is running if you wish to purchase subsidized computing and/or storage systems, priority allocated for your own use.
Storage, Software, and Consulting
Several options for Data Storage and Archiving are available for all of these systems, with a greatly expanded online storage capacity of over 450 TB (usable) of disk space going online at the MGHPCC very soon.
These systems offer a wide range of software packages and utilities including programming languages, parallelizing compilers, mathematical and scientific libraries, graphics and visualization software, statistical packages, and discipline-specific application packages.
Our consulting staff, both scientific programmers and systems administrators, are available to help you with using all of our computational facilities at no cost so please don’t hesitate to contact us for help.
Additional Help
If this page did not answer your questions, please consult our FAQ or send email to help@scv.bu.edu.