CyberInstitute Projects

New York State Grid Overview

Grid represents the next generation of clustering that is revolutionizing science and engineering through cyberinfrastructure. Workloads can be spread across multiple processors and are not bound by a single platform or geographic location. Harnessing this emerging and expanding technology allows geographically distributed and independently operated resources to be linked together in a transparent fashion. Processing power can be borrowed from any type of machine, from desktop computers to High Performance Computing clusters. The amounts of calculation and the quantity of information that can be stored, transferred, and used is exploding at an almost disruptive rate. The vast improvements in raw computing power, storage capacity, algorithms, and networking capabilities has paved the way for a new generation of computational models that approach scientific and engineering problems with a deeper perspective. Online digital instruments and wide-area arrays of sensors are providing more comprehensive, immediate, and high-resolution measurements. Scientists in many disciplines have begun revolutionizing their fields by using computational and data grids, digital data, and networks to extend or replace traditional techniques. The use of intelligent network storage empowers scalable grid computing environments providing a dynamic and non-disruptive growth of the storage environment. We believe the power of the Grid lies not only in the aggregate computing power, data storage, and network bandwidth that can be readily be brought to bear on a particular problem, but on its ease of use.

The emphasis of the development of the New York State Advanced Computational Data Center Grid (NYS ACDC Grid) should be focused on four areas:

• Core Grid Technology - development of secure and high-performance common grid technology; integration of high-performance sensors; electron microscopes; real-time analysis; data sharing infrastructure.
• Grid Computing Technology - identification and solution of research and development projects; implementation of grid technologies; dynamic resource classification for fast processing on homogeneous parallel platforms; distributed computation for individual computation tasks on heterogeneous platforms.
• Data Grid Technology - development of technology for building a common core database platform on the grid; development of distributed search technology utilizing heterogeneous databases; large-scale distributed text searching; intelligent storage controller development.
• Remote Data Collection Technology - remote data collection, analysis, and sharing utilizing high-performance networks and experimental devices; remote interaction with high-performance sensors; remote collection system for protein crystallographic structure analysis.

The Grid Computing Group has enabled the following applications:

• Shake-and-Bake(SnB) - Molecular Structure Determination Application
• Buffalo-and-Pittsburgh (BnP) - SnB and PHASES Complete Protein Phasing
• Ostrich - Optimization and Parameter Estimation Tool for Groundwater Modeling
• Aseismic Design & Retrofit (EADR) - Passive Energy Dissipation System for Designing Earthquake Resilient Structures
• Princeton Ocean Model Great Lakes (POMGL) - Great Lakes Hydrodynamic Circulation Model
• Titan - Computational Modeling of Hazardous Geophysical Mass Flows
• Chem - Commercial Quantum Chemistry Software Package
• NWChem - Computational Chemistry Software Package developed and maintained by DOE
• Split - Modeling Groundwater Flow with the Analytic Element Method

The CCR Grid Computing Group fosters University, New York State, and International grid collaborations

• University and Metropolitan Grid Partners:UB Department of Media Study, Civil, Structural and Environmental Engineering, Structural Biology, and Computer Science and Engineering; Schools of Dental Medicine and Management; Computing and Information Technology; Science and Engineering Node Services; Hauptman-Woodward Institute, Canisius College
• New York State Grid Partners: SUNY-Binghamton, SUNY-Geneseo, Columbia University, Niagara University, AMDeC, SUNY-Albany
• Grid3: An Application Grid Laboratory for Science Participants (10/2003)
  • National Laboratories and Supercomputing Centers: Argonne, Brookhaven, Fermi National Accelerator Laboratory (FNAL), National Energy Research Scientific Computing Center, San Diego Supercomputing Center (SDSC), UB Center for Computational Research
  • Universities: Boston, Caltech, Chicago, Florida/Gainesville, Florida International, Hampton, Indiana, Iowa, Johns Hopkins, Michigan, New Mexico, Oklahoma, Penn State, Purdue, Rice, Southern Methodist, Texas/Arlington, Wisconsin/Madison, Wisconsin/Milwaukee, UC San Diego, Vanderbilt
  • International Universities: Academia Sinica (Taiwan), Kyungpook National University (Korea), National Technological University (Taiwan)
• Open Science Grid
  • National Laboratories and Supercomputing Centers: Brookhaven, Fermi National Accelerator Laboratory (FNAL), San Diego Supercomputing Center (SDSC), NERSC, Pittsburgh Supercomputing Center (PSU), Texas Advanced Computing Center (TACC), Stanford Linear Accelerator Center (SLAC), UB-CCR
  • Universities: Caltech, Chicago, Duke, Florida/Gainesville, Indiana, Texas Tech, Purdue,  Iowa, Wisconsin/Milwaukee, Oklahoma, U Texas-Austin, Boston, SUNY-Albany, New Mexico, SUNY-Binghamton, Wisconsin/Madison, Vanderbilt, Hampton, Nebraska