1. National Computational Science Alliance Introducing the Alliance Talk to the Assistant Director of the NSF CISE Directorate on his visit to NCSA September 18, 1997

2. National Computational Science Alliance The Alliance National Technology Grid

3. National Computational Science Alliance Leading Edge Centers –Supernodes of the Grid Enabling Technology Teams –Architects of the Grid Applications Technologies Teams –Specifications for the Grid Education, Outreach, and Training Teams –Access to the Grid Partners for Advanced Computational Services –Support for the Grid Industrial Partners and Strategic Vendors –Technology Transfer for the Grid The Alliance is Prototyping the National Technology Grid

4. National Computational Science Alliance Alliance Executive Committee Larry Smarr, Chair Phil Smith, External Chair Charlie Bender, OSC Bob Berdine, Caterpillar David Ceperley, UIUC John Connolly, Kentucky Tom DeFanti, UIC Roscoe Giles, Boston U John Hennessy, Stanford Ken Kennedy, Rice Greg McRae, MIT Jeremiah Ostriker, Princeton Dan Reed, UIUC Rick Stevens, Argonne Mary Vernon, Wisconsin Paul Woodward, Minnesota

5. National Computational Science Alliance Alliance Enabling Technologies Teams - Faculty Leads Parallel Computing (16) –Ken Kennedy, Rice U –Greg McRae, MIT Distributed Computing (15) –Rick Stevens, Argonne –Paul Woodward, U Minnesota Data and Collaboration (14) –Dan Reed, UIUC –Roscoe Giles, Boston U

6. National Computational Science Alliance Alliance Applications Technologies Teams - Faculty Leads and UIUC (NCSA) Anchors Cosmology (5) –Jeremiah Ostriker, Princeton U –Mike Norman, UIUC (NCSA) Environment Hydrology (11) –John Anderson, U Wisconsin –Robert Wilhelmson, UIUC (NCSA) –V.C. Patel, U Iowa –Doug Johnston, UIUC (NCSA) Chemical Engineering (7) –Greg McRae, MIT –Richard Braatz, UIUC (NCSA)

7. National Computational Science Alliance Alliance Applications Technologies Teams - Faculty Leads and UIUC (NCSA) Anchors Bioinformatics (9) –Santae Kim, U Wisconsin –Shankar Subramaniam, UIUC (NCSA) Nanomaterials (11) –John Wilkins, OSU –David Ceperley, UIUC (NCSA) –Robert Dutton, Stanford U –Karl Hess, UIUC (NCSA) Scientific Instruments (8) –David Agard, UCSF –Clint Potter, UIUC (NCSA) –Paul Vanden Bout, NRAO –Richard Crutcher, UIUC (NCSA)

8. National Computational Science Alliance Education, Outreach, and Training Alliance Focus Areas Education: –K-12 –Undergraduate –Graduate –Lifetime Learning Underrepresented Participants –Women –Minorities –People with Disabilities Government –Local (CCnet) –State (Albany) –Federal (FedCon, DoD Mod)

9. National Computational Science Alliance Education, Outreach, and Training FY98 Projects Enabling Technologies Applications Technologies EOT-PACI Project Activities National Education Community Digital Libraries Collaboration Tech. Distance Learning VR/Simulations Molecular Biology Cosmology Scientific Instruments Chickscope Biology Workbench WW2010 Chemistry Visualization

10. National Computational Science Alliance How Application Teams Drive the Grid Cosmology –Metacomputing Environmental Hydrology –Immersive Collaboration Chemical Engineering –Virtual Prototyping Bioinformatics –Distributed Data Nanomaterials –Remote Microengineering Scientific Instruments –Virtual Observatories

11. National Computational Science Alliance Alliance Bioinformatics Team The Biology Workbench Model for Chem Eng WB Genome infomatics tools Structural analysis tools Tools for analysis of experimental data K-12 access to simulations, databases, demonstrations Deliverables Distributed Computing Desktop Collaboration High Performance Storage and Information Mgmt Vis. & Collab. Virtual Environments Advanced Tools for Supercomputing Enabling Technologies

12. National Computational Science Alliance BIMA Distributed Observatory, Digital Library, and Collaboratory BIMA, Courtesy Richard Crutcher, UIUC http://bima-server.ncsa.uiuc.edu/imagelib/VRMLHighlights.html

13. National Computational Science Alliance Replacement of Shared Memory Vector Supercomputers by Microprocessor SMPs

14. National Computational Science Alliance NCSA Combines Shared Memory With Massive Parallelism Future Upgrade Under Negotiation with NSF SN2 (1024) SN1 (1024) Power Challenge (158) Origin (1024) Y-MP Cray-2 X-MP/48 X-MP/24 180% Annual Cluster Growth Rate 24% Annual Vector Growth Rate Actual PCA Monthly Usage 75% Annual DSM Growth Rate

15. National Computational Science Alliance Simulation of Liquid Helium - Path Integral Monte Carlo Particle Code Single Processor Performance Code Parallelizes Linearly with Number of Nodes David Ceperley, Nanomaterials AT Team - NCSA, UIUC 101 MF

16. National Computational Science Alliance Frontier Problems in Computational Science and Engineering Multidiscipline Domains Multiscale Interactions Complex Geometries Full-up Virtual Prototyping Large System Optimizations

17. National Computational Science Alliance Rotating Turbulent Gas Ball Model of the Sun Nine Day Run on NCSA Origin (128-processors) Generated 2 Terabytes of Data, LCSE Visualized in 3 Days Dave Porter, Paul Woodward, et al., LCSE, Univ of Minnesota, June 1997 Building the Visual Supercomputer

18. National Computational Science Alliance Computing on the University of Wisconsin Condor Pool Condor Cycles CondorView, Courtesy of Miron Livny, Todd Tannenbaum(UWisc)

19. National Computational Science Alliance Regional Partners to Partners for Advanced Computational Services PACS Focus Area –Regional Access to Workshops –Distributed Training and User Services –Mid-Level Computational Resources –Specialized Technology Development Sites PACS Members –4 Mid-Level Centers –BU (Origin), OSC (Triton, T3E), Kentucky (HP SPP), Maui (SP-2) –6 Tech Development Sites –Minn, Wisc, Rice, ANL, Wash, UVa –3 Outreach Consortia (CIC, SURA, EPSCoR)

20. National Computational Science Alliance NCSA - HP Relationship Started 1990 with Convex Computer Goals –Focus on Industrial Third Party Applications –Integration of Technical and Data Computing –NT / UNIX Interoperability HP- Intel Create Merced Processor in FY99-00 – full binary compatibility with both –HP PA-RISC and –Intel processor families NCSA / UIUC has Microsoft / Intel / HP Testbed NCSA SPP-2000 to -3000 Upgrade Path

21. National Computational Science Alliance Allstate Pioneering an NT Intranet Standard Software Environment – Microsoft Office –Microsoft Outlook / Exchange –Internet Explorer –Windows NT Desktop / Server for Intel Platforms –Oracle Database Technology –CA Unicenter (TNG) TCP/IP Network –T3 Backbone –Sonet Ring Technology Partnering with NCSA as Microsoft / HP Testbed Partnering with NCSA and Computer Associates

22. National Computational Science Alliance Building Blocks of a Computational Grid Tele- immersion TestbedsTestbeds Data- intensive Distributed supercomputing Real- time Network Technologies Advanced Protocols Computing platforms Interfaces and OS Compilers, languages, libs Web technologies Application- specific tools Object technologies Security, Assurance, etc. Instrumentation & measurement Perf. viz & evaluation High-thruput scheduling High-performance scheduling Network QoS Applns Prog. tools Resource manag. Services Infra- structure Common services From Ian Foster, Argonne Nat. Lab.

23. National Computational Science Alliance OC12 vBNS Ameritech NAP houses STAR-TAP and MREN Hub MREN - America’s First Operational Gigapop - Chicago Area Sites Northwestern U Chicago EVL/UI Chicago Fermi Nat’l Lab Argonne Nat’l Lab MCI Ameritech

24. National Computational Science Alliance MREN and STAR-TAP MREN - America’s First Operational Gigapop - Midwest Sites OC12 vBNS Indiana Hub Indiana Univ Purdue Wisconsin Minnesota/LCSE = Planned NCSA

25. National Computational Science Alliance NSF vBNS and PACI - Mutually Interdependent NPACI NCSA Alliance Both NCSA Alliance and NPACI Other High Performance Connection sites Current vBNS “Backbone” sites

26. National Computational Science Alliance EPSCoR and the State Participation Problem

27. National Computational Science Alliance International Connections Through STAR TAP

28. National Computational Science Alliance National Technology Grid Workshop and Training Facilities 155 Mbps vBNS Image from EVL

29. National Computational Science Alliance Integrating Scalable Computing With Virtual Environments and Large Data Sets http://zeus.ncsa.uiuc.edu:8080/chdm_script.html Bryan and Norman, NCSA, GC3 Team Formation of Large Scale Structure in the Universe

30. National Computational Science Alliance Working DoD Modernization Collaborative Virtual Enviornment Environmental Modeling in Shared VR-space –Chesapeake Bay Simulations and Databases ImmersaDesks vBNS DREN SGI Onyx (NCSA) SGI Onyx (CEWES) Integrated M-Bone Videoteleconferencing Data courtesy Old Dominion University Images produced by John Shalf, NCSA SGI Onyx (Old Dominion) SGI Onyx (U. Wisc)

31. National Computational Science Alliance Using Intranet Technologies to Form Alliance Electronic Communities http://www.ncsa.uiuc.edu/Indices/Spotlight/ Features/feature_CAVERNUS.html CAVE and ImmersaDesk Systems Hypernews Forums User Lists Application Galleries Shared Programs

32. National Computational Science Alliance Caterpillar’s Distributed Virtual Reality Data courtesy of Valerie Lehner, NCSA, 1996

33. National Computational Science Alliance Sears Virtual Store Prototype

34. National Computational Science Alliance Early Alliance Success Stories Application Technology Teams –BIMA Observations of Hale-Bopp –Lyman Alpha Forest in Cosmology Explained –Biology Workbench Acceptance –Kansas Couples Habanero to Chem Eng Enabling Technologies Team –Princeton May Become NCSA Symbio Testbed –Chesapeake Bay I-Desk to I-Desk Demo –MREN Hooks up to ANL, EVL, NCSA –STAR TAP Funded for International vBNS –LCSE Deploys Power Wall at NCSA

35. National Computational Science Alliance Infrastructure Foundations –Build the Alliance Intranet Framework –Create the Origin Repository –Rough Out Intranet Interfaces –Set up the High Performance Networks –Link the CAVE Devices Define the Alliance Work Plan –Timelines and Deliverables for First Year –Interweaving of ET/AT/EOT/RP and NCSA –Identifiy Early Success Goals –Define Alliance Software Set for AT/EOT –Review Alliance Collaborative Software Plans –Requires Strong ET/AT/EOT Brainstorming Launching the Alliance - What We Will Do This Fall