Enlightened: Dynamic E-science Applications Driving Adaptive Optical Control Plane and Compute Resources
The modern explosion of scientific data available, coupled with its wide geographic distribution, has rapidly overwhelmed researchers’ ability to manage, move, store and analyze data. Enlightened studies concrete application projects in astrophysics, coastal modeling, petroleum engineering and atmospheric research that require progress in network technologies and tools that utilize them. These applications are increasing researchers’ reliance on coordinated resource sharing and problem solving in dynamic, multi-institutional virtual organizations.
While much progress has been made toward developing grid technologies for such applications, one underdeveloped area is the underlying network technologies that make grids and their applications truly effective. The Enlightened project takes a novel approach and defines the network through the set of services it can offer and that can be controlled by the application. The project will create an integrated environment by placing the network at the same level as the compute, storage, graphics, instruments and other resources.
In order to test and develop the services needed by the applications, a nationwide footprint 10Gig capacity testbed running over The National Lambda Rail was created for experimentation. LONI is an integrated part of the Enlightened testbed and is used as a laboratory for networking and grid research in the project.
CCT Project leaders
o Dr. Gabrielle Allen (CCT/Computer Science)
o Dr. Edward Seidel (CCT/Physics)
o Dr. Seung-Jong Park (CCT/Computer Science)
o Dr. Jon MacLaren
o Cornelius Toole (CCT)
o Yaaser Mohammed (CCT)
The Campus Connection
CCT researchers are using LSU’s resources through the Louisiana Optical Network Initiative (LONI) to enable testbeds for the partner institutions.
Enlightened computing is sponsored by the National Science Foundation (grant # 0509465).
North Carolina State University, http://www.ncsu.edu/
Renaissance Computing Institute (RENCI), http://renci.org
• T. Goodale, G. Allen, G. Lanfermann, J. Massó, T. Radke, E. Seidel, J. Shalf, The Cactus Framework and Toolkit: Design and Applications, Vector and Parallel Processing -- VECPAR 2002, 5th International Conference, Lecture Notes in Computer Science, Springer, Berlin, 2003.
• [Gordon Bell Prize] G. Allen, T. Dramlitsch, I. Foster, N. Karonis, M. Ripeanu, E. Seidel, B. Toonen: Supporting Efficient Execution in Heterogeneous Distributed Computing Environments with Cactus and Globus, Proceedings of Supercomputing 2001, Denver, USA.