1. National Computational Science Alliance The Alliance Distributed Supercomputing Facilities Opening Talk to the Alliance User Advisory Council Held at Supercomputing ‘98 in Orlanda, Florida, December 5,1998

2. National Computational Science Alliance The National PACI Program - Partners and Supercomputer Users 850 Projects in 280 Universities 60 Partner Universities

3. National Computational Science Alliance PACI - The NSF Partnerships for Advanced Computational Infrastructure The Two Partnerships (NPACI & Alliance) Each Have: –Leading-Edge Site –The Site With the Very Large Scale Computing Systems –Mid-Level Resource Sites –Partners With Alternative or Experimental Computer Architectures, Data Stores, Visualization Capabilities, Etc. –Applications Technologies –Computational Science Partners Involved in Development, Testing and Evaluation of Infrastructure –Enabling Technologies –Computer Science Partners, Developing Tools and Software Infrastructure Driven by Application Partners –Education, Outreach, and Training Partners Network Infrastructure Is Critical. www.npaci.edu www.ncsa.uiuc.edu

4. National Computational Science Alliance NCSA is Combining Shared Memory Programming with Massive Parallelism Doubling Every Nine Months! Challenge Power Challenge Origin SN1

5. National Computational Science Alliance NCSA Users by System 0 100 200 300 400 500 600 Sep94 Nov94Jan95 Mar95 May95 Jul95 Sep95 Nov95Jan96 Mar96 May96 Jul96 Sep96 Nov96Jan97 Mar97 May97 Jul97 Sep97 Nov97Jan98 Mar98 May98 Jul98 Sep98 Number of Users SGI Power Challenge Array CM5 Convex C3880 Convex Exemplar Cray Y-MP Origin SPP-2000 C3880 (retired 10/95) SPP-1200 Y-MP (retired 12/94) Origin SPP-2000 CM-5 (retired 1/97) PCA (retired 7/98) (retired 5/98)

6. National Computational Science Alliance Millions of NUs Used at NCSA FY93 to FY98

7. National Computational Science Alliance Solomon (82) NCSA Supplies Cycles to a Logarithmic Demand Function of Projects Super Large Medium Small Tiny Sugar (2) Knight (67) FY98 Usage < 10 NUs : Evans, Ghoniem, Jacobs, Long, York Karniadakis (31) Hawley (6) Suen (4) Goddard (41) Goodrich (59) Kollman (10) Chen (125) Droegemier (24)

8. National Computational Science Alliance Evolution of the NCSA Project Distribution Function FY93 to FY98

9. National Computational Science Alliance Rapid Increase in Large projects at NCSA FY93-98

10. National Computational Science Alliance Breakout in Supporting Super Projects at NCSA in the Last Year

11. National Computational Science Alliance Migration of NCSA User Distribution Toward the High End +400% +350% +114% -27% -79% Number of Projects

12. National Computational Science Alliance Alliance LES Chose 27 Large PSC Projects to Track Out of 100 Targeted Projects Includes: Droegemeir, Freeman, Karplus, Kollman, Schulten, Sugar 0 100,000 200,000 300,000 400,000 500,000 600,000 700,000 800,000 1QFY972QFY973QFY974QFY971QFY982QFY983QFY98 NUs Per Quarter 8 7 12 15 16 24 26 Number of the 27 Projects Computing at NCSA Bar Shows NUs at NCSA Used Per Quarter

13. National Computational Science Alliance Disciplines Represented in the Large Academic Projects at the Alliance LES Over 5,000 NUs Annually Per Project >100 Projects Over 3.2 Million NUs Note Mapping to AT Teams: Nanomaterials Cosmology Chemical Engineering Molecular Biology Environmental Hydrology Astro and Bio Instruments 6/1/97 to 5/31/98 NCSA

14. National Computational Science Alliance Application Performance Scaling on 128-Processor Origin Conclusion -- 128-Processor Origin is a 15 GF Machine (20-25% of Peak)

15. National Computational Science Alliance Origin Brings Shared Memory to MPP Scalability

16. National Computational Science Alliance Let’s Blow This Up! The Growth Rate of the National Capacity is Slowing Down Again Source: Quantum Research

17. National Computational Science Alliance The Drop in High End Capacity Available to National Academic Researchers Quantum Research FY96-98

18. National Computational Science Alliance Major Gap Has Developed in National Usage at NSF Supercomputer Centers Projection

19. National Computational Science Alliance Allocated Capacity for Meritorious NSF Large National Projects Doubled Data from NSF Metacenter and NRAC Reviews

20. National Computational Science Alliance Clustered Shared Memory Computers are Today’s High End NCSA has 6 x 128 Origin Processors ASC has 4 x 128 ARL has 3 x 128 CEWES has 1 x 128 NAVO has 1 x 128 Los Alamos ASCI Blue Will Have 48 x 128! Livermore ASCI Blue has 1536x4 IBM SP

21. National Computational Science Alliance High-End Computing Enables High Resolution of Flow Details 1024x1024x1024- A Billion Zone Computation of Compressible Turbulence This Simulation Run on Los Alamos SGI Origin Array U. Minn.SGI Visual Supercomputer Renders Images Vorticity LCSE, Univ of Minnesota www.lcse.umn.edu/research/lanlrun/

22. National Computational Science Alliance Cycles Used by NSF Community at the NSF Supercomputer Centers by Vendor SGI SN1 is the Natural Upgrade for 84% of Cycles! June 1, 1997 through May 31, 1998 CTC, NCSA, PSC, SDSC 1019 Projects Using 100% of the Cycles T3D/E Origin/PC C/T90

23. National Computational Science Alliance Peak Teraflops in Aggressive Upgrade Plan

24. National Computational Science Alliance Deputy Director Bordogna on NSF Leadership in Information Technologies Three Important Priorities for NSF in the Area of IT for the Future: –The First Area Is Fundamental and High-Risk IT Research Advanced Computation Research.. –The Second Priority Area for NSF Is Competitive Access and Use of High-end Computing and Networking. –The Third Priority Is Investing in IT Education at All Levels.

25. National Computational Science Alliance President’s Information Technology Advisory Committee Interim Report More Long Term IT Research Needed –Fundamental Research in Software Development –R & D and Testbeds for Scalable Infrastructure –Increase Support for High End Computing Socio-Economic and Workforce Impacts –Address the Shortage of High-Tech Workers –Study Social and Economic Impacts of IT Adoption Modes and Management of Federal IT Research –Fund Projects of Broader Scope and Longer Duration –Virtual Centers for Expeditions into the 21st Century –NSF as Lead Agency for Coordinating IT Research Congressional Testimony 10/6/98

26. National Computational Science Alliance PITAC Draft Refinement of High-End Acquisition Recommendation Fund the Acquisition of the Most Powerful High-End Computing Systems to Support Long Term Basic Research in Science and Engineering Access for (Highest Priority): –ALL Academic Researchers –ALL Disciplines –ALL Universities Access for (Second Priority): –Government Researchers –Industrial Researchers

27. National Computational Science Alliance Harnessing the Unused Cycles of Networks of Workstations Condor Cycles University of Kansas is Installing Condor Alliance Nanotechnologies Team Used Univ. of Wisconsin Condor Cluster - Burned 1 CPU-Year in Two Weeks!

28. National Computational Science Alliance NT Workstation Shipments Rapidly Surpassing UNIX Source: IDC, Wall Street Journal, 3/6/98

29. National Computational Science Alliance 128 Hewlett Packard 300 MHz 64 Compaq 333 MHz Andrew Chien, CS UIUC-->UCSD Rob Pennington, NCSA Reagan Moore, SDSC Plan to Link UCSD & UIUC Clusters “Supercomputer performance at mail-order prices”-- Jim Gray, Microsoft PACI Fostering Commodity Computing Various Applications Sustain 7 GF on 128 Processors

30. National Computational Science Alliance Performance Analysis is Key Computer Science Research Enabling Computational Science Mflops/ProcFlops/ByteFlops/NetworkRT Cray T3E1200~2~2,500 SGI Origin2000500~0.5~1,000 HPVM NT Supercluster300~3.2~6,000 IBM SP2550~3.7~38,000 Berkeley NOW II320~8.0~6,400 Beowulf(100Mbit)300~25~500,000

31. National Computational Science Alliance Performance of Scalable Systems Shows the Promise of Local Clustered PCs Danesh Tafti, Rob Pennington, NCSA; Andrew Chien (UIUC, UCSD) Solving 2D Navier-Stokes Kernel

32. National Computational Science Alliance Near Perfect Scaling of Cactus - 3D Dynamic Solver for the Einstein GR Equations Ratio of GFLOPs Origin = 2.5x NT SC Paul Walker, John Shalf, Rob Pennington, Andrew Chien NCSA Cactus was Developed by Paul Walker, MPI-Potsdam UIUC, NCSA

33. National Computational Science Alliance QCD Performance on Various Machines Doug Toussaint and Kostas Orginos, University of Arizona

34. National Computational Science Alliance The Road to Intel’s Merced The Convergence of Scientific and Commercial Computing http://developer.intel.com/solutions/archive/issue5/focus.htm#FOUR IA-64 Co-Developed by Intel and Hewlett-Packard

35. National Computational Science Alliance User Web Browser Output to User User Input Format Translator, Query Engine and Program Driver Workbench Server Results to User User Instructions and queries Application Programs (May have varying interfaces and be written in different languages) Results Instructions Information Sources (May be of varying formats) Information Queries NCSA Computational Biology Group The NCSA Information Workbench - An Architecture for Web-Based Computing

36. National Computational Science Alliance Structure & Function Pathways & Physiology Populations & Evolution Ecosystems Genomes Gene Products Using a Web Browser to Run Programs and Analyze Data Worldwide NCSA Biology Workbench Has Over 6,000 Users From Over 20 Countries