1. Mark L. Green, Ph.D. Head of Cyberinfrastructure Center for Computational Research and New York State Grid-Cyberinstitute University at Buffalo The State University of New York

2. University at Buffalo The State University of New York Center for Computational Research 2 Outline  Primary Centers  Enabling Technologies  Modern Data Center Trends  Enabling Services and Applications  Enabling the next generation of discovery

3. University at Buffalo The State University of New York Center for Computational Research 3 Outline  Primary Centers  Enabling Technologies  Modern Data Center Trends  Enabling Services and Applications  Enabling the next generation of discovery

4. University at Buffalo The State University of New York Center for Computational Research 4 State University of New York (SUNY)  New York State includes a variety of private and public institutions, including the State University of New York (SUNY), which is comprised of  64 campuses,  has an enrollment of nearly 414,000 students,  is served by more than 30,000 faculty, and  has annual sponsored research expenditures of approximately $850 million.

5. University at Buffalo The State University of New York Center for Computational Research 5  Leading Academic Supercomputing Site  Enable Research at UB and in WNY  90 Research Groups/25 Departments  Industrial Outreach/Technology Transfer to WNY  Funding  NSF, NIH, NIMA, EPA, Keck, Sloan, NYS, UB, SUNY  IBM, SGI, Sun, HP, Dell, Nortel, Myricom  Total Aggregate Computing Capacity  Current - 22 Teraflops  220 Terabytes of On-line Storage  250 Terabytes of tape storage

6. University at Buffalo The State University of New York Center for Computational Research 6  SGI Altix3700 (0.4TF)  64 Processors (1.3GHz ITF2)  256 GB RAM  2.5 TB Disk  BioACE (bioinformatics)  Sun V880 (3), Sun 6800  Sun 280R (2)  Intel P4 Servers  Sun 3960: 7 TB Disk Storage  HP/Compaq SAN  75 TB Disk; 190 TB Tape  64 Alpha Processors  32 GB RAM; 400 GB Disk CCR Compute/Storage Resources (22 Tflops)  Dell Linux Cluster (10TF)  1600 P4 Processors (3.2 GHz)  Myrinet Interconnect  2000 GB RAM  30 TB SAN; 60 TB Local Disk  Dell Linux Cluster (2.9TF)  600 P4 Processors (2.4 GHz)  Myrinet Interconnect  600 GB RAM; 40 TB Disk  Dell Linux Cluster (6TF)  4036 Processors (PIII 1.2 GHz)  2TB RAM  16 TB SAN; 160TB Local Disk  IBM BladeCenter (3TF)  532 P4 Processors (2.8 GHz)  5TB SAN

7. University at Buffalo The State University of New York Center for Computational Research 7 New York State Center of Excellence in Bioinformatics & Life Sciences  The $1B New York State Centers of Excellence program includes  the Center of Excellence in Bioinformatics & Life Sciences at SUNY-Buffalo,  Syracuse’s Center for Excellence in Environmental and Energy Systems,  Rochester’s Center for Excellence in Photonics and Microsystems,  Albany’s Center for Excellence in Nanoelectronics, and  Stony Brook’s Center for Excellence in Wireless & Information Technology.

8. University at Buffalo The State University of New York Center for Computational Research 8 Buffalo Niagara Medical Campus (BNMC)  The BNMC has developed a unique partnership in which the  University at Buffalo,  Roswell Park Cancer Institute,  Olmsted Center for the Visually Impaired,  Kaleida Health,  Hauptman-Woodward Medical Research Institute,  Buffalo Medical Group Foundation and  Buffalo Hearing & Speech Center  are working in collaboration with the surrounding neighborhoods and local government to cultivate a world-class medical campus in downtown Buffalo.

9. University at Buffalo The State University of New York Center for Computational Research 9

10. University at Buffalo The State University of New York Center for Computational Research 10 New York State Grid-Cyberinstitute  NYS Grass-roots Effort  Hauptman-Woodward Institute  SUNY Binghamton  SUNY Albany  Columbia University  WNY Grid NSF Funded  SUNY Buffalo  Hauptman-Woodward Institute  Niagara University  SUNY Geneseo  Expand Virtual Facility

11. University at Buffalo The State University of New York Center for Computational Research 11 Center Infrastructure and Partners  TeraGrid  Science Gateway using ACDC Grid Portal  UltraLight  Configuring a small test cluster for Buffalo - UltraLight - CERN testing, 1GbE to 10 GbE connections  NYSTAR  Working with NYS support for research, education, and economic development, the New York State Office of Science, Technology and Academic Research  Gen*NY*sis Centers  SUNY Albany and Geneseo University

12. University at Buffalo The State University of New York Center for Computational Research 12 Outline  Primary Centers  Enabling Technologies  Modern Data Center Trends  Enabling Services and Applications  Enabling the next generation of discovery

13. University at Buffalo The State University of New York Center for Computational Research 13 ACDC Grid Portal Gateway

14. University at Buffalo The State University of New York Center for Computational Research 14 Grid-enabling Application Template (GAT)

15. University at Buffalo The State University of New York Center for Computational Research 15 Grid-enabling Application Template (GAT)

16. University at Buffalo The State University of New York Center for Computational Research 16 ACDC Data Grid Database Schema ACDC Grid Data Grid ACDC Grid Data Grid

17. University at Buffalo The State University of New York Center for Computational Research 17 Data Grid API

18. University at Buffalo The State University of New York Center for Computational Research 18 ACDC Grid Dashboard http://osg.ccr.buffalo.edu

19. University at Buffalo The State University of New York Center for Computational Research 19 ACDC Operations Dashboard http://osg.ccr.buffalo.edu

20. University at Buffalo The State University of New York Center for Computational Research 20 Grid Monitoring and Administration Collaborative Environment (Grid MACE)

21. University at Buffalo The State University of New York Center for Computational Research 21

22. University at Buffalo The State University of New York Center for Computational Research 22

23. University at Buffalo The State University of New York Center for Computational Research 23 Outline  Primary Centers  Enabling Technologies  Modern Data Center Trends  Enabling Services and Applications  Enabling the next generation of discovery

24. University at Buffalo The State University of New York Center for Computational Research 24 Modern Data Center  Space  48U Server Racks  Blade Centers, Multi-core Technology  Virtual Machines  Power  AC vs DC Power 20-40% less thermal load and 30% less power consumption with DC power  Cooling  Data Center Thermal Management Infrastructure Floor mounted air handlers  Server Rack Mounted Fans and Heat Exchangers  Water Cooled Server Racks

25. University at Buffalo The State University of New York Center for Computational Research 25 Storage Trends & Solutions  Storage Area Network (SAN)  Convenient, Failover Protection, Mid-level Performance  Network Attached Storage (NAS)  Dedicated, Failover Protection, High-level Performance  Data Rates and File Usage  Databases growing from 1 TB to 10s TB 3 year trending toward 64% growth rate per year  20% of filesystem files account for 80% of storage 3 year trending toward 75% growth rate per year 70% of files not touched 3 months after creation 40-50% of files not touched 6-12 months after creation

26. University at Buffalo The State University of New York Center for Computational Research 26 Storage Trends & Solutions  Move away from Direct Attached Storage (DAS)  Use NAS or SAN solutions  File System Archiving  Email Archiving Eliminate multiple user email databases  Single Instance Storage Eliminate multiple user document copies  Smaller Backup Windows Less media Less infrastructure  Reduce Primary Storage Using Tiered Approach Use filesystem guidelines for usage patterns Designate volatile storage areas Quota and scrub filesystems

27. University at Buffalo The State University of New York Center for Computational Research 27 Computational Trends & Solutions  xU Based Servers  Required by science and engineering drivers  x-core technology ready  Blade Centers  High density  x-core technology ready  Virtual Machines  User can choose entire environment  Operate multiple environments simultaneously  Coprocessors and Field Programmable Gate Arrays (FPGAs)  3-10x more flops using less power

28. University at Buffalo The State University of New York Center for Computational Research 28 Outline  Primary Centers  Enabling Technologies  Modern Data Center Trends  Enabling Services and Applications  Enabling the next generation of discovery

29. University at Buffalo The State University of New York Center for Computational Research 29 Domain Science and Engineering  Shake-and-Bake (SnB)  Molecular Structure Determination Application  Buffalo-and-Pittsburgh (BnP)  SnB and PHASES Complete Protein Phasing  Q-Chem  Commercial Quantum Chemistry Software Package  SledgeHMMER  Sequence analysis using profile hidden Markov models  QMolDyn  Quantum Molecular Dynamics  ARACNE  Algorithm for the Reconstruction of Accurate Cellular Networks

30. University at Buffalo The State University of New York Center for Computational Research 30 Domain Science and Engineering  NWChem  High Performance Computational Chemistry Software  Ostrich  Optimization and Parameter Estimation Tool for Groundwater Modeling  Evolutionary 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

31. University at Buffalo The State University of New York Center for Computational Research 31 Outline  Primary Centers  Enabling Technologies  Modern Data Center Trends  Enabling Services and Applications  Enabling the next generation of discovery

32. University at Buffalo The State University of New York Center for Computational Research 32 Enabling the Next Generation of Discovery  Train the Next Generation Work Force  Provide Ubiquitous Cyberinfrastructure  Ensure Interoperability Through Standards Based Infrastructure  Generate Virtual Facilities and Institutes  Enable Collaborative Environments  Obtain Efficient Utilization of Computational and Data Resources

33. University at Buffalo The State University of New York Center for Computational Research 33 Contact Information  ACDC Grid and Operations Dashboards  URL: http://osg.ccr.buffalo.edu  ACDC Grid Portal  URL: https://grid.ccr.buffalo.edu  For GRASE VO Membership, email:  grid-help@ccr.buffalo.edu grid-help@ccr.buffalo.edu  Center for Computational Research  URL: http://www.ccr.buffalo.edu  URL: http://www.ccr.buffalo.edu/grid  General contact info  Mark L. Green: mlgreen@ccr.buffalo.edumlgreen@ccr.buffalo.edu